├── README.md ├── modules ├── ConvRNN.py ├── Model.py ├── TimeDistributed.py ├── __init__.py ├── __pycache__ │ ├── ConvLSTM.cpython-35.pyc │ ├── ConvLSTM.cpython-36.pyc │ ├── ConvRNN.cpython-35.pyc │ ├── ConvRNN.cpython-36.pyc │ ├── Model.cpython-35.pyc │ ├── Model.cpython-36.pyc │ ├── TimeDistributed.cpython-35.pyc │ ├── TimeDistributed.cpython-36.pyc │ ├── __init__.cpython-35.pyc │ ├── __init__.cpython-36.pyc │ ├── blocks.cpython-35.pyc │ └── blocks.cpython-36.pyc └── blocks.py ├── pre_process.py ├── test.py ├── test_params.py ├── utils ├── Logger.py ├── NaiveDataset.py ├── Sampler.py ├── __init__.py ├── __pycache__ │ ├── Logger.cpython-35.pyc │ ├── NaiveDataset.cpython-35.pyc │ ├── __init__.cpython-35.pyc │ ├── __init__.cpython-36.pyc │ ├── post_process.cpython-35.pyc │ ├── post_process.cpython-36.pyc │ ├── statistic.cpython-35.pyc │ ├── statistic.cpython-36.pyc │ ├── tools.cpython-35.pyc │ ├── visualize.cpython-35.pyc │ └── visualize.cpython-36.pyc ├── feat_vis │ └── result │ │ ├── bottom_1.bmp │ │ ├── bottom_10.bmp │ │ ├── bottom_11.bmp │ │ ├── bottom_12.bmp │ │ ├── bottom_13.bmp │ │ ├── bottom_14.bmp │ │ ├── bottom_2.bmp │ │ ├── bottom_3.bmp │ │ ├── bottom_4.bmp │ │ ├── bottom_5.bmp │ │ ├── bottom_6.bmp │ │ ├── bottom_7.bmp │ │ ├── bottom_8.bmp │ │ ├── bottom_9.bmp │ │ ├── middle_0.bmp │ │ ├── middle_1.bmp │ │ ├── middle_10.bmp │ │ ├── middle_11.bmp │ │ ├── middle_12.bmp │ │ ├── middle_13.bmp │ │ ├── middle_14.bmp │ │ ├── middle_2.bmp │ │ ├── middle_3.bmp │ │ ├── middle_4.bmp │ │ ├── middle_5.bmp │ │ ├── middle_6.bmp │ │ ├── middle_7.bmp │ │ ├── middle_8.bmp │ │ ├── middle_9.bmp │ │ ├── top_0.bmp │ │ ├── top_1.bmp │ │ ├── top_10.bmp │ │ ├── top_11.bmp │ │ ├── top_12.bmp │ │ ├── top_13.bmp │ │ ├── top_14.bmp │ │ ├── top_2.bmp │ │ ├── top_3.bmp │ │ ├── top_4.bmp │ │ ├── top_5.bmp │ │ ├── top_6.bmp │ │ ├── top_7.bmp │ │ ├── top_8.bmp │ │ └── top_9.bmp ├── plot.py ├── point_move │ └── __init__.py ├── post_process.py ├── result_vis │ ├── D0025759109.jpg │ ├── D0025759109_1.bmp │ ├── D0025759109_2.png │ ├── D0038207736.jpg │ ├── D0038207736_1.bmp │ ├── D0038207736_2.png │ ├── E0015433121.jpg │ ├── E0015433121_1.bmp │ ├── E0015433121_2.png │ ├── E0016786877.jpg │ ├── E0016786877_1.bmp │ ├── E0016786877_2.png │ ├── E0048968076.jpg │ ├── E0048968076_1.bmp │ ├── E0048968076_2.png │ ├── E0056225398.jpg │ ├── E0056225398_1.bmp │ ├── E0056225398_2.png │ ├── E0066596328.jpg │ ├── E0066596328_1.bmp │ ├── E0066596328_2.png │ └── result │ │ ├── D0025759109.eps │ │ ├── D0025759109.png │ │ ├── D0025759109_cropped.eps │ │ ├── D0038207736.eps │ │ ├── D0038207736_cropped.eps │ │ ├── E0015433121.eps │ │ ├── E0015433121_cropped.eps │ │ ├── E0016786877.eps │ │ ├── E0016786877.png │ │ ├── E0016786877_cropped.eps │ │ ├── E0048968076.eps │ │ ├── E0048968076.png │ │ ├── E0048968076_cropped.eps │ │ ├── E0056225398.eps │ │ ├── E0056225398.png │ │ ├── E0056225398_cropped.eps │ │ ├── E0066596328.eps │ │ ├── E0066596328.png │ │ └── E0066596328_cropped.eps ├── tools.py └── visualize.py └── weights.pth /README.md: -------------------------------------------------------------------------------- 1 | # Sequential-patch-based-segmentation 2 | ## Data Preparation 3 | test image(name.png) and corresponding ground truth(name_1.bmp) in the same folder. The shape of test image should be (296, 296) 4 | ## How to test 5 | Set your test parameters in test_params.py file 6 | and run test.py to get the predictions. 7 | -------------------------------------------------------------------------------- /modules/ConvRNN.py: -------------------------------------------------------------------------------- 1 | import torch 2 | import torch.nn as nn 3 | import torch.nn.functional as F 4 | from torch.autograd import Variable 5 | 6 | 7 | class ConvRNNCell(nn.Module): 8 | def __init__(self, in_channels, shape, num_filter, kernel_size=3): 9 | super(ConvRNNCell, self).__init__() 10 | padding = (kernel_size - 1) // 2 11 | self._shape = shape 12 | self._num_filter = num_filter 13 | self.conv_1 = nn.Conv2d(in_channels + num_filter, num_filter, kernel_size=1, padding=0, bias=True) 14 | self.conv_2 = nn.Conv2d(in_channels + num_filter, num_filter, kernel_size=kernel_size, padding=padding,bias=True) 15 | 16 | def forward(self, x, hidden): 17 | """forward process of ConvRNNCell""" 18 | combind = torch.cat((x, hidden), 1) 19 | reset_gate = F.sigmoid(self.conv_1(combind)) 20 | 21 | reset_hidden = reset_gate * hidden 22 | 23 | combin_reset = torch.cat((x, reset_hidden), dim=1) 24 | new_hidden = F.relu(self.conv_2(combin_reset)) # TODO: applying tanh maybe a better choice 25 | return new_hidden 26 | 27 | def init_hidden(self, batch_size): 28 | return Variable(torch.zeros(batch_size, self._num_filter, self._shape[0], self._shape[1])).cuda(0) 29 | 30 | 31 | 32 | class ConvRNN(nn.Module): 33 | def __init__(self, in_channels, shape, num_filter, kernel_size=3, num_layer=1, bidirectional=True): 34 | super(ConvRNN, self).__init__() 35 | self._in_channels = in_channels 36 | self._shape = shape 37 | self._num_filter = num_filter 38 | self._kernel_size = kernel_size 39 | self._num_layer = num_layer 40 | self._bidirectional = bidirectional 41 | self._padding = (self._kernel_size - 1) // 2 42 | self._cell_list = None 43 | self._forward_cell_list = None 44 | self._backward_cell_list = None 45 | 46 | if self._bidirectional: 47 | forward_cell_list = [] 48 | backward_cell_list = [] 49 | 50 | for idx in range(self._num_layer): 51 | forward_cell_list.append( 52 | ConvRNNCell(self._in_channels, self._shape, self._num_filter, self._kernel_size)) 53 | backward_cell_list.append( 54 | ConvRNNCell(self._in_channels, self._shape, self._num_filter, self._kernel_size)) 55 | self._forward_cell_list = nn.ModuleList(forward_cell_list) 56 | self._backward_cell_list = nn.ModuleList(backward_cell_list) 57 | else: 58 | cell_list = [] 59 | for idx in range(self._num_layer): 60 | cell_list.append(ConvRNNCell(self._in_channels, self._shape, self._num_filter, self._kernel_size)) 61 | self._cell_list = nn.ModuleList(cell_list) 62 | 63 | def forward(self, x, hidden_state): 64 | curr_forward_x = x.transpose(0, 1) 65 | curr_backward_x = x.transpose(0, 1) 66 | 67 | forward_hidden_state, backward_hidden_state = hidden_state 68 | 69 | seq_len = curr_forward_x.size(0) 70 | 71 | if self._bidirectional: 72 | for idx_layer in range(self._num_layer): 73 | layer_forward_hidden = forward_hidden_state[idx_layer] 74 | layer_backward_hidden = backward_hidden_state[idx_layer] 75 | inner_forward_output = [] 76 | inner_backward_output = [] 77 | for t in range(seq_len): 78 | # forward 79 | layer_forward_hidden = self._forward_cell_list[idx_layer](curr_forward_x[t, ...], 80 | layer_forward_hidden) 81 | inner_forward_output.append(layer_forward_hidden) 82 | # backward 83 | layer_backward_hidden = self._backward_cell_list[idx_layer](curr_backward_x[seq_len - t - 1, ...], 84 | layer_backward_hidden) 85 | inner_backward_output.append(layer_backward_hidden) 86 | 87 | curr_forward_x = torch.cat(inner_forward_output, 0).view(curr_forward_x.size(0), 88 | *inner_forward_output[0].size()) 89 | curr_backward_x = torch.cat(inner_backward_output, 0).view(curr_backward_x.size(0), 90 | *inner_backward_output[0].size()) 91 | 92 | curr_forward_x = curr_forward_x.transpose(0, 1) 93 | curr_backward_x = curr_backward_x.transpose(0, 1) 94 | return curr_forward_x, curr_backward_x 95 | else: 96 | raise Exception('No single direction implemnted!') 97 | 98 | def init_hidden(self, batch_size): 99 | """ 100 | init hidden state and cell state 101 | :param batch_size: 102 | :return: 103 | """ 104 | if self._bidirectional: 105 | forward_hidden_state = [] 106 | backward_hidden_state = [] 107 | for i in range(self._num_layer): 108 | forward_hidden_state.append(self._forward_cell_list[i].init_hidden(batch_size)) 109 | backward_hidden_state.append(self._backward_cell_list[i].init_hidden(batch_size)) 110 | return tuple(forward_hidden_state), tuple(backward_hidden_state) 111 | else: 112 | hidden_state = [] 113 | for i in range(self._num_layer): 114 | hidden_state.append(self._cell_list[i].init_hidden(batch_size)) 115 | return tuple(hidden_state) 116 | -------------------------------------------------------------------------------- /modules/Model.py: -------------------------------------------------------------------------------- 1 | import math 2 | import torch 3 | import torch.nn as nn 4 | from torch.autograd import Variable 5 | import torch.nn.functional as F 6 | from modules.blocks import DownBlock, UpBlock, ConvLSTMBlock, ConvRNNBlock 7 | from modules.TimeDistributed import TimeDistributed 8 | 9 | 10 | def init_weights(m): 11 | if isinstance(m, nn.Conv2d): 12 | num = m.kernel_size[0] * m.kernel_size[1] * m.out_channels 13 | m.weight.data.norm_(0, math.sqrt(2. / num)) 14 | if m.bias: 15 | m.bias.data.zero_() 16 | elif isinstance(m, nn.ConvTranspose2d): 17 | pass 18 | 19 | 20 | class SkipConnecModel(nn.Module): 21 | def __init__(self, img_shape, num_class, batch_size): 22 | """ 23 | SkipConnection Model,which is a U-net like net structure 24 | :param num_class: 25 | """ 26 | super(SkipConnecModel, self).__init__() 27 | self._num_class = num_class 28 | 29 | self.downblock_1 = DownBlock(1, 32, 3) 30 | self.t_max_pool_1 = TimeDistributed(nn.MaxPool2d(2, 2)) 31 | 32 | self.downblock_2 = DownBlock(32, 64, 3) 33 | self.t_max_pool_2 = TimeDistributed(nn.MaxPool2d(2, 2)) 34 | 35 | self.downblock_3 = DownBlock(64, 128, 3) 36 | 37 | self.bottom_clstm = ConvLSTMBlock(batch_size, 128, (img_shape[0] // 4, img_shape[1] // 4), 128, 3) 38 | self.middle_clstm = ConvLSTMBlock(batch_size, 64, (img_shape[0] // 2, img_shape[1] // 2), 64, 3) 39 | self.top_clstm = ConvLSTMBlock(batch_size, 32, img_shape, 32, 3) 40 | 41 | self.upblock_1 = UpBlock(128, 64, up_scale=2) 42 | self.upblock_2 = UpBlock(64, 32, up_scale=2) 43 | 44 | self.final_conv = TimeDistributed(nn.Conv2d(32, num_class-1, kernel_size=1, stride=1)) 45 | 46 | def forward(self, x): 47 | x_pool_1_pre = self.downblock_1(x) 48 | x = self.t_max_pool_1(x_pool_1_pre) # (batch_size seq 32 H/2 W/2) 49 | 50 | x_pool_2_pre = self.downblock_2(x) 51 | x = self.t_max_pool_2(x_pool_2_pre) # (batch_size seq 64 H/4 W/4) 52 | 53 | x = self.downblock_3(x) # (batch_size seq 128 H/4 W/4) 54 | 55 | x = self.bottom_clstm(x) 56 | 57 | x = self.upblock_1(x, x_pool_2_pre) # (batch_size seq 64 H/2 W/2) 58 | 59 | x = self.middle_clstm(x) 60 | 61 | x = self.upblock_2(x, x_pool_1_pre) 62 | 63 | x = self.top_clstm(x) 64 | 65 | x = self.final_conv(x) 66 | 67 | return x 68 | 69 | def reinit_hidden(self): 70 | """ 71 | reinit the hidden state for all the lstm module 72 | :return: void 73 | """ 74 | self.bottom_clstm.reinit_hidden() 75 | self.middle_clstm.reinit_hidden() 76 | self.top_clstm.reinit_hidden() 77 | 78 | 79 | class SkipConnecRNNModel(nn.Module): 80 | def __init__(self, img_shape, num_class, batch_size): 81 | """ 82 | SkipConnection Model,which is a U-net like net structure 83 | :param num_class: 84 | """ 85 | super(SkipConnecRNNModel, self).__init__() 86 | self._num_class = num_class 87 | 88 | self.downblock_1 = DownBlock(1, 32, 3) 89 | self.t_max_pool_1 = TimeDistributed(nn.MaxPool2d(2, 2)) 90 | 91 | self.downblock_2 = DownBlock(32, 64, 3) 92 | self.t_max_pool_2 = TimeDistributed(nn.MaxPool2d(2, 2)) 93 | 94 | self.downblock_3 = DownBlock(64, 128, 3) 95 | 96 | self.bottom_clstm = ConvRNNBlock(batch_size, 128, (img_shape[0] // 4, img_shape[1] // 4), 128, 3) 97 | self.middle_clstm = ConvRNNBlock(batch_size, 64, (img_shape[0] // 2, img_shape[1] // 2), 64, 3) 98 | self.top_clstm = ConvRNNBlock(batch_size, 32, img_shape, 32, 3) 99 | 100 | self.upblock_1 = UpBlock(128, 64, up_scale=2) 101 | self.upblock_2 = UpBlock(64, 32, up_scale=2) 102 | 103 | self.final_conv = TimeDistributed(nn.Conv2d(32, num_class-1, kernel_size=1, stride=1)) 104 | 105 | def forward(self, x): 106 | x_pool_1_pre = self.downblock_1(x) 107 | x = self.t_max_pool_1(x_pool_1_pre) # (batch_size seq 32 H/2 W/2) 108 | 109 | x_pool_2_pre = self.downblock_2(x) 110 | x = self.t_max_pool_2(x_pool_2_pre) # (batch_size seq 64 H/4 W/4) 111 | 112 | x = self.downblock_3(x) # (batch_size seq 128 H/4 W/4) 113 | 114 | x_bottom = self.bottom_clstm(x) 115 | 116 | x = self.upblock_1(x_bottom, x_pool_2_pre) # (batch_size seq 64 H/2 W/2) 117 | 118 | x_middle = self.middle_clstm(x) 119 | 120 | x = self.upblock_2(x_middle, x_pool_1_pre) 121 | 122 | x_top = self.top_clstm(x) 123 | 124 | x = self.final_conv(x_top) 125 | 126 | return x, x_bottom, x_middle, x_top 127 | 128 | def reinit_hidden(self): 129 | """ 130 | reinit the hidden state for all the lstm module 131 | :return: void 132 | """ 133 | self.bottom_clstm.reinit_hidden() 134 | self.middle_clstm.reinit_hidden() 135 | self.top_clstm.reinit_hidden() 136 | 137 | 138 | class MultiLevelModel(nn.Module): 139 | def __init__(self, bacth_size, img_shape, num_class): 140 | super(MultiLevelModel, self).__init__() 141 | pass 142 | 143 | def forward(self, x): 144 | pass 145 | 146 | def reinit_hidden(self): 147 | """ 148 | reinit the hidden state for all the lstm module 149 | :return: void 150 | """ 151 | self.bottom_clstm.reinit_hidden() 152 | self.middle_clstm.reinit_hidden() 153 | self.top_clstm.reinit_hidden() 154 | 155 | -------------------------------------------------------------------------------- /modules/TimeDistributed.py: -------------------------------------------------------------------------------- 1 | import torch 2 | import torch.nn as nn 3 | 4 | 5 | class TimeDistributed(nn.Module): 6 | def __init__(self, module): 7 | """ 8 | Given an input shaped like (batch, time_step, [rest]), and a Module 9 | TimeDistributed Module reshap the input to be (batch*time_step, [rest]) 10 | :param module: 11 | :return: 12 | """ 13 | super(TimeDistributed, self).__init__() 14 | self._module = module 15 | 16 | def forward(self, x): 17 | batch, time, C, H, W = x.size(0), x.size(1), x.size(2), x.size(3), x.size(4) 18 | shape = x.size() 19 | x = x.view(batch*time, C, H, W) # 20 | x = self._module(x) 21 | C, H, W = x.size(1), x.size(2), x.size(3) 22 | new_shape = (batch, time, C, H, W) 23 | x = x.view(new_shape) 24 | return x 25 | -------------------------------------------------------------------------------- /modules/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/modules/__init__.py -------------------------------------------------------------------------------- /modules/__pycache__/ConvLSTM.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/modules/__pycache__/ConvLSTM.cpython-35.pyc -------------------------------------------------------------------------------- /modules/__pycache__/ConvLSTM.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/modules/__pycache__/ConvLSTM.cpython-36.pyc -------------------------------------------------------------------------------- /modules/__pycache__/ConvRNN.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/modules/__pycache__/ConvRNN.cpython-35.pyc -------------------------------------------------------------------------------- /modules/__pycache__/ConvRNN.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/modules/__pycache__/ConvRNN.cpython-36.pyc -------------------------------------------------------------------------------- /modules/__pycache__/Model.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/modules/__pycache__/Model.cpython-35.pyc -------------------------------------------------------------------------------- /modules/__pycache__/Model.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/modules/__pycache__/Model.cpython-36.pyc -------------------------------------------------------------------------------- /modules/__pycache__/TimeDistributed.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/modules/__pycache__/TimeDistributed.cpython-35.pyc -------------------------------------------------------------------------------- /modules/__pycache__/TimeDistributed.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/modules/__pycache__/TimeDistributed.cpython-36.pyc -------------------------------------------------------------------------------- /modules/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/modules/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /modules/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/modules/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /modules/__pycache__/blocks.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/modules/__pycache__/blocks.cpython-35.pyc -------------------------------------------------------------------------------- /modules/__pycache__/blocks.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/modules/__pycache__/blocks.cpython-36.pyc -------------------------------------------------------------------------------- /modules/blocks.py: -------------------------------------------------------------------------------- 1 | import torch 2 | import torch.nn as nn 3 | from torch.autograd import Variable 4 | import torch.nn.functional as F 5 | from modules.TimeDistributed import TimeDistributed 6 | from modules.ConvLSTM import ConvLSTM 7 | from modules.ConvRNN import ConvRNN 8 | 9 | 10 | def repackage_hidden(h): 11 | """Wraps hidden states in new Variables, to detach them from their history.""" 12 | if type(h) == Variable: 13 | return Variable(h.data.zero_()) 14 | else: 15 | return tuple(repackage_hidden(v) for v in h) 16 | 17 | 18 | class DownBlock(nn.Module): 19 | def __init__(self, in_planes, out_planes, kernel_size): 20 | """ 21 | DownBlock 22 | :param in_planes: 23 | :param out_planes: 24 | """ 25 | super(DownBlock, self).__init__() 26 | 27 | padding = (kernel_size-1) // 2 28 | 29 | self.t_conv_1 = TimeDistributed(nn.Conv2d(in_planes, out_planes, kernel_size=kernel_size, padding=padding, 30 | stride=1, bias=True)) 31 | self.t_conv_2 = TimeDistributed(nn.Conv2d(out_planes, out_planes, kernel_size=kernel_size, padding=padding, 32 | stride=1, bias=True)) 33 | 34 | def forward(self, x): 35 | x = F.relu(self.t_conv_1(x)) 36 | x = F.relu(self.t_conv_2(x)) 37 | return x 38 | 39 | def init_weight(self): 40 | # TODO: weight init 41 | pass 42 | 43 | 44 | class UpBlock(nn.Module): 45 | def __init__(self, in_planes, out_planes, up_scale=2): 46 | """ 47 | upsampling with deconvolution 48 | :param in_planes: 49 | :param out_planes: 50 | """ 51 | super(UpBlock, self).__init__() 52 | self._in_planes = in_planes 53 | self._out_planes = out_planes 54 | self.t_deconv_1 = TimeDistributed(nn.ConvTranspose2d(in_planes, out_planes, kernel_size=up_scale, 55 | stride=up_scale, bias=True)) 56 | self.conv_1 = TimeDistributed(nn.Conv2d(out_planes*2, out_planes, kernel_size=3, padding=1, stride=1, bias=True)) 57 | self.conv_2 = TimeDistributed(nn.Conv2d(out_planes, out_planes, kernel_size=3, padding=1, stride=1, bias=True)) 58 | 59 | def forward(self, x, pre): 60 | x = self.t_deconv_1(x) 61 | x = torch.cat((pre, x), dim=2) 62 | x = F.relu(self.conv_1(x)) 63 | x = F.relu(self.conv_2(x)) 64 | return x 65 | 66 | 67 | class ConvRNNBlock(nn.Module): 68 | def __init__(self, batch_size, in_channels, shape, num_filter, kernel_size): 69 | super(ConvRNNBlock, self).__init__() 70 | self.conv_rnn = ConvRNN(in_channels, shape, num_filter, kernel_size) 71 | self.conv = TimeDistributed(nn.Conv2d(2 * num_filter, num_filter, kernel_size=1, bias=True)) 72 | self._hidden_state = self.conv_rnn.init_hidden(batch_size) 73 | 74 | def forward(self, x): 75 | forward_out, backward_out = self.conv_rnn(x, self._hidden_state) 76 | out = torch.cat((forward_out, backward_out), dim=2) 77 | out = F.relu(self.conv(out)) 78 | return out 79 | 80 | def reinit_hidden(self): 81 | self._hidden_state = repackage_hidden(self._hidden_state) -------------------------------------------------------------------------------- /pre_process.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | from skimage.io import imread, imsave, imshow, show 3 | from glob import glob 4 | import os 5 | 6 | 7 | HEIGHT = 296 8 | WIDTH = 296 9 | PATCH_HEIGHT = 32 10 | PATCH_WIDTH = 32 11 | PADDING_SHAPE = (436, 436) 12 | 13 | train_data_dir = '' 14 | 15 | val_data_dir = '' 16 | 17 | seq_length = 15 18 | extract_stride = 4 19 | 20 | 21 | directions = [(0, 1), (-1, 2), (-1, 1), (-2, 1), (-1, 0), (-2, -1), (-1, -1), (-1, -2)] 22 | 23 | 24 | def load_img(file_dir, img_name): 25 | """ 26 | load origin img and responding ground truth img 27 | :param img_name: 28 | :return: img gt_img 29 | """ 30 | img = imread(file_dir + img_name + '.jpg') 31 | gt_img = imread(file_dir + img_name + '_1.bmp') 32 | return img, gt_img 33 | 34 | 35 | def get_coordinate(img, gt_img, padding): 36 | """ 37 | get crop from img and gt_img 38 | :param img: 39 | :param gt_img: 40 | :param padding: 41 | :return: center point_move of the gt 42 | """ 43 | x_1 = -1 44 | x_2 = -1 45 | # from top to down 46 | for i in range(gt_img.shape[0]): 47 | chip = gt_img[i] 48 | if np.any(chip > 0): 49 | x_1 = i 50 | break 51 | 52 | # from down to top 53 | for i in range(gt_img.shape[0] - 1, -1, -1): 54 | chip = gt_img[i] 55 | if np.any(chip > 0): 56 | x_2 = i 57 | break 58 | 59 | y_1 = -1 60 | y_2 = -1 61 | # from left to right 62 | for i in range(gt_img.shape[1]): 63 | chip = gt_img[:, i] 64 | if np.any(chip > 0): 65 | y_1 = i 66 | break 67 | 68 | # from right to left 69 | for i in range(gt_img.shape[1] - 1, -1, -1): 70 | chip = gt_img[:, i] 71 | if np.any(chip > 0): 72 | y_2 = i 73 | break 74 | 75 | coordinate = [x_1, x_2, y_1, y_2] 76 | 77 | return (coordinate[0] + coordinate[1]) // 2, (coordinate[2] + coordinate[3]) // 2 78 | 79 | 80 | def _get_patch(img, gt_img, coord): 81 | patch = img[coord[0] - 15: coord[0] + 17, coord[1] - 15:coord[1] + 17] 82 | anno = gt_img[coord[0] - 15: coord[0] + 17, coord[1] - 15:coord[1] + 17] 83 | return patch, anno 84 | 85 | 86 | def set_patch(result, counter_map, patch, coord): 87 | """ 88 | set patch in result 89 | :param result: whole image result 90 | :param patch: patch result 91 | :param coord: coordinate of center point_move 92 | :return: 93 | """ 94 | result[coord[0] - 15: coord[0] + 17, coord[1] - 15:coord[1] + 17] += patch 95 | counter_map[coord[0] - 15: coord[0] + 17, coord[1] - 15:coord[1] + 17] += 1 96 | 97 | 98 | def _extract_patches(img, gt_img, coordinate, length=15, stride=4): 99 | """ 100 | extract patch from raw images, for each sequence extract 10 patches with stride 4 101 | :param img: 102 | :param gt_img: 103 | :param coordinate: 104 | :param length: 105 | :param stride: 106 | :return: 107 | """ 108 | seq_patches = [] 109 | seq_annos = [] 110 | for direction in directions: 111 | patches, annos = direction_extract(img, gt_img, coordinate, direction, length, stride) 112 | seq_patches.extend(patches) 113 | seq_annos.extend(annos) 114 | return seq_patches, seq_annos 115 | 116 | 117 | def direction_extract(img, gt_img, coordinate, direction, length=15, stride=4): 118 | """ 119 | extract patches along specified angle 120 | :param img: 121 | :param coordinate: 122 | :param direction: tuple for axis 123 | :param length: 124 | :param stride: 125 | :return: two list patchs and annos. each list contains two np array sequence 126 | """ 127 | patches = [] 128 | annos = [] 129 | coord = [] 130 | coord.append(coordinate[0]) 131 | coord.append(coordinate[1]) 132 | # positive direction 133 | pos_patches = [] 134 | pos_annos = [] 135 | 136 | for i in range(length): 137 | coord[0] += direction[0] * stride 138 | coord[1] += direction[1] * stride 139 | patch, anno = _get_patch(img, gt_img, coord) 140 | pos_patches.append(patch) 141 | pos_annos.append(anno) 142 | patches.append(np.array(pos_patches)) 143 | annos.append(np.array(pos_annos)) 144 | 145 | # negetive directioin 146 | coord[0] = coordinate[0] 147 | coord[1] = coordinate[1] 148 | neg_patches = [] 149 | neg_annos = [] 150 | 151 | for i in range(length): 152 | coord[0] -= direction[0] * stride 153 | coord[1] -= direction[1] * stride 154 | patch, anno = _get_patch(img, gt_img, coord) 155 | neg_patches.append(patch) 156 | neg_annos.append(anno) 157 | patches.append(np.array(neg_patches)) 158 | annos.append(np.array(neg_annos)) 159 | 160 | return patches, annos 161 | 162 | 163 | def encode_records(data_path, out_dir,record_name): 164 | count = 0 165 | 166 | regx = data_path + '*.jpg' 167 | names = glob(regx) 168 | all_img_seqs = [] 169 | all_label_seqs = [] 170 | for name in names: 171 | # print(name) 172 | short_name = name.split('/')[-1] 173 | short_name = short_name.split('.')[0] 174 | 175 | print('process ' + short_name) 176 | img, gt_img = load_img(data_path, short_name) 177 | # essential padding before extracting 178 | new_img = np.zeros(PADDING_SHAPE, dtype=np.uint8) 179 | new_img[(PADDING_SHAPE[0] - HEIGHT) // 2:(PADDING_SHAPE[0] - HEIGHT) // 2 + 296, 180 | (PADDING_SHAPE[0] - WIDTH) // 2:(PADDING_SHAPE[0] - WIDTH) // 2 + 296] = img 181 | new_gt = np.zeros(PADDING_SHAPE, dtype=np.uint8) 182 | new_gt[(PADDING_SHAPE[0] - HEIGHT) // 2:(PADDING_SHAPE[0] - HEIGHT) // 2 + 296, 183 | (PADDING_SHAPE[0] - WIDTH) // 2:(PADDING_SHAPE[0] - WIDTH) // 2 + 296] = gt_img 184 | 185 | coordinate = get_coordinate(new_img, new_gt, 0) 186 | imgs, annos = _extract_patches(new_img, new_gt, coordinate, length=seq_length, stride=extract_stride) 187 | 188 | for seq_imgs, seq_annos in zip(imgs, annos): 189 | count += 1 190 | all_img_seqs.append(seq_imgs) 191 | all_label_seqs.append(seq_annos) 192 | all_img_seqs = np.array(all_img_seqs) 193 | all_label_seqs = np.array(all_label_seqs) 194 | print(all_label_seqs.shape) 195 | np.save(out_dir + record_name + '_img.npy', all_img_seqs) 196 | np.save(out_dir + record_name + '_label.npy', all_label_seqs) 197 | print(count) 198 | 199 | 200 | if __name__ == '__main__': 201 | # encode_records(train_data_dir, '/data/jinquan/data/', 'train') 202 | encode_records(val_data_dir, '/data/jinquan/data/', 'val') 203 | -------------------------------------------------------------------------------- /test.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is just an example to show 3 | how our method works. For convenience, 4 | we directly calculate the mass center 5 | of the object according to the ground 6 | truth(in function: get_coor(mask, is_gt)) as the 7 | initialize point. 