├── README.md
├── Teaser.png
├── binvox_rw.py
├── complete_train.sh
├── deform_train.sh
├── joint_test.sh
├── joint_train.sh
├── main.py
├── models.py
├── patch_train.sh
├── pc_util.py
├── splits
    ├── compose2.py
    ├── compose_total.py
    ├── content_boat_test.txt
    ├── content_boat_train.txt
    ├── content_cabinet_test.txt
    ├── content_cabinet_train.txt
    ├── content_car_test.txt
    ├── content_car_train.txt
    ├── content_chair_test.txt
    ├── content_chair_train.txt
    ├── content_couch_test.txt
    ├── content_couch_train.txt
    ├── content_lamp_test.txt
    ├── content_lamp_train.txt
    ├── content_plane_test.txt
    ├── content_plane_train.txt
    ├── content_table_test.txt
    ├── content_table_train.txt
    └── merge_splits.py
├── train_complete.py
├── train_deform.py
├── train_joint.py
├── train_patch.py
└── utils.py


/README.md:
--------------------------------------------------------------------------------
  1 | # PatchRD
  2 | Code for ECCV 2022 paper PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformation. ([PDF](https://arxiv.org/pdf/2207.11790.pdf))
  3 | <p align="center"> 
  4 | <img src="Teaser.png">
  5 | </p>
  6 | 
  7 | ## Installation
  8 | Install [Pytorch](https://pytorch.org/get-started/locally/). It is required that you have access to GPUs. The code is tested with Ubuntu 18.04, Pytorch v1.9.0 and CUDA 10.2.
  9 | 
 10 | Install [ChamferDistancePytorch](https://github.com/ThibaultGROUEIX/ChamferDistancePytorch) by following the instructions in their github repo. 
 11 | 
 12 | Install [psbody](https://github.com/MPI-IS/mesh) for mesh reading and writing. 
 13 | 
 14 | Install the following Python dependencies (with `pip install`):
 15 | 
 16 |     numpy
 17 |     scipy
 18 |     h5py
 19 |     sklearn
 20 |     skimage
 21 |     opencv-python
 22 |     kornia
 23 |     pytorch=1.9.0
 24 | 
 25 | ## Data Download
 26 | You can download the dataset [here](https://www.dropbox.com/s/phiw7kjw7d1dfu4/data.zip?dl=0). It's a voxelized dataset for 8 classes in ShapeNet. Train/Test spliting is in `./splits`.  
 27 | To evaluate the chamfer distance, we convert our output to point cloud and use the point cloud with 16384 points from [Completion3D](https://completion3d.stanford.edu/) dataset as the ground truth. You can either download it from the offcial website or directly [here](https://www.dropbox.com/s/e1g071m10xm7zug/completion3d.zip?dl=0).  
 28 | 
 29 | 
 30 | ## Demo with Pre-trained Models 
 31 | You can download the pre-trained models for the chair category [here](https://www.dropbox.com/s/y6yzehq39ereekx/checkpoints_chair.zip?dl=0). 
 32 | 
 33 | To run the completion pipeline, first **uncomment `--dump_deform`, `--mode test`, `--small_dataset` in `patch_train.sh` and `deform_train.sh`, then uncomment `--small_dataset` in `joint_test.sh`**. 
 34 | 
 35 | Then run: 
 36 | 
 37 | ```
 38 | ./patch_train.sh
 39 | ```
 40 | ```
 41 | ./deform_train.sh
 42 | ```
 43 | ```
 44 | ./joint_test.sh
 45 | ```
 46 | You will get the input, output meshes for a small set of samples in the `samples_joint` folder. 
 47 | 
 48 | 
 49 | 
 50 | ## Training 
 51 | There are four steps to train our framework. 
 52 | The default settings train model for the chair category. You can change the arguments `--data_content` and `--data_dir` in each bash script to train on other categories. 
 53 | 
 54 | ### Step 1: Coarse Completion 
 55 | This stage takes a partial shape as input, and output the coarse full shape (4x downsampled shape of the detailed full shape). 
 56 | ```
 57 | ./complete_train.sh
 58 | ```
 59 | 
 60 | ### Step 2: Retrieval Learning 
 61 | First train the patch encoder to learn the feature embeddings for the coarse and detailed patch pair. 
 62 | ```
 63 | ./patch_train.sh
 64 | ```
 65 | Then dump the intermediate retrieval results to train the deformation. **You have to add `--dump_deform` in `patch_train.sh`**, then run 
 66 | 
 67 | ```
 68 | ./patch_train.sh
 69 | ```
 70 | 
 71 | ### Step 3: Initial Deformation Learning 
 72 | This step learns the initial deformation for the jointly learning stage. Run
 73 | 
 74 | ```
 75 | ./deform_train.sh
 76 | ```
 77 | Then dump the intermediate initial deformation results to train the deformation and blending stage. **You have to add `--dump_deform` in `deform_train.sh`**, then run 
 78 | 
 79 | ```
 80 | ./deform_train.sh
 81 | ```
 82 | 
 83 | ### Step 4: Deformation and Blending 
 84 | This step joinly learn the deformation and blending. Run 
 85 | ```
 86 | ./joint_train.sh 
 87 | ```
 88 | 
 89 | ## Evaluation 
 90 | After training all four networks, you can run the following scripts to run the completion results from a randomly cropped shape. You can find the input and output mesh in `./samples_joint`. 
 91 | ```
 92 | ./joint_test.sh
 93 | ```
 94 | 
 95 | 
 96 | ## Citation 
 97 | If you find our work useful in your research, please consider citing:
 98 | 
 99 |     @inproceedings{sun2022patchrd,
100 |         author = {Bo, Sun and Kim, Vladimir(Vova) and Huang, Qixing and Aigerman, Noam and Chaudhuri, Siddhartha},
101 |         title = {PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformation},
102 |         booktitle = {Proceedings of the IEEE European Conference on Computer Vision},
103 |         year = {2022}
104 |     }
105 | 


--------------------------------------------------------------------------------
/Teaser.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/GitBoSun/PatchRD/223af88e57f31daf2a016683d2804921fab903e2/Teaser.png


--------------------------------------------------------------------------------
/binvox_rw.py:
--------------------------------------------------------------------------------
  1 | #  Copyright (C) 2012 Daniel Maturana
  2 | #  This file is part of binvox-rw-py.
  3 | #
  4 | #  binvox-rw-py is free software: you can redistribute it and/or modify
  5 | #  it under the terms of the GNU General Public License as published by
  6 | #  the Free Software Foundation, either version 3 of the License, or
  7 | #  (at your option) any later version.
  8 | #
  9 | #  binvox-rw-py is distributed in the hope that it will be useful,
 10 | #  but WITHOUT ANY WARRANTY; without even the implied warranty of
 11 | #  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 12 | #  GNU General Public License for more details.
 13 | #
 14 | #  You should have received a copy of the GNU General Public License
 15 | #  along with binvox-rw-py. If not, see <http://www.gnu.org/licenses/>.
 16 | #
 17 | 
 18 | """
 19 | Binvox to Numpy and back.
 20 | 
 21 | 
 22 | >>> import numpy as np
 23 | >>> import binvox_rw
 24 | >>> with open('chair.binvox', 'rb') as f:
 25 | ...     m1 = binvox_rw.read_as_3d_array(f)
 26 | ...
 27 | >>> m1.dims
 28 | [32, 32, 32]
 29 | >>> m1.scale
 30 | 41.133000000000003
 31 | >>> m1.translate
 32 | [0.0, 0.0, 0.0]
 33 | >>> with open('chair_out.binvox', 'wb') as f:
 34 | ...     m1.write(f)
 35 | ...
 36 | >>> with open('chair_out.binvox', 'rb') as f:
 37 | ...     m2 = binvox_rw.read_as_3d_array(f)
 38 | ...
 39 | >>> m1.dims==m2.dims
 40 | True
 41 | >>> m1.scale==m2.scale
 42 | True
 43 | >>> m1.translate==m2.translate
 44 | True
 45 | >>> np.all(m1.data==m2.data)
 46 | True
 47 | 
 48 | >>> with open('chair.binvox', 'rb') as f:
 49 | ...     md = binvox_rw.read_as_3d_array(f)
 50 | ...
 51 | >>> with open('chair.binvox', 'rb') as f:
 52 | ...     ms = binvox_rw.read_as_coord_array(f)
 53 | ...
 54 | >>> data_ds = binvox_rw.dense_to_sparse(md.data)
 55 | >>> data_sd = binvox_rw.sparse_to_dense(ms.data, 32)
 56 | >>> np.all(data_sd==md.data)
 57 | True
 58 | >>> # the ordering of elements returned by numpy.nonzero changes with axis
 59 | >>> # ordering, so to compare for equality we first lexically sort the voxels.
 60 | >>> np.all(ms.data[:, np.lexsort(ms.data)] == data_ds[:, np.lexsort(data_ds)])
 61 | True
 62 | """
 63 | 
 64 | import numpy as np
 65 | 
 66 | class Voxels(object):
 67 |     """ Holds a binvox model.
 68 |     data is either a three-dimensional numpy boolean array (dense representation)
 69 |     or a two-dimensional numpy float array (coordinate representation).
 70 | 
 71 |     dims, translate and scale are the model metadata.
 72 | 
 73 |     dims are the voxel dimensions, e.g. [32, 32, 32] for a 32x32x32 model.
 74 | 
 75 |     scale and translate relate the voxels to the original model coordinates.
 76 | 
 77 |     To translate voxel coordinates i, j, k to original coordinates x, y, z:
 78 | 
 79 |     x_n = (i+.5)/dims[0]
 80 |     y_n = (j+.5)/dims[1]
 81 |     z_n = (k+.5)/dims[2]
 82 |     x = scale*x_n + translate[0]
 83 |     y = scale*y_n + translate[1]
 84 |     z = scale*z_n + translate[2]
 85 | 
 86 |     """
 87 | 
 88 |     def __init__(self, data, dims, translate, scale, axis_order):
 89 |         self.data = data
 90 |         self.dims = dims
 91 |         self.translate = translate
 92 |         self.scale = scale
 93 |         assert (axis_order in ('xzy', 'xyz'))
 94 |         self.axis_order = axis_order
 95 | 
 96 |     def clone(self):
 97 |         data = self.data.copy()
 98 |         dims = self.dims[:]
 99 |         translate = self.translate[:]
100 |         return Voxels(data, dims, translate, self.scale, self.axis_order)
101 | 
102 |     def write(self, fp):
103 |         write(self, fp)
104 | 
105 | def read_header(fp):
106 |     """ Read binvox header. Mostly meant for internal use.
107 |     """
108 |     line = fp.readline().strip()
109 |     if not line.startswith(b'#binvox'):
110 |         raise IOError('Not a binvox file')
111 |     dims = list(map(int, fp.readline().strip().split(b' ')[1:]))
112 |     translate = list(map(float, fp.readline().strip().split(b' ')[1:]))
113 |     scale = list(map(float, fp.readline().strip().split(b' ')[1:]))[0]
114 |     line = fp.readline()
115 |     return dims, translate, scale
116 | 
117 | def read_as_3d_array(fp, fix_coords=True):
118 |     """ Read binary binvox format as array.
119 | 
120 |     Returns the model with accompanying metadata.
121 | 
122 |     Voxels are stored in a three-dimensional numpy array, which is simple and
123 |     direct, but may use a lot of memory for large models. (Storage requirements
124 |     are 8*(d^3) bytes, where d is the dimensions of the binvox model. Numpy
125 |     boolean arrays use a byte per element).
126 | 
127 |     Doesn't do any checks on input except for the '#binvox' line.
128 |     """
129 |     dims, translate, scale = read_header(fp)
130 |     raw_data = np.frombuffer(fp.read(), dtype=np.uint8)
131 |     # if just using reshape() on the raw data:
132 |     # indexing the array as array[i,j,k], the indices map into the
133 |     # coords as:
134 |     # i -> x
135 |     # j -> z
136 |     # k -> y
137 |     # if fix_coords is true, then data is rearranged so that
138 |     # mapping is
139 |     # i -> x
140 |     # j -> y
141 |     # k -> z
142 |     values, counts = raw_data[::2], raw_data[1::2]
143 |     data = np.repeat(values, counts).astype(np.bool)
144 |     data = data.reshape(dims)
145 |     if fix_coords:
146 |         # xzy to xyz TODO the right thing
147 |         data = np.transpose(data, (0, 2, 1))
148 |         axis_order = 'xyz'
149 |     else:
150 |         axis_order = 'xzy'
151 |     return Voxels(data, dims, translate, scale, axis_order)
152 | 
153 | def read_as_coord_array(fp, fix_coords=True):
154 |     """ Read binary binvox format as coordinates.
155 | 
156 |     Returns binvox model with voxels in a "coordinate" representation, i.e.  an
157 |     3 x N array where N is the number of nonzero voxels. Each column
158 |     corresponds to a nonzero voxel and the 3 rows are the (x, z, y) coordinates
159 |     of the voxel.  (The odd ordering is due to the way binvox format lays out
160 |     data).  Note that coordinates refer to the binvox voxels, without any
161 |     scaling or translation.
162 | 
163 |     Use this to save memory if your model is very sparse (mostly empty).
164 | 
165 |     Doesn't do any checks on input except for the '#binvox' line.
166 |     """
167 |     dims, translate, scale = read_header(fp)
168 |     raw_data = np.frombuffer(fp.read(), dtype=np.uint8)
169 | 
170 |     values, counts = raw_data[::2], raw_data[1::2]
171 | 
172 |     sz = np.prod(dims)
173 |     index, end_index = 0, 0
174 |     end_indices = np.cumsum(counts)
175 |     indices = np.concatenate(([0], end_indices[:-1])).astype(end_indices.dtype)
176 | 
177 |     values = values.astype(np.bool)
178 |     indices = indices[values]
179 |     end_indices = end_indices[values]
180 | 
181 |     nz_voxels = []
182 |     for index, end_index in zip(indices, end_indices):
183 |         nz_voxels.extend(range(index, end_index))
184 |     nz_voxels = np.array(nz_voxels)
185 |     # TODO are these dims correct?
186 |     # according to docs,
187 |     # index = x * wxh + z * width + y; // wxh = width * height = d * d
188 | 
189 |     x = nz_voxels / (dims[0]*dims[1])
190 |     zwpy = nz_voxels % (dims[0]*dims[1]) # z*w + y
191 |     z = zwpy / dims[0]
192 |     y = zwpy % dims[0]
193 |     if fix_coords:
194 |         data = np.vstack((x, y, z))
195 |         axis_order = 'xyz'
196 |     else:
197 |         data = np.vstack((x, z, y))
198 |         axis_order = 'xzy'
199 | 
200 |     #return Voxels(data, dims, translate, scale, axis_order)
201 |     return Voxels(np.ascontiguousarray(data), dims, translate, scale, axis_order)
202 | 
203 | def dense_to_sparse(voxel_data, dtype=np.int):
204 |     """ From dense representation to sparse (coordinate) representation.
205 |     No coordinate reordering.
206 |     """
207 |     if voxel_data.ndim!=3:
208 |         raise ValueError('voxel_data is wrong shape; should be 3D array.')
209 |     return np.asarray(np.nonzero(voxel_data), dtype)
210 | 
211 | def sparse_to_dense(voxel_data, dims, dtype=np.bool):
212 |     if voxel_data.ndim!=2 or voxel_data.shape[0]!=3:
213 |         raise ValueError('voxel_data is wrong shape; should be 3xN array.')
214 |     if np.isscalar(dims):
215 |         dims = [dims]*3
216 |     dims = np.atleast_2d(dims).T
217 |     # truncate to integers
218 |     xyz = voxel_data.astype(np.int)
219 |     # discard voxels that fall outside dims
220 |     valid_ix = ~np.any((xyz < 0) | (xyz >= dims), 0)
221 |     xyz = xyz[:,valid_ix]
222 |     out = np.zeros(dims.flatten(), dtype=dtype)
223 |     out[tuple(xyz)] = True
224 |     return out
225 | 
226 | #def get_linear_index(x, y, z, dims):
227 |     #""" Assuming xzy order. (y increasing fastest.
228 |     #TODO ensure this is right when dims are not all same
229 |     #"""
230 |     #return x*(dims[1]*dims[2]) + z*dims[1] + y
231 | 
232 | def write(voxel_model, fp):
233 |     """ Write binary binvox format.
234 | 
235 |     Note that when saving a model in sparse (coordinate) format, it is first
236 |     converted to dense format.
237 | 
238 |     Doesn't check if the model is 'sane'.
239 | 
240 |     """
241 |     if voxel_model.data.ndim==2:
242 |         # TODO avoid conversion to dense
243 |         dense_voxel_data = sparse_to_dense(voxel_model.data, voxel_model.dims)
244 |     else:
245 |         dense_voxel_data = voxel_model.data
246 | 
247 |     fp.write('#binvox 1\n')
248 |     fp.write('dim '+' '.join(map(str, voxel_model.dims))+'\n')
249 |     fp.write('translate '+' '.join(map(str, voxel_model.translate))+'\n')
250 |     fp.write('scale '+str(voxel_model.scale)+'\n')
251 |     fp.write('data\n')
252 |     if not voxel_model.axis_order in ('xzy', 'xyz'):
253 |         raise ValueError('Unsupported voxel model axis order')
254 | 
255 |     if voxel_model.axis_order=='xzy':
256 |         voxels_flat = dense_voxel_data.flatten()
257 |     elif voxel_model.axis_order=='xyz':
258 |         voxels_flat = np.transpose(dense_voxel_data, (0, 2, 1)).flatten()
259 | 
260 |     # keep a sort of state machine for writing run length encoding
261 |     state = voxels_flat[0]
262 |     ctr = 0
263 |     for c in voxels_flat:
264 |         if c==state:
265 |             ctr += 1
266 |             # if ctr hits max, dump
267 |             if ctr==255:
268 |                 fp.write(chr(state))
269 |                 fp.write(chr(ctr))
270 |                 ctr = 0
271 |         else:
272 |             # if switch state, dump
273 |             fp.write(chr(state))
274 |             fp.write(chr(ctr))
275 |             state = c
276 |             ctr = 1
277 |     # flush out remainders
278 |     if ctr > 0:
279 |         fp.write(chr(state))
280 |         fp.write(chr(ctr))
281 | 
282 | if __name__ == '__main__':
283 |     import doctest
284 |     doctest.testmod()
285 | 


--------------------------------------------------------------------------------
/complete_train.sh:
--------------------------------------------------------------------------------
 1 | python main.py \
 2 | --data_content content_chair \
 3 | --data_dir ./data/03001627/ \
 4 | --input_size 32 \
 5 | --output_size 128 \
 6 | --sample_dir samples_complete \
 7 | --checkpoint_dir checkpoint_complete \
 8 | --gpu 0 \
 9 | --epoch 101 \
10 | --lr 1e-4 \
11 | --g_dim 32 \
12 | --w_posi 1.5 \
13 | --w_mask 0.5 \
14 | --csize 26 \
15 | --c_range 26 \
16 | --train_complete \
17 | --model_name coarse_comp \
18 | #--mode test \
19 | #--continue_train \
20 | 


--------------------------------------------------------------------------------
/deform_train.sh:
--------------------------------------------------------------------------------
 1 | python main.py \
 2 | --data_content content_chair \
 3 | --data_dir ./data/03001627/ \
 4 | --input_size 32 \
 5 | --output_size 128 \
 6 | --sample_dir samples_deform \
 7 | --checkpoint_dir checkpoint_deform \
 8 | --gpu 0 \
 9 | --epoch 100 \
10 | --lr 1e-4 \
11 | --z_dim 3 \
12 | --g_dim 32 \
13 | --K 2 \
14 | --w_dis 3.0 \
15 | --csize 26 \
16 | --c_range 26 \
17 | --max_sample_num 600 \
18 | --train_deform \
19 | --model_name chair_model0 \
20 | --dump_deform_path ./dump_deform/chair/model0 \
21 | #--dump_deform \
22 | #--small_dataset \
23 | #--mode test \
24 | #--continue_train \
25 | 


--------------------------------------------------------------------------------
/joint_test.sh:
--------------------------------------------------------------------------------
 1 | python main.py \
 2 | --data_content content_chair \
 3 | --data_dir ./data/03001627/ \
 4 | --input_size 32 \
 5 | --output_size 128 \
 6 | --sample_dir samples_joint \
 7 | --checkpoint_dir checkpoint_joint \
 8 | --log_dir logs/joint \
 9 | --gpu 0 \
10 | --epoch 1 \
11 | --lr 2e-4 \
12 | --g_dim 32 \
13 | --gw_dim 32 \
14 | --max_wd_num 400 \
15 | --loc_size 5 \
16 | --wd_size 8 \
17 | --sample_step 2 \
18 | --trans_limit 2.0 \
19 | --w_s 10 \
20 | --train_joint \
21 | --model_name chair_model0 \
22 | --dump_deform_path ./dump_deform/chair/model0 \
23 | --compute_cd \
24 | --mode test \
25 | #--small_dataset \
26 | 


--------------------------------------------------------------------------------
/joint_train.sh:
--------------------------------------------------------------------------------
 1 | python main.py \
 2 | --data_content content_chair \
 3 | --data_dir ./data/03001627/ \
 4 | --input_size 32 \
 5 | --output_size 128 \
 6 | --sample_dir samples_joint \
 7 | --checkpoint_dir checkpoint_joint \
 8 | --log_dir logs/joint \
 9 | --gpu 0 \
10 | --epoch 1 \
11 | --lr 2e-4 \
12 | --g_dim 32 \
13 | --gw_dim 32 \
14 | --max_wd_num 400 \
15 | --loc_size 5 \
16 | --wd_size 8 \
17 | --sample_step 2 \
18 | --trans_limit 2.0 \
19 | --w_s 10 \
20 | --train_joint \
21 | --model_name chair_model0 \
22 | --dump_deform_path ./dump_deform/chair/model0 \
23 | #--small_dataset \
24 | #--compute_cd \
25 | #--continue_train \
26 | 


--------------------------------------------------------------------------------
/main.py:
--------------------------------------------------------------------------------
 1 | import os
 2 | import numpy as np
 3 | import argparse
 4 | 
 5 | parser = argparse.ArgumentParser()
 6 | 
 7 | # training options
 8 | parser.add_argument("--train_complete", action="store_true", dest="train_complete", default=False, help="True for training the coarse completor")
 9 | parser.add_argument("--train_patch", action="store_true", dest="train_patch", default=False, help="True for training feature embedding for retrieval")
10 | parser.add_argument("--train_deform", action="store_true", dest="train_deform", default=False, help="True for training initial deformation")
11 | parser.add_argument("--train_joint", action="store_true", dest="train_joint", default=False, help="True for jointly training deformation and blending")
12 | parser.add_argument("--mode", action="store", dest="mode", default="train", help="mode: train or test")
13 | parser.add_argument("--gpu", action="store", dest="gpu", default="0", help="to use which GPU")
14 | 
15 | # training parameters 
16 | parser.add_argument("--epoch", action="store", dest="epoch", default=20, type=int, help="Epoch to train")
17 | parser.add_argument("--batch_size", action="store", dest="batch_size", default=1, type=int, help="Batch size [1]")
18 | parser.add_argument("--lr", action="store", dest="lr", default=1e-4, type=float, help="Learning rate")
19 | parser.add_argument("--decay_step", action="store", dest="decay_step", default=1, type=int, help="lr decay step")
20 | parser.add_argument("--lr_decay", action="store", dest="lr_decay", default=0.99, type=float, help="lr decay rate")
21 | parser.add_argument("--continue_train", action="store_true", dest="continue_train", default=False, help="If True, continue training, otherwise train from scratch")
22 | 
23 | # dump and eval options 
24 | parser.add_argument("--dump_deform", action="store_true", dest="dump_deform", default=False, help="True for dumping intermediate retrieval and  deformation results in mode --train_patch and --train_deform")
25 | parser.add_argument("--compute_cd", action="store_true", dest="compute_cd", default=False, help="True for evaluating chamfer distance and dumping mesh resulst in mode --train_joint")
26 | parser.add_argument("--small_dataset", action="store_true", dest="small_dataset", default=False, help="True for only use four samples in the testing mode")
27 | 
28 | 
29 | # model parameters 
30 | parser.add_argument("--g_dim", action="store", dest="g_dim", default=32, type=int, help="Channel dimension for models")
31 | parser.add_argument("--z_dim", action="store", dest="z_dim", default=8, type=int, help="Dimension of the latent feature embedding for retrieval learning")
32 | 
33 | # data parameters 
34 | parser.add_argument("--input_size", action="store", dest="input_size", default=32, type=int, help="Input voxel size")
35 | parser.add_argument("--output_size", action="store", dest="output_size", default=128, type=int, help="Output voxel size")
36 | parser.add_argument("--patch_size", action="store", dest="patch_size", default=18, type=int, help="Patch size for retrieval and deformation")
37 | parser.add_argument("--csize", action="store", dest="csize", default=26, type=int, help="Average size of cropped area")
38 | parser.add_argument("--c_range", action="store", dest="c_range", default=26, type=int, help="Devation of cropped size")
39 | parser.add_argument("--K", action="store", dest="K", default=2, type=int, help="ratio of randomly sampled patch pairs VS similiar pairs in retrieval learning")
40 | parser.add_argument("--max_sample_num", action="store", dest="max_sample_num", default=200, type=int, help="Maximum number of patches in retrieval learning")
41 | 
42 | 
43 | # paths  
44 | parser.add_argument("--data_content", action="store", dest="data_content", help="Data category. See ./splits for all categories")
45 | parser.add_argument("--data_dir", action="store", dest="data_dir", help="Root directory of dataset")
46 | parser.add_argument("--dump_deform_path", action="store", dest="dump_deform_path", help="Directory to dump intermidiate retrieval and initial deformation results.")
47 | parser.add_argument("--model_name", action="store", dest="model_name", default="checkpoint", help="Model name.")
48 | parser.add_argument("--checkpoint_dir", action="store", dest="checkpoint_dir", default="checkpoint", help="Directory name to save the checkpoints")
49 | parser.add_argument("--sample_dir", action="store", dest="sample_dir", default="./samples/", help="Directory name to save the image samples")
50 | parser.add_argument("--log_dir", action="store", dest="log_dir", default="./logs/", help="Directory name to save the training logs")
51 | 
52 | 
53 | # loss weights 
54 | parser.add_argument("--w_mask", action="store", dest="w_mask", default=1, type=float, help="[coarse completion]: weight for the occupied area in the reconstruction loss")
55 | parser.add_argument("--w_posi", action="store", dest="w_posi", default=1, type=float, help="[coarse completion]: weight for the occupied area in the cross entropy loss")
56 | parser.add_argument("--w_ident", action="store", dest="w_ident", default=0, type=float, help="[retrieval learning]: weight for similar pairs")
57 | parser.add_argument("--w_dis", action="store", dest="w_dis", default=1, type=float, help="[initial deformation]: weight for the patch distance prediction")
58 | parser.add_argument("--w_r", action="store", dest="w_r", default=1, type=float, help="[deformation and blending]: weight for reconstruction term")
59 | parser.add_argument("--w_s", action="store", dest="w_s", default=0, type=float, help="[deformation and blending]: weight for smoothness term")
60 | 
61 | # parameters for training deformation and blending (--train_joint) 
62 | parser.add_argument("--max_wd_num", action="store", dest="max_wd_num", default=32, type=int, help="Maximum number of windows")
63 | parser.add_argument("--sample_step", action="store", dest="sample_step", default=32, type=int, help="Sample stride of retrieved patches")
64 | parser.add_argument("--loc_size", action="store", dest="loc_size", default=32, type=int, help="Number of windows in one subvolume")
65 | parser.add_argument("--wd_size", action="store", dest="wd_size", default=8, type=int, help="Window size")
66 | parser.add_argument("--trans_limit", action="store", dest="trans_limit", default=1e-4, type=float, help="Translation limit upon the initial deformation")
67 | parser.add_argument("--gw_dim", action="store", dest="gw_dim", default=32, type=int, help="Channel dimension for the window encoding branch")
68 | 
69 | FLAGS = parser.parse_args()
70 | 
71 | os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
72 | os.environ["CUDA_VISIBLE_DEVICES"]=FLAGS.gpu
73 | 
74 | 
75 | if FLAGS.train_patch:
76 |     from train_patch import MODEL_PATCH
77 |     model = MODEL_PATCH(FLAGS)
78 |     model.train(FLAGS)
79 | 
80 | elif FLAGS.train_complete:
81 |     from train_complete import MODEL_COMPLETE
82 |     model = MODEL_COMPLETE(FLAGS)
83 |     model.train(FLAGS)
84 | 
85 | elif FLAGS.train_deform:
86 |     print('***********train deform')
87 |     from train_deform import MODEL_DEFORM
88 |     model = MODEL_DEFORM(FLAGS)
89 |     model.train(FLAGS)
90 | 
91 | elif FLAGS.train_joint:
92 |     print('***********train joint')
93 |     from train_joint import MODEL_JOINT
94 |     model = MODEL_JOINT(FLAGS)
95 |     model.train(FLAGS)
96 | else:
97 |     print('Invalid training options!')
98 | 