8 | """ 9 | import torch 10 | import os 11 | import test_params 12 | import numpy as np 13 | from glob import glob 14 | from math import floor 15 | from torch.autograd import Variable 16 | import torch.nn.functional as F 17 | from skimage.io import imsave, imread 18 | from pre_process import direction_extract 19 | from modules.Model import SkipConnecRNNModel 20 | from skimage.measure import regionprops, label 21 | from pre_process import set_patch 22 | from utils.post_process import post_process 23 | from utils.visualize import visulize_gt 24 | 25 | HEIGHT = 296 26 | WIDTH = 296 27 | PATCH_HEIGHT = 32 28 | PATCH_WIDTH = 32 29 | PADDING_SHAPE = (436, 436) 30 | directions = [(0, 1), (-1, 2), (-1, 1), (-2, 1), (-1, 0), (-2, -1), (-1, -1), (-1, -2)] 31 | 32 | model_file = 'weights.pth' 33 | 34 | 35 | def integrate(result, counter_map, patches, coordinate, direction): 36 | """ 37 | integrate patch result into whole image 38 | :param result: 39 | :param patches: segmentation result np.array 40 | :param direction: 41 | :param short_name: 42 | :return: whole image segmentation result 43 | """ 44 | seq_length = len(patches[0]) 45 | coord = [coordinate[0], coordinate[1]] 46 | 47 | # positve direction 48 | for i in range(seq_length): 49 | coord[0] += direction[0] * 4 50 | coord[1] += direction[1] * 4 51 | set_patch(result, counter_map, patches[0][i], coord) 52 | 53 | coord = [coordinate[0], coordinate[1]] 54 | 55 | # negative direction 56 | for i in range(seq_length): 57 | coord[0] -= direction[0] * 4 58 | coord[1] -= direction[1] * 4 59 | set_patch(result, counter_map, patches[1][i], coord) 60 | 61 | 62 | def find_red(img): 63 | coords = [] 64 | H, W, C = img.shape 65 | for i in range(H): 66 | for j in range(W): 67 | if img[i][j][0] == 255 and img[i][j][1] == 0 and img[i][j][2] == 0: 68 | coords.append([i, j]) 69 | return np.asarray(coords) 70 | 71 | 72 | def get_coor(mask, is_gt = False): 73 | """ 74 | get the coordinate of the center point_move 75 | """ 76 | if is_gt: 77 | areas = regionprops(label(mask // 255)) 78 | assert len(areas) == 1 79 | centroid = np.rint(areas[0].centroid) 80 | return centroid.astype(np.int) 81 | else: 82 | coords = find_red(mask) 83 | centroid = np.mean(coords, axis=0) 84 | centroid = np.floor(centroid).astype(np.int) 85 | return centroid 86 | 87 | 88 | def inference(): 89 | """ 90 | Test the model on the testing data 91 | :return: 92 | """ 93 | os.makedirs(test_params.output_dir + '/whole_seg', exist_ok=True) 94 | net = SkipConnecRNNModel(img_shape=(32, 32), num_class=2, batch_size=2) 95 | net.load_state_dict(torch.load(model_file)) 96 | net.cuda() 97 | net.eval() 98 | 99 | names = glob(test_params.test_data_dir + '*.jpg') 100 | names = [name.split('.')[0].split('/')[-1] for name in names] 101 | print(len(names)) 102 | 103 | # start predicting 104 | for name in names: 105 | print(name) 106 | img = imread(test_params.test_data_dir + name + '.jpg') 107 | gt_img = imread(test_params.test_data_dir + name + '_1.bmp') 108 | 109 | result = np.zeros(PADDING_SHAPE, dtype=np.float) 110 | counter_map = np.zeros(PADDING_SHAPE, dtype=np.float) 111 | 112 | new_img = np.zeros(PADDING_SHAPE, dtype=np.uint8) 113 | new_img[(PADDING_SHAPE[0] - HEIGHT) // 2:(PADDING_SHAPE[0] - HEIGHT) // 2 + 296, 114 | (PADDING_SHAPE[0] - WIDTH) // 2:(PADDING_SHAPE[0] - WIDTH) // 2 + 296] = img 115 | new_gt = np.zeros(PADDING_SHAPE, dtype=np.uint8) 116 | new_gt[(PADDING_SHAPE[0] - HEIGHT) // 2:(PADDING_SHAPE[0] - HEIGHT) // 2 + 296, 117 | (PADDING_SHAPE[0] - WIDTH) // 2:(PADDING_SHAPE[0] - WIDTH) // 2 + 296] = gt_img 118 | 119 | coordinate = get_coor(new_gt, is_gt=True) 120 | 121 | for direction in directions: 122 | img_seqs, label_seqs = direction_extract(new_img, new_gt, coordinate, direction) 123 | for i in range(15): 124 | imsave('label_' + str(i) + '.bmp', label_seqs[1][i]) 125 | img_seqs = np.asarray(img_seqs).astype(np.float32) 126 | img_seqs = np.expand_dims(img_seqs,axis=2) 127 | img_seqs /= 255 128 | assert img_seqs.shape == (2, 15, 1, 32, 32) 129 | img_seqs = torch.from_numpy(img_seqs) 130 | img_seqs = Variable(img_seqs.cuda(), volatile=True) 131 | net.reinit_hidden() 132 | 133 | logits, x_bottom, x_middle, x_top = net(img_seqs) 134 | x_bottom, x_middle, x_top = x_bottom.data.cpu().numpy(), x_middle.data.cpu().numpy(), x_top.data.cpu().numpy() 135 | np.save('x_bottom.npy', x_bottom); np.save('x_middle.npy', x_middle); np.save('x_top.npy', x_top) 136 | 137 | probs = F.sigmoid(logits) 138 | masks = (probs > 0.5).float() 139 | masks = masks.data.cpu().numpy() 140 | masks = np.squeeze(masks, axis=2) 141 | 142 | integrate(result, counter_map, masks, coordinate, direction) 143 | 144 | result /= counter_map 145 | result = result * 255 146 | 147 | result_img = result[(PADDING_SHAPE[0] - HEIGHT) // 2:(PADDING_SHAPE[0] - HEIGHT) // 2 + 296, 148 | (PADDING_SHAPE[0] - WIDTH) // 2:(PADDING_SHAPE[0] - WIDTH) // 2 + 296] 149 | imsave(test_params.output_dir + 'whole_seg/' + name + '_1.png', result_img.astype(np.uint8)) 150 | 151 | result_img = post_process(result_img.astype(np.uint8)) 152 | imsave(test_params.output_dir + 'whole_seg/' + name + '_2.png', result_img.astype(np.uint8)) 153 | 154 | result_img = visulize_gt(result_img.astype(np.uint8), gt_img) 155 | imsave(test_params.output_dir + 'whole_seg/' + name + '_3.png', result_img.astype(np.uint8)) 156 | 157 | 158 | 159 | 160 | 161 | 162 | if __name__ == '__main__': 163 | inference() 164 | 165 | 166 | 167 | 168 | -------------------------------------------------------------------------------- /test_params.py: -------------------------------------------------------------------------------- 1 | test_data_dir = '' 2 | output_dir = '' 3 | batch_size = 2 4 | -------------------------------------------------------------------------------- /utils/Logger.py: -------------------------------------------------------------------------------- 1 | import os 2 | import sys 3 | import shutil 4 | import builtins 5 | 6 | 7 | # log ------------------------------------ 8 | def remove_comments(lines, token='#'): 9 | """ Generator. Strips comments and whitespace from input lines. 10 | """ 11 | 12 | l = [] 13 | for line in lines: 14 | s = line.split(token, 1)[0].strip() 15 | if s != '': 16 | l.append(s) 17 | return l 18 | 19 | 20 | def open(file, mode=None, encoding=None): 21 | if mode == None: mode = 'r' 22 | 23 | if '/' in file: 24 | if 'w' or 'a' in mode: 25 | dir = os.path.dirname(file) 26 | if not os.path.isdir(dir): os.makedirs(dir) 27 | 28 | f = builtins.open(file, mode=mode, encoding=encoding) 29 | return f 30 | 31 | 32 | def remove(file): 33 | if os.path.exists(file): os.remove(file) 34 | 35 | 36 | def empty(dir): 37 | if os.path.isdir(dir): 38 | shutil.rmtree(dir, ignore_errors=True) 39 | else: 40 | os.makedirs(dir) 41 | 42 | 43 | # http://stackoverflow.com/questions/34950201/pycharm-print-end-r-statement-not-working 44 | class Logger(object): 45 | def __init__(self): 46 | self.terminal = sys.stdout #stdout 47 | self.file = None 48 | 49 | def open(self, file, mode=None): 50 | if mode is None: mode ='w' 51 | self.file = open(file, mode) 52 | 53 | def write(self, message, is_terminal=1, is_file=1 ): 54 | if '\r' in message: is_file=0 55 | 56 | if is_terminal == 1: 57 | self.terminal.write(message) 58 | self.terminal.flush() 59 | #time.sleep(1) 60 | 61 | if is_file == 1: 62 | self.file.write(message) 63 | self.file.flush() 64 | 65 | def flush(self): 66 | # this flush method is needed for python 3 compatibility. 67 | # this handles the flush command by doing nothing. 68 | # you might want to specify some extra behavior here. 69 | pass 70 | 71 | 72 | def write_list_to_file(strings, list_file): 73 | with open(list_file, 'w') as f: 74 | for s in strings: 75 | f.write('%s\n'%s) 76 | pass 77 | 78 | 79 | # https://stackoverflow.com/questions/1855095/how-to-create-a-zip-archive-of-a-directory 80 | def backup_project_as_zip(project_dir, zip_file): 81 | shutil.make_archive(zip_file.replace('.zip',''), 'zip', project_dir) 82 | pass 83 | 84 | 85 | # https://github.com/pytorch/examples/blob/master/imagenet/main.py ############### 86 | def adjust_learning_rate(optimizer, lr): 87 | for param_group in optimizer.param_groups: 88 | param_group['lr'] = lr 89 | 90 | 91 | def get_learning_rate(optimizer): 92 | lr=[] 93 | for param_group in optimizer.param_groups: 94 | lr +=[ param_group['lr'] ] 95 | return lr 96 | 97 | -------------------------------------------------------------------------------- /utils/NaiveDataset.py: -------------------------------------------------------------------------------- 1 | import torch 2 | import pickle 3 | import numpy as np 4 | from torch.utils.data import Dataset 5 | from skimage.io import imsave, imshow 6 | 7 | 8 | def image_to_tensor(img_seq, mean=0, std=1.): 9 | """ 10 | convert the image sequence into torch tensor 11 | do normalization 12 | :param img_seq: (seq H W) 13 | :param mean: 14 | :param std: 15 | :return: 16 | """ 17 | img_seq = np.expand_dims(img_seq, axis=1) 18 | assert img_seq.shape == (15, 1, 32, 32) 19 | 20 | img_seq = img_seq.astype(np.float32) 21 | img_seq = (img_seq - mean) / std 22 | tensor = torch.from_numpy(img_seq) ##.float() 23 | return tensor 24 | 25 | 26 | def label_to_tensor(label, threshold=0.5): 27 | label = (label > threshold).astype(np.float32) 28 | tensor = torch.from_numpy(label).type(torch.FloatTensor) 29 | return tensor 30 | 31 | 32 | def tensor_to_image(tensor, mean=0, std=1): 33 | image = tensor.numpy() 34 | image = image * std + mean 35 | image = image.astype(dtype=np.uint8) 36 | return image 37 | 38 | 39 | def tensor_to_label(tensor): 40 | label = tensor.numpy() * 255 41 | label = label.astype(dtype=np.uint8) 42 | return label 43 | 44 | 45 | class CustomizedDataset(Dataset): 46 | def __init__(self, path, transforms, mode): 47 | """ 48 | Customized dataset wrapper for cvpr-18 49 | :param path: 50 | :param transforms: 51 | :param mode: 52 | """ 53 | super(CustomizedDataset, self).__init__() 54 | self._path = path 55 | self._transforms = transforms 56 | self._mode = mode 57 | 58 | self._load_data() 59 | 60 | def _load_data(self): 61 | if self._mode == 'train': 62 | self._train_data = np.load(self._path + 'train_img.npy') 63 | self._train_labels = np.load(self._path + 'train_label.npy') 64 | self._num_samples = self._train_data.shape[0] 65 | elif self._mode == 'val': 66 | self._val_data = np.load(self._path + 'val_img.npy') 67 | self._val_labels = np.load(self._path + 'val_label.npy') 68 | self._num_samples = self._val_data.shape[0] 69 | else: 70 | self._test_data = np.load(self._path + 'test_img.npy') 71 | self._num_samples = self._test_data.shape[0] 72 | 73 | def get_train_item(self, index): 74 | img_seq = self._train_data[index] 75 | label_seq = self._train_labels[index] 76 | 77 | img_seq = img_seq.astype(np.float32) / 255 78 | label_seq = label_seq.astype(np.float32) / 255 79 | 80 | # transform into torch tensor 81 | for t in self._transforms: 82 | img_seq, label_seq = t(img_seq, label_seq) 83 | img_seq = image_to_tensor(img_seq, mean=0, std=1) 84 | label_seq = label_to_tensor(label_seq) 85 | return img_seq, label_seq, index 86 | 87 | def get_val_item(self, index): 88 | img_seq = self._val_data[index] 89 | label_seq = self._val_labels[index] 90 | 91 | img_seq = img_seq.astype(np.float32) / 255 92 | label_seq = label_seq.astype(np.float32) / 255 93 | 94 | # transform into torch tensor 95 | for t in self._transforms: 96 | img_seq, label_seq = t(img_seq, label_seq) 97 | img_seq = image_to_tensor(img_seq) 98 | label_seq = label_to_tensor(label_seq) 99 | return img_seq, label_seq, index 100 | 101 | def get_test_item(self, index): 102 | pass 103 | 104 | def __getitem__(self, index): 105 | if self._mode == 'train': 106 | return self.get_train_item(index) 107 | elif self._mode == 'val': 108 | return self.get_val_item(index) 109 | else: 110 | return self.get_test_item(index) 111 | 112 | def __len__(self): 113 | return self._num_samples 114 | 115 | 116 | def run_check_dataset(): 117 | dataset = CustomizedDataset(path='/data/jinquan/data/cvpr_kidney/input/vanilla/', transforms=[], mode='train') 118 | print('load complete') 119 | for n in range(2): 120 | img_seq, label_seq, index = dataset[n] 121 | img_seq = tensor_to_image(img_seq, std=255) 122 | label_seq = tensor_to_label(label_seq) 123 | print(img_seq.shape) 124 | print(label_seq.shape) 125 | count = 0 126 | for img, label in zip(img_seq, label_seq): 127 | imsave('./test/img_' + str(n) + '_' + str(count) + '_1.png', img.squeeze()) 128 | imsave('./test/img_' + str(n) + '_' + str(count) + '_2.png', label) 129 | count += 1 130 | 131 | if __name__ == '__main__': 132 | run_check_dataset() 133 | -------------------------------------------------------------------------------- /utils/Sampler.py: -------------------------------------------------------------------------------- 1 | import random 2 | from torch.utils.data.sampler import Sampler 3 | 4 | 5 | class RandomSamplerWithLength(Sampler): 6 | def __init__(self, data, length): 7 | """ 8 | Random Sampler with fixed length 9 | :param data: dataset 10 | :param length: num of data 11 | """ 12 | self.num_samples = length 13 | self.len_data = len(data) 14 | 15 | def __iter__(self): 16 | l = list(range(self.len_data)) 17 | random.shuffle(l) 18 | l = l[0:self.num_samples] 19 | return iter(l) 20 | 21 | def __len__(self): 22 | return self.num_samples -------------------------------------------------------------------------------- /utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/__init__.py -------------------------------------------------------------------------------- /utils/__pycache__/Logger.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/__pycache__/Logger.cpython-35.pyc -------------------------------------------------------------------------------- /utils/__pycache__/NaiveDataset.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/__pycache__/NaiveDataset.cpython-35.pyc -------------------------------------------------------------------------------- /utils/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /utils/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /utils/__pycache__/post_process.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/__pycache__/post_process.cpython-35.pyc -------------------------------------------------------------------------------- /utils/__pycache__/post_process.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/__pycache__/post_process.cpython-36.pyc -------------------------------------------------------------------------------- /utils/__pycache__/statistic.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/__pycache__/statistic.cpython-35.pyc -------------------------------------------------------------------------------- /utils/__pycache__/statistic.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/__pycache__/statistic.cpython-36.pyc -------------------------------------------------------------------------------- /utils/__pycache__/tools.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/__pycache__/tools.cpython-35.pyc -------------------------------------------------------------------------------- /utils/__pycache__/visualize.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/__pycache__/visualize.cpython-35.pyc -------------------------------------------------------------------------------- /utils/__pycache__/visualize.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/__pycache__/visualize.cpython-36.pyc -------------------------------------------------------------------------------- /utils/feat_vis/result/bottom_1.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/bottom_1.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/bottom_10.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/bottom_10.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/bottom_11.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/bottom_11.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/bottom_12.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/bottom_12.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/bottom_13.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/bottom_13.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/bottom_14.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/bottom_14.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/bottom_2.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/bottom_2.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/bottom_3.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/bottom_3.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/bottom_4.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/bottom_4.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/bottom_5.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/bottom_5.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/bottom_6.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/bottom_6.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/bottom_7.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/bottom_7.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/bottom_8.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/bottom_8.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/bottom_9.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/bottom_9.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/middle_0.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/middle_0.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/middle_1.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/middle_1.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/middle_10.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/middle_10.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/middle_11.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/middle_11.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/middle_12.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/middle_12.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/middle_13.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/middle_13.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/middle_14.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/middle_14.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/middle_2.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/middle_2.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/middle_3.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/middle_3.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/middle_4.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/middle_4.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/middle_5.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/middle_5.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/middle_6.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/middle_6.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/middle_7.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/middle_7.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/middle_8.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/middle_8.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/middle_9.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/middle_9.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/top_0.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/top_0.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/top_1.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/top_1.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/top_10.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/top_10.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/top_11.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/top_11.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/top_12.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/top_12.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/top_13.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/top_13.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/top_14.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/top_14.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/top_2.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/top_2.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/top_3.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/top_3.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/top_4.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/top_4.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/top_5.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/top_5.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/top_6.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/top_6.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/top_7.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/top_7.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/top_8.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/top_8.bmp -------------------------------------------------------------------------------- /utils/feat_vis/result/top_9.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/feat_vis/result/top_9.bmp -------------------------------------------------------------------------------- /utils/plot.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | 3 | import matplotlib 4 | 5 | matplotlib.use('Agg') 6 | import matplotlib.pyplot as plt 7 | 8 | import collections 9 | import pickle as pickle 10 | 11 | _since_beginning = collections.defaultdict(lambda: {}) 12 | _since_last_flush = collections.defaultdict(lambda: {}) 13 | 14 | _iter = [0] 15 | 16 | 17 | def tick(): 18 | _iter[0] += 1 19 | 20 | 21 | def plot(name, value): 22 | _since_last_flush[name][_iter[0]] = value 23 | 24 | 25 | def flush(): 26 | prints = [] 27 | 28 | for name, vals in _since_last_flush.items(): 29 | print(type(vals)) 30 | print(type(vals.values())) 31 | prints.append("{}\t{}".format(name, np.mean(list(vals.values())))) 32 | _since_beginning[name].update(vals) 33 | 34 | x_vals = np.sort(list(_since_beginning[name].keys())) 35 | y_vals = [_since_beginning[name][x] for x in x_vals] 36 | 37 | plt.clf() 38 | plt.plot(x_vals, y_vals) 39 | 40 | plt.xlabel('iteration') 41 | plt.ylabel(name) 42 | plt.savefig(name.replace(' ', '_') + '.jpg') 43 | 44 | # print("iter {}\t{}".format(_iter[0], "\t".join(prints))) 45 | _since_last_flush.clear() 46 | 47 | with open('log.pkl', 'wb') as f: 48 | pickle.dump(dict(_since_beginning), f, pickle.HIGHEST_PROTOCOL) 49 | -------------------------------------------------------------------------------- /utils/point_move/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/point_move/__init__.py -------------------------------------------------------------------------------- /utils/post_process.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | from skimage.io import imread, imsave 3 | from copy import deepcopy 4 | 5 | import numpy as np 6 | import scipy.ndimage as nd 7 | import matplotlib.pyplot as plt 8 | 9 | eps = np.finfo(float).eps 10 | 11 | 12 | def bwdist(a): 13 | """ 14 | Intermediary function. 'a' has only True/False vals, 15 | so we convert them into 0/1 values - in reverse. 16 | True is 0, False is 1, distance_transform_edt wants it that way. 17 | """ 18 | return nd.distance_transform_edt(a == 0) 19 | 20 | 21 | # Displays the image with curve superimposed 22 | def show_curve_and_phi(fig, I, phi, color): 23 | fig.axes[0].cla() 24 | fig.axes[0].imshow(I, cmap='gray') 25 | fig.axes[0].contour(phi, 0, colors=color) 26 | fig.axes[0].set_axis_off() 27 | plt.draw() 28 | 29 | fig.axes[1].cla() 30 | fig.axes[1].imshow(phi) 31 | fig.axes[1].set_axis_off() 32 | plt.draw() 33 | 34 | plt.pause(0.001) 35 | 36 | 37 | def im2double(a): 38 | a = a.astype(np.float) 39 | a /= np.abs(a).max() 40 | return a 41 | 42 | 43 | # Converts a mask to a SDF 44 | def mask2phi(init_a): 45 | phi = bwdist(init_a) - bwdist(1 - init_a) + im2double(init_a) - 0.5 46 | return phi 47 | 48 | 49 | # Compute curvature along SDF 50 | def get_curvature(phi, idx): 51 | dimy, dimx = phi.shape 52 | yx = np.array([np.unravel_index(i, phi.shape) for i in idx]) # subscripts 53 | y = yx[:, 0] 54 | x = yx[:, 1] 55 | 56 | # Get subscripts of neighbors 57 | ym1 = y - 1 58 | xm1 = x - 1 59 | yp1 = y + 1 60 | xp1 = x + 1 61 | 62 | # Bounds checking 63 | ym1[ym1 < 0] = 0 64 | xm1[xm1 < 0] = 0 65 | yp1[yp1 >= dimy] = dimy - 1 66 | xp1[xp1 >= dimx] = dimx - 1 67 | 68 | # Get indexes for 8 neighbors 69 | idup = np.ravel_multi_index((yp1, x), phi.shape) 70 | iddn = np.ravel_multi_index((ym1, x), phi.shape) 71 | idlt = np.ravel_multi_index((y, xm1), phi.shape) 72 | idrt = np.ravel_multi_index((y, xp1), phi.shape) 73 | idul = np.ravel_multi_index((yp1, xm1), phi.shape) 74 | idur = np.ravel_multi_index((yp1, xp1), phi.shape) 75 | iddl = np.ravel_multi_index((ym1, xm1), phi.shape) 76 | iddr = np.ravel_multi_index((ym1, xp1), phi.shape) 77 | 78 | # Get central derivatives of SDF at x,y 79 | phi_x = -phi.flat[idlt] + phi.flat[idrt] 80 | phi_y = -phi.flat[iddn] + phi.flat[idup] 81 | phi_xx = phi.flat[idlt] - 2 * phi.flat[idx] + phi.flat[idrt] 82 | phi_yy = phi.flat[iddn] - 2 * phi.flat[idx] + phi.flat[idup] 83 | phi_xy = 0.25 * (- phi.flat[iddl] - phi.flat[idur] + 84 | phi.flat[iddr] + phi.flat[idul]) 85 | phi_x2 = phi_x ** 2 86 | phi_y2 = phi_y ** 2 87 | 88 | # Compute curvature (Kappa) 89 | curvature = ((phi_x2 * phi_yy + phi_y2 * phi_xx - 2 * phi_x * phi_y * phi_xy) / 90 | (phi_x2 + phi_y2 + eps) ** 1.5) * (phi_x2 + phi_y2) ** 0.5 91 | 92 | return curvature 93 | 94 | 95 | # Level set re-initialization by the sussman method 96 | def sussman(D, dt): 97 | # forward/backward differences 98 | a = D - np.roll(D, 1, axis=1) 99 | b = np.roll(D, -1, axis=1) - D 100 | c = D - np.roll(D, -1, axis=0) 101 | d = np.roll(D, 1, axis=0) - D 102 | 103 | a_p = np.clip(a, 0, np.inf) 104 | a_n = np.clip(a, -np.inf, 0) 105 | b_p = np.clip(b, 0, np.inf) 106 | b_n = np.clip(b, -np.inf, 0) 107 | c_p = np.clip(c, 0, np.inf) 108 | c_n = np.clip(c, -np.inf, 0) 109 | d_p = np.clip(d, 0, np.inf) 110 | d_n = np.clip(d, -np.inf, 0) 111 | 112 | a_p[a < 0] = 0 113 | a_n[a > 0] = 0 114 | b_p[b < 0] = 0 115 | b_n[b > 0] = 0 116 | c_p[c < 0] = 0 117 | c_n[c > 0] = 0 118 | d_p[d < 0] = 0 119 | d_n[d > 0] = 0 120 | 121 | dD = np.zeros_like(D) 122 | D_neg_ind = np.flatnonzero(D < 0) 123 | D_pos_ind = np.flatnonzero(D > 0) 124 | 125 | dD.flat[D_pos_ind] = np.sqrt( 126 | np.max(np.concatenate( 127 | ([a_p.flat[D_pos_ind] ** 2], [b_n.flat[D_pos_ind] ** 2])), axis=0) + 128 | np.max(np.concatenate( 129 | ([c_p.flat[D_pos_ind] ** 2], [d_n.flat[D_pos_ind] ** 2])), axis=0)) - 1 130 | dD.flat[D_neg_ind] = np.sqrt( 131 | np.max(np.concatenate( 132 | ([a_n.flat[D_neg_ind] ** 2], [b_p.flat[D_neg_ind] ** 2])), axis=0) + 133 | np.max(np.concatenate( 134 | ([c_n.flat[D_neg_ind] ** 2], [d_p.flat[D_neg_ind] ** 2])), axis=0)) - 1 135 | 136 | D = D - dt * sussman_sign(D) * dD 137 | return D 138 | 139 | 140 | def sussman_sign(D): 141 | return D / np.sqrt(D ** 2 + 1) 142 | 143 | 144 | # Convergence Test 145 | def convergence(p_mask, n_mask, thresh, c): 146 | diff = p_mask - n_mask 147 | n_diff = np.sum(np.abs(diff)) 148 | if n_diff < thresh: 149 | c = c + 1 150 | else: 151 | c = 0 152 | return c 153 | 154 | 155 | def level_set(I, init_mask, max_its=200, alpha=0.2, 156 | thresh=0, color='r', display=False): 157 | I = I.astype(np.float) 158 | 159 | # Create a signed distance map (SDF) from mask 160 | phi = mask2phi(init_mask) 161 | 162 | if display: 163 | plt.ion() 164 | fig, axes = plt.subplots(ncols=2) 165 | show_curve_and_phi(fig, I, phi, color) 166 | plt.savefig('levelset_start.png', bbox_inches='tight') 167 | 168 | # Main loop 169 | its = 0 170 | stop = False 171 | prev_mask = init_mask 172 | c = 0 173 | 174 | while (its < max_its and not stop): 175 | # Get the curve's narrow band 176 | idx = np.flatnonzero(np.logical_and(phi <= 1.2, phi >= -1.2)) 177 | 178 | if len(idx) > 0: 179 | # Intermediate output 180 | if display: 181 | if np.mod(its, 50) == 0: 182 | # print('iteration: {0}'.format(its)) 183 | show_curve_and_phi(fig, I, phi, color) 184 | else: 185 | if np.mod(its, 10) == 0: 186 | # print('iteration: {0}'.format(its)) 187 | pass 188 | 189 | # Find interior and exterior mean 190 | upts = np.flatnonzero(phi <= 0) # interior points 191 | vpts = np.flatnonzero(phi > 0) # exterior points 192 | u = np.sum(I.flat[upts]) / (len(upts) + eps) # interior mean 193 | v = np.sum(I.flat[vpts]) / (len(vpts) + eps) # exterior mean 194 | 195 | # Force from image information 196 | F = (I.flat[idx] - u) ** 2 - (I.flat[idx] - v) ** 2 197 | # Force from curvature penalty 198 | curvature = get_curvature(phi, idx) 199 | 200 | # Gradient descent to minimize energy 201 | dphidt = F / np.max(np.abs(F)) + alpha * curvature 202 | 203 | # Maintain the CFL condition 204 | dt = 0.45 / (np.max(np.abs(dphidt)) + eps) 205 | 206 | # Evolve the curve 207 | phi.flat[idx] += dt * dphidt 208 | 209 | # Keep SDF smooth 210 | phi = sussman(phi, 0.5) 211 | 212 | new_mask = phi <= 0 213 | c = convergence(prev_mask, new_mask, thresh, c) 214 | 215 | if c <= 5: 216 | its = its + 1 217 | prev_mask = new_mask 218 | else: 219 | stop = True 220 | 221 | else: 222 | break 223 | 224 | # Final output 225 | if display: 226 | show_curve_and_phi(fig, I, phi, color) 227 | plt.savefig('levelset_end.png', bbox_inches='tight') 228 | 229 | # Make mask from SDF 230 | seg = phi <= 0 # Get mask from levelset 231 | 232 | return seg, phi, its 233 | 234 | 235 | def post_process(img): 236 | """ 237 | post_process: 238 | 1. threshold 239 | 2. CRF 240 | 3. minimum connected graph 241 | 4. level-set 242 | :param img: 243 | :return: 244 | """ 245 | mask = deepcopy(img) 246 | mask[mask < 255] = 0 247 | mask = mask / 255 248 | seg, _, _ = level_set(img, mask, max_its=800, display=False, alpha=1.0) 249 | return seg*255 250 | 251 | 252 | if __name__ == "__main__": 253 | img = imread('example.png', flatten=True) 254 | # mask = np.zeros(img.shape) 255 | # mask[20:100, 20:100] = 1 256 | 257 | seg = post_process(img) 258 | 259 | # seg, _, _ = level_set(img, mask, max_its=500, display=True, alpha=1.0) 260 | -------------------------------------------------------------------------------- /utils/result_vis/D0025759109.