--------------------------------------------------------------------------------
/models.py:
--------------------------------------------------------------------------------
  1 | import torch
  2 | import torch.backends.cudnn as cudnn
  3 | import torch.nn as nn
  4 | import torch.nn.functional as F
  5 | from torch import optim
  6 | from torch.autograd import Variable
  7 | import numpy as np
  8 | 
  9 | #cell = 4
 10 | #input 256
 11 | #output 120 (128-4-4)
 12 | #receptive field = 18
 13 | 
 14 | #            0  18
 15 | #conv 4x4 s1 4  15
 16 | #conv 3x3 s2 6  7
 17 | #conv 3x3 s1 10 5
 18 | #conv 3x3 s1 14 3
 19 | #conv 3x3 s1 18 1
 20 | #conv 1x1 s1 1  1
 21 | 
 22 | #            0  41
 23 | #conv 3x3 s1 4  39
 24 | #conv 3x3 s2 6  19
 25 | #conv 3x3 s1 10  17
 26 | #conv 3x3 s1 14 15
 27 | #conv 3x3 s2 18 7
 28 | #conv 3x3 s1 26 7
 29 | 
 30 | leaky_f = 0.02
 31 | USE_25=True
 32 | 
 33 | class CoarseCompletor_skip(nn.Module):
 34 |     def __init__(self, d_dim, ):
 35 |         super(CoarseCompletor_skip, self).__init__()
 36 |         self.d_dim = d_dim
 37 | 
 38 |         self.conv_1 = nn.Conv3d(1,             self.d_dim,    5, stride=1, padding=2, bias=True)
 39 |         self.conv_2 = nn.Conv3d(self.d_dim,    self.d_dim*2,  3, stride=2, padding=1, bias=True) # 64
 40 | 
 41 |         self.conv_3 = nn.Conv3d(self.d_dim*2,  self.d_dim*2,  3, stride=1, padding=1, bias=True)
 42 |         self.conv_4 = nn.Conv3d(self.d_dim*2,  self.d_dim*4,  3, stride=2, padding=1, bias=True) # 32
 43 | 
 44 |         self.conv_5 = nn.Conv3d(self.d_dim*4,  self.d_dim*4,  3, stride=1, padding=1, bias=True)
 45 |         self.conv_6 = nn.Conv3d(self.d_dim*4,  self.d_dim*8,  3, stride=2, padding=1, bias=True) # 16
 46 | 
 47 |         self.conv_7 = nn.Conv3d(self.d_dim*8,  self.d_dim*8,  3, stride=1, padding=1, bias=True)
 48 |         self.conv_8 = nn.Conv3d(self.d_dim*8,  self.d_dim*8,  3, stride=2, padding=1, bias=True) # 8
 49 | 
 50 |         self.conv_9 = nn.Conv3d(self.d_dim*8,  self.d_dim*8,  3, stride=2, padding=1, bias=True) # 4
 51 |         self.conv_10 = nn.Conv3d(self.d_dim*8,  self.d_dim*8,  3, stride=1, padding=1, bias=True) # 4
 52 |         
 53 |         self.dconv_1 = nn.ConvTranspose3d(self.d_dim*8,  self.d_dim*8, 4, stride=2, padding=1, bias=True) # 8
 54 | 
 55 |         self.dconv_2 = nn.Conv3d(self.d_dim*16,  self.d_dim*8, 3, stride=1, padding=1, bias=True)
 56 |         self.dconv_3 = nn.ConvTranspose3d(self.d_dim*8,  self.d_dim*8, 4, stride=2, padding=1, bias=True) # 16
 57 | 
 58 |         self.dconv_4 = nn.Conv3d(self.d_dim*16,  self.d_dim*8, 3, stride=1, padding=1, bias=True)
 59 |         self.dconv_5 = nn.ConvTranspose3d(self.d_dim*8,  self.d_dim*4, 4, stride=2, padding=1, bias=True) # 32
 60 | 
 61 |         self.dconv_6 = nn.Conv3d(self.d_dim*8,  self.d_dim*4, 3, stride=1, padding=1, bias=True)
 62 |         self.dconv_7 = nn.ConvTranspose3d(self.d_dim*4,  self.d_dim*2, 4, stride=2, padding=1, bias=True) # 64
 63 | 
 64 |         self.dconv_8 = nn.Conv3d(self.d_dim*4,  self.d_dim*2, 3, stride=1, padding=1, bias=True)
 65 |         self.dconv_9 = nn.ConvTranspose3d(self.d_dim*2,  self.d_dim, 4, stride=2, padding=1, bias=True) # 128
 66 | 
 67 |         self.dconv_10 = nn.Conv3d(self.d_dim,  1,  3, stride=1, padding=1, bias=True)
 68 | 
 69 |     def forward(self, partial_in, is_training=False):
 70 |         out = partial_in
 71 |         out = self.conv_1(out)
 72 |         out1 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
 73 | 
 74 |         out = self.conv_2(out1)
 75 |         out2 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
 76 | 
 77 |         out = self.conv_3(out2)
 78 |         out3 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
 79 | 
 80 |         out = self.conv_4(out3)
 81 |         out4 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
 82 | 
 83 |         out = self.conv_5(out4)
 84 |         out5 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
 85 | 
 86 |         out = self.conv_6(out5)
 87 |         out6 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
 88 | 
 89 |         out = self.conv_7(out6)
 90 |         out7 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
 91 | 
 92 |         out = self.conv_8(out7)
 93 |         out8 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
 94 | 
 95 |         out = self.conv_9(out8)
 96 |         out9 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
 97 | 
 98 |         out = self.conv_10(out9)
 99 |         out10 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
100 | 
101 |         out = self.dconv_1(out10)
102 |         outd1 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
103 | 
104 |         out = torch.cat([outd1, out8], dim=1)
105 |         out = self.dconv_2(out)
106 |         outd2 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
107 | 
108 |         out = self.dconv_3(outd2)
109 |         outd3 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
110 | 
111 |         out = torch.cat([outd3, out6], dim=1)
112 |         out = self.dconv_4(out)
113 |         outd4 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
114 | 
115 |         out = self.dconv_5(outd4)
116 |         outd5 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
117 | 
118 |         out = torch.cat([outd5, out4], dim=1)
119 |         out = self.dconv_6(out)
120 |         outd6 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
121 | 
122 |         out = self.dconv_7(outd6)
123 |         outd7 = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
124 | 
125 |         out = torch.cat([outd7, out2], dim=1)
126 |         out = self.dconv_8(out)
127 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
128 | 
129 |         out = self.dconv_9(out)
130 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
131 | 
132 |         out = self.dconv_10(out)
133 | 
134 |         #out = torch.max(torch.min(out, out*0.002+0.998), out*0.002-0.998)
135 |         out = torch.sigmoid(out)
136 |         return out
137 | 
138 | 
139 | class PatchEncoder(nn.Module):
140 |     def __init__(self, d_dim, z_dim):
141 |         super(PatchEncoder, self).__init__()
142 |         self.d_dim = d_dim
143 |         self.z_dim = z_dim
144 | 
145 |         self.conv_1 = nn.Conv3d(1,             self.d_dim,    4, stride=1, padding=0, bias=True)
146 |         self.conv_2 = nn.Conv3d(self.d_dim,    self.d_dim*2,  3, stride=2, padding=0, bias=True)
147 |         self.conv_3 = nn.Conv3d(self.d_dim*2,  self.d_dim*4,  3, stride=1, padding=0, bias=True)
148 |         self.conv_4 = nn.Conv3d(self.d_dim*4,  self.d_dim*8,  3, stride=1, padding=0, bias=True)
149 |         self.conv_5 = nn.Conv3d(self.d_dim*8,  self.d_dim*16, 3, stride=2, padding=0, bias=True)
150 |         if USE_25:
151 |             self.conv_6 = nn.Conv3d(self.d_dim*16, self.d_dim*16, 3, stride=1, padding=1, bias=True) # extra layer
152 |             self.conv_7 = nn.Conv3d(self.d_dim*32, self.z_dim, 1, stride=1, padding=0, bias=True)
153 |         else:
154 | 
155 |             self.conv_6 =  nn.Conv3d(self.d_dim*16, self.z_dim*2, 1, stride=1, padding=0, bias=True)
156 |             self.conv_7 =  nn.Conv3d(self.z_dim*2, self.z_dim, 1, stride=1, padding=0, bias=True)
157 | 
158 |     def forward(self, voxels, return_feat=False, is_training=False):
159 |         out = voxels
160 | 
161 |         out = self.conv_1(out)
162 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
163 |         feat1 = out.detach()
164 | 
165 |         out = self.conv_2(out)
166 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
167 |         feat2 = out.detach()
168 | 
169 |         out = self.conv_3(out)
170 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
171 |         feat3 = out.detach()
172 | 
173 |         out = self.conv_4(out)
174 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
175 |         feat4 = out.detach()
176 | 
177 |         out_1 = self.conv_5(out)
178 |         out_1 = F.leaky_relu(out_1, negative_slope=leaky_f, inplace=True)
179 |         feat5 = out_1.detach()
180 | 
181 |         if USE_25:
182 |             out_2 = self.conv_6(out_1)
183 |             out_2 = F.leaky_relu(out_2, negative_slope=leaky_f, inplace=True)
184 |             feat6 = out_2.detach()
185 |             out = self.conv_7(torch.cat([out_1, out_2], dim=1))
186 |         else:
187 |             out = self.conv_6(out_1)
188 |             out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
189 |             out = self.conv_7(out)
190 | 
191 |         out = torch.max(torch.min(out, out*0.002+0.998), out*0.002-0.998)
192 |         # out = torch.sigmoid(out)
193 |         if return_feat:
194 |             return out, feat1, feat2, feat3, feat4, feat5, feat6
195 |         return out
196 | 
197 | 
198 | def reshape_to_size_torch(v1, v2_shape):
199 |     _,_,x1,y1,z1 = v1.shape
200 |     x,y,z = v2_shape
201 |     new_v1 = v1
202 |     padding = np.zeros(6)
203 |     if z1 < z:
204 |         padding[0], padding[1] = int((z-z1)/2), z-z1-int((z-z1)/2)
205 |     else:
206 |         new_v1 = new_v1[:,:,:, :,int((z1-z)/2):int((z1-z)/2)+z ]
207 |     if y1 < y:
208 |         padding[2], padding[3] = int((y-y1)/2), y-y1-int((y-y1)/2)
209 |     else:
210 |         new_v1 = new_v1[:,:,:, int((y1-y)/2):int((y1-y)/2)+y,: ]
211 |     if x1 < x:
212 |         padding[4], padding[5] = int((x-x1)/2), x-x1-int((x-x1)/2)
213 |     else:
214 |         new_v1 = new_v1[:,:,int((x1-x)/2):int((x1-x)/2)+x,:,: ]
215 |     new_v1 = F.pad(new_v1, tuple(padding.astype(np.int8)))
216 |     return new_v1
217 | 
218 | class PatchDeformer(nn.Module):
219 |     def __init__(self, d_dim, z_dim, pre_dis=False, include_coarse=False):
220 |         super(PatchDeformer, self).__init__()
221 |         self.d_dim = d_dim
222 |         self.z_dim = z_dim
223 |         self.pred_dis = pre_dis
224 |         self.include_coarse = include_coarse
225 | 
226 |         self.conv_1 = nn.Conv3d(1,             self.d_dim,    3, stride=1, padding=1, bias=True)
227 |         self.conv_2 = nn.Conv3d(self.d_dim,    self.d_dim*2,  3, stride=2, padding=1, bias=True)
228 |         self.conv_3 = nn.Conv3d(self.d_dim*2,  self.d_dim*4,  3, stride=2, padding=1, bias=True)
229 | 
230 |         self.conv_d1 = nn.Conv3d(1,             self.d_dim,    3, stride=1, padding=1, bias=True)
231 |         self.conv_d2 = nn.Conv3d(self.d_dim,    self.d_dim*2,  3, stride=2, padding=1, bias=True)
232 |         self.conv_d3 = nn.Conv3d(self.d_dim*2,  self.d_dim*4,  3, stride=2, padding=1, bias=True)
233 | 
234 |         self.fc1 = nn.Linear(self.d_dim*8*5*5*5, 4096)
235 |         self.fc2 = nn.Linear(4096, 1024)
236 |         self.fc3 = nn.Linear(1024, self.z_dim)
237 | 
238 |         if self.pred_dis:
239 |             self.dis_fc1 = nn.Linear(self.d_dim*8*5*5*5, 2048)
240 |             self.dis_fc2 = nn.Linear(2048, 512)
241 |             self.dis_fc3 = nn.Linear(512, 1)
242 | 
243 |         if self.include_coarse:
244 |             self.cdis_fc1 = nn.Linear(self.d_dim*4*5*5*5, 1024)
245 |             self.cdis_fc2 = nn.Linear(1024, 512)
246 |             self.cdis_fc3 = nn.Linear(512, 1)
247 | 
248 |             self.ddis_fc1 = nn.Linear(self.d_dim*4*5*5*5, 1024)
249 |             self.ddis_fc2 = nn.Linear(1024, 512)
250 |             self.ddis_fc3 = nn.Linear(512, 1)
251 | 
252 |     def forward(self, c_vox, d_vox, is_training=False):
253 | 
254 |         out = c_vox
255 |         out = self.conv_1(out)
256 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
257 |         out = self.conv_2(out)
258 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
259 |         out = self.conv_3(out)
260 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
261 |         out_1 = out.view(-1, 5*5*5*self.d_dim*4)
262 | 
263 |         out = d_vox
264 |         out = self.conv_d1(out)
265 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
266 |         out = self.conv_d2(out)
267 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
268 |         out = self.conv_d3(out)
269 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
270 |         out_2 = out.view(-1, 5*5*5*self.d_dim*4)
271 | 
272 | 
273 |         out = torch.cat([out_1, out_2], dim=1)
274 |         out = self.fc1(out)
275 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
276 |         out = self.fc2(out)
277 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
278 |         out = self.fc3(out)
279 |         # out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
280 |         out_de = torch.max(torch.min(out, out*0.002+0.998), out*0.002-0.998)
281 | 
282 |         if self.pred_dis:
283 |             out = torch.cat([out_1, out_2], dim=1)
284 |             out = self.dis_fc1(out)
285 |             out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
286 |             out = self.dis_fc2(out)
287 |             out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
288 |             out = self.dis_fc3(out)
289 | 
290 |             out_dis = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
291 |             # out_dis = torch.max(torch.min(out, out*0.002+0.998), out*0.002)
292 |             if not self.include_coarse:
293 |                 return out_de, out_dis
294 |             else:
295 |                 # out = torch.cat([out_1, out_2], dim=1)
296 |                 out = out_1
297 |                 out = self.cdis_fc1(out)
298 |                 out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
299 |                 out = self.cdis_fc2(out)
300 |                 out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
301 |                 out = self.cdis_fc3(out)
302 |                 out_c_dis = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
303 | 
304 |                 out = out_2
305 |                 out = self.ddis_fc1(out)
306 |                 out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
307 |                 out = self.ddis_fc2(out)
308 |                 out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
309 |                 out = self.ddis_fc3(out)
310 |                 out_d_dis = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
311 | 
312 |                 return out_de, out_dis, out_c_dis, out_d_dis
313 | 
314 |         return out_de
315 | 
316 | class JointDeformer(nn.Module):
317 |     def __init__(self, d_dim, dw_dim, k_dim,loc_size, use_mean_x=False, wd_size=8):
318 |         super(JointDeformer, self).__init__()
319 |         self.d_dim = d_dim
320 |         self.dw_dim = dw_dim
321 |         self.k_dim = k_dim
322 |         self.d = loc_size
323 |         self.use_mean_x = use_mean_x
324 |         self.wd_size = wd_size
325 | 
326 |         # input
327 |         self.conv_1 = nn.Conv3d(2,             self.d_dim,    5, stride=1, padding=2, bias=True)
328 |         self.conv_2 = nn.Conv3d(self.d_dim,    self.d_dim*2,  3, stride=2, padding=1, bias=True) # 64
329 |         self.conv_3 = nn.Conv3d(self.d_dim*2,  self.d_dim*2,  3, stride=1, padding=1, bias=True)
330 |         self.conv_4 = nn.Conv3d(self.d_dim*2,  self.d_dim*4,  3, stride=2, padding=1, bias=True) # 32
331 | 
332 |         self.conv_5 = nn.Conv3d(self.d_dim*4,  self.d_dim*4,  3, stride=1, padding=1, bias=True)
333 |         self.conv_6 = nn.Conv3d(self.d_dim*4,  self.d_dim*8,  3, stride=2, padding=1, bias=True) # 16
334 |         self.conv_7 = nn.Conv3d(self.d_dim*8,  self.d_dim*8,  3, stride=2, padding=1, bias=True) # 8
335 |         self.conv_8 = nn.Conv3d(self.d_dim*8,  self.d_dim*8,  3, stride=2, padding=1, bias=True) # 4
336 | 
337 |         # partial
338 |         self.conv_p1 = nn.Conv3d(1,             self.d_dim,   5, stride=1, padding=2, bias=True)
339 |         self.conv_p2 = nn.Conv3d(self.d_dim,    self.d_dim*2,  3, stride=2, padding=1, bias=True) # 64
340 |         self.conv_p3 = nn.Conv3d(self.d_dim*2,  self.d_dim*2,  3, stride=1, padding=1, bias=True)
341 |         self.conv_p4 = nn.Conv3d(self.d_dim*2,  self.d_dim*4,  3, stride=2, padding=1, bias=True) # 32
342 | 
343 |         self.conv_p5 = nn.Conv3d(self.d_dim*4,  self.d_dim*4,  3, stride=1, padding=1, bias=True)
344 |         self.conv_p6 = nn.Conv3d(self.d_dim*4,  self.d_dim*8,  3, stride=2, padding=1, bias=True) # 16
345 |         self.conv_p7 = nn.Conv3d(self.d_dim*8,  self.d_dim*8,  3, stride=2, padding=1, bias=True) # 8
346 |         self.conv_p8 = nn.Conv3d(self.d_dim*8,  self.d_dim*8,  3, stride=2, padding=1, bias=True) # 4
347 | 
348 |         # windows
349 |         self.conv_w0 = nn.Conv3d(self.k_dim,     self.dw_dim,    5, stride=1, padding=2, bias=True)
350 |         self.conv_w1 = nn.Conv3d(self.dw_dim,    self.dw_dim,    3, stride=1, padding=1, bias=True)
351 |         self.conv_w2 = nn.Conv3d(self.dw_dim,    self.dw_dim*2,  3, stride=2, padding=1, bias=True) # 12 . 16
352 |         self.conv_w3 = nn.Conv3d(self.dw_dim*2,  self.dw_dim*2,  3, stride=1, padding=1, bias=True)
353 |         self.conv_w4 = nn.Conv3d(self.dw_dim*2,  self.dw_dim*4,  3, stride=2, padding=1, bias=True) # 6 . 8
354 | 
355 |         self.conv_w5 = nn.Conv3d(self.dw_dim*4,  self.dw_dim*4,  3, stride=1, padding=1, bias=True)
356 |         self.conv_w6 = nn.Conv3d(self.dw_dim*4,  self.dw_dim*8,  3, stride=2, padding=1, bias=True) # 3 . 4
357 |         if self.wd_size==16:
358 |             self.conv_w7 = nn.Conv3d(self.dw_dim*8,  self.dw_dim*8,  3, stride=2, padding=1, bias=True) # 3 . 4
359 | 
360 | 
361 |         self.fc1 = nn.Linear((self.dw_dim*8*self.d*self.d*self.d + self.d_dim*8*4*4*4*2), 4096)
362 |         self.fc2 = nn.Linear(4096, 1024)
363 | 
364 |         # X
365 |         self.fc_x1 = nn.Linear(1024, 256)
366 |         self.fc_x2 = nn.Linear(256, 1024)
367 |         self.fc_x3 = nn.Linear(1024, self.dw_dim*8*self.d*self.d*self.d)
368 |         self.dconv_x0 = nn.Conv3d(self.dw_dim*8,  self.dw_dim*8,  3, stride=1, padding=1, bias=True)
369 |         self.dconv_x1 = nn.ConvTranspose3d(self.dw_dim*8,  self.dw_dim*4, 4, stride=2, padding=1, bias=True) # 8
370 |         self.dconv_x2 = nn.Conv3d(self.dw_dim*4,  self.dw_dim*4, 3, stride=1, padding=1, bias=True)
371 |         self.dconv_x3 = nn.ConvTranspose3d(self.dw_dim*4,  self.dw_dim*2, 4, stride=2, padding=1, bias=True) # 16
372 |         self.dconv_x4 = nn.Conv3d(self.dw_dim*2,  self.d_dim*2, 3, stride=1, padding=1, bias=True)
373 |         self.dconv_x5 = nn.ConvTranspose3d(self.dw_dim*2,  self.dw_dim, 4, stride=2, padding=1, bias=True) # 32
374 |         self.dconv_x6 = nn.Conv3d(self.dw_dim,  self.dw_dim, 3, stride=1, padding=1, bias=True)
375 |         self.dconv_x7 = nn.Conv3d(self.dw_dim,  self.k_dim, 3, stride=1, padding=1, bias=True)
376 | 
377 |         # D
378 |         self.fc_d1 = nn.Linear(1024, 1024)
379 |         self.fc_d2 = nn.Linear(1024, 1024)
380 |         self.fc_d3 = nn.Linear(1024, self.k_dim*3)
381 | 
382 | 
383 |     def forward(self, partial_in, input_in, windows_in, window_masks_in, loc_mask_in,  is_training=False):
384 |         leaky_f = 0.02
385 |         out = torch.cat([input_in, window_masks_in], dim=1)
386 |         out = self.conv_1(out)
387 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
388 |         out = self.conv_2(out)
389 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
390 |         out = self.conv_3(out)
391 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
392 |         out = self.conv_4(out)
393 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
394 |         out = self.conv_5(out)
395 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
396 |         out = self.conv_6(out)
397 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
398 |         out = self.conv_7(out)
399 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
400 |         out = self.conv_8(out)
401 |         out_coa = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
402 | 
403 |         out = partial_in
404 |         out = self.conv_p1(out)
405 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
406 |         out = self.conv_p2(out)
407 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
408 |         out = self.conv_p3(out)
409 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
410 |         out = self.conv_p4(out)
411 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
412 |         out = self.conv_p5(out)
413 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
414 |         out = self.conv_p6(out)
415 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
416 |         out = self.conv_p7(out)
417 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
418 |         out = self.conv_p8(out)
419 |         out_p = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
420 | 
421 |         out = windows_in
422 |         out = self.conv_w0(out)
423 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
424 |         out = self.conv_w1(out)
425 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
426 |         out = self.conv_w2(out)
427 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
428 |         out = self.conv_w3(out)
429 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
430 |         out = self.conv_w4(out)
431 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
432 |         out = self.conv_w5(out)
433 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
434 |         out = self.conv_w6(out)
435 |         out_w = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
436 |         if self.wd_size==16:
437 |             out_w = self.conv_w7(out_w)
438 |             out_w = F.leaky_relu(out_w, negative_slope=leaky_f, inplace=True)
439 | 
440 |         out_coa = out_coa.view(1, self.d_dim*8*4*4*4)
441 |         out_p = out_p.view(1, self.d_dim*8*4*4*4)
442 |         out_w =out_w.view(1, self.dw_dim*8*self.d*self.d*self.d)
443 | 
444 |         out = torch.cat((out_w, out_coa, out_p), dim=1)
445 |         out = self.fc1(out)
446 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
447 |         out = self.fc2(out)
448 |         out_latent = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
449 | 
450 |         # D
451 |         out = self.fc_d1(out_latent)
452 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
453 |         out = self.fc_d2(out)
454 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
455 |         out = self.fc_d3(out)
456 |         # out_D = torch.max(torch.min(out, out*0.002+0.998), out*0.002-0.998)
457 |         out_D = torch.clip(out, -1.0, 1.0)
458 |         out_D = out_D.view(self.k_dim, 3)
459 | 
460 |         # X
461 |         out = self.fc_x1(out_latent)
462 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
463 |         out = self.fc_x2(out)
464 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
465 |         out = self.fc_x3(out)
466 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
467 | 
468 |         out = out.view(1, self.dw_dim*8, self.d,self.d,self.d)
469 |         out = self.dconv_x0(out)
470 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
471 |         #print('0',out.shape)
472 |         out = self.dconv_x1(out)
473 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
474 |         #print('1',out.shape)
475 |         out = self.dconv_x2(out)
476 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
477 |         #print('2',out.shape)
478 |         out = self.dconv_x3(out)
479 |         #print('3',out.shape)
480 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
481 |         out = self.dconv_x4(out)
482 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
483 |         #print('4',out.shape)
484 |         out = self.dconv_x5(out)
485 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
486 |         #print('5',out.shape)
487 |         out = self.dconv_x6(out)
488 |         out = F.leaky_relu(out, negative_slope=leaky_f, inplace=True)
489 |         #print('6',out.shape)
490 |         out_X = self.dconv_x7(out) # [1, kdim, vx, vy, vz]
491 | 
492 |         # out_X = torch.max(torch.min(out_X,out_X*0.002+0.998), out_X*0.002)
493 |         # out_X = torch.sigmoid(out_X)
494 |         out_X = torch.clip(out_X, 0.0, 1.0)
495 |         # loc_mask_in = F.interpolate(loc_mask_in, scale_factor=8, mode='nearest')
496 |         out_X = F.avg_pool3d(out_X, kernel_size=8, stride=8)
497 | 
498 |         if self.use_mean_x:
499 |             out_X = out_X*loc_mask_in/(torch.sum(out_X*loc_mask_in, dim=1).unsqueeze(1)+1e-5)
500 |         else:
501 |             out_X = torch.exp(out_X)*loc_mask_in/(torch.sum(torch.exp(out_X)*loc_mask_in, dim=1).unsqueeze(1)+1e-5)
502 | 
503 |         #print('out_x', out_X.mean())
504 |         return out_D, out_X
505 | 
506 | 
507 | 


--------------------------------------------------------------------------------
/patch_train.sh:
--------------------------------------------------------------------------------
 1 | python main.py \
 2 | --data_content content_chair \
 3 | --data_dir ./data/03001627/ \
 4 | --input_size 32 \
 5 | --output_size 128 \
 6 | --sample_dir samples_patch \
 7 | --checkpoint_dir checkpoint_patch \
 8 | --gpu 0 \
 9 | --epoch 250 \
10 | --lr 1e-4 \
11 | --z_dim 128 \
12 | --g_dim 32 \
13 | --K 2 \
14 | --w_ident 8 \
15 | --csize 26 \
16 | --c_range 26  \
17 | --max_sample_num 400 \
18 | --train_patch \
19 | --model_name chair_model0 \
20 | --dump_deform_path ./dump_deform/chair/model0 \
21 | #--dump_deform \
22 | #--small_dataset \
23 | #--mode test \
24 | #--continue_train \
25 | 


--------------------------------------------------------------------------------
/pc_util.py:
--------------------------------------------------------------------------------
  1 | # Copyright (c) Facebook, Inc. and its affiliates.
  2 | #
  3 | # This source code is licensed under the MIT license found in the
  4 | # LICENSE file in the root directory of this source tree.
  5 | 
  6 | """ Utility functions for processing point clouds.
  7 | Author: Charles R. Qi and Or Litany
  8 | """
  9 | 
 10 | import os
 11 | import sys
 12 | BASE_DIR = os.path.dirname(os.path.abspath(__file__))
 13 | sys.path.append(BASE_DIR)
 14 | 
 15 | # Point cloud IO
 16 | import numpy as np
 17 | try:
 18 |     from plyfile import PlyData, PlyElement
 19 | except:
 20 |     print("Please install the module 'plyfile' for PLY i/o, e.g.")
 21 |     print("pip install plyfile")
 22 |     sys.exit(-1)
 23 | 
 24 | 
 25 | # Mesh IO
 26 | #import trimesh
 27 | 
 28 | import matplotlib.pyplot as pyplot
 29 | 
 30 | # ----------------------------------------
 31 | # Point Cloud Sampling
 32 | # ----------------------------------------
 33 | 
 34 | def random_sampling(pc, num_sample, replace=None, return_choices=False):
 35 |     """ Input is NxC, output is num_samplexC
 36 |     """
 37 |     if replace is None: replace = (pc.shape[0]<num_sample)
 38 |     choices = np.random.choice(pc.shape[0], num_sample, replace=replace)
 39 |     if return_choices:
 40 |         return pc[choices], choices
 41 |     else:
 42 |         return pc[choices]
 43 | 
 44 | # ----------------------------------------
 45 | # Point Cloud/Volume Conversions
 46 | # ----------------------------------------
 47 | 
 48 | def point_cloud_to_volume_batch(point_clouds, vsize=12, radius=1.0, flatten=True):
 49 |     """ Input is BxNx3 batch of point cloud
 50 |         Output is Bx(vsize^3)
 51 |     """
 52 |     vol_list = []
 53 |     for b in range(point_clouds.shape[0]):
 54 |         vol = point_cloud_to_volume(np.squeeze(point_clouds[b,:,:]), vsize, radius)
 55 |         if flatten:
 56 |             vol_list.append(vol.flatten())
 57 |         else:
 58 |             vol_list.append(np.expand_dims(np.expand_dims(vol, -1), 0))
 59 |     if flatten:
 60 |         return np.vstack(vol_list)
 61 |     else:
 62 |         return np.concatenate(vol_list, 0)
 63 | 
 64 | 
 65 | def point_cloud_to_volume(points, vsize, radius=1.0):
 66 |     """ input is Nx3 points.
 67 |         output is vsize*vsize*vsize
 68 |         assumes points are in range [-radius, radius]
 69 |     """
 70 |     vol = np.zeros((vsize,vsize,vsize))
 71 |     voxel = 2*radius/float(vsize)
 72 |     locations = (points + radius)/voxel
 73 |     locations = locations.astype(int)
 74 |     vol[locations[:,0],locations[:,1],locations[:,2]] = 1.0
 75 |     return vol
 76 | 
 77 | 
 78 | def volume_to_point_cloud(vol):
 79 |     """ vol is occupancy grid (value = 0 or 1) of size vsize*vsize*vsize
 80 |         return Nx3 numpy array.
 81 |     """
 82 |     vsize = vol.shape[0]
 83 |     assert(vol.shape[1] == vsize and vol.shape[1] == vsize)
 84 |     points = []
 85 |     for a in range(vsize):
 86 |         for b in range(vsize):
 87 |             for c in range(vsize):
 88 |                 if vol[a,b,c] == 1:
 89 |                     points.append(np.array([a,b,c]))
 90 |     if len(points) == 0:
 91 |         return np.zeros((0,3))
 92 |     points = np.vstack(points)
 93 |     return points
 94 | 
 95 | 
 96 | 
 97 | 
 98 | def point_cloud_to_volume_v2_batch(point_clouds, vsize=12, radius=1.0, num_sample=128):
 99 |     """ Input is BxNx3 a batch of point cloud
100 |         Output is BxVxVxVxnum_samplex3
101 |         Added on Feb 19
102 |     """
103 |     vol_list = []
104 |     for b in range(point_clouds.shape[0]):
105 |         vol = point_cloud_to_volume_v2(point_clouds[b,:,:], vsize, radius, num_sample)
106 |         vol_list.append(np.expand_dims(vol, 0))
107 |     return np.concatenate(vol_list, 0)
108 | 
109 | def point_cloud_to_volume_v2(points, vsize, radius=1.0, num_sample=128):
110 |     """ input is Nx3 points
111 |         output is vsize*vsize*vsize*num_sample*3
112 |         assumes points are in range [-radius, radius]
113 |         samples num_sample points in each voxel, if there are less than
114 |         num_sample points, replicate the points
115 |         Added on Feb 19
116 |     """
117 |     vol = np.zeros((vsize,vsize,vsize,num_sample,3))
118 |     voxel = 2*radius/float(vsize)
119 |     locations = (points + radius)/voxel
120 |     locations = locations.astype(int)
121 |     loc2pc = {}
122 |     for n in range(points.shape[0]):
123 |         loc = tuple(locations[n,:])
124 |         if loc not in loc2pc:
125 |             loc2pc[loc] = []
126 |         loc2pc[loc].append(points[n,:])
127 | 
128 |     for i in range(vsize):
129 |         for j in range(vsize):
130 |             for k in range(vsize):
131 |                 if (i,j,k) not in loc2pc:
132 |                     vol[i,j,k,:,:] = np.zeros((num_sample,3))
133 |                 else:
134 |                     pc = loc2pc[(i,j,k)] # a list of (3,) arrays
135 |                     pc = np.vstack(pc) # kx3
136 |                     # Sample/pad to num_sample points
137 |                     if pc.shape[0]>num_sample:
138 |                         pc = random_sampling(pc, num_sample, False)
139 |                     elif pc.shape[0]<num_sample:
140 |                         pc = np.lib.pad(pc, ((0,num_sample-pc.shape[0]),(0,0)), 'edge')
141 |                     # Normalize
142 |                     pc_center = (np.array([i,j,k])+0.5)*voxel - radius
143 |                     pc = (pc - pc_center) / voxel # shift and scale
144 |                     vol[i,j,k,:,:] = pc
145 |     return vol
146 | 
147 | def point_cloud_to_image_batch(point_clouds, imgsize, radius=1.0, num_sample=128):
148 |     """ Input is BxNx3 a batch of point cloud
149 |         Output is BxIxIxnum_samplex3
150 |         Added on Feb 19
151 |     """
152 |     img_list = []
153 |     for b in range(point_clouds.shape[0]):
154 |         img = point_cloud_to_image(point_clouds[b,:,:], imgsize, radius, num_sample)
155 |         img_list.append(np.expand_dims(img, 0))
156 |     return np.concatenate(img_list, 0)
157 | 
158 | 
159 | def point_cloud_to_image(points, imgsize, radius=1.0, num_sample=128):
160 |     """ input is Nx3 points
161 |         output is imgsize*imgsize*num_sample*3
162 |         assumes points are in range [-radius, radius]
163 |         samples num_sample points in each pixel, if there are less than
164 |         num_sample points, replicate the points
165 |         Added on Feb 19
166 |     """
167 |     img = np.zeros((imgsize, imgsize, num_sample, 3))
168 |     pixel = 2*radius/float(imgsize)
169 |     locations = (points[:,0:2] + radius)/pixel # Nx2
170 |     locations = locations.astype(int)
171 |     loc2pc = {}
172 |     for n in range(points.shape[0]):
173 |         loc = tuple(locations[n,:])
174 |         if loc not in loc2pc:
175 |             loc2pc[loc] = []
176 |         loc2pc[loc].append(points[n,:])
177 |     for i in range(imgsize):
178 |         for j in range(imgsize):
179 |             if (i,j) not in loc2pc:
180 |                 img[i,j,:,:] = np.zeros((num_sample,3))
181 |             else:
182 |                 pc = loc2pc[(i,j)]
183 |                 pc = np.vstack(pc)
184 |                 if pc.shape[0]>num_sample:
185 |                     pc = random_sampling(pc, num_sample, False)
186 |                 elif pc.shape[0]<num_sample:
187 |                     pc = np.lib.pad(pc, ((0,num_sample-pc.shape[0]),(0,0)), 'edge')
188 |                 pc_center = (np.array([i,j])+0.5)*pixel - radius
189 |                 pc[:,0:2] = (pc[:,0:2] - pc_center)/pixel
190 |                 img[i,j,:,:] = pc
191 |     return img
192 | # ----------------------------------------
193 | # Point cloud IO
194 | # ----------------------------------------
195 | 
196 | def read_ply(filename):
197 |     """ read XYZ point cloud from filename PLY file """
198 |     plydata = PlyData.read(filename)
199 |     pc = plydata['vertex'].data
200 |     pc_array = np.array([[x, y, z] for x,y,z in pc])
201 |     return pc_array
202 | 
203 | 
204 | def write_ply(points, filename, text=True):
205 |     """ input: Nx3, write points to filename as PLY format. """
206 |     points = [(points[i,0], points[i,1], points[i,2]) for i in range(points.shape[0])]
207 |     vertex = np.array(points, dtype=[('x', 'f4'), ('y', 'f4'),('z', 'f4')])
208 |     el = PlyElement.describe(vertex, 'vertex', comments=['vertices'])
209 |     PlyData([el], text=text).write(filename)
210 | 
211 | def write_ply_color(points, labels, filename, num_classes=None, colormap=pyplot.cm.jet):
212 |     """ Color (N,3) points with labels (N) within range 0 ~ num_classes-1 as OBJ file """
213 |     labels = labels.astype(int)
214 |     N = points.shape[0]
215 |     if num_classes is None:
216 |         num_classes = np.max(labels)+1
217 |     else:
218 |         assert(num_classes>np.max(labels))
219 | 
220 |     vertex = []
221 |     #colors = [pyplot.cm.jet(i/float(num_classes)) for i in range(num_classes)]
222 |     colors = [colormap(i/float(num_classes)) for i in range(num_classes)]
223 |     for i in range(N):
224 |         c = colors[labels[i]]
225 |         c = [int(x*255) for x in c]
226 |         vertex.append( (points[i,0],points[i,1],points[i,2],c[0],c[1],c[2]) )
227 |     vertex = np.array(vertex, dtype=[('x', 'f4'), ('y', 'f4'),('z', 'f4'),('red', 'u1'), ('green', 'u1'),('blue', 'u1')])
228 | 
229 |     el = PlyElement.describe(vertex, 'vertex', comments=['vertices'])
230 |     PlyData([el], text=True).write(filename)
231 | 
232 | def write_ply_rgb(points, colors, out_filename, num_classes=None):
233 |     """ Color (N,3) points with RGB colors (N,3) within range [0,255] as OBJ file """
234 |     colors = colors.astype(int)
235 |     N = points.shape[0]
236 |     fout = open(out_filename, 'w')
237 |     for i in range(N):
238 |         c = colors[i,:]
239 |         fout.write('v %f %f %f %d %d %d\n' % (points[i,0],points[i,1],points[i,2],c[0],c[1],c[2]))
240 |     fout.close()
241 | 
242 | # ----------------------------------------
243 | # Simple Point cloud and Volume Renderers
244 | # ----------------------------------------
245 | 
246 | def pyplot_draw_point_cloud(points, output_filename):
247 |     """ points is a Nx3 numpy array """
248 |     import matplotlib.pyplot as plt
249 |     fig = plt.figure()
250 |     ax = fig.add_subplot(111, projection='3d')
251 |     ax.scatter(points[:,0], points[:,1], points[:,2])
252 |     ax.set_xlabel('x')
253 |     ax.set_ylabel('y')
254 |     ax.set_zlabel('z')
255 |     #savefig(output_filename)
256 | 
257 | def pyplot_draw_volume(vol, output_filename):
258 |     """ vol is of size vsize*vsize*vsize
259 |         output an image to output_filename
260 |     """
261 |     points = volume_to_point_cloud(vol)
262 |     pyplot_draw_point_cloud(points, output_filename)
263 | 
264 | # ----------------------------------------
265 | # Simple Point manipulations
266 | # ----------------------------------------
267 | def rotate_point_cloud(points, rotation_matrix=None):
268 |     """ Input: (n,3), Output: (n,3) """
269 |     # Rotate in-place around Z axis.
270 |     if rotation_matrix is None:
271 |         rotation_angle = np.random.uniform() * 2 * np.pi
272 |         sinval, cosval = np.sin(rotation_angle), np.cos(rotation_angle)
273 |         rotation_matrix = np.array([[cosval, sinval, 0],
274 |                                     [-sinval, cosval, 0],
275 |                                     [0, 0, 1]])
276 |     ctr = points.mean(axis=0)
277 |     rotated_data = np.dot(points-ctr, rotation_matrix) + ctr
278 |     return rotated_data, rotation_matrix
279 | 
280 | def rotate_pc_along_y(pc, rot_angle):
281 |     ''' Input ps is NxC points with first 3 channels as XYZ
282 |         z is facing forward, x is left ward, y is downward
283 |     '''
284 |     cosval = np.cos(rot_angle)
285 |     sinval = np.sin(rot_angle)
286 |     rotmat = np.array([[cosval, -sinval],[sinval, cosval]])
287 |     pc[:,[0,2]] = np.dot(pc[:,[0,2]], np.transpose(rotmat))
288 |     return pc
289 | 
290 | def roty(t):
291 |     """Rotation about the y-axis."""
292 |     c = np.cos(t)
293 |     s = np.sin(t)
294 |     return np.array([[c,  0,  s],
295 |                     [0,  1,  0],
296 |                     [-s, 0,  c]])
297 | 
298 | def roty_batch(t):
299 |     """Rotation about the y-axis.
300 |     t: (x1,x2,...xn)
301 |     return: (x1,x2,...,xn,3,3)
302 |     """
303 |     input_shape = t.shape
304 |     output = np.zeros(tuple(list(input_shape)+[3,3]))
305 |     c = np.cos(t)
306 |     s = np.sin(t)
307 |     output[...,0,0] = c
308 |     output[...,0,2] = s
309 |     output[...,1,1] = 1
310 |     output[...,2,0] = -s
311 |     output[...,2,2] = c
312 |     return output
313 | 
314 | def rotz(t):
315 |     """Rotation about the z-axis."""
316 |     c = np.cos(t)
317 |     s = np.sin(t)
318 |     return np.array([[c, -s,  0],
319 |                      [s,  c,  0],
320 |                      [0,  0,  1]])
321 | 
322 | 
323 | 
324 | # ----------------------------------------
325 | # BBox
326 | # ----------------------------------------
327 | def bbox_corner_dist_measure(crnr1, crnr2):
328 |     """ compute distance between box corners to replace iou
329 |     Args:
330 |         crnr1, crnr2: Nx3 points of box corners in camera axis (y points down)
331 |         output is a scalar between 0 and 1
332 |     """
333 | 
334 |     dist = sys.maxsize
335 |     for y in range(4):
336 |         rows = ([(x+y)%4 for x in range(4)] + [4+(x+y)%4 for x in range(4)])
337 |         d_ = np.linalg.norm(crnr2[rows, :] - crnr1, axis=1).sum() / 8.0
338 |         if d_ < dist:
339 |             dist = d_
340 | 
341 |     u = sum([np.linalg.norm(x[0,:] - x[6,:]) for x in [crnr1, crnr2]])/2.0
342 | 
343 |     measure = max(1.0 - dist/u, 0)
344 |     print(measure)
345 | 
346 | 
347 |     return measure
348 | 
349 | 
350 | def point_cloud_to_bbox(points):
351 |     """ Extract the axis aligned box from a pcl or batch of pcls
352 |     Args:
353 |         points: Nx3 points or BxNx3
354 |         output is 6 dim: xyz pos of center and 3 lengths
355 |     """
356 |     which_dim = len(points.shape) - 2 # first dim if a single cloud and second if batch
357 |     mn, mx = points.min(which_dim), points.max(which_dim)
358 |     lengths = mx - mn
359 |     cntr = 0.5*(mn + mx)
360 |     return np.concatenate([cntr, lengths], axis=which_dim)
361 | 
362 | def write_bbox(scene_bbox, out_filename):
363 |     """Export scene bbox to meshes
364 |     Args:
365 |         scene_bbox: (N x 6 numpy array): xyz pos of center and 3 lengths
366 |         out_filename: (string) filename
367 |     Note:
368 |         To visualize the boxes in MeshLab.
369 |         1. Select the objects (the boxes)
370 |         2. Filters -> Polygon and Quad Mesh -> Turn into Quad-Dominant Mesh
371 |         3. Select Wireframe view.
372 |     """
373 |     def convert_box_to_trimesh_fmt(box):
374 |         ctr = box[:3]
375 |         lengths = box[3:]
376 |         trns = np.eye(4)
377 |         trns[0:3, 3] = ctr
378 |         trns[3,3] = 1.0
379 |         box_trimesh_fmt = trimesh.creation.box(lengths, trns)
380 |         return box_trimesh_fmt
381 | 
382 |     scene = trimesh.scene.Scene()
383 |     for box in scene_bbox:
384 |         scene.add_geometry(convert_box_to_trimesh_fmt(box))
385 | 
386 |     mesh_list = trimesh.util.concatenate(scene.dump())
387 |     # save to ply file
388 |     trimesh.io.export.export_mesh(mesh_list, out_filename, file_type='ply')
389 | 
390 |     return
391 | 
392 | def write_oriented_bbox(scene_bbox, out_filename):
393 |     """Export oriented (around Z axis) scene bbox to meshes
394 |     Args:
395 |         scene_bbox: (N x 7 numpy array): xyz pos of center and 3 lengths (dx,dy,dz)
396 |             and heading angle around Z axis.
397 |             Y forward, X right, Z upward. heading angle of positive X is 0,
398 |             heading angle of positive Y is 90 degrees.
399 |         out_filename: (string) filename
400 |     """
401 |     def heading2rotmat(heading_angle):
402 |         pass
403 |         rotmat = np.zeros((3,3))
404 |         rotmat[2,2] = 1
405 |         cosval = np.cos(heading_angle)
406 |         sinval = np.sin(heading_angle)
407 |         rotmat[0:2,0:2] = np.array([[cosval, -sinval],[sinval, cosval]])
408 |         return rotmat
409 | 
410 |     def convert_oriented_box_to_trimesh_fmt(box):
411 |         ctr = box[:3]
412 |         lengths = box[3:6]
413 |         trns = np.eye(4)
414 |         trns[0:3, 3] = ctr
415 |         trns[3,3] = 1.0
416 |         trns[0:3,0:3] = heading2rotmat(box[6])
417 |         box_trimesh_fmt = trimesh.creation.box(lengths, trns)
418 |         return box_trimesh_fmt
419 | 
420 |     scene = trimesh.scene.Scene()
421 |     for box in scene_bbox:
422 |         scene.add_geometry(convert_oriented_box_to_trimesh_fmt(box))
423 | 
424 |     mesh_list = trimesh.util.concatenate(scene.dump())
425 |     # save to ply file
426 |     trimesh.io.export.export_mesh(mesh_list, out_filename, file_type='ply')
427 | 
428 |     return
429 | 
430 | def write_oriented_bbox_camera_coord(scene_bbox, out_filename):
431 |     """Export oriented (around Y axis) scene bbox to meshes
432 |     Args:
433 |         scene_bbox: (N x 7 numpy array): xyz pos of center and 3 lengths (dx,dy,dz)
434 |             and heading angle around Y axis.
435 |             Z forward, X rightward, Y downward. heading angle of positive X is 0,
436 |             heading angle of negative Z is 90 degrees.
437 |         out_filename: (string) filename
438 |     """
439 |     def heading2rotmat(heading_angle):
440 |         pass
441 |         rotmat = np.zeros((3,3))
442 |         rotmat[1,1] = 1
443 |         cosval = np.cos(heading_angle)
444 |         sinval = np.sin(heading_angle)
445 |         rotmat[0,:] = np.array([cosval, 0, sinval])
446 |         rotmat[2,:] = np.array([-sinval, 0, cosval])
447 |         return rotmat
448 | 
449 |     def convert_oriented_box_to_trimesh_fmt(box):
450 |         ctr = box[:3]
451 |         lengths = box[3:6]
452 |         trns = np.eye(4)
453 |         trns[0:3, 3] = ctr
454 |         trns[3,3] = 1.0
455 |         trns[0:3,0:3] = heading2rotmat(box[6])
456 |         box_trimesh_fmt = trimesh.creation.box(lengths, trns)
457 |         return box_trimesh_fmt
458 | 
459 |     scene = trimesh.scene.Scene()
460 |     for box in scene_bbox:
461 |         scene.add_geometry(convert_oriented_box_to_trimesh_fmt(box))
462 | 
463 |     mesh_list = trimesh.util.concatenate(scene.dump())
464 |     # save to ply file
465 |     trimesh.io.export.export_mesh(mesh_list, out_filename, file_type='ply')
466 | 
467 |     return
468 | 
469 | def write_lines_as_cylinders(pcl, filename, rad=0.005, res=64):
470 |     """Create lines represented as cylinders connecting pairs of 3D points
471 |     Args:
472 |         pcl: (N x 2 x 3 numpy array): N pairs of xyz pos
473 |         filename: (string) filename for the output mesh (ply) file
474 |         rad: radius for the cylinder
475 |         res: number of sections used to create the cylinder
476 |     """
477 |     scene = trimesh.scene.Scene()
478 |     for src,tgt in pcl:
479 |         # compute line
480 |         vec = tgt - src
481 |         M = trimesh.geometry.align_vectors([0,0,1],vec, False)
482 |         vec = tgt - src # compute again since align_vectors modifies vec in-place!
483 |         M[:3,3] = 0.5*src + 0.5*tgt
484 |         height = np.sqrt(np.dot(vec, vec))
485 |         scene.add_geometry(trimesh.creation.cylinder(radius=rad, height=height, sections=res, transform=M))
486 |     mesh_list = trimesh.util.concatenate(scene.dump())
487 |     trimesh.io.export.export_mesh(mesh_list, '%s.ply'%(filename), file_type='ply')
488 | 
489 | # ----------------------------------------
490 | # Testing
491 | # ----------------------------------------
492 | if __name__ == '__main__':
493 |     print('running some tests')
494 | 
495 |     ############
496 |     ## Test "write_lines_as_cylinders"
497 |     ############
498 |     pcl = np.random.rand(32, 2, 3)
499 |     write_lines_as_cylinders(pcl, 'point_connectors')
500 |     input()
501 | 
502 | 
503 |     scene_bbox = np.zeros((1,7))
504 |     scene_bbox[0,3:6] = np.array([1,2,3]) # dx,dy,dz
505 |     scene_bbox[0,6] = np.pi/4 # 45 degrees
506 |     write_oriented_bbox(scene_bbox, 'single_obb_45degree.ply')
507 |     ############
508 |     ## Test point_cloud_to_bbox
509 |     ############
510 |     pcl = np.random.rand(32, 16, 3)
511 |     pcl_bbox = point_cloud_to_bbox(pcl)
512 |     assert pcl_bbox.shape == (32, 6)
513 | 
514 |     pcl = np.random.rand(16, 3)
515 |     pcl_bbox = point_cloud_to_bbox(pcl)
516 |     assert pcl_bbox.shape == (6,)
517 | 
518 |     ############
519 |     ## Test corner distance
520 |     ############
521 |     crnr1 = np.array([[2.59038660e+00, 8.96107932e-01, 4.73305349e+00],
522 |  [4.12281644e-01, 8.96107932e-01, 4.48046631e+00],
523 |  [2.97129656e-01, 8.96107932e-01, 5.47344275e+00],
524 |  [2.47523462e+00, 8.96107932e-01, 5.72602993e+00],
525 |  [2.59038660e+00, 4.41155793e-03, 4.73305349e+00],
526 |  [4.12281644e-01, 4.41155793e-03, 4.48046631e+00],
527 |  [2.97129656e-01, 4.41155793e-03, 5.47344275e+00],
528 |  [2.47523462e+00, 4.41155793e-03, 5.72602993e+00]])
529 |     crnr2 = crnr1
530 | 
531 |     print(bbox_corner_dist_measure(crnr1, crnr2))
532 | 
533 | 
534 | 
535 |     print('tests PASSED')
536 | 
537 | 
538 | 
539 | 


--------------------------------------------------------------------------------
/splits/compose2.py:
--------------------------------------------------------------------------------
 1 | import numpy as np
 2 | import os
 3 | 
 4 | #path = '/home/bo/data/shapenet_processed2/02801938'
 5 | #path = '/home/bo/data/shapenet_processed/02828884'
 6 | path = '/home/bo/data/shapenet_processed'
 7 | 
 8 | #f1 = open('content_bench_train.txt', 'w')
 9 | #f2 = open('content_bench_test.txt', 'w')
10 | f1 = open('total_sub_train.txt', 'w')
11 | f2 = open('total_sub_test.txt', 'w')
12 | 
13 | f0 = open('content_chair_train.txt', 'r')
14 | lines = f0.readlines()
15 | for l in lines:
16 |     f1.write('03001627/%s\n'%(l.strip()))
17 | f0.close()
18 | f0 = open('content_chair_test.txt', 'r')
19 | lines = f0.readlines()
20 | for l in lines[0:200]:
21 |     f2.write('03001627/%s\n'%(l.strip()))
22 | f0.close()
23 | 
24 | f0 = open('content_table_test.txt', 'r')
25 | lines = f0.readlines()
26 | for l in lines:
27 |     f1.write('04379243/%s\n'%(l.strip()))
28 | f0.close()
29 | f0 = open('content_table_test.txt', 'r')
30 | lines = f0.readlines()
31 | for l in lines[0:200]:
32 |     f2.write('04379243/%s\n'%(l.strip()))
33 | f0.close()
34 | 
35 | 
36 | for cat in os.listdir(path):
37 |     if cat in ['03001627', '04379243']:
38 |         continue
39 |     if not cat in ['02801938', '02828884', '03691459']:
40 |         continue
41 |     if not cat.startswith('0'):
42 |         continue
43 |     names = os.listdir(os.path.join(path, cat))
44 |     data_len = len(names)
45 | 
46 |     for i in range(data_len):
47 |         if i<int(4*data_len/5) and i<2000:
48 |             f1.write('%s/%s\n'%(cat, names[i]))
49 |         elif i>=int(4*data_len/5) and i<int(4*data_len/5)+200:
50 |             f2.write('%s/%s\n'%(cat, names[i]))
51 | 
52 | f1.close()
53 | f2.close()
54 | 


--------------------------------------------------------------------------------
/splits/compose_total.py:
--------------------------------------------------------------------------------
 1 | import numpy as np
 2 | import os
 3 | 
 4 | #path = '/home/bo/data/shapenet_processed2/02801938'
 5 | #path = '/home/bo/data/shapenet_processed/02828884'
 6 | path = '/home/bo/data/shapenet_processed/02958343'
 7 | path = '/home/bo/data/PCN/ShapeNetCompletion/train/partial/03001627/'
 8 | 
 9 | f1 = open('content_pcn_train.txt', 'w')
10 | f2 = open('content_pcn_test.txt', 'w')
11 | 
12 | names = os.listdir(path)
13 | data_len = len(names)
14 | print(len(names))
15 | 
16 | data_len = 4000
17 | 
18 | for i in range(data_len):
19 |     if i<int(5*data_len/6):
20 |         f1.write('%s\n'%(names[i]))
21 |     else:
22 |         f2.write('%s\n'%(names[i]))
23 | 