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/D0025759109.jpg -------------------------------------------------------------------------------- /utils/result_vis/D0025759109_1.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/D0025759109_1.bmp -------------------------------------------------------------------------------- /utils/result_vis/D0025759109_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/D0025759109_2.png -------------------------------------------------------------------------------- /utils/result_vis/D0038207736.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/D0038207736.jpg -------------------------------------------------------------------------------- /utils/result_vis/D0038207736_1.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/D0038207736_1.bmp -------------------------------------------------------------------------------- /utils/result_vis/D0038207736_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/D0038207736_2.png -------------------------------------------------------------------------------- /utils/result_vis/E0015433121.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/E0015433121.jpg -------------------------------------------------------------------------------- /utils/result_vis/E0015433121_1.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/E0015433121_1.bmp -------------------------------------------------------------------------------- /utils/result_vis/E0015433121_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/E0015433121_2.png -------------------------------------------------------------------------------- /utils/result_vis/E0016786877.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/E0016786877.jpg -------------------------------------------------------------------------------- /utils/result_vis/E0016786877_1.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/E0016786877_1.bmp -------------------------------------------------------------------------------- /utils/result_vis/E0016786877_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/E0016786877_2.png -------------------------------------------------------------------------------- /utils/result_vis/E0048968076.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/E0048968076.jpg -------------------------------------------------------------------------------- /utils/result_vis/E0048968076_1.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/E0048968076_1.bmp -------------------------------------------------------------------------------- /utils/result_vis/E0048968076_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/E0048968076_2.png -------------------------------------------------------------------------------- /utils/result_vis/E0056225398.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/E0056225398.jpg -------------------------------------------------------------------------------- /utils/result_vis/E0056225398_1.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/E0056225398_1.bmp -------------------------------------------------------------------------------- /utils/result_vis/E0056225398_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/E0056225398_2.png -------------------------------------------------------------------------------- /utils/result_vis/E0066596328.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/E0066596328.jpg -------------------------------------------------------------------------------- /utils/result_vis/E0066596328_1.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/E0066596328_1.bmp -------------------------------------------------------------------------------- /utils/result_vis/E0066596328_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/E0066596328_2.png -------------------------------------------------------------------------------- /utils/result_vis/result/D0025759109.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/result/D0025759109.png -------------------------------------------------------------------------------- /utils/result_vis/result/D0025759109_cropped.eps: -------------------------------------------------------------------------------- 1 | %!PS-Adobe-3.0 EPSF-3.0 2 | %%Creator: PIL 0.1 EpsEncode 3 | %%BoundingBox: 0 0 150 150 4 | %%Pages: 1 5 | %%EndComments 6 | %%Page: 1 1 7 | %ImageData: 150 150 8 1 0 1 1 "image" 8 | gsave 9 | 10 dict begin 10 | /buf 150 string def 11 | 150 150 scale 12 | 150 150 8 13 | [150 0 0 -150 0 150] 14 | { currentfile buf readhexstring pop } bind 15 | image 16 | 726a5a57666c6a6f6b68686d6e6d70767179858d8c857b758085898a8a84756858616a6e6b6868 17 | 696465625e62728794a5a08b6e5e5640251c1e1d19161514121b25271d192027271c1b19181616 18 | 17181a213640312423211e25251d191a1308112038536a787d7c837c7779818785808f87818489 19 | 86776958596574726667736a69655b4a392b241c16110d09070d1610132f58613e6e6a61657677 20 | 6d6b645f5f6669666568696e7b8c958b705a6e7c8a949a947b605f5c606d7d837c736b6e6a6364 21 | 707a7c8ca0996d453830242224221c171715111821231d1d22201718151313161a1d1e0f0d1c2c 22 | 2923211b1d2a2f231817140e14242f33456476767d736b707e8a8d8a938880848f92897e745b53 23 | 6671665c5e7075776e5c46362e2d15070e130a03051e14132f5f71776b67717c79706a6662636a 24 | 6c686464666975858b7b5d455060738a99886b5f6561616872746d6563646760596674717c8e8b 25 | 562f2318231a2a33291a16191d191b160f1522241c211712171c1c1b1d0b0b0d12181c1b1a1d18 26 | 13121212151924231d19234164797578766f6b7383908c817c82837d7f868c74594c50585a586a 27 | 767d7a7268564537291e1a10010004131c191a3e6b726f6e70706f747c7373757879756b635e63 28 | 7182816a4e3c515d66727f77635b6a6765686a675e565b5b606163737c726b736d3f222018221e 29 | 2d3630241d1b1a161511111f2d2819130f10191e1c191a1514151b21211b15090b0f171d1f2121 30 | 21211c151a304b5b6f7a7b6a5b62798c857d7a7f7e787a83847f715a46445362717b807a78796f 31 | 604d3a2921170c0a1016140c0d24476d6a6a6b6a6c737b757b7d7d82857d707778818778563d37 32 | 505d61677980746a716b6460616466685e5d646b7485867553514b28161e1b231b27313028201a 33 | 15171a1a1a222a24170c0e151e201b17151918191e222018110308111a1f1f1a151c1e1a12101b 34 | 2b3454708072626a819284808286847e818a7e87877255485262707c7d73747f7f745f4831241b 35 | 121115190e07080e205c56535a656966616c73736f78898b808178746e5534282f4b5859607b8b 36 | 7e6e686765626264696c615e646b73807e6a40363821141f1f241a20282b29241e191f26271f19 37 | 191a1915192024221b161312131415161718191115181b1e1d150d171b1b130e10161a3158787c 38 | 788088897c7e84898782858d7f878e8a7c6a5c546472746764727a756a533b2c2219141317100c 39 | 0c0a0e3b38373d4953534e686b64585d717b776d5e50453323263540453d42647a71615c62686a 40 | 655d55515b575a5d616e6d5a34263025172021221e1f22272a29272626241d14111418191f2224 41 | 23201d1a190f11110e0c13212d1f1f1d1a1e24211a131b1e18121213131d3b5c6f7d8782756f73 42 | 7b807f7d8288868990979482675258676c625e68737573624f41372a1c1512100c07070c1d2225 43 | 222431404b6060564741495151493e312b28272c333430202346656d6e696764605b59595a635d 44 | 5d5f64727260321b282517212422201c1b1e2122252826170807131f201c2222201c1c21232216 45 | 1716110f17293924221a121620211a131b211d18171818111e34506e81827a7577797a7c80878e 46 | 8c8f94958f816f64575d6465666b737b756d63584b39251710100800010b191f20191823333c3e 47 | 42433c3029292b222326303f49423431281616314f667a7870655d5c636c73726763677384816a 48 | 3a141a1d15262c27241d181918171a2022170e101a22252424221c171c262b291f1d1916161c26 49 | 2d1f1d130a0d18170d151d231f1a1b1c1c0b0c1a3858707f88837d756f727d89918d90928f8981 50 | 7b785d5454636d6e70777475726a5a442c1b19171007060a2625201c212a2a2415202f352b1b16 51 | 191a283e5a7b8c7b5e332b191320324b687472706f6f6e6b6876655e657688806443111015142c 52 | 352f2c241e1c1813151c1d2327251d1a222d28251c171e2b2f2c241e19181b1d1c1a13140e080f 53 | 1b190e171f231f1a1b1d1e0c08132d45576d828277665a5d6d7d878b8a8a8c8e8c8681624c455b 54 | 6c6b676b787d7e77664e34222422201b120b261e1b1d1e1b1d221c21282c2822252c2f375883a3 55 | b6b4a15f1f11271c152a3648536365616b71676f686872776d5a4b241e1c222a2d2f322f1e1318 56 | 1d1b1a1c1f24231e1d22221d1b21211a15161a1c18161412100f1217111412121d2721111d2325 57 | 22232827231613171f25314f6e777d7867606870717d8692958d848184736c62584f5060706f7b 58 | 7d726f6e5c433c2e221d140a2722202427272b312d2f3437332c2b2f373c5e90b5c5bda76e3721 59 | 231515211b2c2e373f4a617579706e6f70675441372c27262a2c282626231e1c1e1e1914131b20 60 | 2423211e1a151c21221a14121313171b1b14121619161c272a211c1e1d16171e24252727201715 61 | 161b1e1a1d36526a787e7771716e68717d8a8e877e7c7e87837b69544b56666e7d84818182725b 62 | 403226221b1229282a303334373b3534373c3b36343525274b82a7b0a0885c3827221d2a32211c 63 | 23282b3344525859606967563d2e2b28272a2e2c231c1a1d2428241e1b1a191a1c21221c120e0f 64 | 1d22231c151312101820211a181c1b162028291f1614120e1215181a1e1f1a12161b22231b192b 65 | 43586f8488837b6c5e64707e8584817f7f8f908b77594548567681868282847b6c47392d2a251c 66 | 262f3e4c545656564f4a484a484038352a2945718b8f83705b42332e2b353e35455a53301c2027 67 | 29414e5e62523a2c291b1e262e2c2118150e1c21150a0e161a202125241a0f10171d21211c191b 68 | 1c1b1c1e2325221a15141d1b151013150e0318130d0c11181c1c1e2024241d1c28384f6884918f 69 | 8473656068727c858b8985888d8e8167504a506f73716b6a70726f514336302b212a3f5c76858a 70 | 88847c7269635a4a3c3538313c52647a898874553e373134495e8fb3974311111c223742545e57 71 | 4230291e2028302f2318131122281b0f121c21242b3332261b1d25181b1b191a21262720191f2c 72 | 27140c141b1712111417140d21170d0a0d131b201f1b171717192027495e778689847c7568686a 73 | 707f8c8b8286898e8d7f6b5d596162625f5e62696e605242362a1b3f587a94a3a9a59f9189807a 74 | 7060524c403631375189bdcfb687573d291f3b65aeddc061271b191c222a3a4b4f43342b2d2a2d 75 | 33312618111a28312c211d22272739453e2d222022121516151820252421181b2622110c16151b 76 | 1e191110151c1a140f0d0b0a0d12130e090d16202729374558666e747a7e77746c687281847e89 77 | 888c918c7d6c62676b71746f696a6e7165523e2b195068869ba9b1b2aea6a29f9f9a8f88857167 78 | 595270b9f7ffffc77f482006133989b6a3613b251315151925353d382e292d26242a2e261a1214 79 | 1920231e1a1f2843575c43271e1c1a12161716181c1a161d1c1a151315181a151a1d19110e161f 80 | 0f0d0d0e0904070f100e0d121c272e30262f3d4b5867788589887b6b697885878e89898d8c8173 81 | 6c686e787f7a7171797f76644e382551688397a9bac3c5cecbcccdc9c0bbbba69c87758bcdfcfd 82 | fbcb834b291218355975633d322417252221262f322c24212017141d27251c151f1b1d24262632 83 | 416c7c7246211a1c1a161a1d1b1a18120a18221b06061a241e1d17131417191a1b0e0d0e100b08 84 | 101d1d1e1d1c1d212425232a364555687f9095978b7369788d98938e8a8c8a837b775156647173 85 | 717b89857f705b46374f6b839abfdeeffafffdfcfefffdf5eee0d7bfa29ab5e2ffffce7c49341a 86 | 1c3f5d62563924201e171e232a2d2a2219140e0b0f1a221f1813191d2324263a648aad9b7f5a3c 87 | 393c3229291b131d24201e25231b1211171d1e161e14040911100f04090d0c09080c101c231610 88 | 1e1e18252d3d403e485566798d989582757d8a8f8d8e867b7c84837960585d676a737c7b7a7873 89 | 6958435b82a7c4e3f5f9fcfefcfbfdfffff9f4f3f9f3d7bcb5c4d3dfba855f4b35262845525340 90 | 2c221a121d1a181a1d1e1b180c101b272b2723231f1a131834669ec4aa9f989086837d6d544a2d 91 | 181b1e19191f201d1714151410212112070c100c0d0c0d0c080303090e171f17111b1a18263137 92 | 31282f4055687782887f75747c817f84827a7b858a86786c65605d687574767779766a5380acd4 93 | eefffffffefefcfafdfffffefbfffffffaf0e1cbb8b0a18e7357463520323d3e30221c1b19120e 94 | 0d131d2525231f23292b261f2027161515255088b2c397909cb3bebfb6a58a754826201e171720 95 | 211e171313100c1c1a141b29261b1b1b1b18130d0b0e1118201d1b21201f2939372f282e3c4a52 96 | 566274817f76727578818581818b93958b7e6d584b596b6c71757c827d66b2d7f3fdfffffdffff 97 | fdfcfdfffffffffffcfaffffffeed6b2a39b8560534e3b363022120b111e2613151a22282a2723 98 | 2f2a241d15121923151f27324f717f7a6c647799acb3b2aaa28859362d251b1a201f18100d1013 99 | 120f0f18354d422a25232524211b1614141f23252a333431303e353236414f524744475c7b8a81 100 | 767478808686898f949388827559424e656a6d7178818372d5f2fffdfbfaf9fffffffefeffffff 101 | fff7fffffffdfdfefde3bea59173665f4e402f1b0e0c121c2420262b2c27201c1a221912101215 102 | 1c23232e30292d3b3f3837324665737b83838875523934291b191a1a1711101518180c0d1a3d59 103 | 4b2e262725211c181617191f1b2233444d493d3d271f293c5a685b4d3c3f5e7a7f7b7a75797e84 104 | 8b8f8d887f8381684b4d616a696c7179817cdff9fffefbfafafffffffffffffefffffdfffffefb 105 | fefffeffd2a48e8070563b3d302625221a15162023252019161b20150e0c151e1f1c1a202a2c24 106 | 1e1e1e1916182b40464d5655564d3b3130241514181d20202122201c110f1533514c39352d251a 107 | 110f131b21170c152e465959473b18070b1f547e7f613f283859707a7f77787c848d918e898185 108 | 8b7d5e546169666a6e727c82e0f9fffefefdfdfffffffffffffefefffffef9fafffffff6ffe9bb 109 | 95887653382d27282e281913171919171311151e251410131e26241d17171a1e2224211b151517 110 | 242b2a333a3432312a292b1f11141b20232222221e191512102340453b392c251a1210151b2012 111 | 020b233850594a2e0d000009427d896945252847677a827f7f80858a8d8f918a848987705f6369 112 | 666e72717781e4fafffbfcfefefffdfefffffffffffffafffffffefefffffaffe4ac928064551f 113 | 1b1e231b1015251f1c1713131518191411141f2727252320130c14212624222120221d19252c22 114 | 272926282b1e13181a1b1813111313101a1710192f332824221f1b17161514131502091c2a4454 115 | 471a03030301306b7863472c2d49697d848282828180828a92908081887866656969737873737a 116 | e7fcfffffffbf7fdfffffffffffffffffefffffffffffffef7ffecbf918484653323232c282320 117 | 1a1a14141b1c181b241f26231a1b262418231910121c23201b1c1b1a1a1c1e1f1f201e2023211c 118 | 191b1f141a1d13191e0c1e1c1714171c1a1311171c170e090c11050d0e112a4a4f3f1803000000 119 | 25596d6b59463c3a445e7785827b706c74818a8474686f7d807468647179757072e6f7fefeffff 120 | fcfffffffffffffffffffefffffffffffffefbfffbe6b48d8a7b6343302f292116080d131f2929 121 | 2421232729251e2026231a241c13131b21211e171718191b1c1c1b1e1d1f211f19171818182832 122 | 2b2f2e1c2524201c1c1b13090c1114110a07090d20180806234953471900000f254d737d82725d 123 | 4a3a343e4d6b7b81766f78807f7f7b79808884725f57646b645c62cdf4fff9f9ffffffffffffff 124 | fffffffffefffffffffffffefffdfeffc9898286784d2e2825221808141a1f1f20262c2e25211d 125 | 1e2225231f16100a0a0f171c1d1214171b1d1e1f1f1e1f242a2c292b2f333137362e3339313535 126 | 332e2a24180c1214171818191b1e1c1406031b41575a351109274e72898b877d6d5944322b2c50 127 | 7188827d83817681868886837a65504b5a655f565ba5e2fff9f4fdfffefffffffffffffffffeff 128 | fffffffffffefff9f7fdc983787e653f25201f201f16272821171c2a333127201d222625222217 129 | 130e0b0d13191d1b1d2124272a2d2f272930373836393e43413c30282c343536383834312d2319 130 | 1413121213141414040c100f152b485c523227456c8694998782786c5f4e3a2b3a5876858a897f 131 | 72838b8b807a766b5c526170726b6b8fb2d9f7fffbf6fffffffffffffffffffefffffffffffffe 132 | fffef9fdd3957f6f51392c2a211e22222a28201a202b271b2621202526211d1e2826221f1e2125 133 | 282b2c2d2d2c2e323631323638332c2b30333a39312d2926262427282728292621221d17120e0b 134 | 0603060d1517151c3248594d4d65828e959f938f87817f73573a28304c7288867c787f86878180 135 | 838079636a747a79768f829ce4fffdeffffffffffffffffffffefffffffffffffefffffdffe4ae 136 | 865c433535382e282c2d22180b060e16150e12171d201f1d1c1b202023262c3135372d2e2e2924 137 | 2123262a2c30312b2323283840392d2c261c1e1a1e20202227282625211b1613100d0b150b0812 138 | 1b2130415b67717f8e8d899395938c878b896d4c251927557a8281867e7e808284837f7b6b6665 139 | 696d6d8c7b85bff6fdf7fffffffffffffffffffefffffffffffffefafbfcffebb4814b36282b38 140 | 3834312b21160c0b10161e2425343c372f2c2924191b212932373736282b2d29211a1819202329 141 | 2c2721232a434c4034382f2021252a2c2a2a2d2d2a1d1b1814110f1011170703121f2432456178 142 | 80828e8d868d999a9288898a7456301b18375f77838b7c716d777d7973736e6560646a6a7f9093 143 | 9ecdfafffdfffffffffffffffffefffffffffffffefffcf9ffe9ae7943321e1e30373529192525 144 | 2d393c3739416274796550453b2f2f2f32363a38312a282f34332c231f1e2023292a221a1c2231 145 | 46494b57482b2433383a3633322f2b32302b241c181718150c0f1c1e1929435f7878758995949c 146 | acafa48f868470563923132044687c83756058687777787f77706e757a796380847696dffffbff 147 | fdfbfdfefcfdfffbfefffffbfffffbfff8f9fde2a66e544215090a121e1410232f3e40464c5673 148 | 8fa6a594856447483d39373d433e30222a2a2b2c2c2a26242a27201916171817221d36616a4d37 149 | 3a435259504948433a34393d382d2523251d0a060c0b142a385f647083939ca0a3abaca391847f 150 | 7569512c160b1f476484756e57587c8a828482796f7a8f8a46546a7785b1e8fffffefafeffffff 151 | fafffbfdfefbfffffef9ffffe1b48d6d583f190d06060f0c161c334b545c626e8996a6a7a09770 152 | 4537322e2a2a2c2c2a27212a33332b282c33313330282120232426273653696d68666c69676a72 153 | 72604c3d39332b2524262926140f0f09112939546172818c959a9ba7a8a1938a88807662402a13 154 | 132a4162777765627d8c88897f796e74827e5256778b7c8bccfff8fdfffffefdfdfdfffbfffff8 155 | f8fffffcfff6c18b6b5a4f3c231e16111518303e64818e8e868895a7b3b6b0965e281522222220 156 | 1e20262b2930363633343b425157574a3d3634322f363c49698f9e99887f7e8a928872604c3f2d 157 | 201b1d202321181c1e15182b394f647982878d908d9699968d8c8f8c8375553c1a070e1f427982 158 | 786d79868686817d72707875896562737da3dffffdfffffefefffffdfffcfffffffcfbf6ffe8c9 159 | a67c55434237292b2727272d5079a4bbc4ba9f8e849da7b0a87e40160f1c212627252326293434 160 | 384455626869838c8d837870675d575d5a55688b9c97888c98a1957a6b6c61533e2b1f1b1a1b19 161 | 1b2a30221b2125425a727d8691928b8a8e8d898d94928a7a5b44240f0f1a3b708182726e767b7a 162 | 817f726c7270eecebba3746eb0f6fffff6f1fafffdebffedecfafffae6cbdcbe9d876d53494e43 163 | 352f272b2e3b6ba5cdd4d9d0b4a289867f8587673821231f2226262524252635445d7991a2acaf 164 | b4bdc2bfbfbfb2a298978c786d6f716d778297a29175707e7d7666533f3028261f233136271c1a 165 | 162c40586d8192948e8d908f8b8d928d8165493f3228231e31566c7b7060636f717f7e716a7171 166 | f3f5fff4a35a82e5f4fffffffcfffff6c4cad9dbcdc3b8a89b917f6858555c65624d362126304c 167 | 8fc6ede6eaebdad8bd92695d695a38231c1f1f1e1c1d232f39547aa8c2c7cbd8e7dce4e5e3e7ec 168 | e1cec6c4b8a18878716f696c7b8f948f939e9a978f7e6853433c2b272d312c2f34302b35485f73 169 | 7f82818e918d8683827566402a2f37382b1215334b6b6d58586a7283867a727879fffdf6ffe68c 170 | 5871c5e7fefcf9fdf7e98ea6bcb29894978e6d635e5d554c5361655031161d2d57add6fff7faf8 171 | e9edd0975f4d5f54351f1420272d2f3446627897bce3ebddd5e5faf4fbf7edeef6f2e4dfe2dac6 172 | b7b3b1ac9185808b9ca6abaeaba79d907d6650432f2322272f404d49393b495d6a6c727b878985 173 | 7c7872604d311b26353c2c0b091a315e6f58536978848c8477797bf9fff9fcffc3807e7d8c9bb0 174 | d2e4c4938e93958f8e9c9577614140606240354a47381e040d2153b3cefff8f7ebd0cfac7a4842 175 | 5e55382d2929394c5661799fbecadff0ecdcd8ebfffafffdefeefcfffbf2faf2dedbe9ede4d8c3 176 | aa9fa1a6a8a8b0a7998c7c664d3a3020191e293c463f3d3d4b626b6a768a8284817a756f5b463c 177 | 2329373e311415122759725b51697b7d8983737073e0f7ffffeec49681939e9987828678604854 178 | 6571747373746a646361513c363e3a1e150a0a224e8bbad6eeefe2cfb7a1794d3f403130362930 179 | 4b67829cadbfd6e3eaf5f7eadee5f6e0eaf5fafdfefdfbfdfffff2eef8fefcffece1ddc7b4b4b8 180 | b5a69e94806d573f3829191318212b312a3a4b58697c827e837975808a7f624945362d34403d29 181 | 15182a577377645d837c8787776869acc4d1cec2aa98979d9f988d8f978f7e4c3f445b5f504e5d 182 | 917d634f423834332b1a1f19131f3f74a9cbe9ece1d6c8bc9a6f402c2416111c3a74a9c1cdd1d8 183 | e5f0f6fefff0dfdae0d1dceefdfffbf4eff4fbfbf3f1fafffcfef7f8f5e9e0d0bab6a9a4a19383 184 | 6d543f31211a19191a1b212935455b6e7778847c797f847b64514a3a2d303a3826141521496671 185 | 655d7f8d8b7f6a5e64889ca6a29a8f8f9e9d9c9a9ba1a59f965c463f4d565156647b766c62615a 186 | 4022150f201f1412224a769bbdc5c1bfb8aea27e40252a191a467cb4dde0dddee4edf0f3f8fbf6 187 | ece6e4e6e7f0fefffffffffcfffffbf8fbfcf7f1fafffffeffecc1bcb0aeaea08c6d4c41332621 188 | 1e181312161720344b5d6b757a7b7e828278665752412f2b32322415171a3a59706c617a8a8375 189 | 66616b86919594948d8d9a9b9ea6b0b2aba39f7d7666585d6d736e747d796b6c725c3a1c162726 190 | 1c161835566f8692a5bdc5bd9f815c504e445c95d8ecede0d7d2d5e2ecebeceff5f9f8f4e9e3e6 191 | f5fcf9fafffffffffcfafcfbf7f1f8fdf8f9fffad6cbbebcbcad936d474030201a150c06071111 192 | 1c31424f6274777f87867d6e5b4d574732292c30271b1b173052737564737c7d7b7570728e8d88 193 | 8d9b9a98a0a3a8b4bcb7aaa4a69fa0927c74776e5e7590957e7477654425181e1b161310233540 194 | 4b6190c5d7cd957c838f7a76a2cffef9eee5d7c1bfd5eceeececf3faf5ead7d6e1f5fffdf7f5f3 195 | f5f5f5f8fdfffffcf8faf9f6fefff3e0d0c8c4b6a1826148321c130a000000101422323b42566c 196 | 767e80776a5d4f43534633272a312d231912274b72775f667b848c86776d9a9083869495949ea4 197 | a9b0b2aca4a4a9aea9a6a49880685a64889782767b6f532a18181311120c1a091a2f4e82aea98c 198 | 62567ca49ca7d6f4ece2d8d4c6abb0d3e1ecf1f0f4f7ead8d5d2d5e0f0fcfffef7f6f5f6fafeff 199 | fffff7fbfff9f8fffff0dbccc0ae9b82664d36231e19101017131a242c2e3344545e625f544f52 200 | 504b433c2e242934332a130b1f426b73595c79848d867266a19b908c8c828292979ca1a4a7a9a9 201 | a7a7a3a3a6a393786470827b5d576d7568312327221f1f1723142b425573856d45373b5f95b9d2 202 | efffdbd0c3c2beacacc2d5e6f1eeeff2e7d4d4ccbfbacce9f9fafffdfcfefffffdfbfef7fbfef7 203 | f8fffdf1e0d5c8ae9171513e2a1f24261e1e261a1e201d1e2731363b3f3c373c4749432e2c251f 204 | 2735362d140c1e3e68735d61747d847d685e9ba1a09a8d79798e8b929ba3b0b8b2a69ca298898e 205 | 9a845f75827a5f5760563b201924201a170d1838484b444b594d313f4b598bd1eaedffddd4c7cc 206 | d6c9afa5d6e9f0e7e4e9e3d4d7d4c7bdceecf9f2f6f5f8fffffffefbfffcfdfaf5fefffce9e3e5 207 | dec19b7049271610191b0f0a1021221a11142026222d32312d333a33241e201d1b2534362d1912 208 | 23416a78656c777d827963549395999b9691939a9898989ca7b3b5b1a7aba594858084888e9580 209 | 6c726640290704191f1811102a50717060583d2b3c3d4b71a8d9f1f7f8f1e1dae1e1c8a185b5d3 210 | e8e6e2e6e4dbd8cfcbd3e1e8e7e3e8fdfffafbfcfbfefffaf9fefef9fbfff4dfd8d9c49e6e472e 211 | 11050a0602070a18191c19110e1724343438392c1b18211f1c191211232f2714101d426a7c7468 212 | 757c827d6d629595999e9f9ea1a6999fa3a3a5aaaba9a5ababa1969291908b949391907a533725 213 | 18222424262a4468738292814c3e645d6b8fbfe4f0ebe4e3e2e4e9e5ceab9090b5d8e0dadbe1e4 214 | d5cecacfd8dddbd8e4f1f7fafffffffffafafbfefefcfdfff6e8e6e7d7b37e4d3e261a19121214 215 | 101411111315161e272a2d37403f32231a24170f0d162a2d1c17101a3e687d796e778088827063 216 | 949296a0a7a6a4a4a1abb1aba5a5aaadaeb5b7b2a9a0968d73788ea19a8062482d1a1b191b2226 217 | 3d56556f928b6b78a6b3b1b8cadce4e5e4e6eff3ede5d8c2aba1b5cdd8d3c9c4c3cfccc9cbcfd3 218 | d3d1d7d5dbeafafffefdf4fafefdfdfefffdfef8fafcf1d79f644b3426201817170f0a04020a12 219 | 171a1d1d25334656543c2422160f0e15282c1d140a0f325d7472686c79878574669995969fa5a2 220 | 9c98949da09a94969da2b2b9bdbcb8b1a3976d61768c7c6457482a1819141318172a3938496073 221 | 93bdd7e5d9cdcad1dce6ecf4fdf8e5dcdfd7c7b0a7abc4dadbcdc2cfd0cfced1d7dad9bfafb1c9 222 | dee9ece8eef8fefdfcfffffcfffffffffef1c1855633201f191212120702020a100f0d0d111a27 223 | 3a5361543d1a13110c09182725150c12355f7573686a7988877465a299939498989899939ba0a0 224 | 9fa09f9ca2a9b2b9bec0b9b18a6b686d543e3d3c3122251e1c23263b3e37384872afd5d5cac9c8 225 | cbd4dee4e6fafff3ddd8e2dfcfb99f95b0d3ded4c8cfd2d1ced2dbe2e2b59da0bbd1e3eae1e6f0 226 | f9fbfbfdfffefffefffbfbfcddab6933151c1a11172318181a1e1a100a0a0e1419223850585421 227 | 130b04021324251d18254a7387827775828f8c77669e958c89898d97a1a0a8b1b5b7b5aca2959d 228 | a5abb2b7b5b09d79625a47322f362e2021181a2831483b2c294b87b3bfbcc3c6c7c8cfd9e0e2f9 229 | fdf4e2dde1d7c4b9a3959fb1b7b4b1b9bdbbb8bfcfd9dac6b1bbd7e6f9fdead3dae6f0f3f2f8ff 230 | fffffffbfbfff5d48a45151415131e2c2b2d313026191314181918182238505e45250d0913272e 231 | 24181a2d5378878177737e8a8a7d718f929697939199a59ca1a4a5a6a9a6a19ea5a9a9a8a8a59f 232 | 9c8369615b422e302918171014222432211c1b4790b5b7bee0ddd1c5c4d1e0e7fdfff7e5d7cdbc 233 | a9978c848791999b99969a9a9aa9c2d2d3d6cbe0f8fbffffdbb4b6c5d9e0dde7f9fdfefffffcff 234 | ffeeb9702a0d0a152121272728271f1614181819191819254058653e211c2636382a151a2f516e 235 | 