--------------------------------------------------------------------------------
/splits/content_boat_test.txt:
--------------------------------------------------------------------------------
  1 | 3076e52758d28680b534b494664155d3
  2 | a755dbab93afbb3a1a05bdebf75f301d
  3 | f99537c4b6d50126d87c63d8b3018b58
  4 | 1b2e790b7c57fc5d2a08194fd3f4120d
  5 | d55ce64040e0b3e4ecc9205d69d88837
  6 | e271e4ef2c327dda28d0def75843d7e0
  7 | d65fc1dbe7fe802a5761a0b53ed37cec
  8 | 406e7646609bc8bd8a53c9119bc523d3
  9 | 74093f3d2583f3be7b0299baad14624c
 10 | 587cc1fc65ac4991ff920fdb73e92549
 11 | 189668ffa80d37877622984b5941cfb8
 12 | e23e4845d3a990d25fc186cfb5f359d1
 13 | b3aa94c4aac0534ec34b1b7198ff8321
 14 | aa83008f44e009177795dd28016933fc
 15 | 1660bbd9c43284d98bfe41fc81907f54
 16 | 8c0199fb20e7d4d391347c63d1dae43c
 17 | ac736a87ca813c6d701c68e1045b606
 18 | 54cf5783ca03b3e015ea3a1685d773da
 19 | 44a50dc1a9d8a8a65144962e2c20b832
 20 | 726a60f7dabb1c88c746ec5b7259bed7
 21 | 2ba37ef44fa116f8300ca77569ad3884
 22 | adb1b651af34dc6f42534f02c8e8b5ac
 23 | 845426b7dd1b0e55a9142e7277ee08f1
 24 | 5a3924c1fb78bb908dea00b146cfa3de
 25 | 5059b4e973a0fc7f928a2a26ac296b52
 26 | 508e6fc3b47590556be64995e9ed73eb
 27 | aa741f0f7784b791e99164b294d0c671
 28 | 176c629c93b5a1f73cf0b8b75857cc24
 29 | 847e8fedddf6bee5518c49741aed1bc1
 30 | eb891509436863da874f0e42f84eb4f5
 31 | d939109a33e6e2d175517226b23c384c
 32 | 61c17240229bf84581d9d9b1473043a2
 33 | 51f002bbc33e4b34aff407511d7dfc96
 34 | 269ada03c39d200498a4434c6f79eefc
 35 | ac4286c2e92e3367d5ba5130450bf929
 36 | f8d3af1d1a20123c249ba97ee36ba54
 37 | 25c736b7ca26bcb7bfccc00eb137e6ec
 38 | 268110d849a3aafdec2f14500e179e92
 39 | 77331918e10b8eacd07153997ca82b26
 40 | c6ef6b859205ab53609e2d916fa0da27
 41 | bdc39427c6267262c541ae04c251c7da
 42 | 33692290561c798e780bc2708a85ba9a
 43 | 27e9a27b6e3b49c227ac692756be9e24
 44 | 3e7923c788b0b9a67297c18bca670e89
 45 | c00a8f1dc19a0e5341213ed93def741e
 46 | a13e0728cbc8a41594ebaf95f022dfde
 47 | 6847480bd905f05b544654c1c7449887
 48 | fa8af8f2bedb0d461f29de30ec1bf6a3
 49 | 2005e1613f1a46b5c083d5272d526845
 50 | a89cda9712b67a97d1e97c10e2464c2d
 51 | bc691ae1f2d6cf0ba628de2fd7989b40
 52 | 3fb4fa12a4718cdb2001fe4ad7074729
 53 | 73e6d10ad309d831ddb86907b4b5f05d
 54 | 512251a635bd548f3463d0a80e47bc52
 55 | 7a5de2857213a2547ea0f302610f14a5
 56 | 19a72473173bf26ff7bc9a344bb7bae5
 57 | 8d7c4ca5e08a8a3a6d4334e260ec617d
 58 | 3bd4a80ef718b9c9a069f11e22e91bb4
 59 | 4cff5eb82cac0f56b7b1411b0ad3bd0d
 60 | 90e6c6083fcd47833e45dd2f173cbf9b
 61 | 4b501c73f3cb02c63438e17bc657daf1
 62 | 61053086346058bd2b477561b6a06f5c
 63 | 3b8c16861667747fcfea3d4fc15719ea
 64 | ac479ce45b04972891bdbed880f31c72
 65 | 522614512d74a2f8c5f391634c2a5ade
 66 | c78d6f5c908e2ff1b05dfc874f00d5f3
 67 | c746175e0993abc19a6e43b878d5b335
 68 | 2988a53fc376653aae529ab4a75c4af
 69 | 1b00e4c41b4195807e1c97634acf0214
 70 | 37ea55e2d023f9ae9588e71e21de9f30
 71 | 5ab18f317c0a5d21576932faf8645222
 72 | 6371cc04f48161ec43b0018b6edb5e48
 73 | a2e82524f7920e12d3ded2945a65f23f
 74 | 39875815bdfdce2193b1b9ed21f1fb92
 75 | efdfd88f3fcbc162b4c316c21a905ad4
 76 | 988e1d7106b705d692336765b86c93d9
 77 | 1e3f014e8eba0db7fa575e221973fef
 78 | 2b58ca08b8f93769c5408f4f799fe72
 79 | 8bef56b64003be1789f903fb361de4ca
 80 | 739a6f209a49040a4f44d84b9baa5f42
 81 | 7703ba29545cc381acf9e4b0d73d2434
 82 | 438a1ce3825bc06a18803813f0c0dee8
 83 | abee560e2dd721eeb129901f80d24b7b
 84 | 75991571412e7ce74059b9174ed51649
 85 | d10cd8bfe5eb85572aec0b439528eb79
 86 | 1f846bab69b20a23561fc06c3ebd59d2
 87 | 12b5302a8aa697a138b0c448fc291f4a
 88 | ae1a4397815849a682b5804533e545b1
 89 | 2a569537a0f6abd34b5acb1c7aa990eb
 90 | 2e19e953c01ddd69d5bb7fc09b61862a
 91 | 2b1d09f8412f647899c0080e6a5589fa
 92 | 25f20d56a125b4028d8e8d98cb30b332
 93 | f4923b4ce88bdda3a9142e7277ee08f1
 94 | 42a8428a3d909fd64de203ef6842ee61
 95 | a554a62acf40e578cba07fb2573fff75
 96 | d350936cad33863bf2ad837508eb2db7
 97 | 5e6e9a61eb078041556f795d265590
 98 | a45cbcfb2763423a6540eb087d7e15bd
 99 | b2b616535ffca936c9189a1f098bd081
100 | 8e7fd92d91a9974a2d220e1baafcedd8
101 | 4719acf1c3e56fb489d39b85991ba25a
102 | b91a01dfd51d615b4f84436cd4bc7d29
103 | e82e97e22066a75d798832e32e32aae6
104 | 7103677dbfe63b1ff85fa5c7c88c6c9f
105 | 1f20ff37655c5dd61aa01ae491663d9
106 | 10a57262251f03b28b27d51d442cae1c
107 | dc38553436df0e4bb129901f80d24b7b
108 | a58fb21bfa4e2f451ddea1d5aef06a06
109 | 950ebca8ad7d94051fba2cab1ada6bf6
110 | 1d6bcf04874000a9ea96bfd37cd8bdfb
111 | a32082d31b6b9a0566dd4c46ee29f5d0
112 | fa2b5f163549ca457ba04de7d6d93ce8
113 | 26bdd8852a95cd2d4e4ba49b2943b913
114 | fe482b5db6daa95f88e2183678696c9a
115 | f4aa1a1c7216fdfcd3d8a17e1b074875
116 | 2228242cfad46b73a0928eccd5f75d69
117 | 1d8adfa96dca83849143982c80da1e75
118 | 6b87ed6710a0fc8d8aae7c4db7244339
119 | 22bfa8eb9cdce735d90cecb09ba6f1b8
120 | 4a523f749fd08ffa698137c717c4ad11
121 | 6bbd0b0e09dd43017ddd35a83509257f
122 | e9c603efb5aea8087610cb1c03c9c3ea
123 | 1b1cf4f2cc24a2a2a5895e3729304f68
124 | 65f78142a6c33a89ea7dce1646d86149
125 | 50ec883d9c1f715614edc3c9b2489f4
126 | 96b27c98daf461269ff59e10e6ad1a4c
127 | c79c87dcf17a40f698501ff072a5cd78
128 | f1d39ce0d8c25403b4caa017b521f7
129 | 7915c47b72e6d496e453885abe85c310
130 | ef666f3eb17ea5cbd56c7296613ec69d
131 | 6e3db071ed95552b3faeafe37c2ce4f6
132 | 92e3343250e181e1428cf87eb5ebe5e6
133 | 65577c66f22fd84d6eb9a4c3b55eb0c4
134 | 677ffbc1ee40a0a0db5a9ea3574bb285
135 | 87e1eda2a99c713d4fbe64e9d0fe42b6
136 | 8d95b6ddd06a8a80f57109a0257e61dd
137 | 1fb07d5bf3421a46e2b83b21c9537e1b
138 | 34b77143d6313e3f717ad2ef4c4af2e5
139 | 6db27ae2c9cf722d1743d8ffcf66c439
140 | 3f3912cf68cd28eed7259ae7450dc47b
141 | ff7b2ba047233a5b149489fae2289e6b
142 | a8455459a7b93aef9e5629b793f22d35
143 | 76dc1a35fee28991a5103c3a2f33a5e9
144 | b2f200bd0861e1daeb78d3e0a9401d4b
145 | cdd493581ed137c5a6dae8586082d789
146 | 548c6234fc7c787bfeea5c85a86089b5
147 | 54daf1472c51bb47a97a590141e0046
148 | f46a84c0b15f8c0492f7f11d4bb65374
149 | 2a9df36f9327beb27244f3b2d7f5074d
150 | cab0b302a23381adcdcba7385a96c2c8
151 | 71fb9e98e62ae65f6a8fde3b294e520d
152 | 799d446d33e604f990f7927ebadab5fc
153 | 933aa8e54e97de9392694c864c93195e
154 | 5a8c1f3f0ff3e5a87bb222726cf5a84c
155 | 421db3c87037e7d6c2363c2f18a57bf4
156 | 3d908c2b4f5812702fc668af6d3ad0ad
157 | 99f00898c6b373d5eb2c303a0e0d287b
158 | a443271055ad0ebccc9f5b25407f3c72
159 | 68f118940e88df383ac122c0078b9b60
160 | dded8a613927539cd72535fe84d882f0
161 | 60cc5839008caf13cea6e9826e81ed40
162 | d4ffdf377bda1aa5f650f4803ec7962d
163 | 388c5175593b057a66bc841ba9cad258
164 | 4fc0f4f2d29a463cb1bb46d2556ba67d
165 | dae38d7110c4bf252f84cb7932f866fd
166 | 429dea3aadb0c3bdc753f4f2b4288d6
167 | 5e9890e2f4cab96dbc6cd96a5e6546c
168 | a2d4f32a82902118aaac2db0a60f403c
169 | 731b8fb370639bec2c8b4a1ac32beb2d
170 | 1dce61f6dd85dc469811751e3fab8939
171 | 7b0ed74742d27ff3ccc6f1de97150965
172 | 5e8276dfb4c1db936f31e247620349e3
173 | 767cd95abc076d3af9d742d7f0246fb0
174 | 804e29433fda9657746ffcbc44510229
175 | 97402ccd78c061251141cd3611961b0
176 | 635bed8b6b180fa3e65273dbd0c0f949
177 | 9ac6483c969f1120b05dfc874f00d5f3
178 | b7c24dca7db1d2985c00e52236fed2eb
179 | bfd8b473e1a8fd650eb615eb69452b
180 | 2507ed5c9eb161569a704df179502ac7
181 | 68e60ab321e4198ab437d385637c4e1c
182 | dbe05209a14fca8fdf72e713dd4f492a
183 | 98da594a65640370c8333f6c4d99e2c8
184 | 8b92073eb06f0365e18960ef54b079a3
185 | ad8b5aaa3eb9f2f69330265a9fff38de
186 | 4e5b83181a13e0661868b1150be0eef4
187 | a8f225774d1bc8d0b7002bddf0942f8e
188 | ec51dbe499e88615a267c8b6fcca89d9
189 | 85481518c0938a6eb1bb46d2556ba67d
190 | 5e8ce498a93fb7eae1a9c234926c21e2
191 | 5c46f6ce5efa21175060c1b57f88c056
192 | 6f3384e934f3588ccc37416b6163cbbd
193 | d57e124826aabbbfc6cb0dfa2f14f9d4
194 | 5b88544e42981ce0a71aa3ce894d7bf7
195 | 13b7b299d346020a4de203ef6842ee61
196 | 9fd71a532f7c732fb036cb639ea80765
197 | 9c4d83025107322b2aed6a9a322ced74
198 | 12900e06f0f4ec9e49f471d054f6b528
199 | e969147de0934040b2533fe4d795f40c
200 | a85ef79371cb1edb52fd6b83c5929135
201 | a492984be2c03294213a43a25cd73264
202 | 2ab688c7eaa21bbd77e7acf84a1c4b6
203 | 787e381b4a968a55af5574caf3b1433d
204 | dcaf4238da8ef379106f24d0bacaba69
205 | 9696dd7f30247c5c573080510ce7a6bb
206 | c359eef375afa3b6dd42314e00caace4
207 | 27476b5c965b010618b731fab8bc3743
208 | a06a7f4b82beb87df6fc999231665677
209 | 293781c9bf4f6168c4ff53ac1cae3d62
210 | f2c8239dc51b315858e86ae676396826
211 | ab40191e935c415cef0a5cdc2cab422d
212 | 4690184ef7ea805dfdd29529d1a15514
213 | 50c0bd9933f7259fe59358c5e6239c84
214 | 33e3b187089a68d3f983f6a1267b9260
215 | 79803d0a02bbdc93ff790997f2048517
216 | 4bcb45bdbf0309201d2d2f3b717d35d5
217 | c991fc4636615e64ed01ae0c90548352
218 | 48a584c9080f7495b97c9314bd4647d5
219 | c46b2f2069ce543c4bbcee86e282d431
220 | 3a4c31888d291859f8e1db0ba8b72d09
221 | 2defbf22a2d6c97d48f817470e1b499a
222 | b10850ed8a61d4dd148bc340784a8c1
223 | 704aaee1bba4d220179fa02faff22219
224 | 29af666e04825f66576378847ca0b69
225 | 5aaec5938224841f36cf5f476d32636f
226 | e92386352c19221ac99bbfcf5650bf52
227 | 217966c23fe43ab83bde759c61eecdb6
228 | 8480865aa92d13dd46687b3834d255fa
229 | 47133569866031669268271e4d570275
230 | f81ae8a4452ad290aa9bbcb26e1c5ea7
231 | ad251b2cd68290a41c9545c3c7193d55
232 | dcb390b2e8e5093def84f4e0accfb14e
233 | a53eb39c51a7e0a2dcb7d7c06abe0da3
234 | ba05637e557909b19527abfa7ff95c0f
235 | a3109a4b09953b5e2b141dc6bd7c4bce
236 | 85dbbed13875a3a2b90142192ec795d
237 | 212a323fdfc0d8e59399f7cdb64577ad
238 | f5812d814e114a185c8b6bf3197caaf6
239 | 3f3bf820fa5d171bd45d4d5673b732bd
240 | ca129502c7b2b8186d54dce3f3e9f18b
241 | c89c8eca488d5072cdd34f38f87d26cf
242 | c8bce97e59665f2811b9a587ace886f7
243 | 759c3321f016c1cf7cd1f8dd6fbce8fb
244 | 6dd917d73699da0d255465ee23ab5b12
245 | d2d3ab44415a3d3fef5e991e1c32e94a
246 | 47c53f9cfdd4addfe054bb56e3407f7b
247 | 1b00f29471a41f59e92b1dc10fc46551
248 | 404061915066692d89e410fd8930ae43
249 | 89ca399e4ab129a60014fe834c82238
250 | 80e8c7703883a40c9e4614310319ea50
251 | 1d451877c6270d97fe755e3418b63110
252 | 3c835bfc9201041a34f2450730697f14
253 | 42d4dfd73f7e27677e72e199dc6b40e
254 | bf47c2f0b5d1c6fef37a9c459d3dd62a
255 | b8905c60432aadddb4a8f569bbe9f7c5
256 | 792427f5da01907ddf48ca5a34c88e7c
257 | 887be2603a56d8acc13b4b8de5611825
258 | 67e41dd24b6902da49f471d054f6b528
259 | fa656e5b70f12edcbe7ca2216dc1576a
260 | 8877086211c9976cd27beaa6c9701d39
261 | 223d2316bb8b74a979170a5f8beda902
262 | 6fbb26f9372ee87648192cebc0015590
263 | 81c9e9d3f461c4da9917c7f0cf5ea813
264 | ad2c82cd40584b43fc4c78b4701b2fab
265 | 3173f703a1e52d7f38d037116a032a18
266 | ebb7451625233d772afc5c10dbf83b25
267 | 327be46d4b15ba2aa79c0870e481d9eb
268 | 2f0acfd47622a8fa419fe456f622e6b2
269 | 567e385bc5c40247e414f982f9c422f7
270 | af936a44c902756dfb04eeadf4d8d0aa
271 | 3ff7e02233affcc350eb615eb69452b
272 | 5a4e0cb4562b2e0ef647317afa6ffdd4
273 | 71d6ab6979e5a313dde8c025d72da437
274 | f7f62b9657aecbe77f00b68989ad3ebc
275 | 9e49192ba54ab0fc92c108c58096cae
276 | 79c98bef5c1870b64c55cd455710ca53
277 | 2e447f96f152a33a7428866500a95dd8
278 | 425ff664205d2a7f5c0be177939e290
279 | 7e96722d076d9e9020dfe072b77502f8
280 | 3948782a95f084b92336765b86c93d9
281 | c00cee4431f3c2db89d39b85991ba25a
282 | 3fe8b8d9fcf031574bac1c894ff81b3e
283 | efc4de2b174c736dc99bbfcf5650bf52
284 | bf5112a856a8f6a3819d76d0172b8abf
285 | 89f52a2a136ce55728ba119bc0e1c878
286 | cc6656baa69ba0defd40bb12da2df97e
287 | 320b3f040f6d5147ab87075c54b494cb
288 | 482ad82769d6b5b11274a3ddd0ec9301
289 | 3c8dc4a3621674aabb29ab7e4f889a04
290 | f45d51939d8ee9122698fe11741f2ba4
291 | 2615224e88e47ed29e5ca238b1551011
292 | 6436ddeaa11efffdcdd34f38f87d26cf
293 | 4e6313bce5ee3698909d4348e3fee2dd
294 | 1b3a8fa303445f3e4ff4a2772e8deea
295 | ff54247b18f676d9129032621d548b11
296 | 2340319ec4d93ae8c1df6b0203ecb359
297 | db01f2f8cff7b7e1c517f0fe59ec7ee
298 | 860e632b27b9d2469f1deb04fb8ae481
299 | b270ca5a6051053d88e2183678696c9a
300 | 88ea6d51dcf2cdee3a6f102e22936e2c
301 | 35e014dccdd4fed12c791a7edd1fdff6
302 | 2a9b44ad6d6200c02b3fb35c6618f417
303 | 9115745cde6f30c67f141c9abbacbdb8
304 | 11e04ef8f037194919869180453a248
305 | abbef6c2f909b9719ef9dcee729574d5
306 | ec97e9975c94f7ba727ef88d634f1148
307 | 234541314abebbd02783b84b5d2d6e46
308 | 82be57a43d5d1e14fa286e2f06a75d07
309 | 4021a170452d19393c79f1baa816886a
310 | d1e59a48852965fb036cb639ea80765
311 | 90bb60a421727973e3852f9948e4ef35
312 | a4d1ec9841281a3cd1e97c10e2464c2d
313 | 7a4fb637dc511c19b1bb46d2556ba67d
314 | 1a2f00c6886f14354d85fb76de815344
315 | 7d2194fb89c42da8ae5c852356538a5e
316 | 7fb484e04409f7323f3cc56bc9bfcde3
317 | f1800fb3a9873af1e64f09105f9c8a56
318 | 91fd8bfce87a0e7d847c4e55bb965ab0
319 | 397f37249263000990960087ed86644
320 | 325d1e9be246e1644d44f5db04bf14b8
321 | 35857ac61388f9fec2912ef1a1302821
322 | 1dffc8919a03627ecc015b9f8906f7b4
323 | 160271b40b1d6822c40386bdd72f9a0
324 | a6d232b7443609fd20ded1536778b0f
325 | 99b36b2d2174f061ff8f632f1c753803
326 | b89d4bfad9c9b64d476a01ad767951be
327 | 2e958577e7756f59bf9717d602b327f4
328 | 70d4ca23f31a5c4373c03aee5e8475d4
329 | a0b661c93028d7de798832e32e32aae6
330 | ac8a42622eed9830ae433bf4d273c8e2
331 | 8682988328acbc62b8acbfab1478caa1
332 | 8cbb360233696342309e1bb5976741f2
333 | c2d6e8710215b74c82689dfa8a7d7e7f
334 | a56c3a66dbe0ddf4a70cfb3232f40c6
335 | 490ba339e10c0b7f4de203ef6842ee61
336 | c8414ce9b8848c3c1a3ad8aa8e24c7d1
337 | afcafaf311af722a5446fdbcaa866773
338 | f83474c31e7bb6bc1022decd5ff96217
339 | 72eb488206297aeaa60ce6f0a0028c13
340 | 4944328c0ea895c53f464857aba8c0eb
341 | ad440e99d3a9bed3cd202a4790115f0c
342 | 1e047e25506b4885eb5715ea2e14242a
343 | 715699f07f8e59a1620e7892e762134
344 | ed397dd3d2ca4c8a69852296a4bb593c
345 | 12159b68a31a4a7eacb3e49e16caebeb
346 | ff70051c32217b2df671917093bd361
347 | 64ccd647293ba2a75e73d168e741c7c8
348 | a6d50000249d71cf70c8aed16b49b164
349 | 5a7635031cd518daefa33903c8f77ab8
350 | 55d87dea079d2b991bc665188b93587b
351 | c715bbc7a1586afe64ab9e610db7c692
352 | 9a20ab78eb6a5e7af7ff315fbee3c6eb
353 | efc2b7a0ab3828761194cbd9c0740031
354 | 93c013c922b90649ec08eb6485163157
355 | 819a7b31f925a302474a33db0a80b327
356 | 2bf9436a79954087bc585c195913193c
357 | 9c3810b8bc98c59426fa791c6af15500
358 | 86e404c548d965c6d28357d0413f2f80
359 | 8508ec8efeedf4a41ff8f5b5b24b7b46
360 | 70744087c22ee199a51aab4cdab636bb
361 | c7fb35a9ca583715ef0445a3d98d3d35
362 | 772835e02fec3a93629f9e3e495fed76
363 | 27f0d2bf42b0e3374ed242fafe836df1
364 | 1f7f1d7c3882f638fb64f9487ce62dd2
365 | 18642f35971d1bec86c51c3aa93bf029
366 | 4ee0ed0c56540273a6dae8586082d789
367 | 991dab2b2339600a27da61c271c9c6a1
368 | f60404b62c44fd3b49f0e3dd7767881
369 | 7edbaebf7d4fa994eca93934e5f39869
370 | 7aaa404bd120be52816427daa1887efe
371 | 953adc8c58842c1281d9d9b1473043a2
372 | 24000ec6bcb6ab9182b5804533e545b1
373 | a49537b465965537fe3128d27fad4d2
374 | 925f3de9b1256113538505dcebf57ab1
375 | 1b89cb2463ccaf15e1e2fc42e32162ff
376 | 5b86640d3bc2e43decac3f40526a2cc2
377 | f6288a9297948fdc67383adf153b22c5
378 | 806834c2b3c0bce7989a4a13be837150
379 | 8faf5fbe39f67f3dfa2eb3102eea4e72
380 | f03f7c963928073227ac692756be9e24
381 | 614aaafb767bfe62dcf47132cab9d51b
382 | 72a9394882b8151bef94bcb012573cf2
383 | d0ed110df0d56672b26ad4ebd4ebcb88
384 | 4c6e4bc79308e23e480060a68009533d
385 | 91c1e885c5cb2ace3c01fd24534f394d
386 | 355a85d0156984c75e559927dcb9417c
387 | 3283111173c12947622984b5941cfb8
388 | f91e712b124915514b6c44ccda750d2e
389 | 


--------------------------------------------------------------------------------
/splits/content_cabinet_test.txt:
--------------------------------------------------------------------------------
  1 | ab7ad8afde03897aa52fef6f94fcc8a
  2 | c95634c0a44d6596e71fb4d3a412f2d0
  3 | 687a33b0fd4a906dc2185cc0ca1b306b
  4 | 3fc6e2baf40f4377f5afb395b99ae069
  5 | d6edc4c02e38c7dda5737ca21e62ad39
  6 | 22e77a41cc388839824662341ce2b233
  7 | 6db5a05080eb2480f863ead9331efd45
  8 | 13d5f9d6a7464e39f0f01f1432a517c3
  9 | ba1230fc38050b1bbf1d236bec6d905
 10 | 82c05fe4890a7f5112de5317fe5b354f
 11 | d7ec3740a0c67d89f8c3d2002c77ddb
 12 | 9c8dff9a5f5cc6ab490ad276cd2af3a4
 13 | 46bb63196198ffa2fc98aa4b97627df6
 14 | 5d8c63fce0f30a46f251828d7c328331
 15 | 55d1668a7d33f8ebc0b2397831029b54
 16 | 401960cb8526894f4b8710a3469971b1
 17 | 21f3c0d4604587b4da5feafe6f1c8fc
 18 | fdf32559c6b7a6643fe047712e43e185
 19 | 12cb11dbb135ca9ac59350d819542ec7
 20 | a46373d86967b3fce9aee4515d4383aa
 21 | 3076e5d4a8078a0c59350d819542ec7
 22 | 1a1b62a38b2584874c62bee40dcdc539
 23 | dca4c8bdab8bdfe739e1d6694e046e01
 24 | 3a910cc1f575b08339d3717288022c20
 25 | 7e2e24fed142bb20310af74324aae27f
 26 | a640e7214f7c5393a5b7c9f0974d595e
 27 | 4e89985989c6a1936aedbd2a02b96953
 28 | 8a758b29a751764d14038d588fd1342f
 29 | 74126116f42f09e2e6e130a30b5ed875
 30 | b404faa639b8600855f46d55537192b6
 31 | 7aee2d4c1e70d27c921dd903dd0b8b17
 32 | 381d0eb848eaaa07eee615e75bc3b77
 33 | bd0388dc8384961ccf004563556ddb36
 34 | 90c2b07e831f5e7fc75178c2e93f5b68
 35 | 429488f8be42c9ed73149e0cf45b2c4e
 36 | 2c1af98d2058a8056588620c25b809f9
 37 | 5f55127e04171d6435836c728d324152
 38 | b8880afd2b1038c8ea7cdfccad65e7e9
 39 | 3824d4b03e74afe0743d4e4333af43e6
 40 | a5d193fd45690070b93ba26740e73067
 41 | c4fc9ac6e45a8ebc90546f5d45015351
 42 | 1e694a1848b810ebc59350d819542ec7
 43 | 29ce2b045bc6111912de5317fe5b354f
 44 | 6059f5f009c40b814702663c3b3faf8f
 45 | 37d41aa1ab8e7318534f016fc3878f48
 46 | 62d67406fb239e21533276a8c0b1c862
 47 | 8f8a2633debaeb96c2b64c0adffbe398
 48 | 31c94abeda52273286d53ab0fe94e911
 49 | 584b055cbd62b8572d7ead8d9eea29b1
 50 | bcee1a76f453723c4cc1952ae0d6e81a
 51 | d0aee9e36e73a88a11fc2b865c2a185b
 52 | a2dc947048077f4bd0b36851d61b6fca
 53 | 9b885f40e2d36819e4e346ee2650d150
 54 | 1a9a91aa5e3306ec5938fc2058ab2dbe
 55 | bb5c331b32e39d0d3ec45bd2bc895504
 56 | 1252e89db37d786386d53ab0fe94e911
 57 | 18a1c4eb2e4b31fce83221ad0d21775
 58 | 2441395102a132354da5feafe6f1c8fc
 59 | 84f34a2d86cd4f0211926054acb73bec
 60 | 2f2e54607ea04be4c93bb8ae72b9da71
 61 | b29f2d0d278e938914038d588fd1342f
 62 | 77aff49eccafcf2726831803d0b48347
 63 | acbc349caf76e6b171337fa12bff07ad
 64 | 86905b35aca5a3f11f8d8332ee17945a
 65 | 740392e1c6522664c20c4293bea04a44
 66 | 7eca681f6174f1ce12de5317fe5b354f
 67 | 6f2ce914b5d4db81e28993aa4d91dd77
 68 | 9b2759851023fad7dedad3eee47fd556
 69 | 927ac18cb336cfe3df289a3ea5d3a440
 70 | dca6f5a582517758eab2bd7322386ffd
 71 | aca4241639feb8f0921dd903dd0b8b17
 72 | 8382308b895aa93286d53ab0fe94e911
 73 | 433b0fe363861867b25e7c54df7809b7
 74 | 2375dfeeab7fd8678430b7446f9e1252
 75 | 6352c69907b70c0480fa521a9c7198a
 76 | 7bd5510b4451cb651d6ac856ecde9eb2
 77 | 41d9c4bc97447c4530ed3cf7f7e32c4a
 78 | 1074bdcb3c2032fe0f3f8b6e1796773
 79 | 7abc6f3fcabd914157d513bbf87f8d1a
 80 | 72105548b0e01be8659e37b49210f361
 81 | 267545b2c6ec6ee1f51f77a6d7299806
 82 | 1258a7bae01e349fa320e34dad7c78bd
 83 | a874dcff3bcf8a802aca02f099166182
 84 | dfa0bf0f2b48ea33e3a031805ace4a99
 85 | 64f02390a1487f791e4b67452ae5160
 86 | 2ba392a70c40dac7c59350d819542ec7
 87 | b8e019587c8157041a3b39b07e4b3d0f
 88 | 9deca642cbf3e4ef49a734174fea032e
 89 | 54a7817fcd0919697753725ea42159e8
 90 | 80a3b5b036021b8e404dc8be84d677e3
 91 | 282f296a666fb63dc59350d819542ec7
 92 | 45679a0d39b500533dd5cc05646564a4
 93 | 836fc8edc0414fdd9925b11f2b3f86ba
 94 | e18f47b52ff3aa2452174f43a416bc6f
 95 | 1ad4c572e0fd6a576e1e9a13188ab4bb
 96 | 6081348fd96b21c3eca22c501ad0a77a
 97 | d4e6002f0114461df879b7d55192442a
 98 | cdf33719d80e3f1dadecb2bfe4fe7f60
 99 | 19127cb1f535bf2c62c9e7b595148d6a
100 | 7b927d55b634c4aa178e7d331e641179
101 | 5556112e5f36cf2755f46d55537192b6
102 | 5a3428f5690f57a7cf004563556ddb36
103 | 6c7a2ca9ef6cf7a3ef4e42d70375aed8
104 | 3d2870c83ad35dfe86d53ab0fe94e911
105 | 3f51197359289bf839d3717288022c20
106 | acba82ca76cb0201774bc00c294ec5e4
107 | cb506ccfb07faa60f51f77a6d7299806
108 | 8e42a0d11784c74fc6a5c971c030877d
109 | 6aebdfb1622324617eee615e75bc3b77
110 | 985eb4a8f9914873738e43095496b061
111 | 60d8c707c5f8278e3c8d0fdfb1cc2535
112 | 7b98e7b25bb83413c59350d819542ec7
113 | 2cd30f8ab084d274391fb969ff1ec5ce
114 | 10b54fe832a00c3ec59350d819542ec7
115 | c5212968cd5ef1dc3c6e7539caf3791c
116 | 3bc232700d2ed20b89a68decc32d3e34
117 | 1c898677c5b4291c847857e42f50ec6e
118 | 58b97051fb1efb3b4bd9e0690b0b191
119 | d347f6e236975a6b7c4767a4f4c46bba
120 | 47b069b828d9fae54692707833167ca3
121 | ca9e248cdcca240f11a59b122fb65ee9
122 | 5a6715ef95a99bf59856fa70a578baeb
123 | 8093937b9072e92afab6e40cce6926d7
124 | b1f23b772bfe59c2f766c600156dc40b
125 | 3700aafc0160b162c59350d819542ec7
126 | 5a5e9a046d79bcc7859a7164d38b0d13
127 | 97ff4614190d8cdfff05fff9845ac53e
128 | 7c12c2a7a1957abc8bf788ad2aab0947
129 | 9524af09747661fbe0f91080da8431d7
130 | 54d9053622deb8866ffe0f6a1d92eb85
131 | 7fadf6464f6ba381921dd903dd0b8b17
132 | 297684bcd05347cd86d53ab0fe94e911
133 | 6e5ac40051b3e17b697129c0aef9e5f7
134 | b28d1c49cfe93a3f79368d1198f406e7
135 | 3e858a898accc14132f8567794723a79
136 | 580a7733e55e08be3c8d0fdfb1cc2535
137 | 779cda069c3b6338824662341ce2b233
138 | d7fe9a6bf2c5ad924c62bee40dcdc539
139 | 4bbac921678eb957614319d7d997614c
140 | 77342f11ba666144d71237b3923fc09
141 | 4cbb978cef36a5b9c60fe2650bbe2bf8
142 | 81bef552e83476ad3da27ece6ae88fff
143 | 195b0fd745df898d86d53ab0fe94e911
144 | 643191e8ee56104e424f8f8e828c9ab9
145 | 95ca7e79cf9b51cbb9a0f5d18f1ce54c
146 | 5bcb725e26e521364c7384dbb75cab0d
147 | 65dcdb468234c4f64e2e1b2af0cc59a7
148 | 87708c9ebd845c21854c6e2381cc9350
149 | 26979d498a0425b6f51f77a6d7299806
150 | 14ed803c2251dfc1ec451f73f474981c
151 | 226873c8d34e38286d53ab0fe94e911
152 | 8e9a51408589448bc59350d819542ec7
153 | b13778ff6594e980605de7eae9f0b0f4
154 | bfb9eda1e7f92339800f2aaba8549124
155 | 148180c71c8ad4e3a1bfe809f99d2951
156 | 131992dab1550a7aec24cae3e129c189
157 | 367044e655cdce1f109be8beeb87a681
158 | 181716a7a34f2708c59350d819542ec7
159 | 92c111f0456557c14da5feafe6f1c8fc
160 | c6a306867328d90fe42c2d012c73c412
161 | c00edc704ff4b133da27ece6ae88fff
162 | 73789bb6c0286415db823df37b893ef4
163 | 131072b0a226f05f51f77a6d7299806
164 | 92ef2c5091a97df18a6e1efe1f5fc0a3
165 | 225e398e99d98995b0c71e21a9386658
166 | 8b24699e1351a78ef8e7f2c38fe37243
167 | 9029a5f19440d04e6b19a27bc4c01b1d
168 | 70d390b1e9b3053a22ca415af010d9a2
169 | d5058b014492f748220c986172788383
170 | 4dcec5b89f1e9e4915dd7d7985e749c1
171 | c18a4772bcfbb98e85bc264270ae0601
172 | aac3c6db20d3248579cea75b38cb7ce
173 | 1b92b53bdb962de337aa612844f43db0
174 | 62e1a04718635c981c7fe5be55ca5cfd
175 | c66e77615d80399466e506c113d5d05e
176 | 198cbe57b01bad9dc59350d819542ec7
177 | 82f7946adba23f5f1c6beaa592f1b2c5
178 | 60ac3a02f8c1116b5588a2543ef0b0b4
179 | a5f28af83eb1dfbc3ffd072b23bde58
180 | dc4affd586bafbc8d45f502ecff9e44f
181 | 13aeab12a8ccdb244da5feafe6f1c8fc
182 | cae4ad6aa7d0e49df160c00ab31497df
183 | 886031ff2a514f86c59350d819542ec7
184 | 23aeb8fdc0d1ed4c4da5feafe6f1c8fc
185 | 54f801646e066ce92afc25cef0918375
186 | d4a7b45abac7a39c59350d819542ec7
187 | 973023bbf9c6a603c59350d819542ec7
188 | a268283b0fab6092eb835f4eccb92a70
189 | 941289c22ad19099a87002a4eeaf610
190 | c4fd6d64caa1e371c59350d819542ec7
191 | 8504af8851175efd253d6f91951c4f58
192 | 44d195279a116e347eee615e75bc3b77
193 | 1d442f753e2d7d3cb90e13b20a8dfddb
194 | 4c44e4124118a2521e4b67452ae5160
195 | 743366dfb72897be1ba9fd11dc8bf457
196 | 11f59587596e3bf1a9958063063ce065
197 | 1459b403c084a33e7694593a26340e
198 | 1e200d34c5555634c59350d819542ec7
199 | e16c0191973a25f02d63c890dc92b5
200 | c99ec52d66a6e89c3c8d0fdfb1cc2535
201 | 40f90a159f03321cc59350d819542ec7
202 | c1f419412a6960a27775562146ecea9
203 | 62f5c85919a21aee7868105076bde789
204 | 20d92bdc128be29c59350d819542ec7
205 | 3b307c9b473270a1c59350d819542ec7
206 | 533ca24b72a0552c5057ad0f363d6ddd
207 | 4392ad03e7d769a6180dd1b6c5060a26
208 | 77d1cf70e480af7e6a400d4015c42de
209 | a1f901768250762d4f60f15da4c665d0
210 | 59d2e972374292c19dadd90fffe49008
211 | ea48a2a501942eedde650492e45fb14f
212 | cac3d104981b47cd3d113b8340bd5029
213 | 1e18f136798cb3f0c59350d819542ec7
214 | b37d269e1ec64992ee71ee29c2167097
215 | 11224ef64e1702b412e0c474ff07001f
216 | 3d5ef34ce469b11c5af597c14b093f6
217 | 8238404daa0a13bfce5d6e9371bb5c33
218 | 43ed2ac5e1836f5ef51f77a6d7299806
219 | 8488c41b4c17d0a81a8dfe268f567c25
220 | 7eecf98d3b8f93a684c210032662e046
221 | 169d64acd930adb12871cc0b3cc1a485
222 | 1767bd876a8b8c6e4da5feafe6f1c8fc
223 | 11b8fd945de0ee99642f6fb37a230b5e
224 | 44e48c541b5466342f38c0d2792fb5e
225 | 1e73a722906872b64da5feafe6f1c8fc
226 | 1f674f735abb7b1d75869f989849123f
227 | 721bd0402e92e339c59350d819542ec7
228 | d17b46d9ad9378209c68640456c0e
229 | 88a1a68c64ef85394da5feafe6f1c8fc
230 | e2d06603fba3bf3310af74324aae27f
231 | 227d258c1045acbe9e4965f0106e00d9
232 | 23e3c2a2f61ddb2986d53ab0fe94e911
233 | 47fa0f6c9b9f019742cc639a26c5af8c
234 | e22f10f551cac7fc6cb99ff1a702c4e9
235 | a477a301e1e1a67fc2185cc0ca1b306b
236 | 21224eab2d099f5012de5317fe5b354f
237 | 636c4d449f17b6a8b47cc2471d9dd7e6
238 | 17ad636e45c233bef79e00aae9a7dcf8
239 | 484aac3c3f3ee4aadfcedefd655bc18c
240 | 6219b46946f62474c62bee40dcdc539
241 | 9b1175f3e0b7f0938ab7e957399ebbf0
242 | 7c68771e303eddc16adc061043e7c712
243 | 3ba62bcd5394d5504c62bee40dcdc539
244 | 5f7e3d694d47fe6cde650492e45fb14f
245 | a64be5342dd3c9f782ef94da039e491f
246 | 721c788bb55b083ae8a9bc001231a118
247 | b154cb1a8dedb14345ef69cff7e6d57d
248 | 323c85aa6d1949abaec7b0e2cd000db4
249 | 5906bfad8f6d794f490ad276cd2af3a4
250 | 353dd8c418146de16c7d1f675f2a04a5
251 | 4e02dea48a1bed6bc59350d819542ec7
252 | 187f9c840611133b7fa41e06a7f4a88
253 | bd2bcee265b1ee1c7c373e0e7470a338
254 | c129e7434b33f3cf1b17743c18fb63dc
255 | be7d2a1a7fa7ce0b11fc2b865c2a185b
256 | c11449b64486b4df4240b2500b599345
257 | 1b3d4f2291545e472dc6c96daf8fd5ea
258 | 422975f531854eeaf36ea1eb6542fe7e
259 | 3eddbe968ac08030c59350d819542ec7
260 | 480a381b676003df4da5feafe6f1c8fc
261 | 5366e82cfca7382729f1ce9399524695
262 | 4f9b95af6720c7fc11fc2b865c2a185b
263 | 83412e29d5978b101f6dfedaba98d5f9
264 | b7be75d3cb83457a44221bef0fa3c36b
265 | 76271327a3224e56c59350d819542ec7
266 | 34bc619e8ab3c0d2a93db6e4c0c75191
267 | 956c437be87a2be5f51f77a6d7299806
268 | 45c91d543ef3c1a829a50a2b3c5e5b6
269 | 45bb41433302f3f5490ad276cd2af3a4
270 | 7f416248bb57f1c0598f1102685df4cd
271 | 7ed5c429313f20e079bb09dc5605a57
272 | 54c4eb19c59440128f7c4148465d43b6
273 | 1919dec93dff59e0ed3ffec8035a48e8
274 | 4d9152d6df9883529c75eb4326997fae
275 | 63f3ea0c41eedd19f51f77a6d7299806
276 | 1fc8231114fa42a7c59350d819542ec7
277 | cd3c926cf4ae4564a80ff03f6dc10926
278 | 3d21c803cfa3bf504c96d44e0e286fe7
279 | 90b901d37c751841c93205b4771d5663
280 | a593528259cf4d78c0f947750540fb22
281 | 70b15dbfed77ad2d4da5feafe6f1c8fc
282 | 7359539c1b62cf1e29a50a2b3c5e5b6
283 | 4298f678b53d370dc59350d819542ec7
284 | 97c6b3099a406960d3dad974dc098fa1
285 | 5ab3129036e7b69e278d386bfa54545
286 | 3b98711b877ae402824662341ce2b233
287 | aa28deb4dd304d12f51f77a6d7299806
288 | 18d84c10a5068315fe5c8ffd0f5eba47
289 | 7470935c77e340f31781dae1261f1d28
290 | 2dddaf7774fd11efe4d4a3bf05a8b705
291 | 3a0492e3892bb29f12de5317fe5b354f
292 | 600d06bd779fbedfce5d6e9371bb5c33
293 | 3c855f2a52d5e3f63c8d0fdfb1cc2535
294 | b99b7673b0927283b1732c7d45a02ba0
295 | b29de5206eb16c146ec91c2f4565a1ff
296 | 5b112266c93a711b824662341ce2b233
297 | 92aa3075799e275a3fe047712e43e185
298 | 5a639987ce024c8223dd83e725809894
299 | c8631f63ec5899a4a84a884e8267301c
300 | 3b5d7b7fb89b178d50711e66b0db6ed
301 | 4e31ddf3828a40f3cd525309aaf63a44
302 | 2d2ce6dc51aa6c7a9856fa70a578baeb
303 | 12de47490769694e490ad276cd2af3a4
304 | 39b51f3a6e8447c3c8a1a154de62786
305 | de23f702d6e8232f12de5317fe5b354f
306 | 931fcaa08876700e788f926f4d51e733
307 | 31a142710610023cf51f77a6d7299806
308 | 50f0ea68b77810121fbac718728a36d
309 | 6bf0f5e06cb748bb9671c58246946ed6
310 | 4a2848db82ae01f7490ad276cd2af3a4
311 | dd7e681525a458befbfd931924135513
312 | 6ab14d89360d0a55ff3ea34d08547895
313 | 809d5384f84d55273a11565e5be9cf53
314 | 19dd35ef180808c38f1735145fdf5c5c
315 | 8cfbb0ecb20361e8a7cb178ec63a7c4a
316 | 


--------------------------------------------------------------------------------
/splits/content_car_test.txt:
--------------------------------------------------------------------------------
  1 | 1d82316d98f620513b86a9df4269733
  2 | ac85727971fe63dd2c67ef33d7521ade
  3 | 53275362ba9169cd6823e5923983562b
  4 | 9e6156aea0c7e60ff7d6fd2038bf9a11
  5 | f8dace6f0c680fae994a3466f8481f8a
  6 | 66ce9fa1bb4d0f9647bbce29b0af912f
  7 | 5e4a1ac9bdce2766473f10e6caaeca56
  8 | c40530e1501a61e77fd954b0e9af4719
  9 | a5ffe1d14364b4df6758a098566bc94e
 10 | 73a1fde5c6a697a6f2cdad303f49c9f9
 11 | 3590916b8ae2fb069b58a6529594c9d
 12 | 9b4324a33b1dbad5a7fd25564c2e888e
 13 | 4f4fd009511b0046ca2b6e5474aad11
 14 | ee351351829c40a1713566bcaeffe8b1
 15 | 81977e8322276869fc82e75321e09f82
 16 | 1ef1be2d62d35937f3efc94c2d31dc5
 17 | b5b7fc2cb1b05d9558d0cbae670ea6fb
 18 | 598f0aea814b1d0f8db98a39370e7faf
 19 | e7f40f595169f1b44a383db4764d5432
 20 | beef4a450e0d42db6436916a86a90ed7
 21 | 59e01fab310fa8c49c9f1f5abaab90a7
 22 | 82c89e9087b8914487a0bb8e3477fdfe
 23 | b67d3833e6991de8dd141480e2c154d3
 24 | 80bdcb908765eb9ec349f2dfac43a4cf
 25 | cb0bffd770644cebcfd826dd468a5497
 26 | e84eb770bb6cedf3bda733a39f84326d
 27 | def59064b72eae5c51cd90e1c7c07656
 28 | 3a48188e012364f8921cb81cb1632a5e
 29 | 16b8c04d29bb4c36b11647ffa4306609
 30 | 5621ebf65ffd38468772afa45900d07f
 31 | b7c5675941f31772dd141480e2c154d3
 32 | 384ef23998d85acd09339126762200b
 33 | 7e7cc90bb7f265d2b3cf5236f651a8e6
 34 | 6567850b0333f4242ed04845a2288fc7
 35 | c042ba6094f443aef0e9d883f1686c11
 36 | 902295bbfe5de7fcde60247b99319a4f
 37 | af700f912634995d6ef5d432e9b64273
 38 | aff67f837a958d2329984c4afd2e98a4
 39 | 678113ed5e1c6463cf9effa1a9fc966a
 40 | 64f940ade3f61f976a106c3e1a10b659
 41 | 39e10c5d24fee4a6311f5d9a1681aa3b
 42 | 88000bd0d8997374350937622ac92802
 43 | dca1e82e7d39edcbc2c2c81e2232aa95
 44 | ffbebc7c9a32a6f88ec8762dea278247
 45 | b3047118a9b0d7b7e858db1dc3499392
 46 | adc523202de4453e5df3c6413d40ccb2
 47 | c5bdc334a3df466e8e1630a4c009bdc0
 48 | 5a5f53455c2b400579206bf213559607
 49 | 1f2d26228823865040afd70980e6f6de
 50 | 32878e1bb56b9c0c23a72fe560e6753
 51 | 1591e215a20df6c7117db354abf0d721
 52 | 424828093021681bb2d73c0334653f3
 53 | 7e7b757052225615a73f47f4261c01dd
 54 | 4a423ae9a28afe3588cf40718544e7cc
 55 | 63cc90709837d314a0b2db16370345f0
 56 | 1ef9fe56b60f13a592cf90fabddd34
 57 | 92ff3c7b2b8b1f65e2693f33cdca907b
 58 | b7b124abe2e1934a5906e84e28bf5c23
 59 | 814da920eec5f79cd536c1ebda275556
 60 | 7e7e1250be2220dd6f635a241c2779f9
 61 | 6c85063bf5e983a3d14b144052416695
 62 | a1e3c4be68cfe110d9e74b7f1cf9cf3c
 63 | 282293948b21262769416db9b743e50b
 64 | 11797258eec3e2b3becf71e2e014ff6f
 65 | 48137fb4ba65d1b161cca2fd9af9f2
 66 | 40313368870df2c0df59ad08996c77e8
 67 | 9e4a79d30930cc2fcefa74f1d0bc6e6
 68 | e75dcc7eb0a60728becf71e2e014ff6f
 69 | e3353ff3fe13530a3f561029f6f1882
 70 | beee540876a0595453597987ab560f7
 71 | 532debbcb814191562660ac8e5aff4c
 72 | e7f01820eb2b9703d8d78955a8fa26c3
 73 | cf88ac755b07beb2becf71e2e014ff6f
 74 | 23744f1fb889cc623406fd3b2a45eff0
 75 | e01a56af0788551e7aa225b44626f301
 76 | 133dab9b251c660c95dfb5938922dffc
 77 | 52b5cf28f4e7fdf4bd238c115e381d5
 78 | ac813039f9a4468ccc777d23edf2f8d8
 79 | 83c31a4085063873dc2afbe43bc71afa
 80 | 34080e679c1ae08aca92a4cdad802b45
 81 | 420d1b7af7ceaad59ad3ae277a5ccc98
 82 | 92c4d4bcb122509aafe1d4530f4c6e24
 83 | 52cff656189850a2546b7395fb17f97e
 84 | db41ab1176360b20314b3b3dfd6337f4
 85 | 4036332be89511e31141a7d4d06dc13
 86 | 61db814bcb47f4d462b21e1bf23b9ba8
 87 | 6482e3afc2664e32d30f2d8d219e111c
 88 | fee1c13922c07e8711b978ff9450f61b
 89 | 7d91eb0b15389c2e53db534e9a1943b
 90 | db8eb94d24f5d8a2350dd0b332d84c76
 91 | 519659d844cf11337edbaa01196a55
 92 | ea4717b09d76cdb5becf71e2e014ff6f
 93 | 4ce77c92ba3f02492f20449572a3a77c
 94 | 9830e235b36af83c11929590a64583e7
 95 | 7d4c3d9795570647657231d17e42d06f
 96 | 42af1d5d3b2524003e241901f2025878
 97 | 20649c88556a7e7a113ef105f1affa3f
 98 | d9cfad911b26b2ae5690f18c88ad5b9e
 99 | 16bd0438de54fc91b1bb46d2556ba67d
100 | d72ffa185738bccd10b75223b5be6dbb
101 | fc12e9e55775982773178d35912d681
102 | db7521a619133bbb75c67b3b1e763fcf
103 | d3f51c2cc6fbf9a52f20449572a3a77c
104 | eb9569bf211fa2c7774e0bc2f3636d5c
105 | 9c686d6ec470f280473f10e6caaeca56
106 | 2dbd3e61fe27cd29bddac102ee6384
107 | 42ca4f6a7d7a39712a9eb0f146e94477
108 | c7205c6c657daed1ecabc5c9d5c21b7f
109 | 10a2f8b85837b0792db5437b4a62726e
110 | dcfdb673231b64ea413908c0e169330
111 | 55920977ea8ef99766751c4836bbc1b3
112 | e866dd4d4bf1f1f5bbadf8db57668863
113 | 5539bb3a770f16235df3c6413d40ccb2
114 | 99606d5346d6b958b96244559b61fdc2
115 | be2aea85e882c0478864662c562d8c17
116 | d353bf0e0dfe3ac29cbc1c09129e1507
117 | 9d400df8825de9a62514ed2901e978de
118 | 8066ee64f5f55f482f20449572a3a77c
119 | 3cdb021c923034c68bb386c7dede359e
120 | a34e74fbe12455e6becf71e2e014ff6f
121 | f07872a3ec2de596e565b03326f48ebc
122 | c76c5d215cfd21cdee10575a68c30871
123 | 721ab64719c7776cd76439fb95cdd2ed
124 | 5057c9dbf72e0352728fa2df514c65d4
125 | 3aa2193b6aefedcab645cbd2ed3c0201
126 | 3217e41f424ec403cfd1806414cca1fe
127 | 90b7b3e20cc687439f3966b50b3410ac
128 | 982313fa1f00439d66fb30f3a032a687
129 | 6ee9f222a540a905e4b68d3b17c43658
130 | 7b01d9b011361e82a7fd25564c2e888e
131 | a2b3346bf52d4d5acee5b7ceecf56d71
132 | 154028cc3c2b4846436916a86a90ed7
133 | 3db1970109895e82994a3466f8481f8a
134 | d581eeadfd6516fe6ca2b6e5474aad11
135 | b1c6a021c1c47884c9463ecce7643e8e
136 | f48dcef252683ce552aa494042b7c9db
137 | 3f702ea027037a5c4d18baf048fb19eb
138 | b9961e33ae6b89ce7c822e99037988d0
139 | b05b57c8a3e850675dd440bd17e9fc21
140 | a9ae1558ff25e5336436916a86a90ed7
141 | 23a71434b0bdd5daefdff89bf9a96890
142 | c5f77a00c9cae334cfd826dd468a5497
143 | ad6572f7ac90b9bf2949d5274e5ab643
144 | 34ab29cea66952f16f48edd113a40fce
145 | 144d0880f61d813ef7b860bd772a37
146 | 7dda076e4954a77d10208e642eed2b0
147 | e93e6ab2f933108fc1bcae9def1986da
148 | 8a2de4054a94f861b3665e9c50491c68
149 | 1c4f6c884a2132903c35e65001c8c258
150 | f53fa6e25b73464f1ccbd9e5bb82dd04
151 | 63eb0b19046ca3b3b75fada7412eea14
152 | d40be55005dd4cb884ccdf529614144
153 | 38f323fd119d14ed2a9eb0f146e94477
154 | 1c8cc8dd7b2d9671c7709b125ddd3d3
155 | 15189ac0d9a6364819d0b04fbc21ff71
156 | 18f6df600df7341ab0bbc6f39febba97
157 | ffb4d9920493f1e5c29076ad43b687b5
158 | 1e58b82b7c7c93b3e3e80cf56a92a302
159 | bf652fdb40c4cb3696ab9df3b3d7537e
160 | c17e88a6b0267754c6529edfd0032791
161 | ab8b6d39057d2f6cc86779a6788ad464
162 | 8606a6353a2c0f7a453660f3d68cae6e
163 | 787a38da42c2026ec29f776eec462c6d
164 | 402d1624e1c28422383a5be3771c595c
165 | 97d0903cf8912c3ee9d790a68c844819
166 | f6bea4a1b30019e5d536c1ebda275556
167 | 6f0213221b4bf95c76da19f6bf9111ed
168 | c0788f1b9f5e1021c8f069d544d87324
169 | 30f0ba361010ea11e66cabd11ba41eae
170 | 8b22da6bba6c81452af3f274e91bb46f
171 | adda68ed2da5cee0a413908c0e169330
172 | c471061360f96647e5473a1847c01bcc
173 | 5afa428d6f0e23c66ca2b6e5474aad11
174 | 30774e3218da1f793eccc98914b46c47
175 | 2a554a704a27618ea37f3fc191551700
176 | 10d739b8d5177373f9e2707a51671bfd
177 | 79d684368c596b4613f9826aa0cb4736
178 | 33ce4837f282443258c27e607f6e2d4c
179 | c09758b6e9b42f4ba475e6ef54b0629
180 | 26b49835f02327b283ffcfc40c29975
181 | 9110240de5959a18b1bb46d2556ba67d
182 | 59fb4af10a8a0f51afe1d4530f4c6e24
183 | c44111ca55c697117fbfaeeb4819ffd2
184 | e1d37310f0da90be8db6b792a14402eb
185 | 174f1a421f652029d577c0ac53e96823
186 | 28aff1e73c832dfb3ab3dfa44f5fab01
187 | b76a9630c1d091da28044fe9244db50a
188 | bd6faec75bdd897fdd141480e2c154d3
189 | 57f33e6592637b678db6098b79d0204
190 | 978c0630f12909488acb0ff76f4aec7d
191 | e16d445578df1e96ac170667112ac32e
192 | d4efeadfdc244c7a4f934ace9a84aad
193 | 5c1784ec446d4ed7980d9863a745964e
194 | 492f36ac59d2d3eb450d7227edc25975
195 | 185059ee821245d176fb25377c3b547e
196 | a2fa0bfd39718f1688a610ac9b7aaa40
197 | bc819b418e67de4c5b10a3a01ac9b9e9
198 | 67e2f8985a28e895a592cf90fabddd34
199 | d6cc74b295d53ff88e763672c0b69b5f
200 | 4476d77118a78261898b91227342b00c
201 | 706671ef8c7b5e28a6c2c95b41a5446d
202 | be5d1773e31df6ef3b91d6baf18b2c46
203 | d4251f9cf7f1e0a7cac1226cb3e860ca
204 | 12b5e4f52c22b348d8499d8846cb4c3b
205 | a26b62fa78e9d6e016abce8cb03e7794
206 | e619129ae2e1d09884ccdf529614144
207 | 64da6ab5c3c61fa028044fe9244db50a
208 | b74d374b48da34918e68390f6e0f7861
209 | 8c264b10c4ec3e91fdeea60824a43a0b
210 | a6fe523f0ef082a2715e04edb8af9c53
211 | 9a858d1ad259d78a9f0a810e67f4b065
212 | a3d77c6b58ea6e75e4b68d3b17c43658
213 | cce0c3ccaf38bdfc56a612a99ee3c15
214 | 97a6deac8b48b36a84b1aa0ed7e58be1
215 | 4b94cdc9c703d00fef3ecc8551d2c1fa
216 | bf7942e357e5ce78c1006ed55bc1a3fc
217 | 2948b8714d3f04fd994a3466f8481f8a
218 | 9cd875a215c8806731b76be6623555e0
219 | eebbce8b77bdb53c82382fde2cafeb9
220 | 6dbae14e481e8fb9333e0bf0b765fa12
221 | a836fc66c01eccca58c27e607f6e2d4c
222 | c8d8089dade71547d2350421a9405ba
223 | 5e785208f01fd016e4d0922154a19a3f
224 | 491c8e8ffa331de926a979740c8db87a
225 | 334d9cdc7c131c5dda56fa14148b39e
226 | 2b766a7abde647c7175d829215e53daf
227 | f3cc275529cda8ed491f8306791ee291
228 | 14c1c507d0ae6243673a614c45f3afe4
229 | e27019b4147f868dbda733a39f84326d
230 | bad0a52f07afc2319ed410a010efa019
231 | 8402d2237afac94a1cf6f8e565096a1e
232 | 38bfc6bb7040291c5af0a602ac88f0ca
233 | 8adaa9c4905bdc38fa0be250bacdbd93
234 | eb57b83549b6caab83653a771e25099b
235 | 355e7a7bde7d43c1ace5721ccacba16
236 | 6b6ef891b8a762c7bd1a651394a2b403
237 | ca9a4a00209632808acb0ff76f4aec7d
238 | cb7afc22f6e05c694d20830118b0e051
239 | 6b642c1c62ae5b49247a5be450795511
240 | 6283a8fcea4976fe47bff85f09fd66b
241 | 74b37c2f88e0ef7a469bb3d27ee3bc4e
242 | d6508cd7de4aa1d96ca2b6e5474aad11
243 | 39a1c850493d0c991059003d2120a559
244 | 294b9a0150636c6796adde1bbd7dc66e
245 | 1f33e1dd21cbe3e882b157e7120744ea
246 | d443e86ae023ceeb16abce8cb03e7794
247 | 6624f033e57c30ffaa9560d04f1c37f2
248 | 4c2c33070c6597ca9004afc0d5dfd164
249 | d776d298be6bfe88e78002a96f52ef26
250 | 9672e9c6633543cde2e594e71066f939
251 | d7b8287ca11d565bd9bd5ae694086d5
252 | 873ddf6d4184ad75c4009bb5fe8354f
253 | 115c6d4da251cbd323682a501e6a09f5
254 | 5ecc0f81e6bd433159d722310a2e912e
255 | ed3a8c51acaa49a7becf71e2e014ff6f
256 | a40a32989c8f81674f53b3809b43201
257 | dc967b353db71ccb69a949ac99a843c4
258 | cfc8e5925bbec93de20af544ce47dd47
259 | 37862f8ab50f1dda6108f064aff2426d
260 | 736505ca98c67ea187dc1da2515df8f7
261 | a2bdf9ef8f45cb485af1f3bd6522cce
262 | 17d3fe6fcaa66dc75bdece2095ceb985
263 | 7f6031f1738d52546436916a86a90ed7
264 | 3c46617db70c57fc2b12ea83455b0f44
265 | f70df58949dcb108b682148e4ffe282d
266 | 8500e32dc88e2c1211c80a762f8034b6
267 | d46f314cce93291a9304918f9368d23a
268 | 46549c511f8af42b589b835e458be15e
269 | a062af31eb72d882713566bcaeffe8b1
270 | a5464210795a915f9aa6f213afdff14d
271 | 127b9ba77b54ba59bda733a39f84326d
272 | 413c5de93bf213ebe2a08ef407c557a4
273 | 5a728c7371f8fa3f1e0401312b984eca
274 | b92152f5b04b4ceb5572c7a61643e6cc
275 | 16cb7990169197465c46d8051f2293ec
276 | a838af854310e283e8d78fb938bac492
277 | 8766f33b2b8c46591ccbd9e5bb82dd04
278 | 6bb14c1083ed44f5ac34b841f2070767
279 | 523673c5b3c12ffcf2c89d2df097ef4
280 | 1f5cdd2022a18d13958806394f060dd8
281 | 476c324967045e798e4c384e22527426
282 | 19042f5a90290859441c11ab4641b257
283 | 491653e537f1a701697b84068abf146c
284 | 88a476c48a4cb5e72d0c578824da8af5
285 | ba7a583467ff8aee8cfac9da0ff28f62
286 | 78bee16fc0bd57ddaeece2324fbbe339
287 | ad5ed790c2f4ddab6f4494de9bc503b9
288 | a1a117f7c2308027ee87b00f75d4f7b1
289 | 43fc1f432d1408cc8e35db9103756ad5
290 | 1feeeaeb8b56e46d2dfaf88f42097063
291 | d8c7f76320624fef02d716c401defb1
292 | b3aea199d8f8945d3c8089ca2f2a9299
293 | e7f8315a2f31d759ac4c8b51312c5a77
294 | cb9577139b34703945e8a12904b50643
295 | b871ea607051b62d52bd19f7df1b9c3c
296 | bf0e8d944ba4843e94e7e8e27399daf7
297 | b0f1e8e11aea5f622fdea40a56b4c57d
298 | b27c818401f48e5220453276fad563e4
299 | 287f4c8f87099957473f10e6caaeca56
300 | 2525b83c84bd3afbde2d51ea8231791
301 | aaee51c78fd20c933343f5fadc4a2136
302 | d1a54cb41a88702b1e8e2692714b2614
303 | af92a36f12e4a9b3afe1d4530f4c6e24
304 | 8174e81407e5ecb4cd0ecaee692643c8
305 | 9b86104ecb0ca73e96db382b382d7132
306 | 58a94c88c3a2d63f1eef55a19490162
307 | 293c7cf5fdde18258acb0ff76f4aec7d
308 | 7c5e0fd7e8c62d047eed1e11d741a3f1
309 | 53507d1d09b3c2671cd97374110efb0a
310 | 1b5b5a43e0281030b96212c8f6cd06e
311 | 4189308a712f05fdb34c54631e616d02
312 | 83db7e16a49191e5ed3696d854eee1ec
313 | 2b800f158324986ab6f657757c95f74e
314 | c197b7bb2d1cbcb79393793f9cf3dbea
315 | 83e5b5a3f3aad942ed29cc2a32e4bbed
316 | bc5f38eb01d965296436916a86a90ed7
317 | ee594be09a857234c9789b2cfb3d252a
318 | db5cb3184b75869a2f20449572a3a77c
319 | fb2d87d2e87ce30d39eb14c85e78fed5
320 | f8430301702e9d826b3000771d5e1507
321 | a4fc879c642e8fc4a5a4c80d90b70728
322 | a2f658d639f46d95c6d2c2010c35d0b9
323 | 85f0d4c31c765f33ab91fe0bf146bca2
324 | 965ff4a5472d5de4d436d4e00775800d
325 | 386717b69af559e2f64801ad2940cdd5
326 | 5b3fe515eaa63bcc53023beffe62cd72
327 | d80658a2f50c753cf1335b4fef92b83f
328 | 207f5bf84fb3b8b2c79a93f53094419
329 | c6b98edfbb65320654b49557f8ea8b42
330 | 8e8da02ac0168a47ec5e3fe5c33367cf
331 | d2729f80a50ea6e097c3059866f88164
332 | 944c277b90facb6095e00c8f4e50aa10
333 | 1bace29924c0ae42226fc3902f16303f
334 | c49370c0bdd301b6c1edc4b12da3351f
335 | 2ef2030220a4344aa70efe34ab035886
336 | b6749c2b917d4aad949b12cf3977a48b
337 | f2422eb6b55e8fb0ef3ecc8551d2c1fa
338 | 1cf3a0122ae9d45afe58aa5d5c441132
339 | 7f8215a98cc3c85f8cb4f1ebb26942b3
340 | 50840e502ec2a45aafe1d4530f4c6e24
341 | 949f6240e1a760992dc53e2d2dfd58d0
342 | 75999f32d196b4cd2b732db1e3f3e1c2
343 | fb20b20452ef661f500cc506a763c18
344 | e00169580fda5461473f10e6caaeca56
345 | 3c33f9f8edc558ce77aa0b62eed1492
346 | 97b9c8ae37e6480e1912cbd26ffcad1c
347 | 7197ec7776d4e23f10a4b3894aadc04
348 | 85d04dc3f455bc56ceb5044e1e1e9739
349 | a0775d8881a5cc9d6cc452b5c35170bc
350 | 9986dd19b2c459152470de2774d6099
351 | e09813b03bdfce83a23218adb697420d
352 | 19bb8605a7a5233e4d7ac55d461d1984
353 | a090de757a54b8ec76660192031b66ca
354 | d6390f62d9e036efb1bb46d2556ba67d
355 | 94edffd805dc965ca5626f7e1b38f05f
356 | 3046e10fccf226311ccbd9e5bb82dd04
357 | a55f4932b0f8a212402257734064a917
358 | 12f268aac77cf8d0b53aac92d2311d0c
359 | 1e5e9a493c235e6d6a29b9f7d2a0a0ab
360 | 2acbb7959e6388236d068062d5d5809b
361 | f3a62e5c5aa8b1b1994a3466f8481f8a
362 | 147889b73fa491d82e877e82c90c24d
363 | ccca16b8302bc8bd13ded1857c15b5b6
364 | 8f8bd59f17f122a163739f01ec1d22b0
365 | 691bf14434c590f212a6200f1680863
366 | 3027c4594df09e5a15b5ce4486462d3f
367 | 5130947e5f18e73a8321b7d65a99d2a
368 | 1937428085d6940586496b2471eea4a4
369 | 5e64716e967db18663f2c3a55558a78f
370 | 48debbfd63725a743978555bf44cfc9a
371 | 4c18a991c14145108efc69f75162eba1
372 | 56b6c950f4c5de80ce27281f3b76d1f5
373 | 47248420e5ad5dd35143c7ad6c4b9568
374 | 4856ef1e80d356d111f983eb293b51a
375 | bbd4299c3023cbb18220afad74944c73
376 | a50a46d3423e7dcad1eb2a2149d13665
377 | 8922c6c3435f16fee694960c91796f38
378 | e10761140d22916243f0e92e826556b8
379 | 89c7e63c3d3d14aa17b597d473206848
380 | bd465877e3d5bdd1c2e8382c9582f1a0
381 | fa234addf8fe4f7fbda733a39f84326d
382 | ba82ca69f15ff6b06433639beceb4d1c
383 | 5d55e460caabadaa9ea5c205086e2a63
384 | 7d900d0c1121f78aa33babffbf9bba90
385 | ee2b541ccee732254c938921b509ee11
386 | ca516a534cc87f64804272696dc83193
387 | eafa5935e963b0035e875676652081cd
388 | 23ae5d6c60ab3f60ee3362a8d2d8318f
389 | 7f751d456e9b67586b731f77d8a60d
390 | 7456ed0a5f0ee2568d1d8dcd8a5c99d4
391 | de835b509653b57885089a13cc567dbd
392 | 2e6a9622bf83f04c38ee77d0178bbf4a
393 | e55d80548463a189927caf2ff655be73
394 | d7bbdc50efc0c9c942fb9eaeb1c30f95
395 | 7a5488ed51e904df6f4494de9bc503b9
396 | 1964ce6c225fb1a5994a3466f8481f8a
397 | d644c3bdce6469d6cb8a89ce9e36cc57
398 | 4b841ea5b31090fe2bc9f17412005422
399 | 5d0657969d668e925546801c78de3e1e
400 | 38bb838058c7094a555e6aace4595727
401 | 3587079f3146273faf8b8a34d449f60b
402 | 8df9feeed8678aa6bdc56c6b6d74b51a
403 | 982448cbcbe56bb78f89cf8d2f8a85b0
404 | 835d8e35119c714bfdb3ae79bdfd4e2b
405 | 8e329884cb842e932f20449572a3a77c
406 | e9bccdd7a52f13329b3f352e6fa9112e
407 | 2ccaaa66525d7f095473e57e894e0ef5
408 | 56a6337ad47de69861fadff3709a130e
409 | 2186810da622f54dd599af4df534a14d
410 | b0fa729f031a97d2c3c561b608f78503
411 | bf3a6e3f657cc7f97aa5068bd213d3b5
412 | c797f54484f7240b9b58a6529594c9d
413 | 8a1c8c516f48b0f3becf71e2e014ff6f
414 | 2b0f7206f871bed39f1ae0afc11c9394
415 | 61645b21c344e22a65dc1e664bdf2e6b
416 | 2a3ed077120c69addeae19b6e682da29
417 | 9c06490e82e122093f599d94ae17ce2b
418 | ec82b3c468b05ecf51a95aaa6caba1d3
419 | 2dcc5ed5780462da124dae0a32996c4c
420 | b7c78b4f5583bde74d715d740bd5ebb4
421 | e00fde4225d166b1ce929ad7e848003e
422 | 328cd076003d1b05ef7b860bd772a37
423 | 57408b92b6f1cba6becf71e2e014ff6f
424 | 3e59d4cf6d27e606c3ca60fdb6f83ff
425 | 6e651b2230b8474c2de77cee5dfe5031
426 | d45b86de9175d1c8becf71e2e014ff6f
427 | a4548c56bea7f927ad02214e86fd5091
428 | a8374f1047c30fa976da19f6bf9111ed
429 | 6cbadb3a39216f12ac6dec6f3725ccf
430 | e60598d4462b852411fae996ae9899df
431 | 7ccdf7bc2af0b068e43ab89cb5563740
432 | 768ea3241699f663f1cb19f636b1c2bd
433 | a82d4faae5475ea9f78a1a0fc1c3959c
434 | 6d79f2cde0340b5fbecf71e2e014ff6f
435 | f85ec444c41c3bfca4c57a1d7d6f4262
436 | dce6f59b6ab987d4bc863bdef4e7bdac
437 | 5800508b48a003f1cc586fd80c02025b
438 | 3461e7287b54eded9b4810259f1c2e3b
439 | b4ea44416a06834af200a72c9245aee7
440 | fabcb04fc015f822ca8bf2993ca245b
441 | ca51679f2a92fd04e76ae2a9f743575b
442 | 642b4f6a2ce0e388284432ce2f42f498
443 | 1778fb4a8eebe3b7a3018bac44737f2c
444 | 29fa33a3950ab6adfc262705c0432659
445 | 40f160e49a6d0b3b3e483abd80a2f41
446 | 9db66f6fbbf6d7d92942fa3063963cb6
447 | a0e9f02baa43461045d0de17435a34c9
448 | 95a6e03656bdff26f69bc9777f9c3c39
449 | 6d619fcbceaa0327104b57ee967e352c
450 | 2d817a6f23d35494d991a658ca89186
451 | 510df40932e79779a324deea8acbeebe
452 | 541c39bc70f526ec1059003d2120a559
453 | f927a65382b9140beb0d54da59ce968
454 | 6be5a91bdd709a42634d30cd3ecea7e5
455 | 1bb6b1ff46096f592dfac2620a0cf07b
456 | 1736b8494abf38ba4eb766e5a46fceab
457 | 6d2b4865801d5391c7b7440780797c16
458 | ecf72e5f365a7a482f9d583ef95487d
459 | 28d7a23b2311b1029dce0c74b747947
460 | ded68cb3b5318425bb164ad50a9faee3
461 | aa16595ca0d7dc91becf71e2e014ff6f
462 | 2c6b14bcd5a5546d6a2992e9465c023b
463 | b76bdcfc277f54007f3efc94c2d31dc5
464 | c43df60f01770cd37481cee66aa2b2f4
465 | f2fecc23f8d7929b9ad3ae277a5ccc98
466 | c487e9850891e1ec2d15396b7bcc6366
467 | b4715a33fe6d1bb7f63ee8a34069b7c5
468 | 4dca2e572dc278d563f2c3a55558a78f
469 | c5ef2eaae2b2d8673cd3add5aad1c863
470 | e00ce2c7cc80e5feafe1d4530f4c6e24
471 | da72b2d00ed2da1c6a5a8dfbc26d4937
472 | fa08d3d2167d2616aa76b8e26c5d935d
473 | d0a5a253cdfc6813fa85f3aff1e2b25c
474 | 7112c1cb9b6461c9a551e6372afde900
475 | ad1a3be29c582a1a111f983eb293b51a
476 | 669974eb491f2bf7f8883e486ec8cb7
477 | 7dac31838b627748eb631ba05bd8dfe
478 | fa26b6b0872af78ac29ffe852f2f9194
479 | 5bb0076c269d5cb1ad19b94b8069bb8b
480 | 93f830e773da90e0179b497eb9b2101f
481 | 6d083701a45fd0721ccbd9e5bb82dd04
482 | 2d6c360e7d8ff4162e603610d34efc63
483 | c1c05c0df6ec2becd4b4ae2ff4c58b57
484 | fa9897315ee8b6ba67789dfcc3262f70
485 | 155066e1f87017c36e966db738361973
486 | 9e78878ee82163ef6e41adcfbca9bc8d
487 | 4f54d7acc33111a56afa0fe12a1de326
488 | 1a0c91c02ef35fbe68f60a737d94994a
489 | dc5b51e73aab8a582bfb4b13c9a95572
490 | 6ad3ccbbf5271d6b82b157e7120744ea
491 | ab76de14b9ad486f2bbf45c09940e82b
492 | c97d198921b3e3b8cbd43b8732e79929
493 | b1736379a44bc475352a2541f8b4515a
494 | 2b5af55efaf27f6e92775927bb83d81b
495 | c721c1e89e68e01fec4be884ee173bab
496 | d832626f2bee7407290fad8e3fdaf4fe
497 | d8f813278a49463db203f960004c7382
498 | 2ec0cde7cf9f49a06f44b8601dfe3f71
499 | c11889acd5f707d9becf71e2e014ff6f
500 | a115d534edec6f89afe1d4530f4c6e24
501 | 