766d64676f7a7e78748797acb6aea2a0a69e9e9992939eaaafadb3b6b3aeaaa5a0a0937b757755 236 | 2d2632201f191e25181914201d3e8ebfc8d5e9e6d9c9c6d3e2e9fffef3dcc4b09c8e8c8276767f 237 | 867f748085868ba1c2d6d9d3d1edfffafae9b89998a9c5cecbd8f0f3f6fffff9fcfef3e59c460e 238 | 041a2314151110100e0b0d120c0c121614172f496c4c342b2932362e21273a566b6d635a666a70 239 | 716c689a958b91a4a8a4a8b2b1b5b7aea3aabab5aea8a7a7a5a5a8a6918b876d5249495e513e2d 240 | 231c150e160b1c5593bdd7e8e6e4e4e1d7cdd0d9effcdcb9b5a28483847a767f868178747e8089 241 | 92a2c4d9d4c9c0d9fcfff8dcb393878ca5b8bfc9d8def6fffffafefffef8c46621161003040000 242 | 020a0d0c1018070409151a1c2a3c64604022293831241c314f6d868b735669767f786963a49c8d 243 | 889192929ca7a5a8aca69ea4b2a39f9ea1a2a09ea0afa297877370726b8b84663c293031273126 244 | 366daaccdae1f0e6dbd5cec6c2c4e9fee9c3af9175786f7a8fa3aba39489776f75869bb3b8aaac 245 | afcfebe9e1d5c09e87849fb4b5b7c2dbf2fffffcffffffffde883a1c0e02040c0a0d1418181a1e 246 | 241d1a1d1c1a26365f674e2e3343361e1a365a798d8e785f6f7d86817573aaa5968e908c8b9697 247 | 939398989498a299989da6aba9a7a7a2a6a28c7b817c618897885f506368585c4e5888bedbe1e2 248 | eadbcecdd1cfcac6e4faecc8ae907c838f9fafb3aca2989187797c898e908b7e8a96b4c8c1bdc2 249 | c1ada4afcbd3c2b6badceffffffeffffffffeeac58291814161a17171d22211f1e322c2928221b 250 | 1d273c524a32394733151e4169808986766575858f887c7aa1a19b9ca29b9297918a878c8f8f91 251 | 9698989ea9b0b0afb0a5adaf9f92988e717d94957b72848c8281727598c2dbe3e5e2dad7dde6ea 252 | e4dee2e9d8c0b6a7999aa2b4c0bcb2b1b5b8a69999998574777b7a81929fa2a5aeb6c3d5ecf5e7 253 | d3cbcedce7f5fcfefffffdfaf6c57135232423221d1b1d201f191318191e221e130e0f132c3535 254 | 404129132449707d786f665e6d818c7f6d6a9898949caaa69a99a09893959a9c9c9d9d9b9da5a9 255 | a8a6a8a29fa09c969da197969c9785797d878b8e8588a0bcccd2d5dfe4ebf2f6f5f0ebe5d7c2be 256 | cac8b09c9fb5ccd4d2d3d8ddc4ada1987f717b897f7b7a889ca9b0b7dcf4fdebd8d7dcdbced1da 257 | eaf7fdfefeffffd9873e242019211d19171918110a0000060d0c06010108182c444e391e18254f 258 | 777f71625a55607882705958a19b9195a6a69ea0b5aea8a7abafafaeb0aba9abaaa5a2a28c8891 259 | 99928f9290918f90918a7f7f868c8a92a6b9c0bebccad9e8ece9e8e8e7e6d0c2cfe5e4c19b96a0 260 | b3c4cfd6e1eddeb89a8b7972777b827d7582a2b4bcc9e6f7f9e9e1e6dfcebbb2b6cfebfafdffff 261 | ffe59d4a241a0e181815121416140e040302030405080a10193050542f12162e5981887768605d 262 | 63787f6c5a5faba49795a0a09ca3b9b4adabaeb3b5b3b8b3b0b1afa8a3a28d91a2a89a8f8a827a 263 | 7a8493978d85858e8c93a7bbc2bfb9bacad7d5d0d3dadfd0c0c2d9eeefd2af8b808297aebfd6ed 264 | e1bd9d88756f6f6a7078767e98a8bad6e6f2fdfffcf0dac7b29e9cbae1f6fbfdf9fbf1b45a2616 265 | 080a0e0f0e121b1f1e17140f0b0b101415101d3450512d11163b5d7978696164666f7b7a69616e 266 | a7a59b979c97949cafaba6a3a6acaeaeaba7a7aaa9a29c9b959ba49d8c898c8685807e83898a87 267 | 85958e90a3bdccccc7c4d0d5ccc3c7d2d9afa8b6d1e3e9dfc9a88c7f8e9ca0abbecebaa791766e 268 | 7270597076788691abd6e8eefefffce2d3d4b59a92b1dcf3f8f9fbfffec763220d000005090a11 269 | 1f292b1b1a1613131515140b1f384d4f341c1c40566257484a596473786f5e5f718f9ba3a7adb0 270 | a492a8a0a4aca18e92a79d979397a2acb0b0a8ada59a968f8b92958a858a8c88898e9a8f91abc6 271 | d0cdc9c9c5c3bfbfcbc7af8687a1c5dae4e3d8b3877a909994979db0aca4968172727a72777f7d 272 | 727496bdd0d7e9efe0d8dad8c3aa98abcbd9e8fffffdf6d78c350a0a07101d23201c232e25201a 273 | 191b1a11070820445949291b22475047393c485768787466575c7192989c9ea8b3b0a4a0999ca5 274 | a49a9ba69c9b9b9ca1a8afb4b0b1b0b4b29c909a9f9b9a9d9d9792909d989eb2c2c1bcbac7c9ce 275 | cbc6cbc0a56f7095cbe9e8d2b8a48f8078727c8a8c9b9289837e7a7c81797d7d797b8ba2b2bec1 276 | ced2c8cddee6dbcbbabeced5e2fcfefdfeeaa7552825262627241c15171d1e1b16151617141010 277 | 2645513a190f173f4e4f474c586a7e817d6f62677b9d9e9b979eaaaeaa9d9898a0a6a7a5a59ea1 278 | a19d9899a1a9aba19aa3a490899c8e8f8d898888857f9092a0b3bcb7b3b5c6cad1cec6c5b59780 279 | 7b9bd1eae1cab39d87756963718489858280807d787a7f7a7b7470809ba6a1a0a3aeb1aebfdeee 280 | ecece2dadad8e0f3fbfcfffbc2724139322a23201c161415181817161515171a1c2d3e3a1f090e 281 | 203e525956595f6d818984776a6c7dabaca69b95989c9d9b9a999aa1a8a8a4a4a6a7a39e9ea3a9 282 | a59e95969787808c8d8d847776818784878b9aafb9b6b5b9c3c4c8c5bfbda8868c88a9dae9dccb 283 | bf9f745f696d6d757c6a737f827a707179726f6a6c7c8f948d868b979b9bb3d6e7e7f3f1e6e3e1 284 | e3edfafaffffcc7c44342d241f2225211a1613181d1d1711131a2133403417040c1d3a4d585c64 285 | 676d7b8b867a6d6d78adb2b1a597919194989d9d9a9ca5aaa9a8a7a8aaadb0b1b1a8b5b6b1afa1 286 | 8d8596968c7d7a858d8d93919aaebcbdbec2c3c3c8cac8c3a77c7477a1dbf1e2c5ac9572667272 287 | 6966655c5f697375737478716b6c737775777d7d7f87898ba8ccdbdee7e1d7dce2e5ecfdf9fffd 288 | ce7d3f29292322292d2619100c131d1f140809122339483c200b080d273846586c73757e837f76 289 | 6d6c73a3a9ada9a19a98999ca3a8a7a6aab0b3a6a29fa3a8a7a098a0b5b7adadaba19c9c9d9991 290 | 8c8c8c8a989297acc0c8cdd2ccd0dae0ddd4b183797490c4e2dab68e8181847f75797a6e72645d 291 | 67787f7a7379757a827c6d6b757f7e7f7d83a5c9d5dcdbcdc6d2dee4ecfff9feffd58541241816 292 | 1a23261f140e060c16190f040917313c3b271411181f1826364e69706f7675736e6a686c9c9a9c 293 | a1a5a5a09c9fa4acb1afaaa9ac9f9c9a9c9e988c8294a09d93929398a4a4a4a7a7a1969192918b 294 | 91a5b7c1cad2ccd3deded5ccaf888d8693adbfc1ab8a7d7f837f7880877d83766e757f7f766f7f 295 | 82888c89817b797f7f82848fb2d0d4dad7cccedde2e4ecfff7fdffdd8c43200d0d111819141213 296 | 0c0d1216110e1f3544402b0e021021291a27374f6669676f767573706d6c9c928c95a3a8a1999b 297 | 9ca5aeab9e9695999a9da2a5a1978e959b9a978f7f7d8f9a989ba09b8e8a90908b8f9da8acb4bd 298 | c1c7cdc4b4ad9e82828ca1acabada795886c636e706f717174798287817670707e878d8e959a90 299 | 807b7f8a93a3c3d8d4d6d7d7e2f1ede6ebfcf5fcffe18f411a18171716120e111817131417171e 300 | 38564b463012060c100b1e2f42596d6e6f7c868584807a748e8f939aa1a19b95928f939b988b82 301 | 839aa6aba29b9c999390a0aaa39388858487858b9496908e91908f97a6adabadb3adb6b9afa29b 302 | 948d8a818fafb9a89fa7928279706569727373777a7a756e68657a80818397ada892898190aab7 303 | c5deeef4e6e4e9e8eef7f7fff7ffffe48d483129261f19191e1d171b21231c17223b514c341d14 304 | 0e0401061225435e70797c7e858d888288899b9c9fa4a6a1968d8b8a8b8d8c8c90979ca09f9894 305 | 979c9fa19f9a96989992899197999493989a979899a3b2b9b7b9c0c4c0af968788939a94939fb5 306 | beb5a8a497938f82747a8582867e7574757063576c71707186a0a598a29da4b0b8cadbddd2d4e7 307 | f7f6f5f8f5fff7fdffd5834838372b1c1313181d2026282b2e343f4e5835251716140e0d131525 308 | 3e596c787b7c78756e707976a09f9fa1a4a39f9a9da09f9c9da6afb5b0adacaba8a6abb3b8aea0 309 | 989ba19d94949f9b898799a6a49b9fabb7b6afafb7b9b3a4918891a1acadb3beccd1c3a8929597 310 | 988873757d78797c7c756b676a6f75777270819daba99e98989ba4bac4bbaab8daf5f7f6fbfaff 311 | fafff9c679473d3d2a170f0b080d151211152337474e4e2a211d1e1c16171d1726415e747e7c77 312 | 7f77707a8378a7a19996999fa5a8afb6b7b3b6bfc1bbadaaacb2aea29fa5a1a39d9087878d9096 313 | 9b937f7987989f959fb1bab1a3a3ad9ea6b0b8bcbcb8b4b2bbd1eaeccd9f7f7d797c7766616666 314 | 686f74716b707f8d8786817d879cabb09c9094a4b4c5c9beafb6cfe6eaf1fcfffafbfff5c17746 315 | 372c1b10131208060e0200051426302f291e1b1b1c1a171b22232e435d737e807d91908c92998d 316 | b4aca09895989da1a6aaaaa9b1bbb8aca7a3a5aba79b9599919a9d9387858b90969591887d787e 317 | 888d9eb7c3b8a6a6b19fafcae2ebdec6b4a4acd1ffffd3997c6a595e6d686068707a6e63677785 318 | 8987868788898e99a3a99e8fa1cce2e1d7cbc6bec4d1d7e3f1f4eff8fff8c8844e371c100f1b1f 319 | 18161d161d28303026170d0a0b0d0f10121b242e3a4e62737c80818b948e889094b0ada8a39f9d 320 | 9c9c9b999697a1acaeaaaba5a09f9e9d9fa4a7a9a69f9995908a888a919790827e838a9ab4c4bd 321 | a89fa2a8b6cde3e7dac7bcafb3d5ffffcc947d77636573716d767f877c716e747c80808a8d959e 322 | a2a2a2a59d90ade7feefd9c9b7a5a2adb8c8d5d5e3f6fffed1925d412319151a1d19181b23374d 323 | 53452e1c120e0e0e0c0c0f171e26436a858a80736b737c70637186a5a6a6a6a5a4a4a49f9b9a9c 324 | 9fa1a6aca19d938b8c959da0a8a59e96928f887f838a909392908d8b8891a8c3cab9a59cafbacb 325 | d4cdc1bfc5c4c4d4e8e0b68c79827a78736a707c7d797c7c766f72808c9b9ea9b5b4a69b979e94 326 | acddf5f0dfceab968e949baab6b5cfecfff2c186573e27211b1715120d091229414535231b1c19 327 | 181612101215172349778e866f5e576464544b5d72a7a6a4a1a0a1a5a8a3a2a6a9a09598a49f9f 328 | 968a8b989f9d9b9e9d948f90949692999484828e91898489a2c9e2dcc4b3bbc8d7d5c0afb4c3c3 329 | c2c3c2b7a18777757d7c66586c7e776d6b6a6e78858f95a7a8b1bbb39b867d8e8492b2cbdbd9cb 330 | c6ac9c96939aa4a4b9daf0daa3683f2a1b1d1d1a19170e03021424200f050a1512131312141719 331 | 19334d6668574a4f59615849495a63a6b6b6a49eabaea49da6aba69f9d9c9b958d92a2a4948684 332 | 959796929499968f94918e8d8c89847f8081a3c9d9e8e8d1bbb5aca8adb8bdbec0bfbcb4a99d94 333 | 8f88776c6f726d6b6f686a7175727893b1afb4bbbcb0967761756b6e8298adcce9dccebebac1c4 334 | b5a2a7bbc7b68c5c3724160b0e1f251a1216171e1e150f12161617131114171b232d4a63766b4e 335 | 41526a666461606979a2b2c0bfb5aeb0b69ba5aca89f9a9592908a888d8b817d7f7f84878a9197 336 | 938b94908c8b8c8c8b897e88aeced1d5ddd8c4b19a9095a3b3bdc9c4bcb3aba6a5a69689818381 337 | 767072797c7f7e78798696a4a4a4a29a8b796c6e66646e809abfded9cec8d5edf3dbbeb6c2c8b5 338 | 88532d1c120b0b161d1d21292b2f2c211a1a1b1a0704080f0e0e21395c7a8466434360797d7f7d 339 | 7c818d9e9eacbcb9a7a6b3a1a9afada8a1989091908e8984868e969a948a858b979c9c938f8c8b 340 | 8d9193958491bbe0e3dde1e4dbbd9d8f909aabbabcbab7b1a9a19994918c8b8d877a7273787b7b 341 | 78787e85878d8b898885807a756b6b696a7795bedce1d9d5e1f9fffceae7e8e1c58d4f2a1f1e18 342 | 100b0d151e242b2b271f1a19171303050d110c0e2a4d596b6646385072818d8f8c868589a89692 343 | a4aea6a0a4aaabadafb3b2a699989fa0958d90999faca2938b8e979ea0908e8c8b8d9195978c96 344 | bef2fffcf1eee5cbb2ababadb6c2bab5ada3978c827c7c7c80837e7470726f716e6a738388837b 345 | 7b7b7b7a79777570787c7a84a5cfecebeeefeff2fafffffff8e7be7c3e22232a26190c0c171c19 346 | 16151412110f0a060b151b171423435d554c3931466a7c7a80807c787779b1a69fa2aaada7a1aa 347 | a49fa4b2b9ae9d9ca5a89c8e8888888e8d8d90918e8a878a8a8a89898a8c8e8b94b5e8fffef1f2 348 | dfd1c6c6c8c7cad1d0c0a89389878a8c7a7b7e7d77706f73727473727b88877d807e7a76727071 349 | 71757e827e87a9d8f9f2fdfffffffdfcf9ece2c7934f1a0e1a1d1d18131b28281d0d0c0c0e0d08 350 | 030009171a121e405b6160473746677c7c75706f6d6f787ea4b1b8b0a8a8a8a4a59d9598a6afa7 351 | 98969b9f9c938a85858b8a8b8a867f7d7f87878785838283858490a4c5e1e0ddeae7e4dfdad5d2 352 | d0d0cabdab9d979798998c8c89837b75747673777c828a8d887f8d877d736b6a6d717678767177 353 | 96c7edfffffdfcfffffff8ecddb6763209040d0a0f12151f272217100e0d0f0e0a090b08100f0f 354 | 2a53645c584c4f66797c7a7b7877767980859dafbbb5a8a4a6a8aaa6a19ea2a59e95928b8b9294 355 | 9091979b9690887f7b84918c8c8985818083878a9193a8cbd3ced6e4eff1e4d7d1c9c0b2afaaa8 356 | a59f948c91908b847e7b79797473777f82807f8184827c756e6d7073767371707181a7ccfdfbf6 357 | f2f6fcfcf7f6e2b06a2f130b08070d151918140f0a0f0c0d1114182430271c1623415b5f56545b 358 | 6a7980808184868989868482acafb4b5b2aeafb2b5b7b5ada5a29d989280788289888d988b8d90 359 | 9088848e9d94928e878283898e9794889dd0e1cec5cae2eee3d6d0c5b5b1aba4a09d978d858584 360 | 827e7c7c7c7a7d746e6e6b666c786f74797a787574757673777c797992b1e8f7fffffbf4efece6 361 | d19c582c1d14080b141e20160b090d0b090b141d2b43595035293f595e58546a7884868a8f8e87 362 | 858e928d8480ddc2b7bcbab5afa5afb6bebcae9f9ea49a948e8f92938e887f8c9494979f9c9186 363 | 8683848c938c80898390b4d3d7cac0cfebf6e2cec6b9a5adafa2897e858d8d8a857e7b7b7a7570 364 | 767272736b5e5d6568696e747777777875807a767e78788ed3eef7e0cdd5e9f4e3a364301e1e14 365 | 19172a30262329200b0c0f10101a2e414b453a3b4a5656575d72818e8d83808b978f8d8c8c8987 366 | f3d3bcb5b4b6af9eadacaeaea8a1a2a7aba196969b9d978f969fa7a8a6a095898b8b89888d908a 367 | 7f827784b0d8e1d9d4d5f3f9ddcccdbb9c969a9a94908d867f877e7471757774706a6c7275716a 368 | 6769636970726d696b6f67757674786f6d81a8c6d7cdc8daf1fbda904918101c1e2e3e3f33211c 369 | 20190a1013131219242b2c313a4c5d63646a727b797676787d8386807f81858686efcdb2adb5c5 370 | c7b7a9a3a1a5aaacafb3b5b0a8a0999593929694959998928f909294949393938e87877a8cc2ed 371 | efded5d8faffebdddec3989794969b9a8f847f7c756d6d737776726a737b7c7b7a76717b7c7b78 372 | 746f6a666f7b80807f74707e93b5d1d8e1f8ffffd7863f1718272b3e372d1e161a22231e171a1b 373 | 1b1e2324202e4b69747170767c716f6d6e74797d7e73707175787cebc3aaabb0b5b7b1a6a19ea1 374 | a4a2a1a398a1a69c8b838a948b7c727577798698989a9b98938d8884898099d6fef6dbcee1f8ff 375 | f0e6e7d6bbb4a69d9c958887907a78757576787878717c828081888a868b837c7c85888073888a 376 | 8a8b8982818895b5d3e2f2fffff4ca7e442a30352a331d130d111a202325191e1f1d2029323644 377 | 627a797171716d6a7885847870747b736e6b6e7074c7a297a6a69da0a8a5a4a4a2988b83837e88 378 | 91918c898d938d7c7276757079898d9092928d8581808d8498c9ecebe1e0f5f7f5ebe1dde0e3c8 379 | bab0ab9b8b90a29390897e747379807780817a7a879294757675788392989594898587898d9294 380 | 9bb0c3cedfece0c79e623a2d35351e1d1d1510110f0b0b101115150f11233b4b5c6e77716e7471 381 | 657b8b98917d6d6e7579777a80817da78d90a6a4989eaaa0a4aaa99e908b8d938e8d949e9f968b 382 | 878287918f80787b777a838d91909194a19697aabdcbddf1fffdfffeeed6ced4c6c3c4c3b3a2a4 383 | b3b5ad9b85736f7780818582766d73808b7380857c78869ba8918281888b97a5a6b7bfc3c7d8e4 384 | d0b1693e271f2b311c1817110a060201040a06090702092140557179797478828177878887827c 385 | 797b7d7d818b959485b6a9a8aa9f979794979ba2a6a29d9fa6a59d979ba3a296898285909b9b90 386 | 8582767881909898999ca19e9a9494a3c3dfe8edf8fff4dcc7bdbdbdbebcb4aeb3bec2b7a59180 387 | 7773727c80827a6e6a798c9da59e887a8498a491868f9997a3b6b8cdcfcdcfdde1bf94462c2017 388 | 2331211c0d0b07060a1215150306091023425e6c8287888380838482817a716f757d84877f8186 389 | 8c8572b1b0aea49ba3a595908f9093939399a194969897959392928d8e9194949291908c888b93 390 | 948c8685818e94897f89a6c0c4cbd3dae0e1d9ceb5aea59d9ca4b3bfbbb3a79d92837063676f7b 391 | 817a7789a3c3bba48b85929c9b928d9faba0a8bcbfc2c5c5c9d4cc9a6236272318213122191a1a 392 | 18171f262014080c15294a6d848c8990948b7c7374787c78726d6d737c82827b767166539a8f8c 393 | 99a6a69d979996979287898c8387878e8c81838d8f8b8e93948d8a94a2a59c959491867466756f 394 | 747263698eaeafa6afc0c5c9cdcbb2a79b9390929ca7b5b8b2a08e827d79686870726c738183ab 395 | a493838799a09c8887949d9aa0acafaec2cad1d4a8684a3135362f231b1b1f1514121c28221c24 396 | 1b2e485c6d7d888b7c807f7671767e838584848587857f7a7d68564e41318a878b939796989ca4 397 | a3a599848085808a918f878688858083878e969c9d98939693908c89898b8f90867f6e51547ca0 398 | b0b1babdbbc1c5bcb3a18c7f7d889dafaeafa99b8f8b8b8a6e68717a746e6a6180899095a0a9a1 399 | 929592999b97a4bbc6becbcacac5965331313231291d151315100f090d17171e313e536a787e82 400 | 827f7d7a736d707b8386898a8c8f8f8a827c5c463534342ea4a6a69e8e807f8697948f79606174 401 | 7b8f9b92889392838079848f949b9f978a88878685888f989da195896c484a78a0bcc0c7c7c7d8 402 | e2d7b8a1857473839db3bbb8ac9a8c888684716a7b959c9896928f979c9ea3a7a19595969fa09b 403 | abc9d8d1d6c9b4986a3a2636332e261d17151617160f0f151726415363747a7a797775847e7470 404 | 767e7d767279838985756051402f252d3838a0a4a8a59c9290917d71624a394d7489909988808a 405 | 77626e768c98918b919591898a8b8f969a948b968b7d60404a7faba597959fafcadcdbc4ac8f7c 406 | 79849aacb6b2a6948883817e7b748aa9b2b5c7d6d4d2c7b3a6a4a5a59ea8babeb6c0d5decac6ae 407 | 835533282c342f27201b1b1e201b1b171b262c3d586a73787571757b7e817f7c7c808075686466 408 | 6661554331242b2627344141898a8d949b9d958d6f5e4d3c3b5e8ca2a7a59188835a45627d929c 409 | 948e959a988d979fa09f9c93898c7a64452c417aa4855c4c64829eb9c7cfb697827b818f9da9ac 410 | a9a29d9ea09fa4a2b4c5bab5cee9f4f4ebd4beb5b9bfb5c0d0cfbfbdc3bfa794754d291d242c26 411 | 21191413181f2412110d172b384a657477766f6c707679717578797a7971676a5f4d3a2a222020 412 | 1e22272c3030756f686c79807769665a514c527296a2a8a4989281584d6b858e96999fa49e9384 413 | 99a7a094929699947754321f3769886d3d2c4a6884a9c7ceb69782797b848da0a7a9a19a989a9a 414 | afb4c9d2beb6cbe2e5e4ded0c5c6d4e2e0e2e4d5beb5afa0836245352c3030241e1c181311151c 415 | 2213110c14242d3a51676c6f6f7174736f656766605b5a5956534d43362a221f1e2b302d201512 416 | 4e4840415267706e6760606063788f928c8f928c7964637082868e979c9b948d84929a928d9298 417 | 988f6e4b30263956604a2c2638465e8bb1bdab978b847f7f8187909186787274768e96adbbb6ba 418 | ccd7d9d0c5bfc3d0e2effef7eedac4bbae966b4c3c3a383d351c2123241f171315191b22272e34 419 | 2d2d3d5b5f63686e70675c4e4e493f3836332f2b3035352e241c18333a36241511433e332d3a56 420 | 6d77726e716f6d7c8d8e8e9aa59a8581837b7a818c90887f828b91918c8a95a09a89775b423431 421 | 3f4841382f31312839678daba29b99958a7f797c888e857a7981898c90a2b3bbcbdadadbd0c7c9 422 | d3dbdfe0e5dcd3c2b2ab9a7d5d48444334322c1623292d271a0f0b0b192e445354413741464543 423 | 43474538292c2e2d2927251e15202222201d1b1e20202f352d27262e4c3c21375866726f787a74 424 | 76858f8f969b9d958a858b93807c818d9590898695989b9da09c8f81694a2f2d363733322d3240 425 | 473b3c6da9b6aba5a5a29a96998c8b837c828e908890a0bad0d7d6dde9e8ebecebe8dfccbbbcb0 426 | 9e928a857f7963605e5b4c3320191e2e3831211d28343c48535143373334362b242727211a180b 427 | 222720272f2923252f29171526312e2f2a231f22263a393c3c415874807c736b63657d92928c86 428 | 7b73727a868f8582848b8e8d90958a95958b8a8e826d4f4433272d3b3c33213a5c67534e80c0c0 429 | bdb4a89d9a9c9f808385827a767e8b95a8c6dee4dfe0e6eee7dbd1cbc3b1a09b9283746e75828d 430 | 84847f756c5f47313234333132373f454c4b453b30282728241d1a1c1c1a1b1f172525212a302c 431 | 2b2c2b2620212b353a2e281d14161e6840404e404561686c56515457728b888676635c65758085 432 | 91908f8c857f81888090907f7a7e6a4a3d453b262a414535223b5c644d43689ca3b2b9ab968b8c 433 | 8f8a8c959a8f838da1afbacbd8dcdde3ece6d5bcaaa5a6a197938b80797a828e9691948e858a8f 434 | 7b5d4a3b2d2e3c494c4a4c3f2f2522211d1a0c0d1015191c242d2c2e26242c2c272a272020272a 435 | 25252b28241b100d13af724e4c423d42425646556e74828c7e88786765707c807e9394948f867d 436 | 7a7a87959a938e825c3340473d2b304547372d30383a2f2738526e8eb0b19476717c93969ca3a2 437 | 9fa1a7b0b6bec3c5c7cdd3c4b49a86838e989c9491919aa6a8a09693918986919d9380624b3531 438 | 393e3b363023171923271f150d0f151b1f2123252621171b26211b231f1d212a2b20140f131819 439 | 141012e9b76e4b54503e3b4f4f76a7b7b1a490867a6e6f7a83858282838485878a8c8c969ca9b7 440 | b3925c33453b302d38423e33322a26272522242a46648c977855597385969e979397968e939eaa 441 | b0b0aaa29d9e9a8d7a71768188818894a2acada8a2a69a8f8e9293908d7f6951413629211f160c 442 | 0812232b24191c1d1d1f211c12080d08030d1c17121c1f24272728261c0f040d15161518ffeea1 443 | 625f573e3a3d4c7dc3ead7b19e746a6266748287877574706f778591959497a6b7b08752303a27 444 | 1e2b3c3c31292f2f31312e28222027374c503d2f446684a2af9a88898a838f95999a989690898f 445 | 979789787071737b8791918b8d99a6afa39b9c9a928d8f87745e4b36211718130d0b132128251e 446 | 1c1b19181a180d010f0e0b111b150f162024221b1c25251f111616121014feffd88f5941383334 447 | 4a75c3fad48d76574f4b576d7e827f7778736a69748188898f95907c5b38202b1e1b2e3f3b2a1c 448 | 2225292d2f2d23191c272c282a3e57668da4b1a4938f8f8c9898928a8b9192908a94988f837f80 449 | 828e92938b81808b959c9c9d9d9b938578624f3f382f221d20202123262827231f1c1b150f1015 450 | 15101f231e1d221e181e1f1b18151312161c1919140b070aebfafcb8522e3935485d7cc5fec15a 451 | 38423b3d516d7e7b717b8382766d70797f84908b6d4c36231224212534433f2914120e0c172a35 452 | 2a1a293a3e384e77887e8b90969b9a96918d8e91918e8f93908880858682838e9ba29a95909094 453 | 928a8287939894928c7152321e1219232424282a323b3d362b221d2a281d0d070e171a1b24221f 454 | 2628282f2217161c1401000b0a0b09040509fbfff8cb8a584c56708590adc7953f183646515974 455 | 8f8a707f90988b7d8194a39a9281694a2f201d1e21272c2b26262b1d1f24282a2b2f343e536c7d 456 | 8a928c807d7a74758595938688909594959a9993827d7b828d93928d898685888e9495948a838b 457 | 9083726151250d0313201a141719242f312a211c1b252e2b190c0f191e1919191513151c23110f 458 | 17232010060709080a0d0b08f7ffffedb579585468a7c8bc9c5e2922405e716e7180878078767a 459 | 858a8b8f9687837356382520211f1d1d1d1915192022272c30323845506b7780818387857d817f 460 | 7a7a859191898e9194989d9f9b949f958b8a8f938f8a838180848c949798867d78726c6e644d27 461 | 18152226190e0e1013171716191f24282e2f29211e1c1a221e1915141517180b090d16150e111a 462 | 161214191913f5f6fdfad18c594762a4bfa37a4f34374e69786d636b7576604f52728c8b83817c 463 | 7e704e2e23262b25282f322d221c1d222d3a424a5768768a8d857770777d7d898e939596938a81 464 | 7c747077848e9497aca59e9a99968f898b8a8a8d91918d8982776b5f606f684a2d1e1416140c0d 465 | 150f0e0c0d111820251e1f252e32302d2d2d261e1a1a1915110e0b0d12110d111b1211151f2521 466 | f1e0dee4cb91604e668388786c5d4e4c5b5e594d4d54534944373a536969605c626d684b2f2a32 467 | 3831353c423f3835383b46535d66727c81878981716b757f82898f979a948b8787857d7a808688 468 | 8b9191979ea09c948c878a8a8a8b877c6d62564a4240424c442c26180e0c0d0d141c1717191d21 469 | 221f1b1711152128282b33302b25201e1b171415111116140b040200010a151d1eecd1c4ccc198 470 | 7265636666686a645e616759463a3d3f34232a2f31313235363435464c3e2c2930364a4746494f 471 | 5a6c7c74757372777e7d777d878b858284837d797b80827b757e8d959aa1a29885777274829196 472 | 918a898a807b746c625444392d1c1d292a282721181514191f1f1b18191a1f262b281f17231c1a 473 | 1d1a1111182424211d1714141616100d131711040000030b0f1011f5d9c7c7bb9773634f414059 474 | 737d7a757066584c443b2d2217252a1f171c252a242e3632271e1e234246505e6b798a99989286 475 | 7c7f88857b7c8a9495949082736a72818a7d68656f8896a1a0968b827b7b848d8f8b888c918b7d 476 | 685444372c262713152524222a32201d18161a1f1d181112161d2325221e2d2c2d2c2518100d16 477 | 1717110b090c10160e090e181d1811171d1f181210ffebd7cbb894705b452c2238618488767170 478 | 6f6c604e3e35272a2c2a2522272e2e2a2c2f281b171d2a3a556f7c7e7f82989790888c95918683 479 | 87878589908d82717d95a3916e5c5f889fb0b2b1b3aa9b8f8f8f8f8e8d8a8882735d493a312a25 480 | 2415161e1d1f27292c281b0b070f1719111214181c20222224282d303432271c1815100b070608 481 | 0a110d0a0b101618161f22211a1718fff2e0d0ba9b7b674e3a2722386274656d6f767d79665044 482 | 504039403d2c23262f23212c2d22212b41506b838d8985858f999c98989a91828b83736a7791a2 483 | a5838797a292756d7990b4d3dad9cfad86948e8a8d918d7f725850453c37332e2a2a2425252127 484 | 271a252b2615090b1010191a1d1e1f1f1f1f181b1e23313c3423231b110c0b0b0a08070a0a0602 485 | 0000000a0d0c0b121bf5bfb0cdcaa48e8f7a5f422e31517076706965696f6e676268696152473f 486 | 2e1d21212832302a2f3c6574828b939b9b9694969690888282848587795f689bb9ac8b6d5d635f 487 | 535d778b9ab0bcb39676637a716f75766549352b2a2a2b2d2c2a2727252e4045392923231d1c20 488 | 1f160e0c181f25251e1817181a1c20232524211f2016090305090c0c11141716110a0503000607 489 | 010006e8ac9fc0b99388957057423a456680807a6f65666e726e6a7074746f6c69605645464b4d 490 | 413335426d7c8c94989a98927f889190867a73727f797062607b9495765e3f261a213b546e7f97 491 | a4997c61534a515856442d2222191a1c1f211f1b171a23333e3c2f252126222227251b120f1a18 492 | 14111013171a1b1d2023221c15101c1814131414110f131a2226221b1411130d08060506e6a59d 493 | c0ac7d7b955f463536496d888981776e6f787c746a67707b818587868375777a735c443e455e6e 494 | 80898c8d8b8778838f928b827d7d7a675d5646465b6a68644b25131e303949658ca29675564838 495 | 3f4339231316221c1a171616151210202c332a1d1a222925201e201f1a1717110e0d0e13161716 496 | 1b1a1a1b1b1a17141d1c1a1815120f0d0e141a1c19141212120400010710dfa3a7c8a063638155 497 | 3d2d2e3e63848e84817e8186816f5c525d6e7d848586888b8d8e866e51413e465263717a808485 498 | 84878a8d8f93989b7e65564a322735444b51462a1a1f231f2a5490b7ae845c495044362f2b292b 499 | 2f292218120f1012132332362413121b21221c161212151a1f0b0b0b0d1115181a1c140b06070c 500 | 101114110d08070a101511110f090303090f221810111a2bc49ab0ce945458715f4e45464d6989 501 | 96939695918c816b56495162757b78797e7f81838276604b3f4548506073828c91928b85868e97 502 | 9c9e817064553c2f31313530231611151d211d4787b5b188614f5844323137372e271c17120f10 503 | 121415162c3b372b2219111c1a140f0d11151810100e0b0a0f1a241d1306000000000003020000 504 | 030c171f1c1b160d05050d151620272c405ab59fc3d48d5766786b646b737480939aa6acaa9c8e 505 | 84786d54535d6e736e707974767c828278675a584b475771879194969089898d8f8c8877737266 506 | 4c3c33272e241b1a1d232d37293f688c8d725b55443c3738362c1e16090a0e14181a1917162331 507 | 36332d241d141716110d0c0a080f1720211d191a1d1e1914141616120c0808090a0c0f10111519 508 | 1b1711121a22293c4850657dbcb2d4cb734a65706462728385888f8e94a2a6968684888870625f 509 | 6a6e686d7a797d83898d8a837b684e3d4c6d858b898b8c8e8e8b86807c7571756b4b3229242725 510 | 232327303d473b373f51554a474e3937373730241a18121314171a1a18161a1a1e242626292e18 511 | 1c1b130f101110181e2528241e19161c1a1c232c2e2a2417151313120e0701060d15181a22313e 512 | 6662564d5257c2bcd5b34c2a4b51524f5f757c7e807a6b829086797d89918b75676c6d676e7d81 513 | 868a8c8c8d8c8a704f37466b83857f7981898a847e7d7f8076756a42212028333730232438515f 514 | 422d20252a282f3d3e352e2c2b2724242a231a1310101111100f1621231e202828292217141d28 515 | 2b2f23150b0a10191e1a16141a2227252017130f0f11100a04050b131922344e624f331305090c 516 | e1dbc07f3b2a3e4b4c5973878e8f7d5f57627585878182888d8a7a78857c6f78828688837d818d 517 | 997b614345667d848b8d8d8b878584827f7e7f7964493a3d474e554b332e4359604128110e171e 518 | 22252c2a2927232128322d2c2316121919121b130e0e0f0e0e111b1d1f1d1b1a1c1f2923190e07 519 | 0304050a0f171a1208070d0f09101713141610110a0f1a2845636d2b1504030502fcc58c5f3728 520 | 323e566982969a8d807d70717a878a837c7a8c908e8c887c7780757a81878a8987858367434260 521 | 767c838d8d8a858283878b87877f6f615f676e6b706854474a5153352111131e23201d1515181b 522 | 1a16171b2525211a17191b19171d221a080002100b11181e201e1a18201c16110d0803000d0f15 523 | 1b1a1009070d08101a1c21231c1a1a232f415a5c46150600010400df8d4f402d181c2c405d7586 524 | 8b7977938882838e969488807f8490907f79869087878a9197958c827e5f39345063686d757d87 525 | 8e8e8a88878e897b6d6c77808174726b5d4d4039382d211b222d2d241b14141a2325201a181012 526 | 181e1f1f242a1c1d1e1d150d0e13101114191d1c1611100d0b0d1011100d0f0a0b141c1b16130b 527 | 081017171f272436465a60605e3e0c0200000104008b543a3f2b0d10272650646970626285938d 528 | 8a919a9c958d807b8687767e979c94908b88878683817b603d3a546465697377818c8f8a837f86 529 | 7a685d6779817d7a6f6762564235322c2b2e3337332a231411141d221d15110608121e1e191d27 530 | 1816161b1d1b1b1e2c21140f1013120f100e0b090b11191e190d05070e1114160a0e17140c172e 531 | 384d5b6960473317000000000504005344494f35191b292c6379747a6e606d8f8d8b8a8d919494 532 | 9f91918f828a968e8c9194918a86888c86735c5e76817f828d817a7d8486878a8775625f6e7f83 533 | 7e7b6e67675b432e272b323837312b28261e17141a1e1c161315151b211b0e0c1307111c1d120d 534 | 192a352613090b1113121a1b18110a0a121a241a0f09040000040512221e13264a5e46372e210b 535 | 0104030101030502005551544d35272827387091949a937c6f838787807d86949eb5aaa29b938f 536 | 84727b87969e9d989595857c70778c928e91837977818c8f92969d8574788386827f7e79756e57 537 | 372018272f322a201c1f212b231e2124221f1e2425282821181315050912191a1a212a221a1110 538 | 1519181513181b17110e1216201e1d1b120804070010282f2e44606a2b0e000200000102000000 539 | 000000685b4f3c27262d2a3c638a9ba19f9182878b86756c7487949fa49d959690817875747781 540 | 8c918d887674707788898489686a778a918b898d9b82778690867d808d918b724b2b2123262926 541 | 1b151619191a16151a1c1814132024252220211e1a0d070a19282b241d1313161c22231d170a0b 542 | 0d101417191a15171d22201815170e1b3548535d574010020209070704000000000000016e5d4a 543 | 321c1f30354657798f908f8f8a9998896c585a68737d908d889496929b927b65667b8c8e886e70 544 | 6e7582807b826d6f78817c70727d7c6564818f837c86868e845b2910182929271f1513191a170f 545 | 0f131b1c16100e171c19121217140b0b101b232118111115181e2429261f18120a02040d161918 546 | 