--------------------------------------------------------------------------------
/splits/content_chair_test.txt:
--------------------------------------------------------------------------------
  1 | cc70b9c8d4faf79e5a468146abbb198
  2 | cca975f4a6a4d9e9614871b18a2b1957
  3 | ccc4b5366a6dc7c4cffab2c8f8bf5951
  4 | cccc93857d3f5c9950504d983def56c
  5 | ccd5e24c9b96febd5208aab875b932bc
  6 | ccea874d869ff9a579368d1198f406e7
  7 | ccf29f02bfc1ba51a9ebe4a5a40bc728
  8 | ccfc857f35c138ede785b88cc9024b2a
  9 | cd06d0034224a701fb7c76304cb719f8
 10 | cd10e95d1501ed6719fb4103277a6b93
 11 | cd238045ebff9be59186f15d520c12ad
 12 | cd4fa15a13d7448a14038d588fd1342f
 13 | cd5007a237ffde592b5bf1f191733d75
 14 | cd5cc7a5e50478e82b520984c067934c
 15 | cdc2a53559d3db78febad4f49b26ec52
 16 | cdea84a63ad8c44febad4f49b26ec52
 17 | cdfd278e8b1c11bfc36d58d0f13497a0
 18 | cdfe4ea9d00ce861f77e1de7c7a7b6e7
 19 | ce055b7a4cccc7e182db9fca4b68095
 20 | ce074e18e988a481d082d95e9bd50b49
 21 | ce12614d019f86e840ef1c8b63a628f9
 22 | ce242d5e5e3f4befb13cfeddf8d6bfe0
 23 | ce2982a9b05fef738a075f7da2b32df
 24 | ce387113cca9c0754d33a7fd9c37a7d2
 25 | ce50c6235cf3ad8855afe589a9f09982
 26 | ce60636e30770f9d8193714e438a24d5
 27 | ce8e6c13899376e2f3c9c1464e55d580
 28 | ce8f3a0c0c0bb0b9b20716e5484f7807
 29 | ce935c8e977b8c58aa53a70b14c57bcb
 30 | ce95fa90122dd67e5935ba184b9bc177
 31 | cec74855ee27972040a35da25154231f
 32 | ced9c5eee916cce089c398a8a379054a
 33 | cee98619dbdb0e34c5fc2b846c38d941
 34 | cf09618aedde38febda72093f9b5aa73
 35 | cf1e9c2ae3309c65d7bb55f118ea0541
 36 | cf24fc2d10f8da31283b00891f680579
 37 | cf391bbecf5926ecfe51dc4aedc63243
 38 | cf62f90e75531ac63cf953ab4f77463
 39 | cfd2b4a2c8398220731d11154716a6b8
 40 | cfe139c0e8b8cfdae342bce0d924820
 41 | cff9a523a9e20eaeb40f0ac0fb9a650d
 42 | cff9e23014880e20b2e8bfcc2dfe93cd
 43 | cffe40b41d0162c46b2befe83a0efe39
 44 | d00a7550cf050fb3720daf9b94e7a5a
 45 | d020eee9e094050ad776c08b6a3d0a38
 46 | d0215a0b82661b82496d6322c763591
 47 | d02eda9e00688d71d0c63a304a95442d
 48 | d02fc4ae6bc4278b68c4c9cb55925fb2
 49 | d045654d572bc46f19fb4103277a6b93
 50 | d04d854533d618fbfebad4f49b26ec52
 51 | d07675c29d0bd535580b0de4af0eb56b
 52 | d081ce6cdafa416c8687ff9b0b4e4ac
 53 | d0cf0982f16e5d583178d91f48c2217
 54 | d0d18af5959e613ed3040d716596ad68
 55 | d0fa70e45dee680fa45b742ddc5add59
 56 | d0fad7458cdb5178d3f6d823f04dd65
 57 | d10ed00430a61909793b1150bb246dc0
 58 | d11ee4294daf6ebe492d9da2668ec34c
 59 | d1237422881f4d22ff25b0c2db862d19
 60 | d13eb19745344ae5fb0eb7e753c06942
 61 | d14d1da1e682a7cfaac8336231c53cd1
 62 | d15c94b08b5d92e57962800be79c6e52
 63 | d1852e622204dbb0f4b6538438a0b930
 64 | d1b2d8868ca506f2a248097aeae36abc
 65 | d1c2afb3c53dc7c8c563fcc2752ece39
 66 | d1d9da0da16dbb1a765101d95c92a0e5
 67 | d20de927fd1b15ef104c86562c321749
 68 | d221f07c0921e4d2b9576c1fc1b047de
 69 | d23682341fc187a570732116fb5f6e1
 70 | d239d38424429a9a4626612b5d655dc
 71 | d24f623af8e7da479dbf298bdf3162be
 72 | d25b6ce1b5ad6198dbbc9440457e303e
 73 | d274fc14092387c1e17e1cb731e2fa4f
 74 | d2771921272ad1536a69760cb58e50e8
 75 | d2815e678f173616e6cfc789522bfbab
 76 | d283b1073ceae03f35836c728d324152
 77 | d2992fd5e6715bad3bbf93f83cbaf271
 78 | d29c14f180ce319f71271c0017c27c86
 79 | d2a48ffb6d25f88dfb0eb7e753c06942
 80 | d2b334ad08ac9857c3cf9ae716575390
 81 | d2c465e85d2e8f1fcea003eff0268278
 82 | d2c93dac1e088b092561e050fe719ba
 83 | d2fe67741e0f3cc845613f5c2df1029a
 84 | d30e58a2361785683fb0851e9bc87551
 85 | d311e10015f19bb7482d5f087974fa09
 86 | d323e6d19dc58526f2c0effc06a15c11
 87 | d334e5ab55188d62680876614ed35a7f
 88 | d343f06da03eccf34c7384dbb75cab0d
 89 | d350f40e5f04360565ba78ad9601cf1b
 90 | d3562f992aa405b214b1fd95dbca05
 91 | d36de0f850783d8fd6b3090036b71698
 92 | d36ecfec3f3c18a9a28fdea8831e592e
 93 | d374912c3a9fca96c141a04b2a487fd9
 94 | d38129a3301d31350b1fc43ca5e85e
 95 | d3a958aa302f198b938da3ea2c9e0e4f
 96 | d3bf9df2360f0a56731dc97277e95217
 97 | d3f393615178dd1fa770dbd79b470bea
 98 | d3f4ce51467fb777525211e12d56c55f
 99 | d3ff300de7ab36bfc8528ab560ff5e59
100 | d409dbda0a34a953c9020fbe6b2ff6
101 | d417795442cb0f75593ebeeedbff73b
102 | d43f7db89fe864691e046801e2748f1a
103 | d454f99b99248bf337c99625b0c170be
104 | d46e16509b1c91b3933dc172307a6bb9
105 | d487d3b9579762cb5dd170fd3a296ebf
106 | d49ce87d43cf4c8f1679065e1c457f94
107 | d4b5f8edc72b4676f4175ee3a177350a
108 | d4c3dd37d27afa8e7c5910dd17778965
109 | d4d7607336810a548b95c9b52cba3b9d
110 | d4d9b991ff7d31e8c8687ff9b0b4e4ac
111 | d4f194efb445914e4b3d6a0fb5682cc4
112 | d4f38e40aedc67f779368d1198f406e7
113 | d4f5c3e3eab52d0a3334fb6668ccd834
114 | d504ebe36ddde74cb5e61088d6c054a1
115 | d50c5777a2727679b247f6fe3b8f7af8
116 | d52e7e39bed3ed954f62c7a282978009
117 | d5360f2b0b0299c29b9f2eb77f5e247e
118 | d54100efac3ab743626ced72908b525d
119 | d5424b7fdd031fcdd41c21de8af66e26
120 | d5b909ad5d7c793aa16baf954c1d99bc
121 | d5b9579151041cbd9b9f2eb77f5e247e
122 | d609864ada7d0170278d386bfa54545
123 | d62051da1ac1ef21faf575cbae5008b8
124 | d64c618e8b0c7db73ded7580b6cd3bad
125 | d657236c764dabdf5de9b4b5ce85d50a
126 | d6579d7c278cb9a47f093285855bdfd7
127 | d66cc87c717c15f57f0839ffd260627e
128 | d69aad24d253474dc984897483a49e2b
129 | d6da5457b0682e24696b74614952b2d0
130 | d6dd3de6d6ea6d0b1931ace01cf1b948
131 | d6f2d44c693d2e857062f2d72cde5c95
132 | d708c7ed9201ec45d29e20ec5f479208
133 | d71d9d23d786cc8dfebad4f49b26ec52
134 | d74870729fb3e3c5aa0a75782a86b0f3
135 | d75d41af68f4bf7f9af4053b8815b239
136 | d764960666572084b1ea4e06e88051f3
137 | d792c65f8b1710709b9f2eb77f5e247e
138 | d7b22da1174eade770bc652a18e29c3d
139 | d7da1c65f996cef2febad4f49b26ec52
140 | d7dfcd99197d6ae7b6dbfb7eb145012e
141 | d7e26a070ee3b35cdf6cfab91d65bb91
142 | d8592dc28b9f0afa387379bbd607d69e
143 | d86158642391ea7a150a331b054ed006
144 | d8774646afed0312732375ced502498
145 | d8e2e2a923b372731cf97e154cc62f43
146 | d8ea454fb35e38887b11ae648ea92233
147 | d8f3c4bf9266150a579147ba03140821
148 | d90b1021dc6e09b455369e3e5b79b017
149 | d9156f5552178de2713decb1a0563b12
150 | d915d2f1664bf76e71a70be9f12ce8b0
151 | d9346fab44b6308f40ef1c8b63a628f9
152 | d93760fda8d73aaece101336817a135f
153 | d94490f503e005cb9eeee305ab9432f0
154 | d94eeec9f2fc4d6c33fe87c69b83ce63
155 | d959b7666dc2fda41c691caf3fc2f46d
156 | d97a4a6f84f40854f51fa0238791f5dc
157 | d97c5945e9449a58737e4e0df09d751
158 | d987dc40c90907276bc601efa799c927
159 | d9902456104543c898d5fc0473d00a1c
160 | d990c996a67bab91d9233930731da67
161 | d9943f96dfbdf331b17743c18fb63dc
162 | d9a1f2e7290cd2c3baab0c7159046dc4
163 | d9bbd1a1eaf6d2259d3ea1c6b57a0095
164 | da1ef4e9ccbfab13b3234e0da44b11e4
165 | da264a41dd8fdd655357c338ec9641
166 | da5aa9fe015114731a1272c8e47f5670
167 | da918b121ca55feb9b9f2eb77f5e247e
168 | daabf4a2afac24c97eaf5bcc4a8beb17
169 | dacbb2d9dad289b1492d9da2668ec34c
170 | dae8b3ac69d80cf1b94e60a139ac4b1c
171 | dbf235de67b39c2d25e2408bd7177733
172 | dbf5ea40382c5efed30107faf024a18b
173 | dbfab57f9238e76799fc3b509229d3d
174 | dc0bc65e9181c2f698eb62961a525575
175 | dc182335876fbebbe6fe3612af521500
176 | dcc892f77239ace06b2befe83a0efe39
177 | dd0e48963b73476f7fa93550ab8061c2
178 | dd414923feefc1bd160139aa3ea05a51
179 | dddbd223b3bbfa8efd93c2ac42357c74
180 | de9e40c346ad2779f8c3d2002c77ddb
181 | dec4d499ce2ff518dc732bd0305fe3a3
182 | dec5920f32fa546a6c518c577d808035
183 | def8af022dceee892acbf58c0b138e50
184 | df23ca11080bb439676c272956dad3c2
185 | df28bda265e0e5bd2d282edce951a03f
186 | df2b7e697ab6ca0f155d75bbf62b80
187 | df487c3660e7030dc5ed74d70201d4c
188 | df59c2ab638e5bf47c4b9c3e153dc1c0
189 | df609533cd186278398c7598b0d2e5d5
190 | df6a3bc55f86781218930ac69342cc5c
191 | df7fc0b3b796714fd00dd29272c1070b
192 | df8311076b838c7ea5f9d52c12457194
193 | df8440d8678f3a91c8687ff9b0b4e4ac
194 | df8bb7ecc402ede384a05e54516915de
195 | df9eede2969408d0bd2b1bd66a734698
196 | dfae4f9155877a1ef57b53e86a4ec824
197 | dfc85456795d943bbadc820495ddb59
198 | dfca4eae14e0bb541f6399f392c887ea
199 | dfd92aab082e4915e3d9492680c47206
200 | e017c5c8562ae50882eddefc99ebacfd
201 | e0276adea0d4f4bf1783a44a88d6274
202 | e0311d577cff9d85f6ea7461c0aa61c3
203 | e039a013f1877fbf42bd71dd667c95ad
204 | e04ceec8711a6027a6e27bc066049db5
205 | e052eaa1d5bbe795ded10515704c9720
206 | e07c7d5be62d7cd73ff4affcd321d45
207 | e08add655395ce8df51f77a6d7299806
208 | e09466e9c122dbfdf51f77a6d7299806
209 | e0a011619d6c9df19f1deb04fb8ae481
210 | e0badcef3c110ec6c4963b39d8846214
211 | e0c76c1c82f12df4c1e1aceb66eee9be
212 | e0efbc4e240b9cc235836c728d324152
213 | e1092c9dfe55273876f83644d71a31ee
214 | e12ac2c1c707b7b2f45a7a3d26bcb6ad
215 | e14e8241e0bb563f64810cc21086da42
216 | e158f7ba6828db5c654ea6737b0d3597
217 | e1791ff04ab8348fdb63e6ea2fd66753
218 | e18776689e00c8b84f871aa82358858b
219 | e1897a4391784bc2e8b2b8dc0c816caf
220 | e18ea9d7ff87c3f86a97ad5f72cdc5d6
221 | e19214cabca496a3f7b54e04c7238d7
222 | e193b0d75fa674142b3e9b6eb52d35df
223 | e199b1f6a70c9f56df44d20a516c07b3
224 | e1ab1f421891fb01f302352a74d4e413
225 | e1ca70ecc629eb46ca17c984d94453b4
226 | e1e3796be1c4313f9a59e20336b93b69
227 | e1e7e66978b888703f146f1fbd99cb1a
228 | e27cb29cc3df4d0330989b15eb158e03
229 | e29fb377ebf475c51b1a00a31bfed97b
230 | e2acc4d276fda3d77d70172a29ade99a
231 | e2c16ac7606317b3e85a21e38833ddcd
232 | e2ced471afce616454bfa32aa0766acb
233 | e2dbad7996e7e13430c589758b4b5646
234 | e2dbe84030167f1ca5aad165050e534c
235 | e3079223f4714116ad484915511ccff6
236 | e30bd575bbd6c68c9710e093c764abec
237 | e31d71ed32273fede42ac999db581f5e
238 | e32ee21232d2d5604747ada1cb39a749
239 | e3394ec3b63fdc255d59dae8d8b300a8
240 | e34658debcd1644dc8687ff9b0b4e4ac
241 | e3479f55f5894bb3c7f1f7c0570e288d
242 | e388792a151735e57597e1f94410131a
243 | e3a7c517fbe992ddd493bfe20f94b6ab
244 | e3a838cb224367c59fce07ae6c046b8c
245 | e3bc0a03103cf84e7a471a654ffbc436
246 | e3e76d624f1f855bcc8a9c365968620
247 | e3fba8a576d4d875e1d0950dd1aa903d
248 | e401be99c5a51d8bef8e9284f76f3024
249 | e40d5fac8951692e3849910c5019154
250 | e41e8329ed0c0b88d93768e7b9b1eabf
251 | e4834c88847b288648d8ff57878739ca
252 | e488826128fe3854b300c4ca2f51c01b
253 | e4931ffa06d7b05cb04cb542e2c50eb4
254 | e4a890f2330ebd7e4a11872aa986426d
255 | e4ac472d21d43d3258db0ef36af1d3c5
256 | e4b40369894a16ce6821a1e68ba5ebab
257 | e4c866b5dd958cd0803d0f5bac2abe4c
258 | e4cc5cee7b011df316037b4c09d66880
259 | e505ab84808920d06031c9bf940ea7ea
260 | e50825b2477ba5a0dcc52ca811e565
261 | e50a97aa15d7cbc5972e15b580d9a5b3
262 | e53b07b648e8d041107a17cfae0b6df6
263 | e54417646ad16604738a251b334366e
264 | e57aa2d477a818ed2af6ec758865822
265 | e59cc0fed1520985b21bc3cf138f79e
266 | e5cb5334f18c13c15a7f6c1314f7ac2
267 | e5ce55d61830cc017f1cdfc0a8f38f2e
268 | e5ce7b150310f288b04cb542e2c50eb4
269 | e5ea39e2b4c28ea2a8df8437731d97b4
270 | e60f50cdb48c2626d61bb0c6c287d278
271 | e6328c1bb6b194f262e682c9809bff14
272 | e63546037077f0847dee16617fd6925f
273 | e6408c4be8e6502837a346dba83c013b
274 | e64275c95e41605caf7c7ad2549a1b15
275 | e65ca690574bfca53ccbceb68fb352fd
276 | e65d2f0ed75a786a37b2bb75885cfc44
277 | e66ee381e20dec3a44f23566597ec464
278 | e6778535d7fcbf6fff16555386d173d
279 | e68bb6f55e2454fac7f1f7c0570e288d
280 | e696f4c7cd88b8b52ff834514c92e8fd
281 | e6b0b43093f105277997a53584de8fa7
282 | e6b2017501b20ce1eff1a662025674bf
283 | e6daa4f9485362aa37ecff2686b754f4
284 | e6ea5e70c2f29d881e8fd793667dc14f
285 | e6ec608ccfb38d6247928239f46b6ef1
286 | e6f37dff25ec4ca4f815ebdb2df45512
287 | e72bad036bcc04ea3f68fa735d443de2
288 | e7316ceb5b944b6fd0a96520c31993ad
289 | e767b27d6625f905e9af7c2087a87b0e
290 | e76aad9a92f83d70bda72093f9b5aa73
291 | e76b4872f067395988dc0b76b0c63f53
292 | e76f7d88022a0bf91b17743c18fb63dc
293 | e777e42470ee9bf270ae142beb408e0
294 | e779cf261cf04a77acd8c40fddcf9ca
295 | e77d7eb8a4e8f1816f1e07a56c129dfc
296 | e78f25a1f66c19a38a63c123f2a561a6
297 | e79b6815925c07acb0957d845ac33749
298 | e7ae6edc3fc6c92ac423490470c47d79
299 | e7be08b34dacaafc405e3e2b789a211c
300 | e803b31e2185d0405784b22e1081a3e1
301 | e8089df5cd0f9a573a3e9361d5a49edf
302 | e82136f5c8b2c3156cdce1333d517d16
303 | e82fbdd4857adbd7bc0482e18ec51d0e
304 | e84b5bbe91e0636cb21bc3cf138f79e
305 | e867483a25b070ed89ccdb4a5b6b972a
306 | e88b094644e1e80d8f2ca82d6e1c314
307 | e8c3582f0413179b47edf0d5b6459616
308 | e8f20141696f143cdb77753d44aa25f6
309 | e908c290fb506f2e19fb4103277a6b93
310 | e92063f7bf538df17eb00a494c61433f
311 | e93714e5553f63619215045784774049
312 | e9371c17042131d93506b420c6bcd44
313 | e93d141a3dd25b46219e03e23fb59d78
314 | e967c4817872b637de03ab2a27ba7531
315 | e9a8c9067bc733ed95bea7c29e873d16
316 | e9c344a392e311195b903ba10d2ec446
317 | e9c9d998f7b0de3ca6afe5903a01a59
318 | e9df7789d02eb998c8687ff9b0b4e4ac
319 | e9e224bc0a0787d8320f10afdfbaa18
320 | e9effe5159dc66673b93a3cd851adcaa
321 | ea02e94e39a2fd3922963ea1e168015d
322 | ea06ed485ab0833a2ebeb1e6a8111f53
323 | ea1566ac9fe1670d3b622c8598928cdb
324 | ea19940c812803d1383b5acc757bd668
325 | ea1bfe81b88395fcaa29e9f0529e8ef7
326 | ea389bc8d94f87ad95db811b45a94857
327 | ea572cc193b804399c66df0f068d2a36
328 | ea6c45a1a6accfa7201a419fa3bbf2e4
329 | ea7337dbfced9674d2844b25962c000d
330 | ea762c2f1c6e966be464faca7dae7fdd
331 | ea77c800bba6566aaf7c7ad2549a1b15
332 | ea7be2b97e78d5b35a4480134e0cdd21
333 | ea7e09260babc698983c05814b11dc86
334 | ea91d70feb603421f74aae127b28c047
335 | eaa4ea82bc814005e6fe3612af521500
336 | eab716562b582538f2599a47b2a7e92a
337 | eac0a44a4b4bf460f37e11038ce8fb27
338 | eacc4fa00a65e56e374f33ec97ba7ca2
339 | eae58f128191381de9efec56e07965d4
340 | eafec1b145972dcd815b2b467e8e2eac
341 | eb04d1bffae6038c4c7384dbb75cab0d
342 | eb23621d7ac1094398e0d1738edd4f19
343 | eb2fabae15f77882139d2c86c9e03ddb
344 | eb3029393f6e60713ae92e362c52d19d
345 | eb63908dde4b579e25d45769a218937
346 | eb8073ac89cf7b4181f667e2a25e0619
347 | eb9851403aca75937d395837145ded71
348 | eba001ddae2ce5eed5d673747c0e3adb
349 | ebaffb5ce608e7158d09bc92d0fc6d3a
350 | ebc5bd5566558b64af7c7ad2549a1b15
351 | ebd73aa8ec2fea5c36c26b54df360d91
352 | ebed17a73a2e9e981882515d09f3979e
353 | ebf1982ccb77cf7d4c37b9ce3a3de242
354 | ec00ee8e8345be7a852028c7654a8ec8
355 | ec25a41ca233ed096e5a467428553af2
356 | ec41d22862df4aa7eca29403b7226aa1
357 | ec7076f7f37a6e124e234a6f5a66d6d3
358 | ec758c4557250ca79f2349486c570dd4
359 | ec78623a598fb6d67fa68300c57bff0a
360 | ec91b1b29b6bccd37eaeab1f0c9120b7
361 | ecb43e4b0fc96935664b3b9b23ddfcbc
362 | ecb57b01c7ff75cd416e7824059e108
363 | ecbb4e4665c7fbb45613f5c2df1029a
364 | ece1a921c1bfd44947f5e245ee376525
365 | ece627bd883d9bbfb0eb7e753c06942
366 | ecfc0cf5081976323002761e7a3ba3bd
367 | ecfcc42f2386ef37f51f77a6d7299806
368 | ed108ed496777cf6490ad276cd2af3a4
369 | ed1816d4dee58c7ddc809959e304d48
370 | ed40add41826f68ab76e29c9c43bc7aa
371 | ed47d02d4518fb5d9cc2d4308810279e
372 | ed51660fd119dca819fb4103277a6b93
373 | ed53217c9a4443b8a4ad5308cbfec5eb
374 | ed56af61297594bf1c4300651205adf3
375 | ed6bc67f247a5aa3e43df8c9a38bf11b
376 | ed751e0c20f48b3226fc87e2982c8a2b
377 | ed97d1c954fca49851ceffe90913a32
378 | ee03232aacadee87d4266d69a5c6f129
379 | ee1c0e545ab8dce862b3a719b353f115
380 | ee20e46c542e2268f51f77a6d7299806
381 | ee2ea12a2a2f8eb71335bcae6f5543ce
382 | ee484fb2c1e4e611a0dcc52ca811e565
383 | ee665ce6679ac8cfb502ac2eb9128f9a
384 | ee8208e26cffa9f8ba208e534614d8c0
385 | eea9a17689ef174ec14f867747674e73
386 | eeafc14e4e0db2ca3b481215325f1515
387 | eee8b6fafd8af9d1ea54e1e7afcaee9
388 | eeebe3fe14ee4d3aebefe6b1d594ad2e
389 | ef1152b1660592d413f0924ccc9628e5
390 | ef1824754ae554af83b6e0255ae357be
391 | ef3377832d90dbbacfe150564cb24aad
392 | ef76b9cbf76bad40586ef70b3cee4240
393 | ef89cc3901e27fe0c5cedfd70cc18cf1
394 | efa83c67ce47bfca304edcf7c4314468
395 | efc684ff4dc6ff49ccd42a2d6eea63ed
396 | efd0411eaf2396c4de7ed732f5aeea4
397 | efd07df34c1f73cae2367b9e27f16a71
398 | efe76021aa616a41f51fa0238791f5dc
399 | effb1b260f100f5919fb4103277a6b93
400 | f029adb6cdf37c402b339ec555ba3bfc
401 | f04698af574cb9847edf3a3d7d1bacae
402 | f06d2963ad258feaf5adaa9eef900be3
403 | f09af71bebd4bea8a2651abaf391628e
404 | f0bd1732f37da50c7000797f53fee6e4
405 | f0ca6f9383ee9aae517376ab44a447e5
406 | f0cbf508a2f27a16504721639e19f609
407 | f0f04644e071d9348ca588a3264b9f86
408 | f0f9048f45eed1ab3a8888e78d004b3
409 | f0f9d29b3eb76fb7490ad276cd2af3a4
410 | f106bc80265faaabf78fc6de5952fb84
411 | f1167a0c4bfc1f3fcf004563556ddb36
412 | f128d707527eb10cb04cb542e2c50eb4
413 | f12a3ffbe0f8b5076253bf0968762241
414 | f13d600a3c4515e220ccbe1c34ca182d
415 | f1933161d8b49d8dfb266533561ee98a
416 | f199965dc6746de38b01ef724ff374fa
417 | f19e8da9d8f369c531e63f1270e2b445
418 | f1a1c9f231d2db078a8a3348259a374
419 | f1a5a9aec0b63b91f487e71bd57b6e0c
420 | f1b1c92f91d0e52bc68ff00665267e32
421 | f1c390f2a04d13f6742728b30848ed03
422 | f1c6c74053fe8888c5f49519e3caf51
423 | f1d6552ca66b2e37713decb1a0563b12
424 | f1dac1909107c0eef51f77a6d7299806
425 | f1f8e16d23d3a0ba95f2719038c22311
426 | f1fcbd856669e000118128b8b252e07b
427 | f215c608fe63e97d4aada2bcdc05aa43
428 | f23c1bb951fa8909bc01640b1b5116e7
429 | f23d3a85baabd7ae32d9baba75737e72
430 | f23ecf3348299cf743e99e0cae970928
431 | f2440b15f3773299490ad276cd2af3a4
432 | f294980dc63731dcd0ad32b8d8cec005
433 | f29cbdb2c7bb10f9953d950bcd7de7a
434 | f2c1f929f451753de4ee93147efa8cb1
435 | f2dd3bc7d6c85a8f2813aa30be7ebdbc
436 | f2e2993abf4c952b2e69a7e134f91051
437 | f2ef238e2e4615e92cf8e80367b40c9a
438 | f3249612d067e120384f43a3132c17b6
439 | f33b6f791e9d64387d01b77e04a0bc7b
440 | f347f2a3d85c9a823fa92d98173c06f
441 | f3499b524c5dbbefa23949c21eddef76
442 | f350621fba76ee29e7b1367d085b7e66
443 | f351b1725b288d8847df6165146d5bbd
444 | f35abb8246614d7ff38854b09cdc7cc5
445 | f3718bcd0e497868af7c7ad2549a1b15
446 | f39d0db80cf41db9820bd717b66cebfc
447 | f39d429ab98d5323a1a6556bd50a3110
448 | f3e50f6d0b7b293035836c728d324152
449 | f3fa7bd00b76f6a87a8a6b9421844d96
450 | f4268a28d2a837a1167c009da6daa010
451 | f428a799c3185ee0c8687ff9b0b4e4ac
452 | f439a2db6341cd85f2b931201029bc76
453 | f444df40dadd83e22cedd65b2f6d1fdf
454 | f46ccdbf92b738e64b3c42e318f3affc
455 | f497cbcc4895d5386b684500e5db87c2
456 | f4b6bf9253918b52944d8f8e13d63fde
457 | f4db2e2e90e83c759b9f2eb77f5e247e
458 | f4e24cf8c5d0c5c31dbb0393636b3531
459 | f4f1aba65ebe48eb70930286c914896b
460 | f515332dbceba51120768660cf080d12
461 | f51ab8433184dfd2c8687ff9b0b4e4ac
462 | f52c7425a47ff55f79c8c47a54f30eb
463 | f58ac8ac63d5a52d19fb4103277a6b93
464 | f59627a077dcc2566c63b8b48495261a
465 | f5b08ab02727922b738dd0d3509c7e47
466 | f5caa9b5ada31a8b3cf15c77de45986
467 | f5e5ad69111b96646d6e68ce9f2601c6
468 | f5ef49d354efe6741cda53280488fc3f
469 | f609378d4f5c755c9df2fbafa78e52d9
470 | f6096649f87c37f1af7c7ad2549a1b15
471 | f619416ed17ca24a5dc688388b7d266
472 | f645f79d47e2df0f7dca29e186afcbcf
473 | f64aa038d1e21e0ad2ebe04c523a4739
474 | f68b7c3a1ed7506bedd9ab1253e1a9c4
475 | f68c32ea1e6cecd3c48d90eef8384210
476 | f68ecc9ec512915f36d8dd30a594b2af
477 | f6cb298705842600bd259faf16bdac27
478 | f76d50f900b034af19fb4103277a6b93
479 | f85f33b3f6cac48a512d71be7dbf2d60
480 | f8c5604f39699e0fbbc2b2aef664ba29
481 | f979d2ead3517a67f20b781026d21763
482 | f9b24a3b88f9037e4b5cae2ecfffe51c
483 | f9b462997cb333dc7fbc060fd555478
484 | f9c61b40d4f49158ca998f0f87d0c84
485 | f9da1bdadc982c7f78ee935ba846606a
486 | f9dcf630e370f7d5a320e34dad7c78bd
487 | f9e386d968653602d68fb8f5d99affa0
488 | fa041b0276dcaaaf98e0d1738edd4f19
489 | fa172f7f09f785bb492d9da2668ec34c
490 | fa263643fb3f45c7492d9da2668ec34c
491 | fa277e2693cba669731d11154716a6b8
492 | fa4155f8091689a273801486f0f205ad
493 | fa5dab91cbaecea8ce9a0998abec10aa
494 | fa7f42b395c3cfce520ab6214a789faf
495 | fa8f7c225d3b9f1def4a09e7eb872bd9
496 | faa6255bb4de99d90606ee5fb3c339a
497 | faab798b13ecba08e9f0f0173ae2f184
498 | fac321238dc8637eaa7cb30470f3273c
499 | fb00ea443c74c00617c72672c86a49
500 | fb22d2e3174ed0519fb4103277a6b93
501 | fb4e388b57e36e7ceca29403b7226aa1
502 | fb5ba735ef95fe417ca68e217a316e15
503 | fb847cd696ec711197f2016c3d6097c9
504 | fb858b9e5f2b3e1043dbb6421d614c0d
505 | fb8b45151900e6e016a0c57b9ceb6d01
506 | fb912528e642f6ea7c7cfdf5546967dd
507 | fba62693a28b2e4c43f1c519d66bb167
508 | fbafdfd16d929c715b52e74a988c7255
509 | fbca73a2c226a86a593a4d04856c4691
510 | fbd48960edc73ef0490ad276cd2af3a4
511 | fbd890f1f0280b884b47ef9f38e7ab27
512 | fbddac94cfa74a7b5c0228148b88226c
513 | fbe64bd927721467dff2bb0129eed40f
514 | fbf085824e25d7c440ef1c8b63a628f9
515 | fc07472e4dd1b6698ae97f14e63e7e01
516 | fc0e86a20a9606493cd6abbbeca4e2ad
517 | fc4d15c15c56aa7baab4888e25356418
518 | fc6129a9310ba34c645311c54e2f9bdc
519 | fc66e46fe850a243f51f77a6d7299806
520 | fc723b936f8d8443492d9da2668ec34c
521 | fc7d038dc7fe2911a75d03186a0409e2
522 | fc818d6fe03f098fd6f4cef762589739
523 | fcd25e25dfffff7af51f77a6d7299806
524 | fcfb3a50acf5e83ecc0484ea4f50062
525 | fcfb7012968416679c0b027ae5b223d6
526 | fd05e5d8fd82508e6d0a0d492005859c
527 | fd2c754ca43457107d910d51d878f708
528 | fd43278c60023763d4da89766e80607a
529 | fd5ac9b342fe518b9d3ea1c6b57a0095
530 | fd726084724adeea492d9da2668ec34c
531 | fd9c60e969f83e6086debb0a33c851f8
532 | fdac1f9c0b030841c8687ff9b0b4e4ac
533 | fdd21f7f2ca9f0bcbdcbca499b446e89
534 | fdd8b499294575175f1548797747d63
535 | fdef0425d385c1cadef295ef48e5307c
536 | fdfedb5bb8cd35374233148ffd345970
537 | fe1081843a08b7a64d8fdc4d7658fe42
538 | fe307b67739d9620d874a9fab241259d
539 | fe31beab802cfc56c2bcda262700befe
540 | fe47e7645f1080735f0277eebfd05be2
541 | fe5310a3457bf0e5c4e8952b27b5f370
542 | fe57bad06e1f6dd9a9fe51c710ac111b
543 | fe99f16c2532cdd07ba99ad16fdc05cd
544 | fedfc00265711f4193c1e619801da0a6
545 | fee248777c9c4807f8bc1f8036e08e44
546 | ff034050f7ca727ea64c9c407ff9dbfa
547 | ff143c09dbfb0e8029e513fd785f7886
548 | ff167d9f25fb6ede2419ec0765e66c90
549 | ff2223a085d32243696b74614952b2d0
550 | ff2333f528efd790fc93ece3545739c4
551 | ff2deccbef73ff5a349bb1cbbf9a4206
552 | ff3a6eb4556b2c0eb04cb542e2c50eb4
553 | ff49ca82d7f8e2bef27383fc5a5a711c
554 | ff546450fb0bd81f6e7c5546c1dbd220
555 | ff6e6b7b7c7f1c0f15f78c98555ab41
556 | ffa1e25f499e586694e98ee4fdfd7464
557 | ffa6c1a509986a5676708f8dec712a28
558 | ffcb8206f907e663eac685b1b2988af
559 | ffd616229a97642c7ea8c9f2db0a45da
560 | ffd9387a533fe59e251990397636975f
561 | ffed7e95160f8edcdea0b1aceafe4876
562 | fffda9f09223a21118ff2740a556cc3
563 | ub5d972a1-de16-4d0a-aa40-85cd3a69aa8a
564 | uca24feec-f0c0-454c-baaf-561530686f40
565 | ue639c33f-d415-458c-8ff8-2ef68135af15
566 | 


--------------------------------------------------------------------------------
/splits/content_couch_test.txt:
--------------------------------------------------------------------------------
  1 | f813edee6c5acaff4fb315ce917a9ec2
  2 | eeb9c7f343677bc7167c63de52dd6bbd
  3 | 6caa1713e795c8a2f0478431b5ad57db
  4 | 24f03d70f686533d7583d8e3d877fffd
  5 | 7b0f429c12c00dcf4a06efdbafdd7ea
  6 | 3fc4cf00b8db1f03b086b372af6b049e
  7 | 57183931e41c7aaa5ff61a3a2a0e2484
  8 | 7e728818848f191bee7d178666aae23d
  9 | 485fd17a8679ebea638c2f4fcd9a8e7b
 10 | a7be35f955f8d45419fb4103277a6b93
 11 | 3ac827b804fee818b0b88207ef0f5bc6
 12 | e8d6ed94c67d6f43708fed31e484f9c0
 13 | 7511cf30cf10869b4f7ad0010e5a372b
 14 | e921afccfbc7137c5a95bb8b37106cdd
 15 | 3ce2794845ba4bff5c63d035d2a7c889
 16 | 62a0f0734b9111084e78d6c405d01fac
 17 | d6176ad267c3ef92f51f77a6d7299806
 18 | 5a2da4b824000054d8390ec1728b1e3e
 19 | c2d26d8c8d5917d443ba2b548bab2839
 20 | 9d77156d64599e9b1206ff076758ec85
 21 | 2097fba74518dc6e4a949e376cab703f
 22 | 1059a78893d810bb14038d588fd1342f
 23 | 9ee861bebbc312d97fac4224dd2383a7
 24 | dd4a6a955c925d7762fd9a1e220aec64
 25 | 8c6348fe629fb8c876a45e9a12af8158
 26 | 9ceb81a09813d5f3d2565bc39479705a
 27 | 4353b992d238cff0cda85f6a3e19b0a1
 28 | 107bce22d72f322eedf1bb0b62653056
 29 | 79bea3f7c72e0aae490ad276cd2af3a4
 30 | dfda3c467eb6066fe6fe3612af521500
 31 | a4c8e8816a1c5f54e6e3ac4cbdf2e092
 32 | 627819d2ea8ab9d9c97e4283c3b75587
 33 | 9beb39285a581fa1f2e202d571b458dc
 34 | b918cd058e822e00cce02970cdd7e7da
 35 | 7961d0f612add0cee08bb071746122b9
 36 | 9c1565c6bc50ba7668bdb5c1c01fdb25
 37 | 40956fd98a04f34914038d588fd1342f
 38 | 40df73dfda0e26ce442b5d6d90d0cc78
 39 | fa0eb1bb05ebe3f2dd3adf3090c701f7
 40 | 4c49cab86dc3ffd2c84c076312b543ae
 41 | 8a4e1f7cc3bb76da9c9245e96a55cc5
 42 | 5f5150a80e5be6159141f9b58470d646
 43 | c05bf63cd7818b6f19fb4103277a6b93
 44 | c87497b3c00b3116be8af56c801ecf41
 45 | dca66ae8a95f7f70552a7b4f3448af2e
 46 | 4f2c9a0709eb8cb9202316dd49948ea2
 47 | 785b692194203f119fb4103277a6b93
 48 | 4faad33041ab0f80dd8479d78721b157
 49 | 45ff5f465a6a907488e82c4bb71ec6f6
 50 | 6051f687d35c6ba577dfa90ae0b0a3ed
 51 | 577625945f1b83d16296847c9d695b0b
 52 | f8998de3b4d36dea4b3c42e318f3affc
 53 | db851fe630734a8aee7d178666aae23d
 54 | 70cf74bb4e1e14dac15fcbb4bdbaf13
 55 | 30e95358ed817addbaa0f6b191f18222
 56 | 2b8a9009d91dc09863d467b618e97922
 57 | e08354a352fd0d6914a163d2b227b320
 58 | 11b544b22dedb59c654ea6737b0d3597
 59 | 5149af0adc1f4a6aa45aa09d68b87656
 60 | cb7cee345d3e7f75593ebeeedbff73b
 61 | c2e4095266254bc1948a3bd895ea5ecb
 62 | 6897c646edcc98c149d579ea0e00a990
 63 | 21addfde981f0e3445c6cb69e0968783
 64 | 453d56b5906989fff29666f384be6c43
 65 | b2f2058ab083cfa0a8055fb11b774454
 66 | b6384ee46eec7bd5df8d3317f6046bb8
 67 | 167088246175f31c593ebeeedbff73b
 68 | 15c66bed7e6bdf85160c7765c528fad6
 69 | 9a1b39f920863964b3c42e318f3affc
 70 | 72b7ad431f8c4aa2f5520a8b6a5d82e0
 71 | fee8e1e0161f69b0db039d8689a74349
 72 | 9e014bda9022a09095369230ec06c72e
 73 | ce049a259cc2e624d5446ca68a7e06a3
 74 | 6bbbddc84bc4d3a68eb3bc6c6d15f9bf
 75 | ad7dd9434ad5f61db759217db94d2883
 76 | dc2b5f9abce70f2b55f9a00acc25f137
 77 | dcd037ab067a0fbc14038d588fd1342f
 78 | c1b8d982d97e337f19fb4103277a6b93
 79 | 5cc8f84b9b53b30bdfa4ff010b8b9d1c
 80 | 7f0d93163b0db7a71ebf17f9e9667427
 81 | 9d1e8c37315e292f31a50841704a69bf
 82 | 9ec5fcbfe43af15b851a116903680096
 83 | 4e37752b33506d0313dd6eafe1477be1
 84 | e809c16325be020c795085b4d203932
 85 | 66240ded565b0927a8373ea4ea947e84
 86 | 28ce909659a826d1599dcc439b161a52
 87 | d47eb4149fbcd0c7907a5a34fd8df2f1
 88 | 6703a4ef8b0ce866a6fee8e2140acec9
 89 | 592ad41d80d018a2d614b159c22611b5
 90 | bcaf0bf7eebb7d7f4fa36fe4cfcd8f6b
 91 | cca6e720741a6d00f51f77a6d7299806
 92 | 1372c28325f2794046dd596893434005
 93 | db8c451f7b01ae88f91663a74ccd2338
 94 | 5fd7cd5ee43e0cf0eaf288f952624966
 95 | 3f8f1d7023ae4a1c73ffdca541f4749c
 96 | 7e40a1af933a05a6ab610b0c94236463
 97 | 9e6ba78f80fbbfde5369e32fb818f337
 98 | b37f1363aa93688619fb4103277a6b93
 99 | 28e246db6ffc3497384b87f5fc9c7afe
100 | 72252b1486f22ce3490e0c0c00192ce3
101 | ce3055223e53a46e67d4ef1ee6cc8170
102 | e3992b75b446fb5af7c7ad2549a1b15
103 | 8641e421ade0f7cae136ac3990ab77b2
104 | 79c3dfc2f90a5cb619fb4103277a6b93
105 | 218233bd68f5261dff318cdb0cb45ca
106 | 6658d651878eb023c7db9c21ccfbc4a1
107 | 15d59eaf24645f501030665054ebb2a9
108 | 5015912352daa0113e2f5d8f8875fba6
109 | 99175131585f4cfded403132b02528bd
110 | f2edaaa8bef11dedbac8a2db6cabda6a
111 | 42e06113efdedd0fbc19762eaa7ba40f
112 | ee71654238a92dabddcbda91db0cadbd
113 | 3dd89f170133fbd7d609055a51359428
114 | effe967a116f8098cc2af5791bd669b8
115 | 79edc7c4e10a6fd8b3aef1eb2166205f
116 | fbd0055862daa31a2d8ad3188383fcc8
117 | 32198f8e02253fc0d1fbf79741fcd6d6
118 | a23357a29af9f63ed26fff8ae28c5292
119 | 656ebb911f3963a81a291b1dd4baf49
120 | 4769bb2062392beb453a4adde9273930
121 | 92720933afa1dfdcb5c1550bc8448972
122 | d0bdb5de2ae0de1adfa4ff010b8b9d1c
123 | 5b70eb12242d4a03fb6ca00006f2c76c
124 | 70be13428e2a6eb1a789fd2e20dfbbd
125 | 4e664dae1bafe49f19fb4103277a6b93
126 | a63bc3a5d43888a962e682c9809bff14
127 | c070cc8563e2b3d65d06d6b9708d8ce0
128 | bc007cba6288e3503790005cfb7639de
129 | 9177c05744b77b6f6157c3a167984fee
130 | 3a99bf8e2a3e5e294b3c42e318f3affc
131 | 74490c45305da48a2b3e9b6eb52d35df
132 | ba8afc95c19a3d369753496ba23f2183
133 | 1b25f96d97a94b05125abe33bf4f0061
134 | 241bf145fb2d14e67ec0186a79b9da3b
135 | 9e88cb24b40dfbfb85b479b317175b55
136 | 5b693b3edfb323d0febad4f49b26ec52
137 | 1667fb24efa940b9527e7f2c027f7469
138 | 1575354ba1faad67490ad276cd2af3a4
139 | 302fc57b3d180ea4733824eae5cd9ae
140 | f1d1fdca528582dca6c4f2c64bf812b4
141 | 35503a69108fd2a790a1391b3fdfda26
142 | 1bb31ffee286d9687597e1f94410131a
143 | df2fd8e97036e287dce02b254c09566e
144 | 39a922f31e5a93bdc563fcc2752ece39
145 | 933a9330407d51b6a8cfd114c4b34e97
146 | 4fc8fd0b2951d0a0b035d20a1a3ca345
147 | 4c29dcad235ff80df51f77a6d7299806
148 | adfda3aefb86478319fb4103277a6b93
149 | 630d612af74628053b28ebac0b25d03d
150 | 9156988a1a8645e727eb00c151c6f711
151 | b6cbabb92f1d0965de85c11d95003a6a
152 | 2c2265c2a9f3c886d0250e0e48027a4c
153 | cd9ef0c92376e604963cdf8b01c64c16
154 | 19f52379f01878ad9517a37c9996fdf8
155 | bf816001f25b2ff822e11aea23332c0
156 | 96e21b275c9bd83bec7cbf3284585a40
157 | 1bfb1f52f2200860c3eb4329189b69dd
158 | 12766a14eb23967492d9da2668ec34c
159 | fa877c7d428253515e4b35ff1ea95f37
160 | 50c1477484688492bbc7a6acbd8f058b
161 | ca8c140ca26c4d6cc9b96a88ab877904
162 | b0ed631f887c522519fb4103277a6b93
163 | c6edb435655e832debe45ef6009149dd
164 | 7c9e1876b1643e93f9377e1922a21892
165 | baef1491d5bfb6cb58e51facd8ce1a25
166 | b15fb2ddfff73f502cf0d9a4f66100ac
167 | 14658bfae450e891b89b974fa14a05a
168 | a207c52399b289be9657063f91d78d19
169 | 8a5a40fe10eb2b2eb022c94235bc8601
170 | 3ea6bec3578d7a0a24e449d22891bdba
171 | dd85decc87fd988c524446331aa4f326
172 | 75e62dceb6fc577e593ebeeedbff73b
173 | 7d71922494b8788ce10ddc5f810dd417
174 | 82a13477581d96a1fd3e75cecd4d5ab7
175 | e541933c90eec36182db9fca4b68095
176 | 839807049a0c29a6ea693790a1608aab
177 | 2ea00b36ccb8d3baefc579970fcfc006
178 | 461772d07ff458d7470846ec41d04ed8
179 | 25fd91f0cc5c2e30e1c2ef56608a124e
180 | 9428c331f2230e33a066c1f884f0378
181 | 8426b07a7f599d011a3b39b07e4b3d0f
182 | cb311c253401e27165eff2c7075317a4
183 | 7b5e46d1cbe7c2de7d92b0739e572d9
184 | b58291a2e96691189d1eb836604648db
185 | b50c0ff1aa497809afbd772c78d05c2b
186 | 3f5fdc05fc572730490ad276cd2af3a4
187 | f1ae0c66488c39c8ecf6d12e1f8958fc
188 | 1712200bca469561d20e3ea5765d7edb
189 | 8180afee86f2075519fb4103277a6b93
190 | 89e00bb2b82e9e86c036a40816608369
191 | 1aaee46102b4bab3998b2b87439f61bf
192 | b8909a5d6702f6f31680549bb1d1b739
193 | 7d019d0342f8a70f3bec56bff764ba78
194 | 7f0a1abbf748d3b09a91829e64097423
195 | 46e6485e5bea085a2b450c5933dcfcb6
196 | 6cc0e9deb3b519eba347d2a9b736d5f
197 | 5f145696aaef1e6f342398ca9dc32672
198 | 7b9d9c738c6042ad1c2c02171f63f02f
199 | 2860b2b5e16f4ae8c29432ec481a60b1
200 | 6226851e0bf7fca877b7247857f4c82f
201 | 251fc26346ac1897febad4f49b26ec52
202 | bb39e48c9c10abee77f0370a839e670
203 | 9f5fd43df32187739f2349486c570dd4
204 | c9c0132c09ca16e8599dcc439b161a52
205 | f114b76d551b5e5affcd08faf4fccd0f
206 | 93bd851dc5bb3527d437a7a1ae2552ff
207 | 4820b629990b6a20860f0fe00407fa79
208 | 24bfcb97fb60fab7e812c99c6645894b
209 | 7598c48286a63854c02170c33e00ea64
210 | f9429d6bef2df25e4dbf8d635749f669
211 | 6131018e5caaedb87980e3c69ea07675
212 | c3cc9a21c0732ef9b2f052bd9ec28053
213 | 9c0c2110a58e15febc48810968735439
214 | 8659f0f422096e3d26f6c8b5b75f0ee9
215 | a1a4f5670251b8314b35a7d7cea7130
216 | 99ec7e5d04f32409d45611d32fd7733d
217 | 83d39faa5782395b651fb4677c188d35
218 | 8f8aa68c8c6cc6b53dfad56d2a4eefcd
219 | cc32fde4ca022cdf965e01bcaa1587c5
220 | 24cbeedf72674d1eb615f5e15a637115
221 | 35eeee5f998f24e8a505985405786f0
222 | 50766e42adb211675e0d6e917505f52f
223 | 946ab73b9f05a85ad5b24cafb84903c7
224 | 16ca439cd60eae5f23500a5b036df62e
225 | 385990d0223c92b5f3598efd14e493d5
226 | 21b8e95a91fe7f044fa89de6e82c448
227 | 509a533e17fa45572814c9aa90ee14e
228 | f125875fefd6a02af487e71bd57b6e0c
229 | 7875815356fb41f3d772e458a8f80cd2
230 | 8a484fb8faf9dea01495d00ce1193982
231 | bd199c38c0fd7602c9f722bbac7c6194
232 | 71147c7ef2258b894a1a4db9532622c3
233 | 9875190ff87d3eb6a510987e3d5db7c5
234 | 4521ce028e5009811866a0bc19f46a1d
235 | e0591c0d35f82023610c2a68437007d6
236 | 4106b3d95b6dc95caacb7aee27fab780
237 | 2ab2a7cdbd8770318f17764fa642770
238 | 7822a1ef8d1eca8af51f77a6d7299806
239 | a73fc5b447cab6493ca57f5648ff1b0d
240 | 1037fd31d12178d396f164a988ef37cc
241 | de4d86efa8bdc67684ad2abb799c0f8d
242 | b02c25874494cd60f51f77a6d7299806
243 | 8b5fb1851caf5b4c5b89c9fa863d4b06
244 | d1a40b075d8aaf62e7c7920f6a65a54d
245 | fcf30cec3180c05da5f9d52c12457194
246 | acf458d2b16dd918ef188758bf2e3a30
247 | f15d3637d11e93f5dd17d7a192a3a64c
248 | 67711689ee7d8dd76b4675882670d943
249 | 8f71670ddaa954c963860d683ccd0da
250 | c80c48b901ad94effebad4f49b26ec52
251 | dd36ab979c4ff93038dc42f802aebe31
252 | 2715a63f41552d6c19fb4103277a6b93
253 | ab2f0f582e3fa5b1780c9f3df5b1ce52
254 | 2ae32451bd6b947e593ebeeedbff73b
255 | 55432fbc7604292ed9993d66b5a0e2be
256 | 717e503b3846d60ee8f8c11a24c52ebb
257 | e352b0882699b66a44db04bfb021976e
258 | eba5b24b9c3dc8cf9c0ca344f487323e
259 | cf4db3515ce7c603cda053036bd1b63f
260 | 68c58177f6ead1ba9f2349486c570dd4
261 | ed90b3d1d41c46a82b09cb731e7a040f
262 | 753e1bb8f3164ded7b3ec0bc4f26f615
263 | bd98ff55306cdd592c509b30860f3d1f
264 | fdb3ab843f2a244eb9b4a0bf4166f120
265 | bb4c963786dc746855f9a00acc25f137
266 | fbf0c4f6a483bc15ab7a3d3a1341aba
267 | 2bbd5947aca68a81d329e53feaade57
268 | f9f7fe005455dbec215b8895763d1ff
269 | d53620b3769bcbd664518692a46d31bd
270 | 25bf067de33706e62bc36def1a7d775b
271 | 35bbb0da45fbb2d93eec26c23f5bc80b
272 | fb0c0e7d7094b64c8e5f5b49c9f5b3f2
273 | 33bfb06af948d3415cab680ae8f530b6
274 | d5b99ed4075d9ad559497798da6e2013
275 | dd370ef3f3e8097abb9760cf9cd1a953
276 | 556166f38429cdfe29bdd38dd4a1a461
277 | 9c0ed8415a0a9e5c49b1e464b71de577
278 | 8b8152865839a79719fb4103277a6b93
279 | 23482a90a12a7052bd184e94aa5ce5e4
280 | 80c143c03d0d7b3087752c136d371e3f
281 | 9aa38ab7fabbd6becb6924eecbe974f
282 | 86b91784e9f32b8f10edd100dffd8d85
283 | b0a85031201b0fb1df6cfab91d65bb91
284 | 8e9de6e848ed53a248cfc982ba61d3a1
285 | 4f2ab57322d7a7e3df63d1c7e43c783f
286 | 5105549b9de890319fb4103277a6b93
287 | 5bd1a7825fd8c16c6eb9b08c8a74d159
288 | 8043ff469c9bed4d48c575435d16be7c
289 | 356ee11c9803f1d2fa6df2d54fa43ce
290 | dca3a1737e2e3c5c6d0fc9460109eda7
291 | 27781344ab489f2df29666f384be6c43
292 | 22c68a7a2c8142f027eb00c151c6f711
293 | 9ed01e198c9d70a5df6cfab91d65bb91
294 | 4a910d2734c9cffb44949d7685cb63ea
295 | 3f8523f11a622d8d6983f351200ac6a
296 | 6f6a4f12041ce6d2593ebeeedbff73b
297 | d97b919139287ace7842a9c47d0b96c6
298 | 581808bf8d8e1d2448eb521885c87e13
299 | 84a119d032947cdf1da03d263d0d0387
300 | 83410e32b49b4f9957aa81cfc66d7b2f
301 | 2a9da31660f0c0b73505e48e4fe20c28
302 | f611f7d72fccaa4c8bfdb54347dbe48d
303 | 4f6ba19d62789d90d71c0b5c63bf171
304 | 4c0aeda1ff524383ce4f58889c7849e3
305 | 35c611ddda81b9941206ff076758ec85
306 | a3eef12c108186997b9a616d4541ada8
307 | ee5cfabb3bbf211f4f46734d27ff5aef
308 | 7606f7f0a8d6434f4b3c42e318f3affc
309 | dc6308addc91fd9eb9e8bdc9c4a49aa2
310 | 6e4fab35f29925f14f438613584cbdf7
311 | c75ade3248fb4f2f8962005ce0e986db
312 | 37b94e004ee1f7847c63c1e5173c47a8
313 | 99ec963187a1cd2593ebeeedbff73b
314 | aadc03f6499b5ec5b60747861a92b009
315 | a11d94a5675bc703265c64fa53bf2c02
316 | c09ae0a971165afe4fb315ce917a9ec2
317 | 9d436dcfd61622d6199833105dc1a90d
318 | 73c8bd191a664678f5ba7cb98f498b13
319 | 7a82cfb4878d1162986fdea3c9eacb1
320 | 1e4a7cb88d31716cc9c93fe51d670e21
321 | 8634968c859b2dba5e4b35ff1ea95f37
322 | 62852049a9f049cca67a896eea47bc81
323 | a0bb04577e35ca2440ea7eb155c4e420
324 | 6cbcf4636ee5593f75a82b88fe6e733f
325 | de3589ff77017c7df15e23b99997e42b
326 | 9a24fd0d36ff856662e682c9809bff14
327 | b3d216ad7575478d202316dd49948ea2
328 | c1ccf7d15c32b156cc2af5791bd669b8
329 | 189e64b308b4345d291d421ca3746ae2
330 | a627a11941892ada3707a503164f0d91
331 | 160887408a65f88f67903707764646db
332 | db49ee0d87af106f2de0bc4fc4d02dd6
333 | f78da0aa23162f3850cf3715818ccfe8
334 | 1a38407b3036795d19fb4103277a6b93
335 | 525c959a4a09aea164def4b29bf333db
336 | 14b9fdab8d264fc214038d588fd1342f
337 | f1241a9c69cf35feb3104e94482ea9ce
338 | d13cd4fdf27074854b3c42e318f3affc
339 | 34878cff5db772bad810b14a81e12eca
340 | f67714d13805df294b3c42e318f3affc
341 | f3abd87858a226aabdbfcb10306a3977
342 | e1662c8dfabda9e76eb9b08c8a74d159
343 | 9b88f0839b22b33022fea5173e5c6318
344 | 71e0e0315d718004e7c7920f6a65a54d
345 | d6b6f8854bda98a6ff458e602ebccbb0
346 | 6262bddcd8bafdac3bec56bff764ba78
347 | 9e0071fda87df6892e73d126bf16e692
348 | 34e10b72cfc4f36ad8e004adc6acd545
349 | aa36fd4d76afcaf8bdcda0bf7e7b4744
350 | 4653af854bf098f2d74aae0eb2ddb027
351 | 28cc5741095e9754cc9651014a82e2b9
352 | 17e050b62fc249687d3c9de9415fb224
353 | dd50bf448cd6d69016e9e510d2c2a9d
354 | 63fe6b5903df38a0ba0f037fee399b18
355 | 36a6725f30a73f0e91ffcd1d3522e1d6
356 | bb2ed216b00409665634c21965ee6bab
357 | 7669de4a8474b6f4b53857b83094d3a9
358 | c8663904bd8af794d9b53420a5458c53
359 | 96055e2a648903bbaf2302630d34f30e
360 | dc079a42bd90dcd9593ebeeedbff73b
361 | 294afbd7a0e90ba9490ad276cd2af3a4
362 | 9c3b2d053adaca577b50cd55c08e6bb6
363 | 3746c2c38faaec395304a08899f58b0b
364 | 41149ca3a44aff87707cdefe012d0353
365 | daf0e2193c5d1096540b442e651b7ad2
366 | fdc419e377f15e728101accd22c701b9
367 | 5eae999a81861da03bec56bff764ba78
368 | 7cfbeb2c5af830a26a97150bb2a72733
369 | 67626389926740a08de89023dfc7cadd
370 | a53114ab5cfe2048f51f77a6d7299806
371 | 9ea47bf98413280bfebad4f49b26ec52
372 | 4bdfbfa1871f2ca114038d588fd1342f
373 | dc62af0b1d8af2c676e9713f57a5fcb6
374 | d54be63f3df4a80aafb1dd61dbf468dd
375 | c8962afab63de682a9ed6dce8b2a37bc
376 | 49d28b2dbf11e3975e4b35ff1ea95f37
377 | b56d901b6dd62332813204830fbed813
378 | a409a2548e7cdac7febad4f49b26ec52
379 | a7b07dd40ee6af36747bd07ee1e3f697
380 | 19f0a14207f4f953bb1b55ae5bd11e93
381 | d13a2ccdbb7740ea83a0857b7b9398b1
382 | 79a9aa1e8b3b108cc48383e281a276ec
383 | cc4a8ecc0f3b4ca1dc0efee4b442070
384 | b23dc14d788e954b3adc3470b30138f3
385 | 4ed802a4aa4b8a86b161f36d4e309050
386 | 4e925afce2f8fcedec9587880f9bd7d8
387 | 2459280764bc155554a99e49f597fe94
388 | 7d8fde70f5c3f351567232766992241d
389 | 804b776428062f18f024b0f23b15c6c8
390 | 9d6ac979ebf86ea9f37af16b2893f1d4
391 | 5509f181ac72de8478eec18a8a3356a2
392 | 5ca1ef55ff5f68501921e7a85cf9da35
393 | 8951dddfc3cd6b08e8f8c11a24c52ebb
394 | 2a154c6f14a749179f6fd848d2db8a5b
395 | 777aa4f75debc4e8acbda81da5062d85
396 | 79b544db8d95c3dbc1a25f36f85c3fd6
397 | ead2f0ef7103c963fc1f58a995f231d1
398 | 67708b6fc3e76563ca691253f597ebb8
399 | 8ed3fa69c808741a42e1bb4fe264125f
400 | 94699d5b8a8682067ff6ace05b36a5
401 | 82b6391291239d90febad4f49b26ec52
402 | 3d164c442e5788e25c7a30510dbe4e9f
403 | 1c912a8597962f1514038d588fd1342f
404 | 9eef66b5d0444f8398cfd47a860803c5
405 | e2965d9df7974ba25369e32fb818f337
406 | 87640cfc9e38bbb3ec563cfb0e79cc4c
407 | 2554d1db5fc9ebe525f8fb09254b26f9
408 | 8a0ee11e68d4565d72e26fa14efa9297
409 | cf81e26374530f8fc08abcaf67cf0417
410 | b913574ffbe7400ce8417aef1b7a422
411 | 4b139ceeb56ca3a1991d32d5bc1065a5
412 | 836d2a7bc26d1b75ec195f2cc52f3287
413 | e3b28c9216617a638ab9d2d7b1d714
414 | 42ebf2d478ab8af85ac3e286c38c6d66
415 | 61711ab3e6fe99ef1c6aa36e5af1449
416 | 4954953090ca7442527e7f2c027f7469
417 | 6aef3ffcf683005263cc440c7caf3d76
418 | 85bb2ac1c8896881837d598c1c392d83
419 | 4a747546b39003dcd59517820ada1bea
420 | 8173fe7964a2a06319fb4103277a6b93
421 | dbbf72729fafaf3737f67f4322e8d3d0
422 | e8dfcea40c6cee9b990561fc34164364
423 | 8918d572cff6b15df36ecf951968a8b0
424 | 813597b7f538820ef51f77a6d7299806
425 | 7061f5384074da6d6f37a8be59c15bbb
426 | c309f25d69ad12dd4733824eae5cd9ae
427 | 859e3eab73311f38ce59ea70152320fa
428 | 882d5d8f49e52e81a53276bbe109327a
429 | 1226d123e89626a2406329dad4c94770
430 | 5a95984eaab1d85dfebad4f49b26ec52
431 | ff73fbfb9f4a273be738f481f8560d58
432 | d3db0f5bf70b9e32f7823f022ac104a2
433 | 59c32d74e6de63643d41bddf307a46a8
434 | 32b6c232154f2f35550644042dd119da
435 | fd2596a60338b08b318694f1cc6fb1f8
436 | bf28dd5d38900b1314038d588fd1342f
437 | c55d36457611e7fb826fc8d57346a2e4
438 | 87f103e24f91af8d4343db7d677fae7b
439 | 3d297a9092136d914038d588fd1342f
440 | 33bd97e462ad2a851b17743c18fb63dc
441 | 361b60c0143d91c3593ebeeedbff73b
442 | 8d98a04f7217d91ad85fd2587ec5bc19
443 | cb93c492c1c3c00a94c9842dcb05f464
444 | ce378b91236095622155ef587b4a7084
445 | c6fbb991bf184331847d00e95a10eacc
446 | 7b8a8776c2bd135694e14fba4acebb36
447 | b6e744f896a202c119fb4103277a6b93
448 | b913678e74f02db521f0090670ee931f
449 | 526c4f841f777635b5b328c62af5142
450 | e817922063c3b24ca296c91af58589c8
451 | ee5f19266a3ed535a6491c91cd8d7770
452 | 4444828846fc38269fbbbda5e1d9195c
453 | a693b27591fe6ca2fee6b7db2f5f826
454 | 978dcc1e9c3f9a3f92a31ec18c4e190a
455 | 37b3c4bd619d1c6541ec70becd1ecc7e
456 | 15410f94aefb4982ded10515704c9720
457 | e4ac864732a8dc40f99656b78fd61fd5
458 | 8827bca86b63f748b2c9b996c5b9e81e
459 | 61ce96ea92a12f402e0ec510458499fa
460 | ca6a71e5ad6e8964ad33b69f9597739
461 | 2a310d5bb9e5b1ec162227055a96104e
462 | c837f4472115496cc93e5ef112648b04
463 | 9d117d7cc29c3ef314513156cf2b8d0d
464 | 500fdf3d6ffbab95cb57ce1986fa546e
465 | c4e36c36679f27887586d00bc0d54b2e
466 | 200324d0bafb1c2e19fb4103277a6b93
467 | b2ea31ad8b8b3e19994626ba7fe8ddf7
468 | 9e35945e9d768135d028c2e338a88f09
469 | e76457b55a3c041cfe49db72b6ffb2c9
470 | 523daab7896a34ed65234765b3a00e8c
471 | 791f224b44cc67b084a05e54516915de
472 | 64800f14a795d8759055f83d11955109
473 | 6d32f20579c9f422843ead12644a79bb
474 | a9da19aecc65656019fb4103277a6b93
475 | 4afee57f3134a483d9b53420a5458c53
476 | 9f5b090a3697b05f8f9cd2ac878055af
477 | c2a8f4c920b6f7c24097c269bc92f53
478 | e75990aa494d4dc7371ea954c8939aa
479 | 16632d002fc0eec9917b96045c9b6dea
480 | b351e06f5826444c19fb4103277a6b93
481 | b0b942c484db4fd7afb07a946d621b3c
482 | 5ad772a3c728b948d329896bbf26eda9
483 | 66d4f7c3c9018c9c4d3ac4ef5709159c
484 | 8731945435676805aa29e9f0529e8ef7
485 | 7550aa9d29f252611431dc89d81d788b
486 | 2b69e899da0c15cfb40f0ac0fb9a650d
487 | c805dab667ee341ca3ee83e6cad78356
488 | 7c31c4d88c67d094b3c42e318f3affc
489 | cf2e145ae0b8923488df69d6c56c6047
490 | 6822eea5cf7f5fc9d92d669b28d58950
491 | 17555a8b1def80abce101336817a135f
492 | 9a7f267890144d4a7afe2ae8eef63a8c
493 | 2bc74fa3617de19fd5bfda5cabec2102
494 | c365bb7af1fd9fd490ad276cd2af3a4
495 | e0c9ef28aff6484e6eb9b08c8a74d159
496 | 7f6c75c2d820337b69867582939a3cf7
497 | 43720278eea721d27d18877f45b7c3cc
498 | 6f84940f81a61eef2e9208ffa1a27124
499 | 4538a9c622fc554dc048a125b47d14c9
500 | f43b6b571d66991f95ca4adb70946a21
501 | fe591a1cfbb6219afebad4f49b26ec52
502 | 68aa553c520fdeada30a92122fc999e9
503 | 6b569ad307bc38c06eb9b08c8a74d159
504 | d0b06478f56a1306e8f8c11a24c52ebb
505 | 9f4ad442e9cb51125a31d91ec836a511
506 | 2e1563209d3318b2d544b90b3a170602
507 | e62ed35d1643a56dc9f016d57db96408
508 | fabbe9b0db0846a8a823d9fb27aec30
509 | 6017c8c817937296e1df71e82caa58ae
510 | 22da5fee0352cf194b3c42e318f3affc
511 | b4043ab6723a39f1406316a80ad8bed9
512 | 7b405c1d6d2dbea9f91663a74ccd2338
513 | 248e014f31771b31d3ddfaaa242f81a1
514 | a6054a189eb45e30672e57a20276f6e9
515 | e6ecc4e6734f056855f9a00acc25f137
516 | 17fbdd9d8e8b3e8dd2afe8d5254a0d04
517 | f43414acdca3878674c5bf7a74b1b6df
518 | 1d9a26feeba782e3f91663a74ccd2338
519 | 605b9827489d47a14038d588fd1342f
520 | 4180d98246089cf014038d588fd1342f
521 | 7dfdfe28e3d25a0d19fb4103277a6b93
522 | 58d87762038f551bf2977dcfb5a9b56a
523 | 4a7cafc9f91cde86200f88c4e37ac5ad
524 | 2b8d1c67d17d3911d9cff7df5347abca
525 | 964887dfda95963fb0957d845ac33749
526 | fb859910000d1e219b709c9b379c59d9
527 | a157ab590ef0f9b6dcdd187a6a5d68ad
528 | 7ca57c98a3557774f251828d7c328331
529 | d3cc9f995b1f2b2dffcd08faf4fccd0f
530 | f4370eb6449a1e8e191682d3b3321017
531 | 8efa91e2f3e2eaf7bdc82a7932cd806
532 | ac16057c9ab79f7f2c7685af80c3d87f
533 | 4e05ca172c988b72dc1f6c4cdb4bb9b3
534 | 2eb0a772c36144eba3f22b4b00de6dfb
535 | 708e7253604979d06d83c04495f2aa08
536 | ef05b57542cbf151e7e684d25d4dcaf0
537 | 3319a9b24416ecea7ff6ace05b36a5
538 | 337b0e3fb3c00f6e6ff454af1e8947f3
539 | 5a94cc0c277f391df9aec59741c69cf7
540 | ea9aaecb6305da9ff51f77a6d7299806
541 | 5cea034b028af000c2843529921f9ad7
542 | 1acdc3f794d927fd63fba60e6c90121a
543 | 3140b8db45212ea0d9b53420a5458c53
544 | 810e4815b0ef6f1314038d588fd1342f
545 | 8981c0ffae1af00a50fc88ed745bdb67
546 | 70ed97376be1d0a84301558fdb0b2522
547 | 2e17fbc8ae8989911751d30f076514e
548 | 2bd1439924492a3fcea6c8d9a419e8e0
549 | 33eb5d4c6ebbd6b1327289c00b6dc9ca
550 | 4e7062e2c776db18dbbc9440457e303e
551 | beb06b61dad3795c95c7d6b48c371712
552 | 44854046021846f219fb4103277a6b93
553 | c44ab66d4938052a36e4b0ae0f52067b
554 | d321d0c149d7762acc8bd7a04c9659f1
555 | bf504bde782c3f2ce8ced3508709e1db
556 | d72e78905c4d975f4f650cd6cdc94858
557 | 51ccdee7080b11dde21111e385a0661f
558 | ada8ce574ee473827c373e0e7470a338
559 | d7220a39bcedbb89a14c5748cc240cc2
560 | 1f74a21433c43c784209d14d674fb332
561 | 42f33746d7f0a8a24d3485a4d7c3a3ee
562 | 48e31e3a3e2aa5c0cabc196a7f35f1aa
563 | e491dc151c8e801186abe5555a3b447d
564 | deb7ac5670e9bb27af8808fbf39db46b
565 | c602f932c692ba2714038d588fd1342f
566 | 77090c15f738bf3079da6431b0766445
567 | ad0e50d6f1e9a16aefc579970fcfc006
568 | c7e3aa97aa279582febad4f49b26ec52
569 | 1a201d0a99d841ca684b7bc3f8a9aa55
570 | 2b7e704b07fd21febe65001d50394fd9
571 | 1843c388615d12dacb16624e184454c
572 | 2e04a6dedc7cc5334b3c42e318f3affc
573 | 7db3c05e67e9b847393b0262b4e8b707
574 | f34cda8bde3c79709829306a513f9466
575 | 709f1d6837ed560bb12cf25c409aac26
576 | 5c66c3e86a131bb969c8f7b0ff61e3de
577 | 2aa0288017b4e249f6a7b03b801e1d47
578 | 85293b59b0f9cc1e593ebeeedbff73b
579 | ed394e35b999f69edb039d8689a74349
580 | a2bdc3a6cb13bf197a969536c4ba7f8
581 | c51e57530257f6e0e0771d4c079a0ec2
582 | 9df9d1c02e9013e7ef10d8e00e9d279c
583 | 932be91adcd83bcf1336f52415aa0825
584 | a7bab06221eb932e79c251b4a7838829
585 | b86d536860cdcf4ce7321f25048c6142
586 | b5fcd21b70bddb3fbd16d4490a10a752
587 | fd56410fc541a09a749add7c3dfb27c1
588 | b3fbac6ffe8e00622f6acf89a420ef0c
589 | 93e20cc90bc4ead618a6353ea60f11b6
590 | 199085218ed6b8f5f33e46f65e635a84
591 | 470dd418057f9946a30f938496151204
592 | e2b1b05de388e7db3b52c6376e0759d3
593 | 4cb25759388ec29935fd302efa96f6d6
594 | 4da74e02ba23a7e98ec703e791db2af5
595 | cf571875efbd60fd3d2617f9171b5ccb
596 | 855a071aeff2351a593ebeeedbff73b
597 | f20e7f4f41f323a04b3c42e318f3affc
598 | 3d5084d5e7654bd11cd6319703a6cb25
599 | ffa7680b18ede5cfedeed2a7fa983956
600 | abc6cff85c8282cf6fe2eb61cd6e74e5
601 | e4ca81487385c5f490ad276cd2af3a4
602 | 9cff96bae9963ceab3c971099efd7fb9
603 | d1c09e81d31e38868cbb8bac2032149c
604 | 1d878962087fbab2350c104b3ba8ddb
605 | ce424dd12ccad62575206c207a147264
606 | 5d2ff1a62e9d58baeaf288f952624966
607 | cf651d12e2048e1a4b3c42e318f3affc
608 | e2c68936d051b926646568c803ce68ef
609 | 60fc7123d6360e6d620ef1b4a95dca08
610 | e66f4bd6f5075d1755f9a00acc25f137
611 | 3af6ec685a6aa14e2f99eeb199d54554
612 | a28bfe80037449cf5eea3e3d89293379
613 | 53812514f0d50568efc579970fcfc006
614 | f05f6b3e7c0afdb352fc7e973ba7787
615 | 4c044b514ab3e0eb6eb9b08c8a74d159
616 | 9e0b01fab5d15b768695754f4338760f
617 | 2b73510e4eb3d8ca87b66c61c1f7b8e4
618 | 1bce3a3061de03251009233434be6ec0
619 | 402ccbc3f5f26c095f8ca2b92d19277
620 | 34e48812eaf19420499252a7ccb366fc
621 | 7140d5cf3fb0c528b43753a53e4593db
622 | 40a6ac0c94ae686e8dd711af5650bdcf
623 | ec4948183b308204e4d5ca1617e68f91
624 | 9c18d53831315667af78305d7f7113c
625 | 29ec7e1541397b0e5ae252905262c0ed
626 | cff485b2c98410135dda488a4bbb1e1
627 | 389751629226a005cbde89e0c48a01bf
628 | ead777f4e8c5bc346ad8177a9d42d3c9
629 | cfa5feb7486f88ee1b8fe07f15de05f7
630 | 8cb3672d113ac9aaef188758bf2e3a30
631 | 9451b957aa36883d6e6c0340d644e56e
632 | b55d24ed786a8279ad2d3ca7f660ddd
633 | 26b0765b08c86fed52db1d2b4104f173
634 | 20ff83acfd590101be65001d50394fd9
635 | ba6c0baa0a122f8ce2aa36c9e5ae7ae
636 | 