11101218191716182b3146606f6c430e0002080200000903020100000002714c393e311824485a 547 | 51647877808b8391806349455466706a74787e868792a9a7aca38a797d878c76797b7d8286817a 548 | 788489817879838b8b7b798686777480857d603519161d1f2427241c1a1f211e15171d24282720 549 | 19272e2c1a09070e13161514161816100b0d111a23241f1c1d17130c08090f12120a060f222621 550 | 2a3b59606664553b1f0d00010304040301000000000000006e503c3e3c2f3241625b6a7a777c86 551 | 8075695950525d6a74777a787c858587958b989f99928d82756e757c808587837c8081878b857f 552 | 8694807b839394857b7c837758311b191c1a1816110d0e11120f0c121b222524211e2737403320 553 | 191c22241f1915141516160f0d0f14141112151b1c1c17110d0c0c141621323d475a6f5e54422d 554 | 1909000000010304040301000000000000006c533e3e484f525566626e7c7b7d827e7268636769 555 | 686b7279787379898a868a9094949294938675747c8385888b8b89898285908c7e7f8d7c7a7e86 556 | 8a8987888c7e5f3d2a26231c09040004090c0e11151a1f1d19191e241e2a33312a2524241e1b17 557 | 120f1014170f08030203020408191c1e19110c0f15161f304352544c43140f0904010205070001 558 | 02030302010000000000000060462f2b333e4a5666656f7e8586837e8277757f7f75727981827d 559 | 8393958d8ea49d918a8c90897e7c81837f7e83888a837e808888807d8183837f7c7e8487858177 560 | 614838322c261510101516151921242521150706121f211c181a1f1f170e0a0f14151310101110 561 | 070000000000010c11181e1d191a1e2f44534e3c260d0000000001030403020001020202020100 562 | 000000000000674d39342e2a3a536d6f7685928f847f82777681847c7c848f9591919a978f8f9d 563 | 999490908e857c7c81827c78797b7b787e7f7e838b8980858a8a8685847c725e5a4f3d2f272320 564 | 27292b29221d20281e211e1305020b1629241e1c191107000910171a18141111120c090a090606 565 | 080409182c3839383a63736c3e0c0000010a070300000000000001010101010100000000000000 566 | 6a584d4d453c4a637981848c968d8082807774797b77787e8891908d93928b8c8f8c8a8a8c8c88 567 | 83878e918e8a86817b848d8a7f828e8c7e7d7f7f7f80827e79514c3f2d1b0e0806162025221d1e 568 | 20210d161e1f1b17181b1a222a2a1c0d080c1415151412101011131111131210141a13111a3045 569 | 53606c695c3b120000050b000000000002050600000000000000000000000000005a4f45444952 570 | 5e697c8c8e8c8d7f79898985817f7e7d7a79808a87848d8e8785877f7a7e868d8f8e979a999695 571 | 95908992938d8382898882777575797d7d7e7f57493522120701000411171316201e120a121c26 572 | 2a2a272511161e221b11101617130f0c0c0d0e0e0e0d0d0d0c0f1c2a23263448514f5057311b02 573 | 00020a0500000002050401000001000000000000010000000000006459463c4b66726e778e9087 574 | 817173908f91918d8d8f8b848f958d868e8e827c7b75768290958f8899958d86888f92908b8480 575 | 8284868b927a7b848f8d7d6d67503d2618141211100f1b1b1319251a021011151d262a29262415 576 | 0c1016140f0d13100d0e1112110e0705030100081d31253a5e76683b1200000002060501000103 577 | 020100000102020100000000000001000000000000676c6e70788488857d999c887f82868c9a93 578 | 939a9c9280747e8e928e8e867c7c7b7878818f9796918d9492867e838d928e867f808587817b66 579 | 67707b7c6d5b513a2e1f171a2126282513091011090912181e221f1a1920271f1c19140f0a0604 580 | 080707080b0f1315100d111a1d1f2d3f4d4f462e10000005020202020202020200000000000000 581 | 000000000000000000000000000000757c81848990918d778c928e91918a888c8a8c918e83756e 582 | 7f939b9a9a948d908d888384898e8e8d979a94857a7e8991918c8786858178716f594a5771775c 583 | 3e1e171318232b2b2820170f10151714112527261f150e0e10191a1a18140e0804040202040709 584 | 0908081223333c44515e22190e0908080400020202020202020200000000000000000000000000 585 | 000000000000000000888f939391908c888180787a8a8d888a8d8e93958b7868617a8f98999d9a 586 | 969a97938d8886878a8c8a8e8b7e7271787e808182817d78716d706c656267634b301514161d25 587 | 261f17181917141b231e1220201d170e0602000a0e14191b1915120c0700000001050700112e48 588 | 56533f2c0a00000002090400020202020202020200000000000000000000000000000000000000 589 | 00000092959794908e8d8d8e7f6d728588848a91949b9f978371687583868790918d909797958d 590 | 847e7e80848c928f86808081767879756c66636469849483664e37251d1e1f1f1c16100c12171a 591 | 1d1f201c161112151514110d0a090b0f13161717171918140f0b090c0e1a344b4d3f290b000403 592 | 010000000102010101010101010100000000000000000000000000000000000000000000 593 | %%%%EndBinary 594 | grestore end 595 | -------------------------------------------------------------------------------- /utils/result_vis/result/D0038207736_cropped.eps: -------------------------------------------------------------------------------- 1 | %!PS-Adobe-3.0 EPSF-3.0 2 | %%Creator: PIL 0.1 EpsEncode 3 | %%BoundingBox: 0 0 150 150 4 | %%Pages: 1 5 | %%EndComments 6 | %%Page: 1 1 7 | %ImageData: 150 150 8 1 0 1 1 "image" 8 | gsave 9 | 10 dict begin 10 | /buf 150 string def 11 | 150 150 scale 12 | 150 150 8 13 | [150 0 0 -150 0 150] 14 | { currentfile buf readhexstring pop } bind 15 | image 16 | a794a4b6b4989c9f91add3cda087858baea79e8997b0b8c5b699958784724f31324d6876697c45 17 | 0301000013739ba1877b78706e4f00001a26286967445356525350443e756947323b3f2c184452 18 | 444a758487a4b98167401916192643555949444e4b3b5e543b37493f292a1c161a2e546146382b 19 | 28110f32402a182b1c3125201b2e271e1c304138334b654c6280a2967162528fa8aa9fa5aebeae 20 | b3ad9ab7e4e8ad9d928eb4c9c8ae979491a9b0a4adb2a3905c312e3d5b8295af67243305132c62 21 | 797f624b535441370007001003203f56594f311b263633185176726247230a1c465e69808c91a0 22 | 77585d55382a222228202531291920385e3c2f3c372332562b1314183545303b1b1203072a473f 23 | 24200b192327273f3d342f3336374a636c605d92a8958b68437b8dafab9e87979cbac6b1b6d3db 24 | bdb9a78a8491a4a8bbab96949ea195818b8964433a2522424c62555e85646073785c535762807c 25 | 50290e06083a34325344526a65463f44382d43525c67604f48465d90957a99b48e412e3c473325 26 | 25251300000b0b000c2f3f293249381418363f30331d20260814292b230b000d22222d150d1208 27 | 0e3b4b4a3a251c34636e5222205286a5b194737a68a7abad988c859db7b3b3c4cecec6b29b8079 28 | 8292a6b9b28c89aaac95887e522f26120f3142506d7b758b8ca7a18b896f352f5564300000423e 29 | 384f6a6150586054525c596f5324112d51626a483b53615b81986f6149403712082f4b4e48331a 30 | 161f1b0c344e1d00252f214046484c363c47271b1024342307091c23443c2e311d3070895d4c46 31 | 51646f572b00224d8fb9a89693ac9e9caabdb3a1847c8fa5bbd2debeaea1b1afad9fa28e8a918b 32 | 8d9da9bdba9f683f33282a41637d9e81436b758c90645a593f3e5a645a55325a44465179747082 33 | 94876d615f646f532623425a636f6753556c706f816a4d3d452f20383e4c48392c2e32230b0b33 34 | 36344f4a3136273e351c1e2e322b182126241f1814150e282b42364e7b755552749f9a775f574b 35 | 6b7196b59f9db3b4b0a9a7a89db0a59895a5c3d6d8b3a798aeacb3a2a4a5848d999680677b816f 36 | 57473c290d001f456d776e71665f958c989369515d68707f5042678e73966b6d6a676053515f60 37 | 6d5b3b3c515d5f8794765c6660576e593c37646a4f3e1908010921302d2a2e0907223419020b19 38 | 12321b110d0b251e44371a0a0b010014304d3d524c6c7b472d4c8bb39e7e859d6c687787a3b5b2 39 | c0c4b2b49b8e8db3d0d7c0b3bdbeb1b8baaaac94a2a8bdb3adac8a89a9a6a9977f6e6a6a6a593e 40 | 3e382d5b9f77644f6677918c66505a655709000243815d5b585e565d7b7f695f424c4c46403b48 41 | 64606f6c5866969f7c443237717f6c694b1d282c2420211d15112d29212e261e37375238576a50 42 | 51280e242c3842281f426a6f3539428096543470aead7e67727d554f9ba8abc7a393b6999faf9d 43 | 827d909f85898ea29bbbb4a58d849ba99fbbc1ada9bbaca8d0c78a656c797e858b6c5d616c7578 44 | b0a08c7978a19b5d51704f05010c0033394e5f4f434d6a7e75625f585655420b3658645f563945 45 | 3f525b6b4f2f33544863534a22111a34331a21082b2817060421343d363c30201f150a072a3835 46 | 3a3b4156735b6f85708179939591949990818595706fa9bfad73488c876aaaa6aec38d85887c8c 47 | 8ea1a4737a8a8e8588979c969eb4cac8ad9ea67b5b3e383a405877776f757b7a7ea1a0ada58f7b 48 | 8185766e691c00001360564c475b5f493a3f454365766c52464e674625484d2b0e24424e3c040d 49 | 468b7d6252332829262c2e2f50532b2a0e1838191a262c2c12051d2a224f4e300e13334b546979 50 | 999c947d68698083898c8c91a1b3ac9a9f99957d61858b90a097a0bbbcb0bec6d2b6b2b09c7b73 51 | 8a9ca5a7a4938887828199a18684765952656a6f8585796f604c56607a909e9557537a6a5c2d2b 52 | 404a576c2a003263836d45446f9ab39e898a6a57350000202d2f1958808b5a272b2c545d3b312c 53 | 3c3f201a2519191e0f403c2f3a19164a30314848362d2a02274440456c8a866c91a9999d7b7d73 54 | 899eb4bcb6aea9a986949892979a969e989e9a99969aa39eb2b9be9d9a9b968d9cb0aea3a1a0a2 55 | a093796c809ba18c7e524260685d677069655d4d6157808c919f70687e626a676f76685d430400 56 | 0f4385a189625a69837383922e0000160200001111508591623d2407142d2b2c27231f0a0a110a 57 | 1721263230090c44533a21356f65250c0f0d1f322b2f6eb3c7afbbb4a28f7fa69b828c999e988f 58 | 929aaab7a4908c99aba7adbbb8b3afb4b9a9a39098909d9f939aaab2acaeb0a7b6b3a5afbf9f7a 59 | 819b86471e2a3133484f5465736a715069947b816c788a6d81ac723a2e50492e38272528313c4a 60 | 5b69604a545b110000070207344652698876562a00214346473d2e1c314d4c27174239261b1c07 61 | 0e2d1f1b35597c5a2732403927283956869f90bdb6b6cea5afd8c4b4b2b8bfb7a6a7b4b1a78e89 62 | 95a9b5a4bcd7ccc3b8c0b2a9a99eb7bdc3b3b4ada6a1aac3c6afb7ceb5a3bdb18171563c0f062d 63 | 51677d787a8e9f92846b70786c6b5866868fb19455283b807b5d4f5567684f3a40515b5e495142 64 | 0d0d1c2e0f2a595877909b69402700102d3b3e22383647555e4e2d322e153118081f0a0a142742 65 | 7056233c53492f253f709da592868aade3c1d1d9bcb8b9c2cac3b1a7a8ccbab6b6b7bfbbad97b3 66 | abada7a99ca3b6b8d1d4ded5a2b2c0b7a7abab9b97d0daad959eafbe9a72483e4e606b72797589 67 | 98896e787172868a7c7d91abc99f8d796e8f8475574665888d705866846f2f1c13283e4852586e 68 | 70576690a28e4d4b2215133c41352a2617001436302b051c584433380f0d0b0107494102070923 69 | 323b4d779ca29b8f9db5b6acb4a597a1a6a39ba2b4bdba967d8f8e94b6bcc39bbb7a8ea0a9bbb5 70 | b18e817596adcbbaaca5a6b1aa918989b0d7cdb8becbcaa47e5c3b364f6785839aa68b576d546f 71 | 85868c8e82818190a29a696e788b6e422939686538365f61566b4d5346260d2c69868f77818295 72 | 4b32251e0c1c01131f121718160a052840461e030c212e1f36454263562c2c0d1b434f5480aebe 73 | c0b7c4bb748a9a98aca3babcabb1cac6aa94729095a7c8a2887d94928886818e96989fa9987560 74 | 7e8ea7b08dc0d7ba8d8a9ed1bba083879f8b49312a1836566e5e6c7c7e8d8251447d7e837c8281 75 | 878b8fa89f959174735464755a5d705857567872525b6e4e1a041f515641678e776c45303a3922 76 | 1a264f522414140a1f2f3e291a1419324e58594521343a21303c4d314344758c9dc0b09da38f99 77 | 878aa3e5bbb8aaa5b3a08d97aca88f7f68401f64739783828c848e88828f9faab4b3a9a0a5938d 78 | 96afa7816975798382816d58394e4c20315f81707069596a7c6a5d847687a2cad6db9aa4b69a7c 79 | 705a5d4356606d7776797c6f7c765a3a1903010200346d5e52543c1e323f3a323438393d4e3c31 80 | 2212242b2a2e3d484959707a514235362e32453f44514c456382aabbb5a4abafc4bba8b1d7a89a 81 | 82878c8685a99f8c7b777770657a4eaf8f756c747a79797f87a2c6ad9a8391b49084b1beb2ac97 82 | 8b8b9fa17e4d131f46525f6a677ca1a78a86918a63938e968f8f85887669645962746f6e797448 83 | 44423949374458503b4651340c0a00335c3e2f2f0e031b2a2c37463d262f332e33353c4a3b302f 84 | 383a2f2a2820000b3d4b3b475d687a875e6c8aaccdc7c5ab9ca8becbb4bda197a697a18a838ba7 85 | bdd7cda0858f9f7762b5beb7a99b9ba4b4aa847c9a8d919297c0998291b0a9bcbcd0ccd2bc9c6d 86 | 2e121a2e4858797886949ba3997a6d642f343e47444e4d607f8c8270646861684f3d3d546d574f 87 | 7e8060709b956e0505344c364c71653c1e060c24373e3e0d05071019374d3c1e1b21231b1d2624 88 | 130b2c393f4b5c9183836e9eb3b39a8c948b859798996b6c6f7a8e8dbdbfcad3c4bfc2b89a8371 89 | 5b665fc4d2c8bebfc1c3c8c2a2898a7e88a4a3aa8e887e9391afbacbbfc3b3a86d4b49391b1123 90 | 496a81735b5e6f759983381a00001a5d69626c8d997a5032142246403d5f7176585a4f43434245 91 | 4f2c08112d33455b543e281a180f03091c292732240a1322212a26261b07020b0d402c24316b7e 92 | 6991998b899d99977183cdc2aca4939c8aa38b979597d2e5e5d3ab9d847076909a8d886e8e8b8e 93 | aba7b3a593a4bebfb3a3868d9aa09e9f888094bcc5b59991865822172633321d14233e53658cb3 94 | ae8f88600b00020713333752677d7a6c777b67343f3d38515e7b7b70686c623e2b385a28000033 95 | 5b451228353e392c211c1b1e213a403e484a512918141e2b3837292c4449558c9e869199807a72 96 | 7a8d748cbdc5d0d1cccbb9ccb3cbbfb8b5b2ab98a8d2d19c6d5b5f70747db18e758aa0aa99879d 97 | c1cecad9b79ea6abbcb19a9292929b9da9926f391e25222b4f5756608891808da99e7d5c500b00 98 | 000d121e2c607a8c959a9e817e37212a2532546d769db3a5886756584131030862a07c3f0a100f 99 | 0d1f3a453e3222282b3a3d2730563d303b4f666c5f41687d7c6b6c8b9a9a878ea4c2b29ea1938a 100 | 918ba0a6a1aea8b8a2a97c7c8c97bbe9e8c7b4907480849bd5c5adb7b7b2a8a6a9a19ba3cbe0cf 101 | c4b8d5d0cfcabf916d598fa39e661b11253741271c26678475819c906e6c6d3434587c6038156a 102 | 85725e697e614942414c1f0328282e3e444c5e614e3e25220a246969331d272d343f4b4f453618 103 | 090a05151b133b2f28231304163f59486091ae7053888ea9948fb4c78ba4c4ac9ba59ec0b79e90 104 | a09d89c29c998e88acb78f7a999b9ac3b8a7cbd7b199aab8d4e8b6b0a492a1a398818f89998083 105 | 9bb2b39f8e8e9793581f1b260e092e1115526c854a47465a5a52599b8f592b1c2c35797787aa8d 106 | 776652404849415d4f51382e5e908152193156775a2c3038363a6141393127180e1b17254b4c3d 107 | 483a201e200e1337516d6a9994798d9fabafa5a1b6ab94a79a7c68839ea9bfbcbac3aea5ae95b4 108 | c6c17b71483d498fadb88d9f82989d7d566586a39eadb4ad737574789ca6bdacbba79eb0c8c9af 109 | 966f55392d210f193a36386e8cb07f6f5b3c46443a708f96834a2e3883787f978093948c695856 110 | 4547513a354f686a676a6d7876683d26414f4e4343080011282f445c5028121a3e686b443f5a58 111 | 3f3c4c4d6f956e62a7bc9c99b28a7584828f9fac9d948a8a9da39eb39288a9afc9b2878e885f4f 112 | 747c96d5cfca8d8bc4c2ac9a88768294acb198968d8a958c9b92b2aba49e9594a1b1a06227111a 113 | 33474931336289c9c1bca35744413f677f8a7040325b9f8d9cb4b59a8891836356658c84555582 114 | 89634a4a5f604e3f2d2a34201f273519264d73858c68422c22252b2a2b2415101f375a7d698cb7 115 | a593b2b59997a08a99a688737f93a4aab1bcb2b1aa9d9aa3b99f9e8a735c3441547574949d9e7e 116 | b6bdd6c390a9b993836c8294b6c2c5caba979590667287979a9492967e695e4d343a545c595262 117 | 6d9ca4a58c5f576e75909c873a001d45533c597aa8956f777f768199b7976d5a65696a69624f57 118 | 4b3a1f17261b1520271f293c566e5e20122a251920243d25040624375788a0868187919e957f6c 119 | 6687b9a19da39ea58d6b7bb1a69d8e877c7c9b979f856c3d101a202a538061443c90aeb8bda6bb 120 | cebabc9e91818fa5b7d5ccab9b8fb1a493898b8d857b8b7162503335525f4b4c514c646f705b1c 121 | 386a68778f7d1e094756524b43295556413e3144726230314d70848e978e7a6463647469524e3d 122 | 192629383a2b2a412f0c234937222a2b42686f5d5b5c5d67858e887d86a1a3848092a6975a83a0 123 | 97cdc9ad796c49566786745e675752332131493b2f37616e7644677e7a80a4a9988d8eb2cac8ad 124 | b9bdb5d2d3c9bbad94a5aca39ea29d8f747e815f250b1c345c69726f797f796612002545636c75 125 | 534f6f597597753143574f4b353b563e173149596a807d675b4a4c5f857f5c5448394b44626751 126 | 475d3e2c353d35424b3237505951505966738baaaeabb0b8b494a8bcb5ae909d736c9289927097 127 | a0947b7c806e5c2c27365d5c6960675360504b717ed5b6a198b0ada8a191a9b5a9bbbea7bbb5ba 128 | b5aea7ad9c8188a6ad9bb4a16d3723231d16112131466587928b4e1c3263806e85967e7940638b 129 | 8c7d8269605a4743443f51666b5a63836b3b34363e484f2b0d2d49363f09060200031b2a2d2e1a 130 | 0d335d60630b00284d485a83b99a6e86adada38a847786cad2d794917e61927288867673806c41 131 | 331d21233d42303c53587a948dc5b7b4acc8bebc9e858f8cbdbe9da3bdb8c9aea3958d7799a088 132 | 89acbdb19bb69d644c442f201615111f3f6a7c7c656881735c3d4c50414e29464d5f735861614e 133 | 2f3d5141424d4d1b032528234a3b1e0a263a3a3b271c3806040b191c27222e434c4747402c0917 134 | 2f34355978728589778c9c919fa48f6378a77daca69eaf6db6a7a37047595643253a4b553c3a4d 135 | 7682719d9eabc5b2bbafafafb2d2d49a7aa8bcacb69c726b94aa9ea5c5b9b6bfbc9e8c9bafa290 136 | 948f5c5a7d63605f4c3e4435616260744e48634a374a3d6a604129515f6b7f9c97775c39150a00 137 | 28320b000e1812191a0f1327200904002253635b413f75522b502e1649381b384b564b4b697e75 138 | 7e9a868f9a8e867c62b4d1b07ca6bfb8c5c3b99ba47c5c45281e46657a8683a49987bbbc80917f 139 | 95a78ab0aca69da8bdb3a9b19c8ca4b0967f6f5d6298d8cbc3d7f1e2bea8a28c95987129294f33 140 | 2225475e66514f5e7964303b5f4d455a898d73432f314455485d7a745a5e5a333846555336192c 141 | 5b4a2a30310f143a4432141e3f533d22375c5b31181f242d3830291606091a2c3663948f78615b 142 | 87abb09aa3b7a797878f9b8b919ebc966c495164899aa3acb0bfbfd2dbb293a37c96757a84929a 143 | 8d8b999ea3aca29597b6c6ceba91777d91b4a183676c94a99a858b92885e535d3719153b4f5561 144 | 4c64829e8568655d42152e38442a2d0e09021c394e4949564313000a2c3b1900114d4c3950541e 145 | 051a22232f432c121c2734363c213a6650332f2232352f240c0d2e52646b7a8474808f82767a5b 146 | 71a29c7d896d6768797576695b647da6a2818ca7b6a99f9598a793b3adac797c908f8b8c86829c 147 | c9d8c795a2b4bebaa78c79638fa6897393b7b8bdb3967c6a7d9a86260d000c3778593f296c7b5f 148 | 54614500000a0f0006000404476e50356168464629271800000d1a123238322d2c1d1c34301b3a 149 | 4a2f1c2645431b32475c62332700233b444428234b736a798881535e7d896f7746507ba0b7a898 150 | 958b7f7b714f606d80b9bd98a8b9b4929faa97afcfd7aed0a6bcc7b6adaaa1887d99b5b2897e7f 151 | 93a4a59c96857485b1c7c0ac99acd2c795645a6a5f53501e191a445c583647648f967e5b240103 152 | 00030000001465958a788c6f424e555f5c3b2538432d0a1a181a395057602b234b625a503d352f 153 | 1d2f2b29352c34263c352e3f3c35487d7a9ea39d757e92b99ba0715c5b82acb194899189867151 154 | 5589a4c7dbe0e7c9c2d4e6cb9faed4b9b2b89abbccc3c7b9b6ae8d71717a9c99a0aaa6999dacb4 155 | 9a99a8a0939daea9bbb4a56f27223d637e7172462c5a7d736571a0a2828183704a151801000840 156 | 6f8baca6764b362b2525414a27182f412828403f252e2b0017476c4c40625c3d1f441a223c2a33 157 | 2e3f56534449483d3d4f528c9cc5c0ae8487a2ab86798b9d8370728aae956e4d4b658eaec7d1ce 158 | c2a4a2bab0b7d0bcc1b2ddb57a637593b2a6b0c9c7a693999da0a7a8a19eafc5a59aa1aea79482 159 | 7283888fbab0511d273b426186926f605947493b3d425489abc0853000000c3a6e847e7e62373c 160 | 57573e0c06170d08181c0c07202b1f364525140c151b28323450848b4f5d755f603f1f394a4741 161 | 414242392e635a757a8a7f728d8faa9b90a29496b3b09858424c7ba0a8c8d7cdb7a8b6edc293bd 162 | e6a09385858e9c6c60719ba4b1c3cbbaa9ac97999b9fa6adafada58e9ec1b28679857a947f7d91 163 | 7c59434d44675c6e6c63684f5c515358525a5b526b7a688fa09c7b6160360b132a3236242e4f4f 164 | 2a232a192029252e494f4445434e636d7a7e8cc4bf98b0cbbbb7a4746b594839313b4848441238 165 | 354e49728f8dab95ae785370736bab9d60273c5377a8b8dccbbbc5c8e5d49987c1d4addabe9da9 166 | c9cbb37f6d868285949fafad9da39c97a0a4a0a19aa09d8a694f6495a78c9eac9883572332224d 167 | 59434442494e6c6b72938a6f7b76706e7068768e8270563a2a2f444733203f4a5258391a253929 168 | 071f3d3e505692d6d3a9b8d5e5fcd3aec4ecf0d9c7d6a8a78e4e213751424c472548676f9b998d 169 | 8da8ab8980847075615a68495f798bb0d4c0c6b9c3c7dab9d0afb9b5c3c6bfaacabbb4a382707c 170 | 7780898f937e82858b9ca6998e9798a8b0ab9c8b98bac79b98a6a49e8155220a0902163b33251d 171 | 42494e7895908b654a485f5e5b686b60515564696862562c120010312e2c445b513a5675768891 172 | aeb6b3c1c99b7fa1c0bacfc7b6c3c6c1d2c4bfbdaf997c61373c2b393b3147454c33496c6b7088 173 | 907b38030a38567798b1c7bfb4b7b8c2b8d7dcbed0c4b3abb0acdc8e8397aaaaa0908b7e82927c 174 | a6afaa9a8876768788a0b7cee2decdc7b49aa6ccd9d0b48b46351500163e4555403e270c0e1e1d 175 | 0e3a2a1700001c3d424c45596e59362e361d1f2a3d4d545e6b5d626697cad3ccbfb6a493a7c1af 176 | 9fb5b3bcd5b494b4c5b4b7d4e0d4c4ac8d7a7f7f664d556c654226344a44334b6f735d614d2b61 177 | 87c6f7e1bebec9d8aec5c9aca98a92929bb2d0caccc7afb3c3d9cdc5bb92818b70799ea79697a3 178 | 9c8d838c878397acb5b8b6a39dada3877356343e36333d24091f231f3857584d402f26393d1500 179 | 111106050622351f081a392635515a44394c607fb0c8bda99faab7fce7cdcce3f1f2f6e9c2c2bc 180 | bad8cca1bde7f5eae3cca89585837a5543515d6c88472d3f3c292c3a3f617a81b6d9f4fde0b5c5 181 | e6ebb1c1c4cdd6c7c3c6bfa084536bc9c5b8b2afb1c6ddc5aea98477887d6e86a4997e879e9d87 182 | 80868c92a0897393aea8956a4c4123243a2f212c28111c33333e555a4e4e5e52402a0606010011 183 | 2323293f503622253536426e99acd5d7a48a9cb5c9ffdedbf5f2d7d0dca0b0e8eecbc3c8cdcbb8 184 | a7bfe5e0cdd4a684807f6642395a5d4646523f1b111c3c4f87c7bbb1b8cde0dfe5e6dacfdfc9c8 185 | bfad9eb1b69c85608d7b929ca9938a8eadb4b3bba6b3b2a0929bacbed0d5cca784889eabaf84a4 186 | a4ab9a808b804d47312d3540462c2c1202000028556059484736485b42491f0f0b12161a120000 187 | 1d37426091b1b7b5c1c3b8dbfff1d7ccaeb9cebdaebeccfffcf3d2bfcdd6e2c0b7a59da8bad2eb 188 | ffcb7b442d2a343948442c1930503e1109042a7b88acb6b5b0c1cdd3cdbab4949d9392746c6175 189 | a0d8ce99958b9aa59b8a93948d9c9fc4d3d4c6b3a09eaec1b6998b9fafa597d7d0999cb8bcb889 190 | 71533419000034201d1c2a3b4140311a01030e001b43282b3d2d2a30303029192b7eaeb0c3dbd7 191 | cac3d2edeffbf9ccbbd6cdd0ba9ebee4d7a7bdd4d2d8d8cbddd9f9ffedcccccebecbeece8d4319 192 | 190010122c58643f1e1e2c5a818985a4c6d6abb1c6d6f6c1aa84998c8c57464475bcb8a9c1a274 193 | 7394b1c2d8d1b0b0bab2c4c4becfddd5c9c0c4b19a99a1acb9c4e6ccd1ddd7dab38857505a2527 194 | 624b5a331f2c34271d202012231c28270a31322e39433c3e5364889eafcaddc8c8f7ccbbc5cad8 195 | d4b3bcc3c2cfb998b8d5b5c5c1c1cae5dbc5e6e0cacfe7f3f2d3a3bae0d7c776150e05280e0421 196 | 3a2f2e4751779aa1cccde3feeed6b57cc2bedfc1b8bed9bbc2a87c64535998c4d2cca4c1a68da4 197 | 9c889f9ea69c7c9eadc8d5dcc0bcccc6ac9484839b9db0b8b1b59e805c29261805160d260f1000 198 | 08041f4f603415191d1b2e4e54505a61552952618cc0cbced8dae4e7cacfd7ceb7acaaa3c4ceec 199 | d196a8c7a5d5d8c2b2a3a1bbc4edefffe0eaf3e5cfdbd3b9bea2686b80634c442f1e465f3b4051 200 | 8ed1e4d2c3bdccd7c4ac9793a9aae2cca4cdd5e0d4adb4977d80839abeb19198bba68186697f9e 201 | a2ae8c90a79a9fa49b8c8e8e7e9baa92796a769c9c8257241612152523322a45444418061c1e04 202 | 000017231f180d0f2f61847da9b4c8dcc6aea59f9b85a6a59878698ab5c3ae96bee7cfbaae8c84 203 | 999faeb8becec9b69dcde0dbbcc9f2eac0b8f7f28f4a2b1924424834425f5f525c95d9e0b9988c 204 | 79bae9e9b7919082afbf9ca1aeb9a2979d86a2836a867d8a9bb2bfb0a9bda4a0adbdcea88f8c8c 205 | 98997d687b9494beb8a08f80869f9ba7896b48342d1e1c2508142241240402122d3f382f2e2a21 206 | 1833648b988fb3bfc3a39ac4c9a69d98876f89bab48d8daa996e7baecde2deb9acb4b4c8d6d5d6 207 | c6bfbfe3c4999ecfece0aca2d4ce936e54523c333a3a2e25223d456b98aab2c2cdc8ced3cc9c79 208 | 837b8db7e4c772655a475334c7c5b8d0a6a19a9091a1b0b09d979295acbbc3c4b6a098a7bfd2c7 209 | a9a7877f95a4aeb4a788848357392e11172d0801063f504c4e5a5d4d2e1e252a25263e6488abc5 210 | ccb1a49a8c9299aebd9ba28e90a09f99a1aa9899aebaafafb2a5a1a4a3b5b19da8b1baafd0d5bb 211 | c5e1d9d4d2d7c59880652b0713233c482f151a0523517490b7d2d4e1d1d1d2935f768a9a90a898 212 | 8bb09d78635891a89ea9afa49d95909fa89db3bebfad9193a8bbc7d3dcc69f929b9fb1928a8684 213 | 9cab9e8e8b82523f3d26342c2627091d23201f2d3e515441271a193c658a93a3d2d4b4bfbbb2b0 214 | a4a9b69a8d888f9182797e80908b98aca68e8287919399b2a5879dbc8f8397b6bbd7d8a599c6f0 215 | dbbfc89835463d23244243303125345986a9c6cec19b81768c8263563f4a4c291b798f371f473e 216 | 8a9b898a90818899968f949ba19dacd1ceccbdb5a5b6bba79db1b8a3c1c7d8af8399a38a9e9779 217 | 514c44292c5a5d65434b412b1c141d334232234173a9ddfdd9acc7c8c0b8a9b4e0d5a6a9b9ffeb 218 | e9e3b17c768a898a7f83a0b3b4b6a68a728b9c95a4afa4bbcbd7bccbd5b5bfdcffede0eab76c34 219 | 62725b3f2a32535835304e6569655d7b8a73533933494d686b410d36432e3125398c9b989fc499 220 | 76757f7d7a7ca39293c0cbdab79089aed0ccbabcb9a59796beb295aaa5859aa585727258434335 221 | 252a21444a3f3a1c00001930364f74a7aeb4a99bc3b2a6c4d9cfc7c5c7d9dcb2c4daddd6dbdcce 222 | b0d7ca9d91969dabab9876788b9aaaa17d91b6fcd7abbae0d7d6e7e0e4e6ba9b62614c30201c25 223 | 39110d1a2f3d4a524c8e97705f6b635953161e372d3657773c130e9c9c8e8499b1b9aea6a4a9b4 224 | d7e6dfca99b0af9c807c84887d7d8c969b59667c839c927b85a17e6a592d29344a2f2f243c373c 225 | 54542b11192330609a91868e9a9ac6bbc2b1c6b4aeb5b2bdc8c79e9bc2dbdfe8f3e3c88e6f7565 226 | 5a7288b0ac8760586c6a65858fc7cddcf4fff0cab3a9c6d7b0a2513a262733393c402248542c09 227 | 1a2c1f1f34315a815937402751644a4c5d79310021a3a1af9e88aacee7e9c799846e8abee6e7d9 228 | cbbda57469637aa4abb7cac3b4a9b4cad1c9a08d6352370c0f2225182e4839292d3114393c3b3c 229 | 7083839ea9c3ccb4aed3fae5cee1f3d3b5a58b99acaea3a9b9cad9dfd3b18c81877d668faea296 230 | a2866c87b5b39eaeb4cef6c6d1c4a3bee3e3e1cda794603d2b00003c554f192c19495941565e4d 231 | 4e647750566e663929263e2d253743a7a8b2a2a99d887f86878a976f6b7c97aec8dee4dec5a982 232 | 7c99957d9bb1a3859ed7d19ca8c4bea36e373441080613273e5a6d6e4e4d485e82bbae9cc5ab9b 233 | 93817f94a8c7e4dbc1c8d8d3cbd0b09093a6a6a3b0c9dfdecddbf3d69b7891a7b2b09b8c92a6b8 234 | 987c75acedc3c9f2fdf9dec7cbbbbab9906048302b4343382a452e43323f889e8c5e343823333a 235 | 50472a172d29153c2ac6d1d5d7adacaaafb6b0b6cbd9c9bba9959dbdd4dccfddffeaa16d4d5d9b 236 | b1856977775d80a4a18963372211463e28151626466756484a5f85c7c2cac9d1ddca967d9abfb0 237 | b4cdc5a0b0d4ceded7c0b4c6d3c7ba83a2c6dee9e7d6c38783959f8e898e876d6471afb8a6bfb9 238 | c7cbcccdbbb2b291c4c1904a354f5b4d41382c272b6a61809366443616160e286c533912102c3e 239 | 200b0099827b9fae978598b7b8abacc7cbd6caa590949caab8c0dfdecbd0b799a5b8c5c0ae9c93 240 | 9c9058312625333333220c0a0d031f5d515e7e90a5e0d9e8d2bdb8c1c2c6d0d3af9ccce3aea8c1 241 | aab8c9c0b1c1d5cdbbbeaea0968e99c8faf7b68ea4cfddb4787aafd8ecded9e6cbc0b4c9ddc5bf 242 | d8ddd6dadebf7f56493e3b3a2d3f69a395a4722b132b2948556d581c111330415332260c958087 243 | bebdaa918b918d90a29a949ba4a4aab6b9ceccb7b6a08c9f94a1908ea5bcbdb0a7859896967d48 244 | 2c2120141437513b304f4359707e97d5c8bee1dcd4b483789bbfd0d1c7bfc8d5d9d8e5cfb8bbc8 245 | c1bac4bbbfb29789929c9eadb7ab927e7488add7f0d6a5a7def6cdc4acb3ae93a6d8f5f0ada4cf 246 | ce9f6a43404c5cb5dab2807653484b3b1643524a3114283342475c465c5eb3bfb1b498a2a39d96 247 | 8a8c9ea0989ca3a3acbbc0c6beccead19e9395a1b9b6958aa0b0aababeb0a9813b1e1d00031733 248 | 3e2c212b5a8392a6b9eae6cdc8b5afb5b7bbbcb4adb2c0cbc7bdc6dad7d1c2b8ad98919f7c9dc1 249 | cab593776891958472716a6f89b18f7e98bed2dfeaf7d5b8918fbecdbea9afc2c4b39d69224262 250 | 6fa19e66472c40353b381e3d27032e3a4e4445565e3d3054bcdcc6ab9994888eabbab0a6808aa5 251 | b8b0a3998f95a5b8a395a7a99da9babbaeb3c4bea7c8b58e836e3f30333d3b48492503091e71ae 252 | b7d5d1dee7cfb89d9bbad9debb8e717cb3daba908e98b0c1c0ae99847e8ab0b1b7b6a195b0daac 253 | 9ca0b1b4a88d6d51668ca8afa8b3d6e1e6e3b6adcbbeaac6cfbb96a0c9b16679999c7757585a3e 254 | 3011163b4a6541230b242b2f3d5e4c264c566574777b7c9ca89d999fadbdb19a939fabb7bab085 255 | 84acb0a3a2929b807992c1d1b39185767e79888763534e381c335a4a30476da6bb84897987bbbc 256 | b29f999ea0a4a0919fb8906b869391afb494818f8f706987a5b4b5a6a4b8c9ccd4d3f5eba59bc8 257 | d3fddcbeadaba3a0bae3d5c19499c0c8dbf3d0b6bbc7b99576848dab7e575d4e39212d3a342039 258 | 27182c2a06020c36373b53663a566578879ca7a5a6adbfd8f6dbb798858599afb79c95abb2a5a7 259 | bb9e8781867b93b49bb7bf8a82846520282a2504161b3974b4c1dea395957da2afe4fed7bc9ca9 260 | b0b3aeae988090bbcabbb5a67b76683e3c3e6583aec3d8dbbdb69db4c4c5bcafb5cdcdabbbd1bf 261 | a8a2ac8f989bb9c6afaaadcfdaebe7ceb496766962646e6f5938215f634c311c1c22050d150007 262 | 1f24354637525493bdbab48a7987826b7494aeb1b3ab9c96a6baabbbc1b09a949da6aa93a1a191 263 | 8583a5d5bf7f81927329270f19153830376bb2c4deb6919498c0bcaab7a5b6a59792a2b2b9c9df 264 | f1eed4bacacfbabebc9f958a83a6c2aca0adb2c1bbe3eed7c7bfafa192a5c5c2afc0dce6c5ab92 265 | b0c7b5bacbcbe3eccaa29ea19483756154514b3824202f353a2b1f2515052c3e422c1224391d20 266 | 4987c9cbe2cbbda8878290928c92a0aeb2aca6a39c92aad3cb967a859fabcdae9a83495f7d98a1 267 | b8ac6d282f1f2b325f513f466196c3e8ced3ddeac8ab9d87b8e0e9e0ddcbc1b7b4b3ada197a7c9 268 | d3d8cda98e7aa2adb4a0abcabba4a9d4e3d1c8cac5bfd2ae9ba8bfd6e1d8d9dcab899bc0d8c9cc 269 | c5d6ebe6d4c9c3dfd5b590807c62401f20253731283c3f5f554341352f414032323776abb79aa1 270 | b6babee3e8b8a79e938e8f93979b8d868aa2c0d0d0cbb7b5c2a5a2b0969c9c937e858e78514944 271 | 2a000010415b576174bcb0b2bfccb89bb3abadb2b2aea1a3a2968fa0b8b29b99b2bbbbb4adbbd2 272 | c1c2c7b0adc2b29ba6a9b3ccdccfc4cdd4b59faeb0a0a3a6afbdb9c9d3c7cacbceb2bceafbe8cc 273 | b9b7cbccb9afa16b2c120100243f465042123256643f2b49512934193360a3bba1abb9a5a1b0ad 274 | beb8a3826c79a2c6dcc9ae958a91a4b49f8aa2cbc7bcbdafcbb08c75786736020c1e10244eabc5 275 | 984a3f96b9bba98c75a7b69a79787f9089878d909ab1c4bba4858b99a7b2b6cbf4ffca9e7e88b3 276 | bcb2c9afafddf9d4a69d9ebfc6cec3adaea39eabb8e1f2d9d6dfb7bbbcb5b8d1ddceb1d1e4e0dc 277 | c9873e0e233a4e3f2c37333e1a000813223622285242273d9996767c9387777f8a919998897f8a 278 | a7beb79b939f97838eb1ad989fb7a3a4c2ad92a9c6b39974490c0729201b2e9ee4d2b18bbaeded 279 | e1c0b6c8a97d76989cafaeadaaa79a7c687a9aa09eb3c9d4c5b4cab0badecc9d919396bbbec9df 280 | e7cbafaeb2c1b1c9decfcbb7babaa4abbcbcc0bdb2b7c2c2bdcbdfe3ddded1c2c4c6a9817e725b 281 | 4d2e1a2c2e27261c1d0d0008025c894a43456d92898ca8cacfa47173819099a0a7a8a59b93827c 282 | 95bbc8bf929bb7bbb9c9c2aa9c92a59ea7aaa5701a2a2328277ac1c2bbbbd8ffefefd5d6c6b8ad 283 | acad787e8cb7b4b4ae927b89aaabaab8b2b1b2b2d7e9d9e2caa9afa48aacc7d8d5c8b7b7c9e8f2 284 | cbd5e4d4e0d9e9d1c6f3fbc7b7c7c4aebcded8b9adb3cebca8a7bdd6dcd4d66c08082b3c3f2611 285 | 2f332d1705223f818922446e8ba8bab7a5a3aeb9c2a6b9c7c5c0c6d3dcb99279859da9b1b98770 286 | 8387a2ac87a1a68b9fa0a48d6d230000185b6e9cb7a6a0b8adae7295b3dcfaddbfb3be9bb0c2ad 287 | 968698bfd7c9af9db4cfb49fa9bdf3edd8ddcfcef2e6b4d8dededbcdab9394c0e7b297aec1be83 288 | a3bcc8e2e7cdc1bcb8acb6c9c2b2acacaba2a8c5e4eee5daba6218202b222e3245421703091138 289 | 5e9c9e26484d679bab958faccfe4d9dac4baa4ada0b0b1ab906e72a0c1beb48dc0b3738883889a 290 | 8a798e9d7b5b49301e2a4d5171aabbcfefd5b2c6a59f9e84bac1bdb1b5c5c4b48d899f8e8cb4b2 291 | a1c1c9efffeae8e6c8b7b69b9bd9fff1ceabcad1d39b858e98baac8f6683b2a6a4bbb3bd93a4c0 292 | c4bf9f8d85a1b3bcd2d2a8a2c3d8c1b8c2bcd58c60561f292b1b171e2d483b66766b7775011417 293 | 3a74979387817d8178827c8e859798a0a2a1cde4dacfc9c6c7daca9d87adb1aec0c59f8b868a9e 294 | 8c50352c1c2e5e8db7d2e1bf98b4dbccb59266525d7a7f78869a9b85979886776f85bfb7acbcc9 295 | a89fcdc2b5b5ccd3bbb1c3c4e9e3d8a79babc0ab8c94a0adb0958da08ba6bed9bb9a8a838ca7cf 296 | c7a9b2b8d6b5c8edd6adb6d6f2c271572500091b47525453231f345d88b70013090a2b617e8c87 297 | 73726f9284917883928d9095a4998794a59985849096a8a49ca5cfbea6a1aebcc08d3d1e271b53 298 | 857e8c9290ab9470a9c1cfb7bf978073616e96adbf9b939da29084a3c7a28982747189a4e8f3ff 299 | eebe978b898b9792bcb69ba2d2ae9db2bfc1cbb59596a6cef2fdc5a98e9dbbb58a5757848f7896 300 | c8ebe1b68f7d81b78962572c3a37061915242b272042a3b6283b2511446776878d8898a39cb8e8 301 | c7a69c8b998e9a9694aab9ab988fc3be9a85bbb2869cb4ccccc6c59f6053380f3b8cb2d4eedfc3 302 | a7a8d3d6e6f7e0cdc7bda8acb09ba6bfc6bec4c6c2d1c2b9c9d1bfbec0ae92abbfac95a3a482a1 303 | b3addbe0c2bcecd4d1d4d1d1d0b89eafbba48c9ea4b384627b715a57768c6ba4bcb9a7b0c2bba8 304 | a8ce92363b3c4b34203e28245a7d85a8707e4b585155698ea1b3b29b9a9bb3a19d98b5e4ddd9b6 305 | c0c1c3c5b59e96bb9e92b39f90746e6795ab9690a79c6f6331152f87c6c1c6ca90686c6b93b8d7 306 | dfc7cde1d9bc997a9dbaa4828faaafa5b1c8c3cbe0bd9cb7b9a7adbcc1cfd4c4b2f2e5d8d0dbdb 307 | e3aeafafcbdbb496a1d0c9a79dbfbcac6245628ab9c2b8baa998999aa6b6c2defffacb90271d35 308 | 3b3036655835475373b0c2cf0a0500000540719dad9f9f9e7e9399a19cb0bac3b3a59496a09581 309 | 7e68849da592969187997f696b797d7b7a46242d3a74bfcddde9d8c1a180c9e7e5a7958085a6c6 310 | cfccd9dfbda19ea7b5b0bfd0c1b6ccdae7fff6dbcdd0ccc3bbb49bc8b9babfd2c4b1abb6b0c2cf 311 | bab3b8ccb2a7a59d6f7d90abc0cccdb3a6bab9bc784d6eabcccfc9aba8bb5d254037271622231c 312 | 322c4776afab161e210a00254674a2bedae2bec69ca084777b716f8899a0a5a3a8b7afabb0afb7 313 | b4bdc4a98f98d0ebbb7f6b473748566089acb0d6b4bfd8dbcca5a39ea27f6786a5aab0b4cedde5 314 | bf98aab4acb5b49a86929e95c4d0cec7cfd4cabfbdc2bbe3e4d9c8c2d6c8a98e6d799c827c6e8e 315 | 8e76435791b9bb9e86859a9c6d4f63828d94bfe9eddeffff9d4150422d351b202c556d9aad9494 316 | 322c30221734436a9aadaa939ab89cc6b29593796982887e8089919a9cabbba7b09c9a92b0b1a2 317 | 9ebcd1c2ab765140647395cbb57080b1b7d1b5aad4d1ceb6b7c5a188abc3a18bacb4a8af967d8e 318 | 7b798c6f66a0bed4dae0f2edd9d6a7c3d1eccfcde6fcffbf9c8c48529b86764c4b3c617a797d6c 319 | 818b8e838494856479999584a4c3b2fcfab469261f0900101e504e4e619a9c998d1916253c483a 320 | 324259616f8c98aeb6a9bf9690b0ada3977472a0a7857c9b846584a49b8e99a09a85777c868a7f 321 | 544d51698898bee3e7f6dad1e1c4ab979b8b93b7b19495b0ad998294a4979ec2dad9c6c4cac5bf 322 | c7b7aac3e8c7c8b2bbcdc2c5c5adadbac0d6c49262424e7a4b1e2b173739366f90c69e909b7977 323 | 727a7ea697aaaca39d8eaebd691b2a300d0c5f4f4b7b566f98aaad041d2b2a2c372f2a477191a3 324 | b3ad997a897a89a5a3929398979da8b3c4d5ad8099bfbdb3a7a19c9b96866f5e3a59612b2b739e 325 | b2d7f4fff6eac57e6a7998825c69879fbbc2b7a87e747e80a9cbbcaab9e3f0d1b2cabcbdd2c5c0 326 | c0a89c9893bcdfd4c3b1c6b88c6868685e5e77a695806a454f848a9f98896e6e7f8cc3becfb2bb 327 | c2c3c2b5bdbf792c222c323033546f898eb0afa5c4241307040006092769978f777789a5b0c2b3 328 | a08aa2bdbea6999997939fc5cab7b0a29397827d879b9e918e968d662e0f4a9ca491b1d2d6c1b9 329 | 87464c8ba8a59dadaba2b1c59ca7aebcb28daec7c8bac0eaffecc9ae8386a693bccccdcdc9c7d2 330 | bca5bed2ddbe7f54617568516468567e72564d7289748191709fb1baa399a296a9b9c2c8d5e7d6 331 | 7c3831281f1d1f697f82898e71bbea612715313b261117304974a68f8a8d878ca4b29f9ea19ba8 332 | 9f6e648090a4b5b9a68586ab978a92a9ac9fa8c3988970656e7482a6acc6cfcacab69a9d968370 333 | 8aa485759b9290a57a76998693999e968f959aa3b2b08695afa8bebed9eed3c7d1b0898e8c879e 334 | 9f8a868c80695d4a8ca6776040636d7397d8bbd1baa39d827f91b1c1cbd7f1f5c559232b201616 335 | 5d89778b868790e6fc682d0f2534353e4e4b3f62a3b3aa9f886d808a729b9787a4a9797083998f 336 | 868888848fa9af9694afb9a6989e9c945f3a496b9bccc1c5d0cebcbebd9d8b80635c69647cbcb7 337 | 9fa38380a1a4bdc8b09c998b758cc4b0bbddd7e9d8bbcdc1b5bed7bc979f9f96a2966a484f656c 338 | 5c7baf775e615d7fbfc8929f7889aecab9917da4c0c3c5d1cec9ab622e1a0c1932785d446e6186 339 | aefff9906d3a272b373e4347485d7fbabfbbab8998998692a28f9fafa7aa94a3a39a89828a8f8b 340 | 9b9092a2a59891968aa38162636581a5bbc2dff0d5cfc7858fb6a2727691a4bac0a09d9fa3aca5 341 | a1d7e2d5b49e9eb4d2a3bcb995cdd5c1b7ab928ab3c9bcb4a0bda3836146464d4858895b225648 342 | 5075abc9888d7b748c9d83797ab7cdc7c0c4afc6c2722b1e1c21425741587d5f8286fffea7874d 343 | 29223d412b1a1724396b8da6baaab7a9978a7d71a6b49cb2b1c7bdb4a595959fa39da3a69f928d 344 | 959f9d9d5e4347333c587893bce9e5cfba828da98d6475929da9bce8e1a979899c706fa2b09184 345 | 919793b4ba927792a0a195a4bcc7d5cbb0bdd1d28f625d667a8c8a66876b5c683d2f50648a899b 346 | 9f9181705e88a2dadee0e2e1d4ead6600d28433a47678aa4b292947ce7ff6a67554e3022080011 347 | 1c16114b6c7d948fa69f9d9ba697a59d99b28ba27b7a9ca28d858a8d93938d8e959288869c6652 348 | 6f77899999977c82847480808985747e9997a8e1f2eadbe8bc859080667692b7c7b19b9eb3c8c0 349 | d4a4858d99cad2b3a3a0a0c9f7cc896c7b7a6c5c4a4a33514a2d635a6052709c988b8a837e75b6 350 | c6d9c0cce3e8dddad17f30363f2e3c88ba88745d4d48cbf23e69662e000b0d000010212556967c 351 | 647e91a09cbcbba5858d8ea089695f77a7b090818f92858690a9cfc794868f83826a5248888884 352 | 7a7ea5af9473576bac6c4a94b6eccec4dbfff3c2b3cabadcd6c2c6a9c0bbeaf1d4d7e2d3c3a2c1 353 | a1b2e8dacaa5a47c505e74755f4b7162547f9283736b8b9790b6a987806f74707f8cacb4c9c4c9 354 | d3d1bc843e0c00011c535e768899a766c5ff6b8e89603f2b1c1e272b292758a1bcbab69e8e8f82 355 | 8e968c846f95a6a29499aca79094aca586706567859581819e8b5b231e234995acb3bddbdec7b8 356 | 72708a8f8e8c84a1ccb79b92a9c9d3cacfc4aa837fbad8ccb5b9bae3ecba9e92afcbd1d4dad5c3 357 | 8245483d353b4c5d5c3c53848f78758eb3a9bf978a8570879c88726badcbd6d9ebbfc9dc94452a 358 | 224c3e4f5c8b9e8b7542a5f3333d545f4e475467572f212e12264f79a3ad9ca29797918079627b 359 | 7faca5aab3a88a75739985817d707a8a838a9c8b6b3b3e2c16347999989392a2d2d1b7b3b7c7bd 360 | 99a1b1dde4b9a1b4bcabc3a9c0bf8cadadb7aec1c4c0925c78b2b8c29d97bbacbc868894654f59 361 | 70815432414f6165696d574f616ca4b59198a1a8b090a8bfe8f8e4b09ca755232f1b42736d6f7b 362 | 745b4d498be0646b69625f2d080a100e1c35100a3353769497b3b0939dcce0a9acbac8b4a3a8b9 363 | c2bdb5949ebac5b6b6b7a6826a4e5130332c0f18403e44597998d4f7ecf9c5b6e9f3ffd1b5b5cc 364 | bc8e86a2bd95aad5d2dcc7c2c3c7b097939fbcd5bfcdb8bcc080694c4a7b98a1856261596a7975 365 | 81786b6f4f4b3784a694b2c5c2dbe0c4e0cdb9c0c2cab8ab45020c0e3b58708783868f8a8f94df 366 | 61717570785229151011181f1e112e497293899296aabab9bda9bbb5a38f7b7d9abbc8c6a4b4ca 367 | c6b8c5ccb4b0a4918e44262c1d4b6e6e7e79755f767ba5eefdd2daf6dcc7e3e8d0c8d8d8c7a7ab 368 | a7bbeaedf0d4bec1ae9cbbe4e4d4baddcda584837681947b87918a735c6e93815c584d4c72754b 369 | 569f9880b8c499b9c5b7cebbb5cadeeddeb56637425a728e968a6e7d9b9ea48ac413213b4f5560 370 | 593b1d1009031200000f4e78767a598c9b75717a957a646c767f8c98989190969c8b7d97a79093 371 | b0aa9a43262f153d6e93bea69c8596978475beb093d2b0a18d99ccf1e4bea48ba3a3b3ddc6e5e9 372 | a3c6e4d5c8c1aaa9d0c18c593d6460723030657a7a736486766b6d83795f584e5d6d648db4a383 373 | 4c698da0b3bde7e7e1c1a97747354150517f969797977c636571974e5c51466859320b0a2b403d 374 | 303b231e2d2e4b788d92a4afa76c63585d667078818a8f8f78787f786c7e8c7a6c8d72602b3355 375 | 3f56483f716e91898aa47f6292a899aeaea3b3ccdcded7d4d6e6bea4a8a7949fad9bb7e0e7ebdb 376 | a0867151456d8077634e55474b59676d6b73847b887d5a49526d9e845a91c6a183767e769fd0db 377 | ddabb6c0b3a35b1f141a3d5a7c778b93727d98677965726d6f4c5d58361e232d2d29432b3b4e2f 378 | 3b6076a5b18e929fb5939d9a999da4a59d948a838e91858b968c88a988773e31453046383e7e72 379 | 948980546fab8b9fc7abeffff3e2d4c1b0acb2918fb2b183acbecfb9b4b3a1bfdebaa279605782 380 | 9b7ea08677837c8c816c8a997b5e6b6966684d483a53b0dde3e1b9a6b69b9c868ccbb8ceb89391 381 | 420d0e0029678667798864666650564134453f335f7e7634000a15140c09062347546c7a89928f 382 | 939fa39ddcbfb8d4ad83a1a79f9c9c9f8788b8caacb0a98e59190319424a477ad6e2aa8e83bec6 383 | 9a7b6f7b9cadb8cad5c7a78c7f6a8b90a4bfc9d4d6dcc7c7e5e5b6a2ba8c738071615f7d705b6f 384 | a99f9c64355d4c36505c54636252406994a5b5d8e4cfb9bcc4c1b6bfd8e6e69c632c1d0b035ba1 385 | 94958d9a946f795452293b4e606f6c646d5d35251901000000193133446a92b8c1bbbbbdbdc3aa 386 | afc3a695b8cba996a4d1c7a0a3a68aa0947465573e304532183885a69893c1c2a06963909c7d77 387 | a1cbd3c3ac94839a9da2afa6a9c7c7b0cee3e0caaea4ad71476b6e505e834e4c7b755f6c596d6e 388 | 884b444e546d7d838dadc5baa8b5ced7d3d8e4f3f8ebd0b9c7c89b391a2b2a49916b878d665958 389 | 5a96853a4e435870624c616e554843282b3637444b3d474a749ca49ba0b6c9e2a9979796a5aeb1 390 | a6898cc3cea893808b94836854372b3e38200c1c4e83a6b79175839e9eacc1baca9b8a9e977989 391 | bbb99995b6c7e1e3a2b3dee0ab868c91846e81877d9b876e60406a5743697fb0ab725d76898b96 392 | 8f8587a8d1eefffffbe9eafefff9e6d2cdd9ffee993b1d2a45687b5068858191a1a3919565615a 393 | 757c74514b4a2d1a0d172641433f2c0c0e25394e565a6c89a0ab96a798858d89948f927e6c5654 394 | 7582a8a59983530f00252b292d2e3e74aabab7a9a6aab5d1dac2938d93a4abaab2c0b3c5c9bba2 395 | b4cca7ced6bb84728f93747366726d6e60696072696c4e5f626272899ba7703f516b7994c3e2e0 396 | dee7eeefe8dec3b4c2d6eeffd572101d4f504c56547b8d83808187a09c8a2325526e837e5e5a6b 397 | 6d592f0007160f0b08072344495a7795a9b2b59d79746d85a99d98adc9c0afa39e9b8489929c92 398 | 68341d212f4260646387a190cbd8cdbfbeab8d838eb0cecebdb4b9c0d1c6a0a5cee2cd9b9f8b7c 399 | 767c8e8a6c2745859887555f76927f8378806e74899c82684b6294855e74a6bab7d5f4e9cde9d7 400 | c3c7e1f5f9f9d4842c130d093d7a90b3955a557b979ca2980f2d5a4d3e4b4e607b9ea474292d37 401 | 2d28252647211f305a86a0a8aa9f9a9685869ba7b6cfc9a5a0b3becbcbb7a6b7b878403c455649 402 | 4138437db3bbbfbda9a4a48480afc7c5c5c0b0a7bad7f5e0a9a1b2a397937b626a7b6d62656273 403 | 69545ea18b7a97a1a579736737665842577a7e786d493a63c1e6c3b3bfc3c2dfd9e7f9fbf4ddbd 404 | 8c5a44515143507890a1aca7a1c1b7584979223b403152637c867381956b31394d4f462b0a1215 405 | 0e112439506e89abafa7b7cabc9b7689a099968d82a7d5c2919c9a430911110608203a4456778f 406 | a2ada59fb7cdbb9a87aec4c0cfece8c8b8d2e6faf3d7c1a0a79db2b279586a7d68526e65423762 407 | 636b795d6d6a3e74605e6b7f7b7c807681a7d7c898a1c5d9e4c3acbfd9d5d4c2913617354b4640 408 | 4e898fa3b7b6897a7c432e451e151746565c7b8963657b511e0e0a07152329474e463c2f1e214a 409 | 779dac9fb5c8b5a6888b967d7373656e7f79597378494f521002031b3124174385af999ea59baa 410 | c4c4d1d8e0e1d9cfccd0cccbc2b6b2dff5b7c5d2f8eb9c73899d8e836d44484047421f1f4b7a92 411 | 7d949d96a0a0878d9c81709adcf2e9f9fbe3d8bdbbe0db988ca79f5d271d000b527fb98c9a8283 412 | 7c5f6d817a5a2b232329415c65574b4e6889853c0a1a0c2014000e2b210b11162950a8b8927f83 413 | 86907a82807e8b95846f6e8b97898b724f59563f51391c222c436fabe2cdbdcbb1a8c8adc8dfdd 414 | ccc1c2c7d3e1d087929facbfeae6d3c7a0889073423f58534954422549546c84627a8f959daba8 415 | 8d96af9e8b8aa0c0e0dfb5aedbcec6cbe3cfc9cd8d33271521263d6e69889879515f7e8179817c 416 | 1d212b375f78889097938c8d6b482c26000003010004000a303e2a183d6c776e6a75919fb1bdad 417 | 8f898e8e8d789ca590684737212d2b191e39383652a3cdcdc6c3b7c5d8cfc8b6a2a1acada39a91 418 | 8d85a8ab88798c7f7fa7b4aaa17936325f777070707690676b978b7983a1b194a0857d8a738395 419 | 968395a8a1b6d1e4e0ecf6fff6d2842b5838212a1b294f615b6585957d66688c930000020b3348 420 | 56627070666375635546150e11100718241d161f2316365069708aa299967f8e9195acb8aa9a8e 421 | 97966f4e422e253a3c3d4d584752839c8f78829cbedacaa5bccdcac2b8a692808c83616399a2a1 422 | ae8c768d9b9ca59a766a888f787276839790948e89829ab19479b4ac98a287a3c7b17d82a8bdd2 423 | d1e0d1e6e9d6d6ad6b1b3730365466757b5a78a1b0a39da8b1b2901115191d1e39484747485162 424 | 4b42474a2e1f23292f3f4f2f00022325354e7a859fb8a5ada08f8dabc2b09ba09e8883582f1b08 425 | 1e15222f38332b5297d6caacabbfd2d5b4c6d3dbd0b6a19ea4c39c95ae968b7b9bc1a9969ca9b7 426 | cbd3943632719184748293b7be86838daaaa9476a2b3c0e4d4c5aa98929bb6c1ab9db295bddb92 427 | 9e692f2c3f434d6e8e9d9c8295a3958fb1bea0883d2b322d261e4158575353637b7b737c785220 428 | 17233c3340433b5767493b33435180a18681a49aa3c0c29e92aea09ba77f4924071a030d182026 429 | 2b4364a1dde8e1dcc5b5aabeb6c0d5d0ad8b7d736381b49e846682727f94add2edeae1b16f585a 430 | 67899faec0b6a06d6b647d8c888aa3b4998b9482686eadb2a7a48296a290bfdbbb913c0b185346 431 | 2c5359568eb8aeb2a885726c5e7236241c0700061e2d35475c738a8f8088908f67585729161c1f 432 | 151f1c00042039312b354e79858d939faaa08e8c76787556474a3c323544514d3f35302c6ba8b3 433 | bbd7ddd9d1ba9070727b7a7f8b9aa9a785708c95a6bac7c6a59ca3989eb4a9a4724b62797da0a8 434 | b9b19c75655c8a8d8c99683a6276858fcbb894a2b9f6cedbe9bccb662f332a322b326f938ea69b 435 | 9aa0956d597294b3861b160c01131a1a23446a88a08a7a756e856e563c040008100811201b0d1a 436 | 1824353d51609d9c8370818b6d493236221820313e2f3e515f4c23111b257d9ca1a6b7cdd3b4d6 437 | bc9a80767e93a7aa8c7a7397a7b3d6c7d1cfa69aa6b1d9ae7381b1b697736e838c928769757e74 438 | ae7846526f85a9beb4b8b9a692afebffdcf7e8a37e35374c360310376ca19c85625743426896b4 439 | c3b68106101e26262d292e49677f937984866875685d453a1d1525343d38283e432d42584c4a3a 440 | 435f6b7186885f3336545a62441d2b302c313726070c3a5f89caffffc2adba96a0afb3a8a0a09a 441 | 8d66809b89a8a7b0d0bac6dfe2f0eacada9f8482777ea09b7f807987aba0b5a685836b5c527195 442 | 949eb0b8919da7bbe3aab0c4bab7423d47272e3247506b726486877c646a93a8a8b0804f251012 443 | 322f1f29252f464c66727480796878908d694941443835362b2b1f0d0c2b4d493013251f364a65 444 | 5b6c624b454d262752341f1d170e171e3f0a2798d8cdc7c9beb88e808795857f9dc3af948d8465 445 | 5d717e97fbf7f1cfbeae8884745e52749295aea1918eaaa5a2b28f949a81829c888acbd8accbc0 446 | a4bdc7d3dadfc7654a37263b3f4b5d80a5a59ba295877da39c98b7865636111f2a3636252b221f 447 | 29304d4f567383737187947d4d3029252c281100020c151f262724020e000000040b1332212a3e 448 | 343b4a2c1006031221220c092469b3c2b9cfd7ba8d9ea98b7f91b1afa19a9883636c8a91acd2ae 449 | 968a8a8e806a6e6f72a0c2ada2a09a918c67649397cce2d3bdb69e9ac2bbbedcb3a4e1efe7c8cb 450 | 9d34170b122638416f9d9f9191947383989b8d9daf943a3b14211e170500121f2838527e6f5c68 451 | 84816d65656458513a17182c2d25211d1300000011161401000511403f3d3946381f202a354c47 452 | 3f4343430d333654aaccacc8fbeed6c4cbaf996c6f696c819da0a1c6e0d099898aa8cab7aaadb9 453 | c9d4beab987b7e7b847f6f617fa8979b827ba0bba592a39dc0eed6cfebd9ccc5ac661c10093e6c 454 | 394781a2826e7673766c8eaeb8aa8b8a51782d24140c0503121e1d1d375f674d4d6a786a595267 455 | 6567502923291c2e333d423b2e292c4d3c241c2b36715f3a29302937442a2d262f2f27273f416a 456 | 3b3b8ed4c2bbc6ad85a9d7a58e769c999793918995c6dcc2fdceb592917d8aa5c0a69a87787890 457 | c6c9ae958c8a99a18e756176a9bcadacbea9b2ced9dcccbadad596535058191e2c396ca5b5abb1 458 | b8ac9cbdb380696d6d6f6590150c010008090e18100417326169748289837b7c75808d71371d19 459 | 0b161816162235444944413f33322b4d32001c49453b2b0a1a081734453a161800020851a6b8b2 460 | c8df9c8c9a89b2bbd2b69c908d8c95bacebab7d4f9d2bfaca18c5e485a7ca3bdbcc4a88892b7bb 461 | a39fb5939dabb0bad8e2ceb1b4bcc9d6c2b2d494460d2f5a2d2e2e2172897793b2a38eb3c99371 462 | 63494f465f82121f2716131816242621343e4a6473787f7a6b6551668371361a2121001222292d 463 | 2d22140d274a413125261b13151d223134201f4d1f0e1e281953483c35477394a7cbf7ffe8f0d7 464 | bc868e95808dafc3c4d8ebe3efe0d7c7b69e9074637a9c98a1d0e2dda7a5afa7a09c8c8e9f9d9a 465 | 99aacdd6c1d4e8dcc4c6be9a823b323c4b5025262572a8875478967d6fa48e64a4b8643c264374 466 | 0514261a3b3c272929232d2337586a74848072714b3b4860636356381b1007080e100c090c233f 467 | 2b1b270e1e010c0a0c0e1f4a633e1d0c19292f46513b3239609ed5e0cab1cedcbdb8d2e0c3bbc4 468 | d5c9aeb5c7c1b68854676a7ba4a99acbf0bc8ba1ac9ed2d6bf7e7aa4a1979fb1c6cab8aab8d2fa 469 | f7d8bfbdad8358262f5139241b43699da4826d8b937f7e7b928682765b584c5a77160206011114 470 | 0003111929182d5b76777261627d705f7399a7a79a7e47210813221b0c05282526080a3d1f4235 471 | 36201d09000a0004294247474b0e13174474777cbae8d5cdd0c3a491a9bfbbc0ccdac8a8a8a68a 472 | 8fbeaca67582a5898e90998085c4dccbb2b3b99b9294818e9cc5e2e5e2d9cfccc8afb0e1efb87c 473 | 591100201a2029466d76646a8fa083635e605e583d36537497ccad1713140b0a0000050e0a060a 474 | 0a032941345fa3b3a9758586707b796d6d5f4021151a1a1114233a43444f54485d49231923110e 475 | 343251531706001335436b806f5e539cb4edfcefcdcae2dfc2c1a69697b3c7ebb3dee3be9f837d 476 | a3ac89918e9ebeb99a8d7494a676768c7b9ebcb7b6bdeceab5c5cef3f2b88d6845552735301a1b 477 | 3d5f6d6e97976649515f66635159440b1d6e9aa8a524151d1613182634301b0a04000f26416e99 478 | 9c835543656b6b969e84725d3713040f23302c292a210c081216140d1033504033493e42362347 479 | 434c5e523c10011d446ba5cfd7f0fff4d1c6d3c2a8b4d0f8fff9b58f776694b5aba99d8bbdd8d7 480 | d4bb9788aa9da09bc2cd95959ac4bc888faba4a5c5e8f39b443c3d330520252040779dac868c87 481 | 693b264069894a3d514c5c7e85778e2512070c212b3945463c2e2438564c50859474656b557a8e 482 | 786f6b6669869d8c592e2a3a58301c232b35444d2e2120281c04031800101e356c522925393627 483 | 282f36175ebfd0dbcfb3a1a6b3bcbce3dfd0cacfc4a89b91a4a0868d99b4b3b0c1d4cbd1f8ffdb 484 | d1d5eedea9b5accfcdbcb7c1ddef96735b443934262e46686d6b8ba7a6a1939393805d48433c2a 485 | 2b4c646685a091a6ba350600000d0c090c14180d000b160813414a4762796380997b62728c9591 486 | 959a89664a403f0e00192b2b2b2c534a49432f1d1104081d141a493d1a1d130500112d443c6771 487 | 848785a5d9ebdac8c0dcd0ccd6bfacb8cfc89a6551616e85899dcff2dbc5d9cbf7f7a886aac7e8 488 | eee1cae0d9b3b8babd823b40764c11473372948f877c82a0746c6e706f7a7e704b3a3c475d90ab 489 | 958f7367393c17050503050e17160f1206000a1a2b40535d68808e827f8d89676b7c8b836b6269 490 | 361c1e322a11090d15111a36668a743c39492b1c36380f00000b31545b45451a1c509edbede1d6 491 | d7ddcecbb3b8dac0a9a0bccbb9b6c6bca69ac5ccb6b1ada4a5dbd9d3c1c4d3d5dedad5b7c6d2be 492 | a7777a88654358432a6a808e9188785c57704b41516d6e60697e9454394e58565c61736c537c5c 493 | 3a221b0f000000020c2c2a30231333616a8777666e6f748c9087624a59767f776d56372a2c2216 494 | 141400030f2c6b97783b333f1a000017181b564b43270e13624b27417bb9d3d6ecffe7fdfbdcc1 495 | dff1ffefeef4e4dbdbc6beb9e2e2c3bcbfbfc4e9ab95c5eee1c2b79ca8a3b8d6cfa97f5259644d 496 | 43566479816d6b7e87817b7a91a0a3a2a18e7773706168715a40475d969906544b3c1809000410 497 | 1f3447312f290e0002212a404c61949b7d8081939daeb8af9a8c8896786057514e412b243d4249 498 | 67693f19000d161e132c2c270003182023384d3232293669a8ccc8b7b2d2d4e5d9e1eafbcbbec5 499 | b8aeb3b5d0dedec9c3dbe9eefec2d0c4a8a5cdf1ecdccab3acb491616a190019446c90989a7a82 500 | a4ae9596acae9dc3a97e94ac9e919b9a907e7682929692a90000614e4f311f2c3c37281f150300 501 | 102e35333b4f73716958577f88949b9f97877e85909fa7b5b5a69577523d3611062b392c2f3c2b 502 | 1d2c1e3426101f496b561d120004040309131f3c76acc5d3b8cfbaa9b4ccc5aeb7bfdaf0d9d5e9 503 | f3d7bcd2e8ddcde4d7d3ded7cfdadad5ac6d2f2b1c002a242b3a5990997c8a90818d8d7f99ab89 504 | 6da59f869fa6a1bbded2c3b29c8c909f906400003d8b8b524b1f212923190e1709141c21414554 505 | 828b737a90866a68776651617273766b6a6e666c694a433c1e0d0111314c716b2a06264230335c 506 | 603b270c112e3347462a44412b395d93cac0c8907c91bcc4ceccd6d3c4cedacde3dac6dbd3b8d1 507 | e3e0e6ddcab9a0847651291b3630264553432b4e647a5c607f9a8f615a8885978b8785716a98ae 508 | cdaabb8c6f7398aea4ae947b00000f2765581c342c151020302f17150f040e0519304a667b7665 509 | 5f36546e7f8b7e55331c1e363a39485e836854737855483f36333a444f452b32573e00002a3e33 510 | 3b79521b1930323245665b7abed8ebf6f8f7e0b7a3acbad1ddd3b5c5bcb6bbc5c3a88c938ea2bb 511 | 904b36191e314d3e355c7174728e92afa4979979a0b3a7a88a9196a1a489a0e0b0959f75595d6c 512 | 7e8a8a9c8b7d000700004b7b41271104000901101624261e231c2d33435c655350668c98a49674 513 | 5f564d4a496f89a6d4e4e0c2cdc79769412f51484c35140806020101112c313c4e453f16121b3b 514 | 4d555a49555273b3e9f8d0c8b9e6fff7e0ecf5e3d4e1dcbabed1a5698e866c482c1d273e7e6b47 515 | 415889b4a8a0907b576a6f687387888b728d9eacb6a08a849bab85807f785a75886e5a6d9ca07a 516 | 010a0b04124f762a1f1b0e181e292b271b15212a4347454b63798a9b747075674c5f94b3a27e8b 517 | 9182837867777e79636a6e55563b493209072231333638495758421d071e393f515350675c3633 518 | 3c6675725274c6e3e3bcaabfc3ab7f8ca38c85906d5967503e1c0834573e414731366db1c3948c 519 | 8b8c84907f65766d7a986e6b7688a1999aa7a297a8bea6827882634766776b64700000050f0005 520 | 5d6a60321823190d0b182c34210f0c0d030d3c6978774649647a7c8fa6a88e6678763e264d8861 521 | 4d8897779da45f3a392a2e567260423f424e5631020f385a5d628d813d3136291c132f3f4d4475 522 | 94888899a0845e4b53628576686f67784f5c5541434d3204386a88958e81847b657c989e99896d 523 | 7b6086cab19e9cafcbbfc39c72727b7280895d5c6479a6a88b645801000006070619786e432a14 524 | 081934280d00000004060003172b425c60728d989391918a64637c725a69859e87708f8b6e909a 525 | 6e73888a72543933403c5142271a326376805624272f1b1e33381a091c4364555c4b3f3137423f 526 | 465f887b705e616a534038776e596f59487b9fa49ea380454a707e86805d40637790bdb5c5aa9f 527 | 9aa7a7996f69888b877a939b797d817d7e6c5d727f06040304020d00315263502a391000000c23 528 | 0d0328302f2b2f3a5b858ea39d7a5c4e4d5547596f6c83a89677796859669ead8989968c715337 529 | 16060e4827000d374a4f342a200a000412070f121b393239453b273d361c1b425f6264553c1a1f 530 | 383f2c073652474565635d7e9f8865768974788d9a949687689dbed1c5c0cac1af94a89f73518f 531 | d2a8947364699bb88e7c9da0916c6d0003060703040b004c6c493c040016171e271316171a1110 532 | 2a424a4e4e70746a77817e81746c777c7d6e6079736e7d87836a608a7d796d655a3b201c335258 533 | 614e2c2714212d44382d17001e3430452534576645383637567662403f35352b4d594c60637a6a 534 | 7d8883a5b487939870657d8a93917e6b88ac8fabb6c0b2a7a8ae9c6b72517a99b7ad7c764f5884 535 | 7e92a09b8d9ad5b0780000000000000000110c6f3c281603070a000114030e07030e0700030f51 536 | 705f5d77888a7d7788a9a06a597a827c6f402536507082704930405d7280a69c8b4c1716191d20 537 | 4e4b20182c404f57545b6764544c4f2c3957603e1f24364a5857433a455153533341656f777b68 538 | 706d4f37435a7eaa9b8a9ba1968d7f8268808e87735f66816c717f64746536849b7b67869e867c 539 | 968d82000000000d070000020b7a8662250f00081400000e19151624221a224c676b5a53596470 540 | 776f6e7c807074936d6867534f5c585b767d7269788b9296abb1b38b75847b6b482f243b51483f 541 | 49446963290d242f1c2736494f3e231921484b4b526c858371446585744d4a564c485858575b50 542 | 47537e7e8973637a91a4adb5b8ab8c7391ccab735261706885caaf9c9fbb986068746f73000000 543 | 000000000e04001f3e4726332607131a151a231c0d06000518261e20426d776f715f6c6d6a7171 544 | 6a6a63636e635b522b15123f67819daaa09490989979768d795e63676d634e4b5b66612908192f 545 | 2f344561695f575e564c535c6f88a9d5fdfffefff4b978585c5f558283797170696b7b60738f7d 546 | 6f8894968671595a718192abb8794d818575acb6ad704f84816d8f788c8d000000000400000503 547 | 0000195a703723141955433d34221310151f2b170e184c84908585586f64474c65685d58688481 548 | 7870524515364c587084847f7a776c52618a949dc0a2adc19d6856583e2d262d3033455e667568 549 | 678ea4a5b4ebf6fdfbfcfff9eef6fffff6ac5c5789846b52505a5e6169736f807d7b8884817c8a 550 | 7a5a586b74746f7e7d988273a292726a609f98739d8daf930000000009090000001000142b9366 551 | 3c34121f1c160300051d2f2e2104141f27354256727e9a895c58727462898f9981685a413b2739 552 | 4045565c4f44475365697b8c91b0c1a5a8b6a38b80765f7e8d78656d818ba8c2c0c6eefffbffff 553 | fffcf8fdfffff6fff2f6fcbd563d707e767368504c719ca68998aaa89d9099828064526f8f8162 554 | 4295c2ae856b69664d756a8a7e5c9bb9ac7d00000000000a0405000700001946794d1016242808 555 | 0a1c2b2a292416183133242942627c829e96747284806f68666b5d5d69605f70511f0312304c65 556 | 5c6d84898e8480accce9edc7b1d1f7fef9e1def7fffdfafff3fffbf3fffffafdfafefff9f8feff 557 | fff8fcffffbf79759aa2887c755f5e83a8c7abb8bda3847688877c68688495918c75a3b28c8a88 558 | 656d8cb197988c64737785610000000000080000000409151000486a56684a1b121a303013080f 559 | 0c2f3b2e1d2d49585d59665d5164839194696a7775819794958b693b24272830424f565446515e 560 | 73b2f2fbfffffff3f4fff9fdfcf7f8fffffbfffffef9fafdfffffcfffffff5f1f3f5fff0d4ab85 561 | 8b9d994f253177b0c4b9a15f5b6f6c677e97b19e8c7c92c4d9c7b58d8e755379aca9ae80988e79 562 | 606389928a80000000000506000406000400000a0e417d59242d1d0806080311221b1e25130009 563 | 243842525e626c848e857f6f7a908a89928a8c6d5a45444126121703223638505a5880c9f7fff8 564 | fffffffdfafffffcf8fffffffaf7fffffffcfcf6fff9f3fafffff5e0975c28153685a2773d4276 565 | a59571635e6f849d85788f8a77739ead947a67574f54818f7c86aaad906b7c9e9f8597aa88696e 566 | 0000000000000000000001020000073074a19168491231322f4b301b0d080b181f160901162d50 567 | 5c746f5173715d5a756c6e7b48424744421d112603212e3b604d423d3d3e5daefbfffdfff5fdfc 568 | f5fffffffff6fffff6fefdfcfff0f9feffefca9c7f77673f362357836e1d00507daa96847f807d 569 | 837c8675a3819a9d8485887d69525d717c8dbcb3796d6b9aaec094819480757f73000000000000 570 | 0000000001020206040c37645e3c1325181f3029241f000f242d210e060a003f5c50525a6d866a 571 | 57597e7d6f735532597e6e2d204f5f757e8a967772615f5f4d5c606bbaebfffcfffffffbf3f9e8 572 | fafaf7fffff4fffcc6b3a1a3a28a849b8950532320312e31496f89a39c737c8a7560597b8185a1 573 | 7d736f8aa4a0a598a09f8a5f617687998a9b8f816b75969587867d000000000000000000000102 574 | 01040100072441514632070d24180f0d040507080502060c4672574f66737d6444392c3a424661 575 | 6e88818f7d626c777575788e8f809b84827e504f515cb3a9b0b4a281777993bec3cbcac4ccb58c 576 | 898da1a59fafc29f7373584a86717c8e523645697f707a60695b8384747576739786999ea08755 577 | 707479777f72768ca0a081807178a1aa989a99a4a20000000000000000000001020300010a0000 578 | 37817d1918180b140004000411233135312d24271327494f555161716a63686a798e8e7e8d7864 579 | 695650576585653d666787b295929e788c626f6a522d2c4470a0a0aa9e8b97968296b197a4826b 580 | 868a757b9bb3d9995a432428487496929a877a65658e8893cdec8e888e989373436d634a4e6c84 581 | 8f8a7b68526b6f7ba49d83908686b30000000000000000000001020700031000001a5b7c476042 582 | 0902000b171d1f17090000001704153353605d7791856b61747f93c18d7f886e5e6b697a78666a 583 | 5042776b78afa085ab9ca8898259554a576e8faea3a59c848f9477737c8cac9e90a9a68f966870 584 | 6a5e2d020f363f577caca484677eacd0c6c1e9dd72768978768186ae9b849aa29e816a696c7079 585 | 8986887a808e5c94e0000000000000000000000102030002050300030c47776b3f17010e1a0803 586 | 00000012242e180a24242a393047614c52718c7b698e817d83838a9187877c6367798ab494868c 587 | 92728686937754506b819aa6b4c5b2a4b09ea9b9a4928b7b79646271696c926893909761293758 588 | 2645678a808474988d8d847782578da9a0868d99a19184988bafc7a2848c8d90938288968285a0 589 | 9699b1000000000000000000000102000000000407020000353f38352b2b2603060c16252e281b 590 | 353b48391e1c2f47443f525653473e6248708c9d9372625b728096a6807d88a8c2cbb98d635f58 591 | 676d8eabc7cecac0998e9f79637279838a8b776774858491b3ccbf827565542f210b3b5f4f547c 592 | 82917d756e698a6fa5a56f82a595a175647a8382815b5584b0dce7a59f9f746273868e72 593 | %%%%EndBinary 594 | grestore end 595 | -------------------------------------------------------------------------------- /utils/result_vis/result/E0015433121_cropped.eps: -------------------------------------------------------------------------------- 1 | %!PS-Adobe-3.0 EPSF-3.0 2 | %%Creator: PIL 0.1 EpsEncode 3 | %%BoundingBox: 0 0 150 150 4 | %%Pages: 1 5 | %%EndComments 6 | %%Page: 1 1 7 | %ImageData: 150 150 8 1 0 1 1 "image" 8 | gsave 9 | 10 dict begin 10 | /buf 150 string def 11 | 150 150 scale 12 | 150 150 8 13 | [150 0 0 -150 0 150] 14 | { currentfile buf readhexstring pop } bind 15 | image 16 | 494f4b3e475256525a7794a1abaea49a9caab69f9eaab895503d6268574e53585346382b283c54 17 | 4623244454463551717b7f713f2f36638b91929e9b9298a28f727c9db69e90979c938e93b4b0a7 18 | a0a1a0917e7d8b8e8c8f897c7a807972788890887a694a302d33312b28302d2f332e2422271d1c 19 | 272d20171c1f21282a2a313a362b202e3a3321151b272c302d2118192025171e1c2734463f464e 20 | 52566787a4b5a79e9d9893a1b798a3ada9834b3e5c655755708f88603e2d3e43352f3b45454431 21 | 1d354d4f53483e394c73909da4a8ab9d989c958687969e8f98b5b494848eaeada498969b9890a2 22 | a49687888a8c93837c767a88908471705f53555243322a30343228242727232e212327190f161d 23 | 21272826272a241a2726252526282a2c2e25150b0c161c1b1c211c12213f3e41464e5c728c9eb5 24 | a0949798959fb1a5b9b291745f514f5e697793aea174563e3d3633404d443021211f3536263037 25 | 373c577787959e9a9d979597989795949092a6baac8c889ca8aaa39591979b99a49b878297a7a7 26 | a7888a888383867e72657484856d4b31282d3430201b262f2e341b131a1c20292b232b2f2d2a29 27 | 25202828221918222e3431231417262914001e21191d2e45403b3a465f7c9099aaa5a09ea1a5a9 28 | aab6bda77d61534d516a859195a0957b71533a2e3d4c45342a1c252d40351a283a2929486b747b 29 | 827b868d918e89888d9498a1a59c8e89919b9fa4a095909495918687828daab6aa9f96978f8585 30 | 8983776e8292896c4c3427252c2e261d1d262e24191d28282b3233232e3838333031311f2c2c1b 31 | 111c2b312a27272e3731160018211e314450493d344163879ba0a4b2b5abacb8b5a7bdaf94754f 32 | 2d365e7f8b7d73889080785f523a282b3a3e3630323243381d2a3c3f36568088878b868c898581 33 | 7d7c838b9ba59d868595927d8b92938f8f9390877a878d97a9ada19bafa28d828b948770878a82 34 | 6e5c4d3a291b202c30220f101d19263f45302224261a283536302d31351e26241d263937272129 35 | 2c251d1b1b1a2b3b43373c4f45474f728c8489b2b9a8a5b4b4a5a2ada8958263382d4a68867c7d 36 | 796e7e8f8551392826314958543b4146443b322f301f2a567c828a948e8974686e747681918989 37 | 898b8a888889898a908c85909e9c959091989c9a9a9d8f919c9c8e898c8988848884715c42261c 38 | 353b2518232b26152a362b1e1f2628182228282c31291a0f1a232b3b4844362928272218152030 39 | 35475f1e2545334b88b9dca68f96a39998a3aba8a7a9a08c867b5232456c7b868d7968797c5e45 40 | 32272932444e473e464337333a3a32191c4071878a8d9184634952718b95978684858b93969491 41 | 94919ba2968e9293849ca5958a90948f8b8b93948b8e98999098a19b8c7e5d312c2e2926334136 42 | 1e13232c231b212a2d212c312d2d2f291e20282c2f3a4849402e31322b1f191e2637577e303e46 43 | 4a73d2f4ffa78f9087959fa0a4adb3b29b897762402c46717e868469535c5e493931353d3c3e3d 44 | 33393d311f233739293b3d47637f837b7d6e513d4e748e8f86928e8d939c9f9890948b97a79a84 45 | 7e7f8ea7b3a79ca0a5a19b9699989196a2a398a6b0a89f9a764036393a383530271e1b2529231f 46 | 242928273136312d2b241b1d2c3b414444392b202b34322c292b2d416a9a556b6c85b4ffffe381 47 | 7c9385a8bcaea1a8afab948d6a3c2835536d79695b4e3b2e3139343b525e52464139413a2b212b 48 | 3c3a2b37433e456a7e7b7d60473b4b60666a71979796989c9e968c887e899a988e8a85a5a0a4af 49 | afa6a4aaa29b9ea09a9ea5a19ca2a8a39d9a7b4b333c4745311c19222a2d2d2725272520232c34 50 | 3738362c21213549504c3f2c1c1a26303131363e445c80a5697d979fc7f8f0ae6e72939ebbc7b5 51 | a8aaa18e8983603f3f4b596a775e44372a1a1a2b414e68705b4b4f545543353944463e36232624 52 | 37586162755f3c2a38413f5271909699999b9e9a93867f858f98a5aa9e9c918f98978c888e908c 53 | 949e9ea1a1979794999c9486694629232d454f4230272e2a231e22292d2b333940484e4c3e3138 54 | 444f514a4137302a2a26201e2a435a7f95aa8993988a9db2ae877f92a7aeb3b2b1bcc1aa8a876c 55 | 46404f4a4e6f987e4d2c2d363f4b5e62706b4c3c49585842353c443c322e26121a465d494a6b50 56 | 30243948475673959ea29e9ea3a19b8f8b8b8b8e9ea4988791948b85888b8a8b87909c9e9e9786 57 | 868692998b765a3e281c264d6c66462c221a12142134434a625f5b5852483a2f333e4a4f4c433a 58 | 342a1e120b0817426e949da6acac8c80859a8e8b99b8b3aaa09ba9c0c6b1988e6c3d374a404470 59 | a1814d394e5f67776e6a6f694c3c48565e4e3e3a3b37302b270f1d48574e5566362f33424e535e 60 | 6d959b9d9a9ea7a69d8e8b93978e8e94928e959996969b9b9791898f9a9d9d94817d8a9b9a8a80 61 | 7057433536506862432815121422364b5a62756d5d4936292627212a37403f352a231c11111816 62 | 1b477c9f9e9db1ad958e99c3a8afa7c0a0a49795a4b1ada29a908154404f4a4864785538507770 63 | 657a68646e7363575e67776f5c49454b483f3e2e3035344249372b383e3735455c6b7f84868998 64 | a9a99e82839aaca0949daaa6908a9ea99e908f8b818692999f9b8a829aaba091999880684a3541 65 | 5b5b3c1b1015243b516066686057442b150f1c2c2624242524211f1f1b18283e392e4d80aaa399 66 | a6a8a8b0b5b6b3b6bab3a69b979ca5a08e838486897c604e4d4d4845384b58464e696b78766e6c 67 | 6b5b5058708476637785725f5e4e41392e262e3f434536303d3f445c606e82827f979e817c8996 68 | a7b4ab9d9d8f8b8b939fa39d958d878389989c8c787f989a89868b8884795b4d4b495553373231 69 | 415356575852494336271f1f222226262c312c26304246455a6b6057677a9394958695a6b5b8b1 70 | a49fa5aaa9a9b4b5a6989798968f9589674738332e2d253a5555576a788375615d67655e647e7a 71 | 768395907c726c5c4a434348525c49524940464039436878847b727e8880848890928b8a96a38d 72 | 9da29892999f9da19b918a8b8c857b81969d9183787f9486736e6f6e787760544f5a66635d574c 73 | 4c38292a3336322f201f293b464b57656d75868d868689828c8a82969c9eaab5b7aca2a4a8a8ac 74 | a9a5a6aeb0a2918b8d81674d3d312822465a5a64726e61717b7d7b796d687183787e8e8c827c78 75 | 786956516177807e727c715f58504340586a6f64595764787e7b8b93848595989da99f81778da5 76 | aa9b9c988f898989889b959094958584988d828081838f938675707a8479664f39402b1e253031 77 | 2d2d272837546b777e8584919c9897a49e81807d72b9b6a6adb9bdb3abababa8b19891a8b6ab9b 78 | 978a8172645a5041353a6a78727c7356485f798b908f85808782838e8671798c8a877c6b677c95 79 | 95857c8c8d7f756d5b4a3d4c4b44433d4f7a8374879c959da695a39b8570758d9d9d87929b9b97 80 | 94918d9c91878f9a9087918c8279777f8d948f877876786c5a4630342e27211d1d2024353e5472 81 | 888e8c8a8992999494a4a0837f827db1b6b0babcb4a8a6aeb3b1b8aca7a69c929bb0958a7b6a59 82 | 4a424060686e85874b2b506a72727a94a5a5a3928e938d7e8fa7a69592888391a0957d5f758a8c 83 | 857e6a503e3c2e2a3235558c9d848a968f9dafa493877f858f8f8983838c969a9b978c81808f92 84 | 8c8c88868d908a7e7c8993918c82644f47414140363136301f182027273f516e8b9a99928e9699 85 | a3a6a0a19d8d8e9395a0a19da7abaaa9b2bdbdb4a6b7b7a298a5ada99a978d7552393e5078827e 86 | 7d6d362249707e7f8095a9aeb0ab948e999c9b9b998a929593999f9685707785877d7e7a695941 87 | 261d23335f95a093969585889b9f938a8a9393898489828181848b8f887e859b9c92979d958b96 88 | 9b9697a6a5948a6a4b35323338372d242620191f2c33305267859ca7a6a3a19e9faeb5a699948e 89 | 98999ba79c90939da6adb6bbb1a294afb7a6a7bbb79f9d978e795840475d83b0ae7d5841333664 90 | 889c999da3a5a8aba498999f9480787a8993918a888785898087897e85918b724f352a2334638b 91 | 949394928982858a9b948d89888990988b847c7b8691928b98a49e97a5ad9c8a8d9d9e9faca38c 92 | 866646302e2f302919161319262d2e3948727f909ca2a5a7a89697a2a5979094939a9292afa8a2 93 | a0a5a49d9c9d968a9cb4c0b1a3a7b2b5a99685786552515d8cbdc69564483b385f7f8f91a0aca7 94 | a097b7b09594937f717c8a938974676a72736e849793969f987e5c4c43313c657f968f82828c8a 95 | 83869491888289979991a49c908b929c9d988b9fa19896938d8e7b9193919a907d7e7d50291916 96 | 1c1d1316152a45402d40698b8d8f8e909498998f90948e8591a2a49d8f8eaabbbdb5b2a399a0a0 97 | 9a9cacacada8a6b5beb69898937e5d474f6491b0bd99716b61444b73919297adbbb9afa78c8391 98 | 897b8282775f4a3b2e3c5c544e6180857379937773543b3f4760888b858690928d8e958f8e98a5 99 | a599929699908f989992959f9c9a9896938f8d8c95868b979084817f834e1e162025272a312d29 100 | 272c4168898c979d938580858a8c948c86939fa0a1a49f9ebabbadb1aea2a0adafa5a2a1a79f93 101 | 99aebdc1a3998f7f6040353c748fa8a3928a75505176918e858d9ca39d9b88808c897d7f635036 102 | 2f34323445413f444d5255616f7962413946485678848d8b81879aa39ea19d9fa39c92929a8b80 103 | 82949e9a979a928a86898d8d919787818c978a7c7e83774d2b2d3c403e3f392615193052758ca3 104 | a5a0958e8f9294a1aaa6a0a3a29da0a09e9fbdb198a0a9b1c1d2c6a89793a9a497a3aba6a89c95 105 | 9083603523296280a6b0a5997e5a626e7c85898a847e8b95918b908b786d43301c253f453c3b2f 106 | 332e242d445250664f3c434d4753767a88897d7f919b9793949ca3a1999aa2a690858f97908683 107 | 9c908e999c928c8e7e79848c7c727d8a815b393439342c29321f122043698697a6a39d999ea7a9 108 | a6adaaa1a2aca79d9ea3a09db9b49f9aa6b4c6d2c0a193a0b8ac9daba58b87888c908255292336 109 | 4471a1aa9f9c90745c5d6b849591837a859aa49e9585664b2d261a21373a2f2b2d30281c284147 110 | 3c3f424b524b445b8187919ea1968c909a89898e979c9da1a7ad927f85909192979f969aacad98 111 | 857f8677787f7876848f825c34221c140e0d1c1b253f607c93a09a9794959da6a59fa592808aa3 112 | a69c9ca9a298b7bab3a6a49b999f9c9ca9c1c4a694a6a3919690918e774d2a2b3e46749ea1989d 113 | 8d673f4a647e85818998889ba79b836c4f31393e352828292c37494031272f3d3d33273c525141 114 | 435c737d92a8a9988a8e999c928a8a8f94989ba28b7c818b8f98a48b8284959c918785957c7886 115 | 8c8d8f8d6f502e1e1a191c2113192f52768d999e9d99918a8a8d8b86978c81899b9a9499a39d94 116 | a6a5aba9a190888b8f9fbac3baa5a5b9b7adb7b2a79070503c383c516f919fa5a8864f3435435b 117 | 6c76889c8d9296825f4a3d2a3e4c432b212a425d705e473d434f524e343c4842343e4f515a8299 118 | 8b808c98959392939799958c858f807a8389878a94857971747d8790979b828299a4a19586725c 119 | 4436302e313522202f547f979c99a8a3978b878b8d8c95a2a7a5a0918c989a9a97938ea0a4a49f 120 | a3a9a3a6b7a9a0a9c5d0c1b6bcb4ad91694d45433f3b496f96a8a17b4e2e24263e5d7481888f87 121 | 85704532332c293a341f1c2a4158685e4e495b76827f5344423b2a2f3f3e4e72867f8097a39c7c 122 | 88969f9e978d86776d6e7e878280868c89807b81909b9f9582869ba19a8e817a68503e322d2e32 123 | 353441608399a1a3a4a29c999da3a39e9ab1b9b0a5989298a0a19f9392b0a9aaacb8c0b4abb397 124 | 8ca5cbcbb2aab1959c8a5e3f3d45464143658d8c6b44291a1d2a3f546777829183816e402b302e 125 | 2b3b372729333a3f393f3e436391a59f6a4e463f2521374346566a79838c9192818a908d888b95 126 | 9d8d7d757c7c6d6160899498969aa5a69e8e7d81908d85837f6958402d22222a323b475d768896 127 | a6b3999b9ea4aeb2a89b9dacaba3a6a59d9ab0aea6a7aaa8afb1b7bcb7aca5a59ca3aeb9bdbab1 128 | aaa19481604246606e6d534e5953413227221b253b506979777b7d6e472e3b483f323440483c27 129 | 222b23323c3a4e7e90796459422c293538314541475b707d8891889a9d8c859198929598898289 130 | 79605f73839aa8a3948988846b69859180747a61543318151b2b3f504a6d8c8a96aba6a9a2a9ba 131 | b89f8b86829197979b96929798a9b1acadaba7adb1aca3a0a7b0aeacafad9a8c9fc1aca18d6a4d 132 | 577381755543454646443c1b151b293d607e856f68553e3332343528314044321f22333f332117 133 | 2c5a6c57493a231b2c444a402b2d374a60738086929f9f9699a5a291969ea09d9c928a8e7f8085 134 | 8b89827f80858a8382918d6b4e54493021282e323b5b63839ea1a4a3958b98acbcc2b89f898b98 135 | 9b9ca09c969ba3a2a1adb6b1aab3b5aca7acb1b0a5afb7af988997afae9c826454616d665e4330 136 | 313e535c54372f2b2a35587a827666483f483c303c404246433424252f35261c1b2a474e3b312c 137 | 2424334443383538342f3b566e7889929596a3b0a48c9097a3a39799a8b0988c817f83878c90a0 138 | 9e8f919b7b452c3932222233372f2c4d71919fa4a299959ba7a89ea3b1a790979f9fa1a8a49fa3 139 | a89991a9bcb4acb2b2adb1b8af9c9cb1b6abadb7aa8fa182624d4c574a2a2e24232d405d6a5f50 140 | 453d383c556968695c3b3855503d484e4338353430292323222d36373d3f352d34362f2b2f3536 141 | 4e564d32293c51586e7c8891a1ada28d8f8a94938693abacac9e908d90929597a3a3938e8e6533 142 | 292e2b21243435292445809a93969494a5b8b7a38a8a9fa496a0a39fa2aaa7a1a79d938ca6b1ac 143 | a3a9a59a9ba5a499b3b3a59bb0ccbf9a9271514140463a1d171a2530405b6a6043363338404d51 144 | 464147312f565d463f302920202830302a3b3235372f2e312d2b2e2b231f27364141595f483639 145 | 3e3a596f838d99a4a298988c909390a0ab9da49d999b9b948c8887a2956f615a422e3839312c30 146 | 2c2528588f9a8b949591a3a5a6a39fa1a6a39aa4a29b9ca29c979f969a97a8a1a3a7ada7958b95 147 | a9b5bbab9da1b0b9b5ac886a52443c434e4e2d2a2d3037516767412d2b393f3f392c3b4d453f59 148 | 63482e1e282b26242f3b404b39333532322d201d1c1c222a30302d2e434c3f374047454b5f727d 149 | 89989f9e9d97969ca6b2ad988e8e94a1a79f918883867b5c3f37352e33393227231e202c5f8487 150 | 829a9f8f919296a0abada59e9ca3a09795978e8b97a3aca9a8a3a6b5b5b0a8a1a4b0baa1a1a8b2 151 | b3a99f9d7a564242434d65754d3b2d292f4c6b7666463c4743352f2d444f4d444c56472c29393f 152 | 342d3643483e343438363832211f1e212a32312a2334363029314653543b44505f78919d9c9da0 153 | 9794a5b0a9a0908a8d9ca8a3928576514a492a1920201c29292322222d416781888b9ea09290a0 154 | a1a19e9894989d9f9c9594968e8fa1adaca6a5b0afb8afafb9c1b9a89b8aa1b1b1ada99b886b3c 155 | 2536495869755b3d27222d4e7484875f4d534734353f3231312b2c3d42332e393a32323f454135 156 | 35383125293330322f2b262226333f3d34292a3a4c4f48303034497094a19e9fa7948595a2a3ab 157 | a292878e98927d6a482b2b2712222d0c0f21292c333b4b62819ba8a5a39c989fb0b2aa988c8f99 158 | a0999995979b969cb2a99a93aba5c2cbb49e9aa0a4a7aa939395999b927e6c5238333b363b5a78 159 | 754c313c525f6d7d69594b4741352b29372a333c33323427332b2930343131361f222d352a1e2c 160 | 4643433115132d4347383f34262b3234382730293564899cb0b2af9d87879a9e94a2a29688888b 161 | 7556352b20202a30291d1422283138344c82a7b3b9b1a6a3a5a6abc0c0a38f96a1a2a69a92949b 162 | 9e9fa296aba7aaa2b9bead9f9c9b948e8d98918b8f958d71564b33374f56576472835c4a63807f 163 | 6b5e5a5b4f38282729262b3545463c39372d2a2f312c25202021181e282f3132363a3e43454037 164 | 343a4128271a131617203334342626435f7996a8a39b9695918579969c927a6b665a493936353a 165 | 3f3c2d1f1823252c3e485b7e939fa7a4a4aaa9a2a8ada79897a3a8a2949394989d9d979090a09c 166 | b9afbba89f9da29f928a8ba297877e7d79665150455b818a84899293684e64807c5f485468623d 167 | 252d3837323b393b494c39272d3a423c312c2d2d2d2c27252f3d3e3631374751422c2d3f403323 168 | 222a262a3c3f392b262f3b54768d8587949990868287897c63524e473d3536393b382b1a0d1122 169 | 2629405b738787959b9aa3b1ad9d9597989aa0a9aba99ea09c9698a0a098919b98b2a19d8d8c97 170 | a8aca29da2a69c856d656c72726365839e988c98a98d60414d666754435c73735235343b3a4041 171 | 312f433e2721262b353d3e39393b332e2623272b2822363a43422d1922395347332f39372f313a 172 | 322e302f2c3b556d6b6f7a82878e9679705e504f514a3d2c2d2e2e271b13110d253131456e8e9b 173 | 8c9a9d97a0b0ae9c8d98a5a9a0989ca6abafa89a99a5a8a09da3a09594907a7c8ea7aea196988b 174 | 826e5d627a8c917d7b8689797484917c52394f747b62495f676b5e46312b2d3643433e351b142c 175 | 2f23263a443d373a302e343d392a252a4b5556442d252c36515949302c2f2d2c3125262d29222a 176 | 374f5a615e5d656f7565584842454741382e303438332d2f361e2a343b5684a09f8b999c9497a7 177 | aba29ea5ada997888b999eaaada39fa39e92a7acaa768e947c757f94967e6863565651566f8e97 178 | 8f94887c6f687888867e5238578a987b595650545d533c3239263a4a4c3d2625393e2d28333a32 179 | 2a2b332f3745433a4358586b7162585b5a515971673e2729323a3b2926271e1e292d2f414e4943 180 | 4447464b4238302a25242636383f454036384132272d466a929f8e858f948f8f9aa2a4a7a19c99 181 | 979495989ea5a49b96999b98a9b0ae728689907769706d543e383a4e616e809393869993836a67 182 | 85978a7e5c4a6389937a5f5445424d4d403c4530455852403d3f3831332e231e21232032333c4b 183 | 555d6976778489858b9997897e8c805f49403d414c3a342c1d243636292d3338393a41494d3c2d 184 | 27231e1c1e2f2f343933282a353726386281989e908d8f92918f90959a9f9c999ca4a8a298a3a1 185 | 9c938f94a1aba7b3b19ba29ea57b57514d3c3030406a8e948f91918c8e978e6a5a768a7d6d6568 186 | 7b887e65525a473937352e2e354568805d2c3040332b4445281b2d3a3640516980949e9586aaa6 187 | 9e9ba8babdb4b9b39f918b75584b51444134202b403c3f2b222c353a4e6664452b2c3738302a20 188 | 1c1e25231f2939352e5486959ca8aa9f9a989a958b898d9ba5adb0b1ad9d8c96979b9d9a979fa9 189 | a7b7b4c1abb08971605d513d3a4648628599968d92a08c8c7d6f6c686d7d6a4a4c6c75614c4033 190 | 404f4f3e2e313d415e726547363b46413b4251524b566b767c92b1c0b8a9a2bab5b2afb6cac9b0 191 | a3b5beb6afa78f73685b3c29323e444a302118223345596a594b342329393d363423202422252d 192 | 2d464c556f92a09c9daaa29a9a9f9c9084a6adb8c0b7a0887b99abaca7a5938a9ca3a6adfbca95 193 | 56575962727b716152596e87928e9097919696918b7c74786b4946606452413629354e656a5c4d 194 | 48405362583b272935363849626e6e737f939fb3c5cbc5bebcb6b5b8b7b7beb090a4bac6beb4af 195 | a2907f6950474e544937171c2731322f35403e34251c212d363720212b2e1e161f293e576d7e8c 196 | 8d8f9b9c9a999b9f9f9a95969ca5a79d8f898badb4aba3a498909faaa6a7fff2ca9b7865758684 197 | 838a7b72737c786d7181a29f9c9c978c8484644137474d4848484341495e747d7366565f685f41 198 | 2626343539475e748695a0a0b3c5cac8c9cfd4c3bcb6aeaebbbba7a8b9bfb1a6aab1b2957f7572 199 | 6b716c53372d282d36352c2424201e1f2126323d2822242d2d28292e486a87969b9697a4999da3 200 | a6a49e9895868c9598928e96a1acaba29fa6a19ba2aeadacf3fcffffcfa18e8176839c98928d7c 201 | 573c4d729484818a8e8d88815a3623272c3547526262585367838573696f776e4b2b2e434a5464 202 | 778ba1b4beacbdc7c0b9bec8cccbbfb4a9aabfcfc8b9c6cabeb1b0b6bb8d899b9b7e7c84736f59 203 | 43404b4d3b262525292d261d222e382b222c3b3d414e668094a2aeaba2a2989ea7aba8a1989392 204 | 93979ea19fa1a59b9b9da5acaaa6a89da7aef6f3feffffe8ae8a8f99968c90928157394c736853 205 | 5c79898c826f5737221c1820333e597479676d87846760697368442836555c728ea1aab0b6bbc5 206 | cdcbbdb3b5b7b5bebabab5b0bac0b6acb7c0bfb5aaa29e848babaf8e868c7a89867d72695a3e24 207 | 2d2c2f30220f090e31332e30353140627387949ca6a498939394979ca1a4a5a5ada19aa1abaca4 208 | 9d9c9ca4aba7a3a4a589949efffcf8f1fffedab29f9d9d84878b8773605f6b5239486f828c8a76 209 | 584439322728343843697b6c697d7d6959656d5d3c304d748796acbab8b3b8c2cbcac6bfbcbab5 210 | afb8b7bab5abadb0a78f8f929697989ca1a29ba1a39ba5aea3aca595857c6c451e222021231f14 211 | 0c082b2c2328352a2b4a638091939897959898928c8a909ca9b1b09d8f96a7b0ada8a8a2a7a694 212 | 8d9394929495fdfffffff5f7fde0ad99a7928a827e7b715f4f442e47717e878c7d554a453e3031 213 | 3b3d37464e494857697269726f563b406992b8b8c0cac5bdc5d7bcb9bbc2c7c2bbb7c5bebaae9d 214 | 9ea6a38d8581838892a4b6b9a99996a6bcc7c4c7b497858988643825201b1d28302a1f29241521 215 | 3d33284161809394989a9a9f9e9b948e8c95a4b0a89c9397a2abb1b5a59ca5a6918b918d9ea1a1 216 | fcfbfafdf5fafffbd3aea0998b766867644f38261e4c8084807c674f443c301f212e322b222028 217 | 2c334c6a787b6e4c3646749bb0acb7c8c6b6b4c1b8b4bac9cec4bab8cec7c1b19991938e878486 218 | 8a87838b99a9a89d9cadb7b3b0b8b8ab9a97978162403628253546402f1e2720293d32355f778e 219 | 98979e9f9590969ca09c9698a4b0afaca9a7a4a2a7b09993a4b0a29ea19796a6affffffffffffd 220 | f7ffffddb0a48180827c6b442f1d4454798d7b6d5341342b2b29232328382d1c19253044607568 221 | 49475e6179b3c3c0c0b3a0a2b1b5aec6d8d5c9c4c1bdb9b5a49894887f848e92918c89867d737d 222 | 8f9c9a979ea7abb9c2c2b9b9bbad967a5c36242d3c3e3737352d2d353847608fa0a69fa2aea691 223 | 9aadb1a09aa8afa9a99d908d949da0a09f9590949a9fa6aeb3aba0fffffffbfffffcffffefd48e 224 | 818a898a885b312a3d3d5e818175583335383b3e3b2f212b2921232d2d2a32536a5f577a99aabf 225 | d0bdb6b9bcc2c3b8b6c4c6bdbec9c9beb59f7d748b9a92899691878288918e847b8d99959299a2 226 | a6b2babdbabdc5c4bdb18357463a2922294235201c2c3f5c7d919d9e918fa1b2b7a8a09898a1a8 227 | a6a19a8e82828c9699979d9694989ea1a7aea9a095fffffffafffffffffffdf8b58d7c78889672 228 | 4c4a453045717c6b4b42423b3339403522181e1b1d2c2f272449696a678fb4bbbdc1b3b6c2c4c4 229 | c6c2c5cac6bec4cec2a99a97847d93a08f7c8788858590988e7c8596a29e9aa2adb2abafb5b9bc 230 | c0c5c9ae8d6b57422c262e222320263749698ea39c928f99a7aeada18a808e9b999aa2b2a69997 231 | 9ea6a8a6a8a4a1a1a09d9ea1a39c94fffffffdfefffffcf8fcfff69e696479846b5a69583d4667 232 | 6b51364d3c2720293431271b221912202f33364d555c77a2b8c3d4baadb3c3c3c1c4c3c1c5ccd3 233 | d5c8ab917899a495908e81767d888c898b8e8373899aa4a19fa9b6bcafadb1b9b8afacafb0ae97 234 | 6d4b3a2c1d06192932383d587fab9d9397a0a5a4a2a0959398938b95aab5ada29c9da3aaafb8b4 235 | aea8a199928f9a9999fffffffffcfdfffdf8f9ffffba866d696b59516352454c5f583d35432510 236 | 17272a2a2c2e372d1d20292f3639395185b5cbdef7d2b9b3c2ced2ccbfb7b8c6d7d0b298907493 237 | 97827e85817b82929482767b817f7e8e9894929eadb5b4a9a7aeaea39c9cb6c5bd966e553d2521 238 | 2626272c324a6c9c9ea09c918d9db1b2b5b3a7958e99a7a4a19b938f95a4b0b5b2aca8a49f9891 239 | 919397fffffffffcfbfffffefcfcffeaca85585f62614630303c493d2b40562b0c111d1d222d2c 240 | 3b3b333028222624385e8aafc9d7dbd2c9c9cac7cbcfc9ccc4c5c8b79a8e93868b7b6f8292836d 241 | 7a919885757a807f8290968f8b95a4aca4978e9195949396a3b1bbb2946e51433d302128404e5b 242 | 6e959da5a5998f9097a8afab9c93969a99a7a6a1978e909ca8a5a29e9fa7aeaaa29e9b9affffff 243 | fcfdfdfdfffffffbfffff6a05b60707a4e241d2730231b466b441f161a1b1c20212c313536271b 244 | 1f2b4a7796a6b5b9afbbcad7cab2b5c7cddcd4c7b7a6968982868879748995836e81959c8f888e 245 | 8b7f929d9f9289909ca38a837c797b7e81849cb0c1bea37e5b443c30243252646f7e989ea5aaab 246 | a28f7f969c9c9490939594a19f9b95908f9296a39d9698a6b3b0a5ada8a3fffffffbfffffbfbff 247 | fef8fafffbb97263697876372122271712495d49342b2c291b0c222322282d20161e3a5484a8af 248 | b3b7b4b5c2cbbdadb7c4bdcccec1aba3a08a6c748380757a83888fa3a9a08f92a2a29398a19f8e 249 | 81858f957c7e7c7671706f6e8eb6cec0aea07d533a33282d41536c8a94a2aba7a1a1a19f9ca3a9 250 | a3958c9099959494989da0a09eb0a59896a3afa99aa9a8a9fffffffffffffffffffffffcfff8fe 251 | b075717f7857331f161c38584a34292f28120a13282d2b2a2a1f1921364f87bac7c2bebbb5b2b9 252 | c6c9c2c0c6c2bdb1a5a09c8f807c7d848a857d8392a2a59b8988969a92a99c97938a8d96968189 253 | 8d867b716b6898b0ccdad2b3825a3e372f2d3a5678908fa1a8a0a0acb0a99fa5b5ac9295a0959b 254 | a5a9a6a9afaa9f9c9c9c9d9fa1a1a19bb1bafffffffffffffffffffffffdfefaffe39f91907d76 255 | 592f171f333f3c2a232a2410081129261b181f1d1c262d5d95bedadec5a6adbec6c1c7d4d1c1a8 256 | abaaa7a5a09181818a9ca49278768595978c776e7a8b9492898d95969b9c939b93877a6f6b7076 257 | 90b1c3bebdb88d58403d34292b446e8e97a2a6a1a0a6a9a59e9da7a9a3aeb29fa0a7a9a5a7ada8 258 | 9e9f9f9e9a95908d8c95a8b2fffffffffffffffffffffffffeffffffb69d99948c672c060d2b41 259 | 442d222d362f2a2d3030271e1e1a1f304c7b99abc9d5c9c2b9cbcec2c7d7d3bdafaba298949390 260 | 8c7c879fac9777778e88857f79777b848c827a818e969e9c8d8b837d7a7166656b8aa3b2b5c2cb 261 | aa794a3f2e22294873929fa1a3a4a3a1a1a29c999d9fa1aeb3a6a3a9aba6a7abaaa49ea2a4a098 262 | 94949699a4acfffffffffffffffffffffffefffffeffbe979d9a845e310a02244d3c1d08112428 263 | 221f1c2d332c211620395586a7bdcebfb6d0d5d2cbc7c7c8c4beb6ac9b8b85889095827f8a988d 264 | 78819c98857b8493979491898184898d979a8f888a939b948481889599a8c1d7d6bb9f674a291f 265 | 335777889a979aa3a49c999c999c9d958f949c9c98a2a7a29d9fa3a49198a0a09d9fa8b1a3a1a4 266 | fffffffffffffffffffffffbfff7fffdd796947973654a281723392b1a0b0a0c08020004151f22 267 | 221e283f5c90b0c0cdbeb7d2dfd6cbc3c0c0c1c09e98908a898c939897847e88887f869ab49783 268 | 8999a0a2a5908f938f878e969192959c9e96919caeaaa9b0c2d2cfbba88b683f2e3d5a737e938d 269 | 92a0a59c9799999e9b9694918c8b8a979f9a8f8c91978d959c9b989aa5b0aa9c98ffffffffffff 270 | fffffffffffffff2fffff298756074714d2d272721262e342e1f110f131719161b2a303645679b 271 | b5b7c8d4ccc7cfd6cfbcb7c2c3b99d928783848991999b89828b928e8e94aa9e989a9c99989c83 272 | 8c989282848d887d8489857e808e9ba8b9c0bac1d0c9b3a488634b4c6380949b9698a4aba7a1a0 273 | 9c9b949aaca890848f99a19f958d8d90a2a8aba69d989ca2ad9d97ffffffffffffffffffffffff 274 | fbfdf8fffbaa6f6b7e764b27222623263139372f2926252b2c262833373f4f5d94c4d3daddc8ab 275 | c4cccdc3b8b3ada6aa9a898484878c928e8c8e949794908e9699a0a8a89e8f857986948d7b7e86 276 | 827581888482878a8792afc3c2c4d1d2c6bb9e765b5b7392a7a9a29ea1a8aaa7a39e9b8e94aeac 277 | 958d9ca0a7acaba49b96a6aeb4b2a9a19fa0a89e9bfffffffffffffffffffffffef4fff3fffecb 278 | 8d7d827c5e351d21303932292933392f211a2a3231302e3e5a7697c4d6c9c1c2bfc7bfc6d1c09a 279 | 8a94a19792979992898489939a98908985839c98979faaaa9783808a9389797f8a86808a898084 280 | 929488819abdd3d1c6c4cbd3a874585f79909caca499969ba2a19b9d9e8d889999919ba19fa4b1 281 | bbb7a99d8e99a7adaba6a2a19c9899fffffffffffffffffffffff9fffcfefff1d19c8d7c746c46 282 | 15071823161e333831261a2b282c2c1e162d4f6b87a9b9b0a4a7b3b4b8bbb6a89a9393878c9298 283 | a2a395837d838d928b817d80918f91a0a89482879e928884817e81898d847b7d8a9697928391a3 284 | b1babebebcccab856d666d8092989c9f9c96959ba1ada3a7b6b3a19ca6a0979198a7afa89d9c93 285 | 9098a0a09e9f9a969afffffffffffffffffffffffbfffafffff9d9957e7b7e7f673f2520231215 286 | 252a2b2d293322120e11172433526b90afb8b0a8a7b7afa8a7a8a39890978d7e79849499948989 287 | 8e9597959598a39f9aa0a390848e82878f948e85858c8788898b8e8f88808699aebabec3c9ccc1 288 | b2987a6262788f9a9d9e9a95969da5a49fabc0c0ada3aa998c868e9aa09f9d92929aa8b0ada9a8 289 | 919597fffffffffffffffffffffffefcfafffdffe79178879189725840302817171f20242d2e2f 290 | 2b241c14131f2b4e6789a0a6a8b4c2c3bdb6b0aa9f8f828b8174707a878c8a868a949da09ea1a6 291 | b7b5b2b4b2a099a6828e9c9e928481868b9297989999938b94aabfc3bfc0c6cbb5b196643c3e66 292 | 8d9b9d9e9a95959ca28e8b97acad9a8f93988c8a969d98969b9b9695999d9d9ea099a09fffffff 293 | fffffffffffffffffffbfdfff6fff499889d9b76554b473e302322241e1e25252b2a2c2b20192b 294 | 456470869ba9b3c2cfc5c7c0ab958c91978d8b8883807e7a77798496a19f98969ba1a8adb2b0a1 295 | 9cab9b9c9c968d8585898f8d86828893938b95acc0c4c1c2c4c4c8c6a86c3a3b658d9b9fa19f99 296 | 969799958e93a0a091898d9c9399aaaa989096a198908f93959390a4a7a6ffffffffffffffffff 297 | fffffdfdfffff0fffbab9da48c57393f4740332825241b1c23232c1915242926395766606e9ac8 298 | d8c6b0bbb9a7897682a0b8a6a6a094847c7f8781828a99a29d938c909ba1a4a49a9cafa79e938d 299 | 8f9496959f937e7480919185859cb2bec8d1d1c9cacab585564b637e9ea2a6a6a19b98969a9294 300 | 9fa0958f929d969eaeab978f979a9798a2adad9f9099959bfffffffffffffffffffffffbfffffd 301 | f2fefcbea398744a3b46473a3024201c161d28281e1c2a3c392a334d4c475889bdd1c4afbfb49c 302 | 827c88969b989c9f9a8e88919e99887f8fa6ab9c8b969d9b9694919ab0a8a29a959a9f9b949d95 303 | 857b8698998d899cafbccbd9d5c7b8b4a3805b4e6583a0a2a4a4a2a1a1a2938f93a0a49c9696a1 304 | 9a9da6a59b9aa3a39f9ca0abb0a5978c858bfffffffffffffffffffffff9fffdfdfbfff8ca998d 305 | 73564644413b302623211c20261f0f2741473a2f344040414f6f94afc0c8c3b79f8c8b928e8182 306 | 889197948f939d9a8e8993a1a2998f93989187837f879ba3abada7a09c9792838a86787887908e 307 | 9faeb9bdc7d3cdbcc0b7a7875c4965909e9a969498a2aeb6aca4a3aaada8a3a3a19e9ea2a2a0a1 308 | a5aca79c93959c9d98929090fffffffffffffffffffffff7fffafdfffff5ce8d8c816849363741 309 | 322c2e2f27241e0e111f221b253d47404a42466289a9bcc4b9ac937f8295a09d96908d8e8b868a 310 | 91868f9c9f968b8a9099a09b928d85869598acb9b1a1999a9c8698998170798b94abb9bfbdc2cd 311 | c8b9c7c3b9995e33446e989086838b9fb6c5c3b4a8a4a3a09fa19b9d9fa0a19f9b98a2a7a59c98 312 | 9999969fa5a2fffffffffffffffffffffffdfff8fff7fdffa87c84887753332b333c291f293737 313 | 2e262f404023173649385f5e52659dbfc1c4aca79d918f959b9b98928e8e8c89898c9a8d8b9697 314 | 8d8b9495a1a298959a9485869ab2baab968f9392989f9c8b7e899cb3c5c8c3ccd3ccc7cbc7ad8a 315 | 5d2d336794978d8488909dafac9f8b8291a9b0a9a09f9fa3a8a5998c8c919ca7a8a09896999ca1 316 | fffffffffffffffffffffffffff8fff6fcffaa8b837e7a684830283e2f1f1c2531373844353031 317 | 303b4c516366616888a8b4b7baae99857c7d7e7c8c94968f8c8e8c86a49289939d9b938f9ca19d 318 | 9498a29b8a8d95a1a79f928b8b8c8c90938e8c9bafd2d4c8bec2c1bcbfbab9ab8c5c333c6490a9 319 | a3888698a0a0a09b938e929a9c999b9b9ca0a6a7a19a9191959da1a0a0a3a9ababffffffffffff 320 | fffffffffffffff8fff7fffeb09f8d878f87633f2e483d2a2027322d1f1f222620203749434c59 321 | 65667095b2b4c2b49c867c7e81807f8e91848088877c8d959d9e989495989e9c928b939e968497 322 | 9ba1a29a9192988f89868b8e94a6b9d6d0bfb5b9b7b1b5b1ada787533a4e6a8aa9ac95939fa29f 323 | a0a0a29f978f9096949496999c9d9f9f9a9b9fa3a39f9fa3adafadfffffffffffffffffffffffd 324 | fffbfffcfff6afa091919e956d483a4e432d1e26311e000e2232271e31413939506d6f6d94b8b5 325 | beb8a9958b8e9497898d8a8281878680708ba09b8c878d939c9b96939ba6a19398a2adada1989f 326 | ad9a8f88898a8e9eb0bfc4bbb6c2c8c0babeb1a3783c2f4c5e7e90999da19c9aa2a5a4a5a4988c 327 | 909d9a9a9c9c9895999f9ba4b1b4a9978e8e95989dfffffffffffffffffffffffcfffefefdfde2 328 | a292817f8c8968453544422f1716221d092117202e2824303a455e7e807b98b3a9b3b6b1a08f8a 329 | 8d919a8f8c9397908a897b888e8783888a86a2a8ababb0b8b8b2989faab1afa9a8ac988f8a8987 330 | 8895a6bbccc9c1d1e1d8cacbb79e6a2d213b48748590979f9a92959d9a9b9d978e909ba0a0a2a2 331 | 9a92959e93a3b6b9a78f8485858893fffffffffffffffffffffffefffffcfbf7cf958d7669737c 332 | 6c4d353b5053381f1a1d1c1a0e0b111d333e34425b74787a8fa09ba3acafa2918683838e838698 333 | 9d8e8384939b9a8c82879299aab3b8b4afafafaea39d9faebbb9ab9f8f88868b8e929faec9d7d1 334 | c6d2dfdad0c4b09265382d41527b9ca49698a09687949395999a979597959395958e858a9595a0 335 | aeb1a49592979d9ca3fffffffffffffffffffffffefffffafdfacd9b92837472797767554c6671 336 | 5a362321231b2928161f485232243d4c52627686929ca5aba69c9288817c7b818c8d86828698a4 337 | aa9e8e8b99a9a5abaea8a1a0a2a4a9a1a0abb5b1a39893898793a1abb7c3caccc6c7d0cdc9cfbf 338 | aa815a423b4d6b87abb39e969b968f97989592959b9e9d948e8c8d88828a999d9d9fa3a29e9ea1 339 | afaaacfffffffffffffffffffffffdfefffaffffd6a995958c7e787b7c79676f6b53392c2c2f2f 340 | 384239292c322910292f354c5e718ca3a8abaaa59c8c7e7c848984828893999494989ea09c9897 341 | 979ca0a0a1a8b0b5a2a4a8a9a2989598a0928d9db2c0cbd3beb8b9ccd6c5bfd3c8ad75493b3445 342 | 6e88a0aba396898c9d9e9d93868796a2a4a89e999995919baca09691969d9c9895a09ea2ffffff 343 | fffffffffffffffffafffff5ffffd59a83989b89818c8e82727776603716121e3b372e2d2f241d 344 | 273236363a4348597682b4b69da29f8a87888287928e8185958d999b92939c998aa1a5afb8b9b5 345 | b4b8a89fa5b4b09b949e9f9a99a4b3bdbfbeb9b9c3c6bbb9bcb9b3845f3f3438394d7787a0afac 346 | 9f999b9f98949698999fa5aaaf9f8e949e9b9791a49c95a4988289959ca0ffffffffffffffffff 347 | fffffafdfafafff7c48c8d938d82869599908889846f4925161627312d252828282f3635333d4f 348 | 565f727da3a4959f9b86828681848e918b898d8a92959398a3a5a0a9ada89d99a1a7a7a6a2aab6 349 | b29e94989d9ea5b3c0c6c5c2bbbabebbb2b6bcb59868473336403d4b75889faaa7a19fa19a9796 350 | 9da7aaa59d8b97928c99a29a91949f9996a19b8e92929da3fffffffffffffffffffffffffcfcff 351 | ffe7b68e99948a83858f979a8c877f735e45322a22353427282f31342c262337566265708d9b8d 352 | 808c8e878e8684858c95958b82878a8f95989a9b9ba0a3957f7e94a4a5a4a5a7a8a1968e8d909b 353 | acbdc8cccac6c0c2c5bdb6bebdac9562403037403a44728a9fa4a3a7acaca3a29b92929a9b9486 354 | 979896a5aea79f9fa09e9c99938d8c94a0a3fffffffffffffffffffffffffbfefff0c7a3958e89 355 | 85837f7e8998867c716d6a5e4c3e222e2e2a2f302f34191412284b5c6370969688808684818c86 356 | 8a8c8f969a8e7d8687919ea19a979a98978c808395a5aa9e9e9b939093969793a4b9c5cacac6c2 357 | c6cdd3cbc5ccc3a69a65412b2a2f2e4165809595949fa7a79faaa793888f979696a7a69ca3acad 358 | ada4a3abab9b908f8c9ba5a2fffffffffffffffffffffff8fbfffad4a28d918378768085818188 359 | 8d82787574664a321f1b1a263128222d191613213947566c86898e93917e6f70828c9190939993 360 | 86878791a2a8a6aab5a59b979b9d9ba0a996999690929da6a8a8b9c8ccc9c8c5c1c7cdd3cdc9d2 361 | c9ac8857351b1116214258748a88858d94948b9da8a4a2a7a49a96a9a696959b9fa49da2b2b7a5 362 | 979899a1a9a6fffffffffffffffffffffffeffffeabd958a929a8378899a9683778f8c8988836e 363 | 492931231a27301f14212a2b25252c3247677f8088908a7a6e6a7c868b8b8d93959088868a9399 364 | 9eabbaaca09fabada2a1ab9ea1a29f9da0a3a3aebecac9c8cccfcec7c5c5bfbcc8c8b5794a2d17 365 | 0c0d173a5b779195909092938f919296a2aba59694a7a698989b99999ca3acb0a5938e95a6abac 366 | fffffffffffffffffffffffffbdfb5948a8f95a6928895a5a39081898d91908b795a3f42382a2b 367 | 2f231c2730342f2825274167867d7e838383827c7f80818183888d8f898a8b8c8d939fa9a89d98 368 | 9c9f9ea1a8adacadaca9a6a6a8bac8cec9c8cfd4d3cac2bfbab3b9bcb174442c2323201a2e526f 369 | 91a19f98999d9d968f8d91969998a0aba59aa2a9a199a7a89d9ba0908391aba7a7ffffffffffff 370 | fffffffffff8dfaa7362768b8f8f8c8e979fa19f9e888e918d887e6a583a3b30272c2e313c282f 371 | 2c252225426c837a7e8a91979484867f79797c7f8386889098999a9ea3a7a79f9084858f989ab4 372 | afaeb3b5b6bec9d8e2e1d4cccecec9cec5c4c1b6b1afa66837262e3d39252a36547e999c93949c 373 | 989fa8a6999097a5a9ab9b91a1ada397aea9908ea49b8d9fafa39dfefbf9f8f8fefffdffffefb0 374 | 987a624f4f6a8b8e6a72837889a39a7c7c8b8e818076573b2f25262a2d3136291d191d19142641 375 | 81888e8d86818388877d6e646a7c8d96949aa49b888a9ba0a9a99e98927d85aeb0a39ca8bdcace 376 | cdd7dfe3e5e1cfcbdad8cdbdb5b9beb6a96132212f383f3a223a54778d8c868f9ea19ea4afaea1 377 | 9a9c9d9a9ca5aaa7a09cb9afa29ca0a7a6a0aeaba0fdfffffff9fcfffff0cea793807065544d64 378 | 879f7c7881788195948a8d979b948d816f523c29282c2c31392f28252116122c4f6d848e837c84 379 | 87817a7c766e73849192899099917e809095959da4a69c898da6b1acafbfd0d2c5b8c9c8c3c6d2 380 | cfc7cacbc9c3bdc0bda68a623b2a30333a3e3340556e7f8f9da3a19ea1a9ab9f9297a78e898b98 381 | a3a39d99b9b1a9a6a6a39c97aaaaa4fdfefcfffbfff9d9b79b84856a58554d4d709fa092909891 382 | 827d818d9090959a8f817f6241292b312f323b39393a34231d35565c6f7e7e7c7e807e7d89897f 383 | 829194897f889695888a9594999da7a69798adbdb5b6bccad7d8c9bac6c0b1b2c9d4ccc5c4c9c8 384 | c2c4bd99715c44393a35353b393e566a768ba6aea5969aa1a39a939cac98908d969f9f9995a4a0 385 | a1a9a89f98979ea2a4fefdfbfffcf0d1a0858b948764505655526f9998a0a1a49e806d7a89877b 386 | 81948b7c85754e302e30282730393c403f352e3847524e6080877674838b9694878c9c98837f86 387 | 98a1a0a6a9a0a3a3b0ae9dabcad1c2c5c4c3c8d0d0cacbcdbfb6c5d2d0ccc3c9c4babab48e624c 388 | 4342443e36302c2e4a65727f919ea0918e919aa0a0a1a4a79f9b9ea2a2a2a397949aa6a69c999f 389 | 9aa0a5fffffff3d8b89574758fa17d615b707259505d8da1a096917b72898d857379928f848e97 390 | 6c4331271b1a23312d2c313739383742384a75897e7a878a908a8292adab9592919ba6adb9bcb0 391 | 9da7c1c7b7bcc6bdc4cdccc1bec7cdcacbd9d3c2bec1c6cfc4c6bfb2aca0794f3a3a3a3f42382a 392 | 232336546e7d848d9597929093989a9a9c9d99989ca0a5aeb79e9b9ea4a29c9ca3a4a6a8fff0d3 393 | 9789775b49608ca6725a5871775a3f3870929c95948a838f8f877c7f8e928f92a4815537251e24 394 | 2f31261a1c2c3d413c2f34425a73838480818481849fc0c7bab1aaabafb3c1c9c0a7b2c6cdc4bd 395 | b7acb0c2cac5c6d0cfc4c5d8daccc1bac0cfc9c8c0b3a68d623d2f302a2d3c392b282a31486c86 396 | 8f9398a2a3a1988d8a929b928f8f94989ca4ad97989a9b9c9ea2a4a49d99bf9f706462573d345a 397 | 8ea57b61546065533f38507890929a9f948789888c8b868c918c94836748332e353c352a1a1320 398 | 3541412d333942546974757e82858da5c0cbc8bebdc4c4bec4cbc5bfc3c2c3c6beb5b7b2bfc3bf 399 | c9d9d3bebfc9cccecfc6c3cdccc4b9ad987750352a2e2324373629292a364a627c919c9fa7acae 400 | a79d97999c9a9491979d9b97958a9397969aa2a29b91817bb5b7a69078563942759b9b8b726060 401 | 5d4c39314365797989a19d8583899a95818590868485785c43383634322d20121527363b382e2d 402 | 383f44576d7e848a929eadb6b9b3bfd3d5c6c2c5bec8ccc3c6d3c8bac4d1d0c2b3bfd5ceb6b8b7 403 | b7c8dad3c6c8c7b8a89a8361423227302625373422231a374d53607e97a0a6a9afb6bbb7a99ca4 404 | 9a97a1aba89a8e909da29b9da49c8a816b65acb7b7aa925d466b8f97999d7f6368653a25414244 405 | 434b6f9aa79c85827d7f8d9a96888a86796552433932292726292f322f2a382d2b394748423f4f 406 | 6b869199a7adaca8babfbdc5cdd4dee4d4c5c4ccd1cec9d6dbcfc2c8cbc3bdb6abaebfc7c4cad7 407 | c4a17f6e5e493935382a1a21322b191723283748515d7b9a98a9a89da3a7a09aa09d9ea5afb1aa 408 | a2a4aba9a6a697827c73726f72989fad8f6963849ea09c9a89726453372e3c4d402a25487e9da1 409 | 817f8da3a491858785898d88755940312d27252d33322f2d253d473e4153534236455c7692a9b2 410 | b0b0b4b0b4c9d2cac4ded5cecfd6dad9d6cdd2cccbd6d6cac5c5c1c1bfb3a3a1a9a7896b5e5340 411 | 312b463c29252f2e262928262c39424f688194a4a59d9f9f9b9d9fa1a4a4a4a5a7a99fa0a1a498 412 | 765c5a6a7e824a767b846b687d929da29f83817a63463e413e4b412e263c648087808090a5a48d 413 | 7f81818185877a614e483f2e24292c2a303c30343a3d3d3e40433b3a4258748fa8b9afb2adb2c5 414 | c8b7acc8c9cbced4dadee0d0c8b8b7c5c9c7ced6d5d1c7b7a28e8177614c4544403e3f4e4c3b2b 415 | 2e31333b342c282c323a4b5d8b9da6a8a99f969a9ea5aaa59c989ea58f8481826d4a3e49708d88 416 | 48585956455c828a8c979a807f837152515a4f585e5c504b5460677f8486858b928e85807b7d82 417 | 7c6c656859412f2a231d2c454631252c333132383c3a424f5a6a8cafa2b1b8babdb5aaabafb5ba 418 | bbbec9d5dcdfceb9b9c7c8c9d5d6d0c7c2c1b38e6a5a4d3c322f323b433f4a42302f32353b3d36 419 | 302d2a2a333f61758a9eaa9d8c8c9da3a8a59c928d8b7b695d513d3444587e94894d46575a424f 420 | 717d8693939d908e82686978758590927c5b4a4e5a69767e7e808991928688929c97867a776758 421 | 4f4a361f21323b3e311e253c3f2f2d2d394a5056729293a7b4babbb1acb5adb2b2acacb7c6cecf 422 | c8bfc7d5cec4c9d3c8b6a8a59b7954514d412f211d212526393b3334332d2d3738373229242932 423 | 324256748c897976898a8d908e806c5d564d4a3f344766708792905352746c514758738d97909f 424 | 8c7f776f7a94a5a4b0b5a27853454945587a9188747a9191969c9d978d837e6c6d7578623d241f 425 | 252f3028242b32343c2f2a333e495f76818d97a6b6b5b1b7bbbfbaaeabb4bcbdc3c3bdc1cdcac3 426 | c8d4cab1927a695746363e40372f2d29241a292f333b362823272e34322a25292f363d404f666a 427 | 5f5a5c5a5a60625844332228404d52718b81908c8b6467746b6d60586b81847e7774665d687f9e 428 | bbb0b3b8b2966b49393b517997917873808d918d817e868c89797d878f856847332f27292f2718 429 | 1d2e41362b2729324455686f77899ea3a2abc0c3c0b7b5bab7adc6c9beb4b9bbb9bdb7ab95785e 430 | 4b3f39242d33353e48443725272631423c2c271f252b2c2b2a2b2c40463e3a484f474038373535 431 | 363532302324486a758c9a87898283756e51698f8d6e6768626258695e50627c96b3beb0a8a99e 432 | 7c553d4e647c8c949384727b8584787b8e98948a86858b9087705b47473924212b281a1c293533 433 | 271f2631515c677583858c9eb7bdbebabdbfb3a2a7b4ae9f9c9689848375655b5243322732312c 434 | 2b3a4a4431362b223046423230222426282b2d2b282a363128333e383130312e28242b3b4a5645 435 | 60848790968372788786766778a1a28f84624d657882785d597ca7bfb0afbac2ac7c574a5d686f 436 | 7f989c87787e7e837b71899c908a8e94989a999591876e5a472c20262c26212a3532313029333d 437 | 4f626a6e78839991868590978a77888078767975604a3f37353b3c332a262a3231333d392e2b2c 438 | 32363d3f33303f2c2630352a2f372b2d28282f35332b252e2e2e35362f446f8383888274757c77 439 | 72737b9e979494999a948778757e96826b66788f9b9b9aa4aaa38f715038315564647b948f7e85 440 | 898b7f737c8988888b908f87828fa0978476613d27272b3d3234362c2b353b3a383f4d514e515a 441 | 6d665b53575e5c554f4c4644484a42362c27283138352f2c333a353038382e2a323635373b2f23 442 | 253832302b27323e3e322e2a2c363f413f3641494d4a44587f84808b9282726c67797a7ea8adb5 443 | ab9498a1938c928e947c6664686a6d73887a80928252353726434e526f8e9187828e9089827979 444 | 848f8a8580767589a192888678543b393c3e31303124223545382c2b37392e2e384a4740383638 445 | 38364747433a37393a39342f30383e3c37342d383022272f2e2d2c3330323e3d2d254141342b33 446 | 3e444b494843414d60696757646b7075747a8c787080948d7c777789827ba8a8a5a89ba0aba08b 447 | 868a816f5c514e53606e82707892885c444c4d4640557a8987897a8a8d91958377879b93877d7e 448 | 8893998c858982664f4b4c2d22272e25243644372b2b363221202e3e3f40434540342a4449473c 449 | 3231353935312f333737332e314137201d29333b3b454344555e544b5a61534c60665a59656b6c 450 | 6c78898d8681837e84999e90866e646c7b7e818a8b8b7763a2988291a3a4a39d77678784694a48 451 | 65868f868693958b888c816c746558668289848a868c888d97867988949b96898c9fa69e968b89 452 | 83695149442b22262c2628343a3430353c311e1f2f37343745514d3a292b3439342e2f3336332f 453 | 2c2e353a3a3643554e342b34465868726e68747e7b7a828a7d7a92957e716e79858d979e988d92 454 | 92888a9ea18c7c726a6663677b877f715743878676779a998a8360598a866c4f50769da5989699 455 | 93898a949389848d857c848f9194a0998d898a7f787f768c958a8696a5a79688847e644e453f36 456 | 31302a2027312f282d373b31242937332a293543443a30252a2d2d303537363a37312f37414441 457 | 4a5c5c4e4a50627a858c857e858b8f97989a908b9aa2917e6f77859299978e879399938c908c82 458 | 817a767067697e826e5a47417a7571627c827461515d817b68555260768b999d8a86959686828c 459 | 8b958f868a8e9097ada39e96877e7a7369707879777f92a492888a866e5a56554b52554536414b 460 | 4340474c483e3a3e4438312e2f302f3238302b2526313d3f3a44403a3842525b5a6b75787a7c77 461 | 7c8e908f868289898d9a98999891909c9985857f828b8d87858992958d85837d7c89807776777a 462 | 847f695b555c8d6b63555e71694b4a6471785c47464d59779895969aa0a095867a918176849083 463 | 7d8da7a4aeaa9085806d76625c6a7375859d9b979e9b816d6d7162778574636f786c767a746355 464 | 514f4b3f3f3d35261d273843372b2d41565b565b5956596a849396a7a7a6acac998c949f968886 465 | 8a83828f9a9da8a2949fa590a3918789877e8493928979757b7878848574727c7f7d7362646774 466 | b36b5143646045424c5b706e50363a516a7b859f8e8a99a297888372828489988f7d80969b9d97 467 | 8a7c6f6766635d5759677d8d8984807c756e7076858997a39b8982899b917f71727467544d4640 468 | 403e3833323b423f5982add8e0ecf1f7fefffffcf8f4fffcfdfef5ddab8b8c857d828c8471818a 469 | 959a99959190978b868e908884868c7b6d6a6c6f7986877f756c625b5b60777a71d385514b6c71 470 | 533d44617d7a5b3f425f7b86868b838490968e848089928d88949b8f8088909591867c76747a69 471 | 5e657273675c726c6d6d5942465c777f8c97968f8e9295898389918d80757665544e4c48423e32 472 | 304fb0fdfffff5fffffdf8f8fbfffffff7f6fffffff9bc86857e777b86888277838c877a77828f 473 | 958b878a887e7a7d837a7576747279848f81706359555c6577766bd6925d6775775a3d496f8485 474 | 7564616f7e817b807e7c7e828688888687847d859d9c827b828a8c8785888d9185859293806b62 475 | 6c747664432b2f3f5a65727b848f95959082808d93897e7c806b56505355535159435bc3fffaf5 476 | f9eef4fcfffffef7f2f7ebf6ffecfeffbd807e7c7d81878d90747b7d74686776858a858487837b 477 | 7a80888484857d7477818169524f5d6b74797b776dbe947f7f6b5d493b567a807a858981797a7c 478 | 7d90897e767c8c979b807d858580939e8a838386888785888d9d9397a49f897d81758d885d3d3b 479 | 3a2e46525a5c687d87857b78797c7b7674757a6b5c585a5b5c5d5d5876cffffafcffffffffffff 480 | fffffffefffffdf4fff0997471747d8483838574716c6765696f7478797e838280858e8f8b8c8c 481 | 8479787f6a4c374a728e9087858480ad8c8e75533e36395d80846e7d88857e7f88909d93857d86 482 | 97a09f918e9ea4918d999999908a88857e7a7b9a87819197897f807d897d5b4d544f3c4f565246 483 | 4859605a596d7976757d817d837f7a74685d5a5d677385bceafafff7fcfefffefaf8f7f8faffef 484 | f4fff7be7b675f5e6871716b6865615a534f55616b787c838888888f988a87898c84746d6f604f 485 | 4a63869994898a8e9192706757453b3e4a678897807a76787c828b95918a84868f93918c9193a3 486 | ab998a929f9e948f918f878385958e8f948f83838c8b786d72746c686b6767583e31343631496a 487 | 8281838d8a7b7d838984715f5c62798d87848ca2c2c1d1def1fefffffffffcfff2faf4aa726a68 488 | 5f56586268645e555a5744323755718b8f9393908f9398888686816e564b4d5c6272848e8e8d8e 489 | 818890675f4b444445536a7886989482767979757c8a8580838f928a8382899091908f87869090 490 | 8d9299968e919a979da39d8d8692a4967b778c8f7b7685817b684c37313334576d80888c8e806d 491 | 6b778586786c707b7590928b7b7995a096999ea4acbbcedbf4fcf0eabe715761706f6a656b7574 492 | 6b616968533c3e5e7e8c8f908d8a898a8b85817966483338496470828e8c85868c7f8185476b5b 493 | 3d43465d81847a84918481857a69708689858b989789858d939c8b7c87887c7c8589939990848a 494 | 999e968d8789929ba0928787918c79737b938d7c644f494e55696d77858f8a796a6c78878c857f 495 | 8896a5a091989486969f919598989594989d999794998c848a74727d807b7d8683777c807d6e5e 496 | 5f738776797a7877787978777264492b23426777787e8687817d7c8c847e76747b73605b647083 497 | 908e929792898175748296969a9d978e8e959489848c95948c86888b8d8a827f8b9a998c807e80 498 | 848e9a8f86868b8478839a918e84857f5c506d8b968e7773858d847e919e9890919699a0a8ada8 499 | 9e95959896908c8b89888b918c858997998b82858a999e908281817d7c8089887364799b8d8576 500 | 6a686b6a65654e3f37313d56657e83827c7a7d7d79837f748b81848d878482849193827d919a93 501 | 826d6b7daa9f96949491909398928b8c9396928d87858d968e7c7f908f898684817f848d898890 502 | 968a797f9391958d8a8b7357557e9aa38f7e838a87879196918e91939297969da59e8a80848e8b 503 | 8987828087918c888e9b9d8f8079929ea398877c78777e726e777f7e7f849d8e786b69685c4d4b 504 | 40424749597483878d8f88817b736b625c5187808a9fa09f938c96947f778c9a988c7873829a93 505 | 8d878280858c95958e868a9699948e7f849c9e877a82888b90938e88878b868a939587767a8a8e 506 | 978f889086634650718b8a858b918e8f8f8c8b8f9596948b8590a6a48d828987878785807f8792 507 | 8d8d8f949690847a8b91999b928581847e8285837e7b7d7fa0968471655c51455a57616a687181 508 | 888a8d8b807369615b463f357a869f9a94938c858d938c888f9194988e848875828c8575707e8f 509 | 8d918a7d80919a9698837f94a194827b858a92999b9894918c8b8c8a7f7579848d918c868b8970 510 | 563044596a8094978f8e88858990979b9d8b8b95a2a0938f97878584858482868c91928e88878c 511 | 8f8e847f85939489848a7e939e8e78727c868a908a72584d50567370787f7b7e837f8780725f4e 512 | 45444438312a848ea59483858f8b87909991938f90958a7e807a89948e807e8e9f90948d7d7e8e 513 | 979597918b8b8d8d8781888688909a9e978f938f8b8a878482828785898d877e746b484c525d71 514 | 878f8d868080868a8b929b949ea2988d8b9297938b85888b888381939693888289959c9283808c 515 | 8e81787a838a887d7b8387837c84816c56525e6a706a6f767880847c74675440322b2b2e2c2724 516 | 8f909a97838ba29e8d8e988790908c87766d759d9c978f8e969fa49b9b9387868f94928e9b9d8c 517 | 7b7a848b938c8587939c978d92929193989890857a748493867571706a6d6b64616c8191837d7f 518 | 87857c7f8a91a1a492848a959aa3958b8c918f88829093959089888f98a0928c9291847a7a8c88 519 | 7d767c888b8587847b6f6a71797d7c726d68636a6e644c413631302f2e3024212291969a958893 520 | a8a4958f8f82868280817a7884a5a0968d8e9699969b96908d8d8f908f8d969c95877f858e9c94 521 | 89858e9998908c8f9191989d988e7b7182958d85837c7b7f7d6d5b5d77938b8386908c7c777f85 522 | 9199948b898f959b8d8282898c8d8d8784878d8b85868d9595989a948a85889290897f797c858c 523 | 87847c777a858d8f8f83745d464347403529222932353433232225989a968d868f9d9b96918888 524 | 7d6d70869196a0939a9a9089898a89928a878b8f8e8d8e948a8d9ca0958c8c9a948a8287939793 525 | 878b8a858a969a968b7c88999aa1a49387878272605d728b968b8e9b99857b8081858f978f807a 526 | 7f81766c6e767f8a928174738087818188838e9a998e838388948c837d7c7e848b757b7e797881 527 | 8f98877e6f50302a33313e2c1f232b2c29272323269c9389878f9799948e8c8c876e5a63839da0 528 | 98999494958a7f8493a091878b8f8d8887838a8c8f948d89928e929688787e8a88838080868988 529 | 888a8988848187919695949a917f6d5d60758689929b998e898b7e7f848e9593897f8179797a77 530 | 818f919e917d7379889192828890928f8a858489847e7d7f80807e7b7e807f7b797a7c60534438 531 | 2e272a303337362b212126291b1b1ea5a18d90989f9d948e909576737379848e9496a2998e847c 532 | 7c879693969896918e90948b908d8a898488989893938d838689808382848a8d8e91958f878081 533 | 878c8c8b9aa0988a7b6b697881828a94968f8b8c8d867d7d8a999c9890888b8e8a8f938ca1a5a1 534 | 938783868890908c8682838b938183878a888278717e8284878f8d704d3b36302b2b2f35392c2b 535 | 292a30332b201b181ca8a494929390847876808c777e85898a8d959baca494837f8894998f999d 536 | 979598989290948e86848490a8a292909594938e818c8c8f94949398a0968982888e8b898b9b9f 537 | 9a928c7d77808583858d918f8a88869494817581959f938d939c9d9f9b8da0aaada1918785848d 538 | 8b867e797f8f9c7f87919691867a726a818e8b8a8466402a2d2b24262e302b2f261a161f2a2b24 539 | 22232fa09899837b6d605c677b8a888482868f989d9ea6a79d90919c9d9497968e8897a79d848e 540 | 918c898e919eb5a18c89969996918892939798938e92999387858f928a899196989391948c848b 541 | 958f8a8b8e8d86807795a18d797d898d807a8291979d9b8d999a96918f91908d82878a87807f85 542 | 8d838a91938d857e7b6a7a8075686053433239362a262a25182b271d110e18242b37424e999093 543 | 766c61606d80909a8f8a868a929a9c9c989e9a9297a29d8c9692847e93aba2868a8d8a8e9a9da1 544 | af9b8987908f8d8d8a8e9195969087878b8b84858f8d84869296958d8e96928b91a39a908b8d8d 545 | 877f7c898b848a979483736d737f858e928991918d888a909493848c95958d858283868b8f8e87 546 | 7e77757c6d5c51483d3432323c3c2f292a24171b21242221272c2e516872989287807a7780909b 547 | 9b978d959e9f9b97999c9699948e94a09d908d918b828ca1a59a8b8d8b919c9993999f9393938b 548 | 8a8f8d8c8f979c988e89898b87898e8c878a929b978d8c95918b90a39b8f87898e8c868489857b 549 | 7e8b8f8a7f7a80848188908e8e989d968b898d90848a9295959393948c909492887a6d6563574b 550 | 42301e1f2c2c373a302623201a1d1e202737464b48638494938e818d8a8b939d9d93898b99a6a9 551 | a199989c9a98918d939b9b958d94938a8b97a1a190939091958c83899f9c9d978c8f958f8c919b 552 | a5a4998e898c8886898f94959497948a8a928e878c9993887f828b8f8b84919687746f7a868688 553 | 9293888994968d989e9a928e8c8b8787898b8f9295979091918d8475645940464a3e2615182325 554 | 2e342e2118191d2b30353d4e616d70778a8e8b83838b8a8c929899928b8a8f979c9c9a97969793 555 | 8f8e929594919797938c8d959998949996918e827c8596979a938a91968b898e99a5a698898185 556 | 807b7f8e9c9b928d8d8688918c8589928e83797b878d8c86909a96877974767a83949789889499 557 | 8d8c8c8f979c9489948e888483827f7d8c88827c75695c53444641342c2415041a222b2b1e141a 558 | 273049626d6f747e858d82698082918e9d8b778a988e878e94928889959c99a09789848f9d9a8d 559 | 8890908a8d948d7d949c8c8ca3998796919697949496908692908e939fa59886817b7a828d9293 560 | 92898f928b8382898f868e8f867f848b8f87939c99928b827a7a787b83898d969f8d8a88878586 561 | 919c94948b8689817574898c78554b564e3532433821202721180f09142e3a3435414c5a7a908a 562 | 82807c5d2f0387818494a89f8a8c8f8d9498918b8a8b8d90939e978a818a9a9f998a8e8e8b8f96 563 | 938a838f878ba19a8d9d929aa09c9896918b8e89868c9da79d8c84817f859097969186898a8885 564 | 85898c8b898689939991847e8c96948e8e90918586878b8f9293938d8a8a8b8a888d939696938a 565 | 7c777a7e797965473e48473920343a2f22171b2c322523364a596b7c7474899c93764e2b0e0401 566 | 968e8895a9a9988b858c9f9d8e8790948f8f96999a938889959c9b8c8a898a8c8e8f8e88969496 567 | a396868f89949d9b9592908f928a838897a19a8e93928e8d97a09c918e8b8a8c9091908e8d8885 568 | 8b979c918288939a958e90989e9597948e9198968e89898d94948d86838c8e9d997b7179765e5b 569 | 4e3e373937301e283132240e173a3e4655646c6e757d96887f704e2c11000000009d9f9a93999a 570 | 958b858c9c968f8f989d9a9a9d929d9f958e90918f928f8e8f8d88888b9aa3a09fa395817f838a 571 | 9192909092949a9289878d918f8a9d9c958e959f9b8e98908b9096968f8a8a8d8e8b8888898b8c 572 | 929694908f9498979d97888792958e82838c989c93847b7878939a7a6d6a5446403c3c3a302218 573 | 252322292b1f253f6b6e747e878c8a867f604121000000011005009aa19f998d898e8f8f90908d 574 | 959998999c99918f9ca1978d8c8d8b9897999a948c8a8e9e9d949196948d8b8d8a898b8e919497 575 | 96918a858283868a95948d878c95948c998d858a8f8b827d868c918e8480868e8282858a8e8d8a 576 | 888d97968781898b857e7c808d95938c877565727a67625c3e3c302b33362814081520262f3f44 577 | 48547d7473849895785b3918010000070a01050000999b96a28f8b909296958a8f9898908f938b 578 | 7c8d96978d878c929292979b99938f8f919b93877e808c9699978f8787898b8e918c8884827f7f 579 | 858c8a89898a8e919393978a848889827c7b86878b91918c8989888281878c88817b889296918c 580 | 8b867f7d77757d868a8d8f836454504b5557463b2a1f2228231914072b45505c666c768380807f 581 | 6d481f0608000006080906000000049a958d9c9398978a8f978d989088888f92887c868d8d8786 582 | 8f94938b979b928b8e929293918f857c86969a9a928d8b88868a91928983848583848885858c97 583 | 978f9097938a868a898280868c888990928e8a89938a8486878380808887878b8f8f89827c7777 584 | 7d807c79787a6043363a454a4835291e1c21272d3131546c7376767984977d5d3f1d0000000702 585 | 080a00000000030606978f878c91a19a7f8496939e8678859799918b7f878b898c93928a8f9d9f 586 | 9189919796848f9e99898c98999b9897968f8a909ba394898a8d88828082828f9e9a8986918d86 587 | 858a8881848f918e8d8c868187918b837d7e8081889184756c75838a8886787b8288837260575b 588 | 513a2d323433382b29242125303f49707f85848379757f5f2b0000030200001603000101060801 589 | 00000096827d8585909a907f879c9c96908d8c8f9aa59a9d907a77878c84929fa798858f9e9ba0 590 | 938d92948f91998c969b958a85888c949a99918d8f8c8487889ca08b899188918e87838c979284 591 | 80929c948a88837b909492888282807b806d636c787d828991847b7669554b4e54422e26282b28 592 | 241b251e2c4f504f6d879394887d70502e00020606010000000000000000000000000000 593 | %%%%EndBinary 594 | grestore end 595 | -------------------------------------------------------------------------------- /utils/result_vis/result/E0016786877.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/result/E0016786877.png -------------------------------------------------------------------------------- /utils/result_vis/result/E0048968076.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/result/E0048968076.png -------------------------------------------------------------------------------- /utils/result_vis/result/E0056225398.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/result/E0056225398.png -------------------------------------------------------------------------------- /utils/result_vis/result/E0066596328.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/utils/result_vis/result/E0066596328.png -------------------------------------------------------------------------------- /utils/tools.py: -------------------------------------------------------------------------------- 1 | import shutil 2 | # https://stackoverflow.com/questions/1855095/how-to-create-a-zip-archive-of-a-directory 3 | def backup_project_as_zip(project_dir, zip_file): 4 | shutil.make_archive(zip_file.replace('.zip',''), 'zip', project_dir) 5 | pass -------------------------------------------------------------------------------- /utils/visualize.py: -------------------------------------------------------------------------------- 1 | from skimage.io import imsave, imread 2 | from skimage.color import gray2rgb 3 | from skimage.feature import canny 4 | from skimage.morphology import dilation, square 5 | 6 | 7 | def visulize_gt(img, gt_img, mode='r'): 8 | """ 9 | visualize mannual delination 10 | on the img 11 | :param img: 12 | :param gt_img: 13 | :return: 14 | """ 15 | rgb_img = gray2rgb(img) 16 | gt_edges = canny(gt_img, sigma=3) 17 | gt_edges = dilation(gt_edges, square(2)) 18 | if mode=='r': 19 | rgb_img[gt_edges == 1, 0] = 255 20 | rgb_img[gt_edges == 1, 1] = 0 21 | rgb_img[gt_edges == 1, 2] = 0 22 | elif mode=='g': 23 | rgb_img[gt_edges == 1, 0] = 0 24 | rgb_img[gt_edges == 1, 1] = 255 25 | rgb_img[gt_edges == 1, 2] = 0 26 | elif mode=='b': 27 | rgb_img[gt_edges == 1, 0] = 0 28 | rgb_img[gt_edges == 1, 1] = 0 29 | rgb_img[gt_edges == 1, 2] = 255 30 | 31 | return rgb_img 32 | 33 | 34 | 35 | 36 | -------------------------------------------------------------------------------- /weights.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sunalbert/Sequential-patch-based-segmentation/395af52d0c00f2e72b97902f35dbeccbbda9c381/weights.pth --------------------------------------------------------------------------------