--------------------------------------------------------------------------------
/splits/content_lamp_test.txt:
--------------------------------------------------------------------------------
  1 | 89f8c456a55c3386157d629c9921fc15
  2 | c6755ed48456490d2744bf8869518694
  3 | 5ec6c52d6d5dbbddded4c23d05709216
  4 | 6b10584984035b088314f68ce9e12e4c
  5 | 596ac8748f6c946efcb8d8c6d4df8143
  6 | 7b005e23eae2768eb08c032bedc99529
  7 | 55b002ebe262df5cba0a7d54f5c0d947
  8 | 42129d6b04cb9038b2f7093e7efce142
  9 | ce406a32bdc610198ca4aeb5e3b33af7
 10 | 923097cec128ae77469cbaa3d6420fb4
 11 | e65eb892b1d1730e52470de2774d6099
 12 | 23040992da19679aaa7cb30470f3273c
 13 | 297d929269bb62da43fdcbcacbbed64c
 14 | e7552c8c718a1a109f2349486c570dd4
 15 | 6d7aeaf3c1705cc5fda82f1d3dffb320
 16 | 763ceeaa4ce2ce1d6afaa22adc38077c
 17 | 60fe504827e96df11fcc6cd2b8a40871
 18 | ea8eb3f3d917d61850c421917af4a474
 19 | 75cd24d6b485e9e01735ea0e092a805a
 20 | c78a8f317896b79f51f77a6d7299806
 21 | 511917ee5ee2f91649244b68aadec703
 22 | ec639d4850ba9aa6fcb8d8c6d4df8143
 23 | 3469cdf83a3cba1f35836c728d324152
 24 | 2691d3491111def44674c364bb213983
 25 | fafef4866d1a74f3fcb8d8c6d4df8143
 26 | b78bef16d4f44844931e98da3a93e73e
 27 | 7a9872f1e0cefafd7d8864caa856253b
 28 | 3533b9eff82f2f9cf22140029982c6f4
 29 | cd0f2eaac6719a3ddb039d8689a74349
 30 | 9fc3ddc511f4ef62dced62abd38a02b0
 31 | 979867c99d8e0b7a4601feca428b2996
 32 | cf09b30a89f70929cc67b3de75c44c76
 33 | b6953f683e8b3feb9571d807bcd25673
 34 | 112058b3f8c94177d2dba55bc7acf0bc
 35 | e12e898cceec4e23f51f77a6d7299806
 36 | 6c4c45af95f811e479414e04132a8bef
 37 | ca5a19cc0a5f34273b8ea30c1700f67
 38 | 5516c456d95ec0df2de0bc4fc4d02dd6
 39 | d1948365bbed9de270bb6bcb670ecdf5
 40 | 600b2f00113ad714e2367b9e27f16a71
 41 | 5c9f3efb7603bd107c57db67d218d3b9
 42 | 181ec75aca2de25f6dbdf247ab8522eb
 43 | b2e4c14ea09658e3d0e9f1d4665fda29
 44 | 6ccb43088eda061dbfc838749f053cf9
 45 | fa9dc903c8324b85e3d605ae370b7c5c
 46 | 76da74f3a8f15fe8bed8734977b26c06
 47 | e4df4ee697e71902f95e2a1e9997b85
 48 | fca3ffd4ee694c1a9c0ca344f487323e
 49 | 933176941f95f833fcb8d8c6d4df8143
 50 | dc5e7460dff922246a44fdd49dec8069
 51 | 69429d8ffb5009a82060e7309fc3fc6
 52 | 2fa7dbc66467235e2102429c788ba90
 53 | 4c266f2b866c59e761fef32872c6fa53
 54 | 6dd3bf7b105e88e79d3154c451a33fc0
 55 | bda58405e4e3319d809772d66d13ee02
 56 | 20cd92a6797a9ee12ebeb1e6a8111f53
 57 | b45b8df0557da6acc14d5c159bab8297
 58 | c1b939cc403a0662664b3b9b23ddfcbc
 59 | d582dce8cd58bc57899bad344dc01f2f
 60 | f673fc77f397a061d49b2e04785f8492
 61 | 5bd90c0cb1f01b24118486d21a76684f
 62 | 1833ca8ab16a7b7a43448fccd73e2957
 63 | c61d6c246dde340462a510b8f97c658e
 64 | 8422870b0a65255d5cae1a083183a237
 65 | fbcd17479bc96e0a899bad344dc01f2f
 66 | 98cdb45ca9925feb194eb328dc97c7e2
 67 | a801be11157a7f243d39d8012919dd25
 68 | 44820a27f86f13e7e420612cf7bb547c
 69 | 8425fcfab0cd9e601f0d826a92e0299f
 70 | c5a69f02323e087181d0740b20dd8fd0
 71 | cd7bda99f9797d8b1878e92fa20d38a6
 72 | 6e51353655289e10ad885ade4bf3150c
 73 | 52e15c498d33748d53227dcd0d547ba6
 74 | 85b3f0b7d9968d79664b3b9b23ddfcbc
 75 | cdbe11124dbf418167ac0fa90111fad0
 76 | d378c508566d68cb48d2aef7552b65e3
 77 | ff22bf19e2ef19d12f7ffc95c59dca52
 78 | 3f22e6719decb1bb3a9ec79b9c5da99b
 79 | fd15a43ef545096fb6f5e7b313e4eaae
 80 | 374ee0d01fb25ecc9bad7d7f6ef7bb21
 81 | c778a6ac6cf0c81d4904d89e9169817b
 82 | 7bebdd742342ba93febad4f49b26ec52
 83 | 5aefcf6b38e180f06df11193c72a632e
 84 | d0018775e9f2d109fcb8d8c6d4df8143
 85 | d82a17b1f646e95dfcb8d8c6d4df8143
 86 | 7d7dfd2bd5cdcc4cfca61b0bec17b8d3
 87 | d6ae7a5542800519fcb8d8c6d4df8143
 88 | e9df996dd33c009bfcb8d8c6d4df8143
 89 | 53ae95290cca57d430c35ecdb9dea035
 90 | d7a10c837316de2f3ca265f557f5dc3e
 91 | 7e5b5fa94575f873c2e0b170f2ad8bc
 92 | 495af808806f1727a753b1b88fff4abb
 93 | a87825df690f900c408d050f12518231
 94 | b6efb78876150d45c94b622f1207af2
 95 | 7ea1864f38bc326696a3517f50eeb9f4
 96 | 525109ea19096fe8eeee03ae21af2d39
 97 | e8927203fbdbe320c02170c33e00ea64
 98 | 37aac1913201b058c02170c33e00ea64
 99 | 45f11cb4099c9c87bbc7a6acbd8f058b
100 | f2f6fbeacda7cbecfcb8d8c6d4df8143
101 | e7da3cd73ebd81146251354a8b1397eb
102 | 5383c9b60d5b66a2d22730b0728b2fc9
103 | caeabb766b3b9c67d3c1dc91e223304c
104 | 24c91045ef1c6a91e4407e92c4b0344c
105 | c263fec31c8d33874f51382fa3549a00
106 | b02bd8e5ef9cfe354b3c42e318f3affc
107 | 47a7bbd995c37d3d4aeb986669a16017
108 | 1dc135b611b2f4b2fcb8d8c6d4df8143
109 | 64f61c9c81e3eb7b8aaae3d020f5ddf8
110 | fd074c0819b9934f73b8ea30c1700f67
111 | 8bd35721e2767dc43225afab722d9fd2
112 | bfeda9055368d2dce76bc197b3a3ffc0
113 | d2c124b8c6a888fedc7a10bd316015b2
114 | 3fca250636e2b47a8d0fc77aab7a8d33
115 | 86d7a728dc35d634f800b597bc1c1eb5
116 | c9b4209f1a7e97cb90a9ce3e4b15521e
117 | 98c7c2542dddd40af24f994bad42f06e
118 | e20889cbe2d917787d616ef0c11d6a7f
119 | 522bc10920249e67141c66e2b49d221
120 | 3a5a0f4c78e17b284f0c4075db76b7c
121 | ab02e202accb9b4b65b77a565916c7f
122 | a186c58be79925634cc30865d6337b9c
123 | c25cc72cd06852e75bbea6ee257e41cc
124 | d748241313e5664696a3517f50eeb9f4
125 | d1ec5f73a0d3d6e4f3ff0017952fe4bc
126 | da09a8c73054e9220ca3aeb14e36a45
127 | 3a0719c32c45c16f96791035e86a30f4
128 | d73b4313372ca6e1a6a7b6e78d8d5bcb
129 | 4bb0f244d4abe00b44949d7685cb63ea
130 | ad7fedee24a70d82a5f600ed2cf472ac
131 | 1499133658ea746d713f2e93cbeac35d
132 | 2419edff383179cbc53c4281a65fe22a
133 | a3b93f34b7e36cc52460e48c67c108d4
134 | 377df6e7a3d84edfa123ce0dff5bf4e6
135 | a82af4e7e81334f8876b399a99a15c0f
136 | a3a13218d61daab550903fb6fac1fa18
137 | fbd59db93e38bdafc8687ff9b0b4e4ac
138 | 7092dd68172560f410edd100dffd8d85
139 | 4bb676c497969016de98d10ab5975b59
140 | c3d57dada3819e60fbaaaf5884f2c88f
141 | cc3eb92ef1319ba38a3c32fbf0f86f95
142 | 73378b714c5bfed2b922d818b19db1e
143 | eeefddb3f2ee93dd49b2e04785f8492
144 | 9a976020602ee60b5fc8f4c1fc00b380
145 | 19fc4044912f5cc4869594a32151bfdf
146 | 34ce1de178694f87e76bc197b3a3ffc0
147 | 51fd15743cd0568219179d4701451afa
148 | 8f85c2195890ccf671f0940f5ed452dc
149 | 181d2b693d7ab89457a48b78ff77644d
150 | 1c7f8ad295bcc3795a233e989a47d3aa
151 | a54ea55a07b96a237b2bb75885cfc44
152 | f46d1e234c05fa4e62635f8519c19a80
153 | 2269f268b32b40b35fc8f4c1fc00b380
154 | 7a67bb268436b3636a578f1b525d976c
155 | d16bb6b2f26084556acbef8d3bef8f28
156 | b54f6d30b6edd7f1579cea75b38cb7ce
157 | 99d884a5b3a6677bbebfb887e83028e1
158 | 53afad2e573b26b141657e31b569b105
159 | 35975525ec3d835046f58f62995211d4
160 | 451fe793f6e8fc29276206fae5d3c473
161 | c7aadb7ac29ac778aaae3d020f5ddf8
162 | 715be273074283557062f2d72cde5c95
163 | 89622a50662e28d56c09b6371c58b533
164 | 20af3e3a79e7023a6c342cf382162bc7
165 | 409ff705d837b30ec3c3e425b20b4636
166 | 571027d7f9639bfa7d7103fc1114c50f
167 | 72bc0272ab1ce5a3f8d6a4359d6a181b
168 | bc218fcb647e7127984fb9ec7e40829
169 | 94af43cc530f8c4649244b68aadec703
170 | 4865be9773c699bd2fadb0a8dd9104b7
171 | 3a58b059261aa07229a42a0444436860
172 | 3766b272cd3836cf28699debac30ad6
173 | 6999ab054bc900d1868fb986bc092533
174 | 89ed63af13b79f3ef42a90fe4baf4591
175 | 1f30b28f2dfe65a21735ea0e092a805a
176 | 44d1dac026839e25f690049a092c5efc
177 | 19171a11ad8bd9d5411a00390d1cd315
178 | 6bf0f3417f775d2c2cd2160e449d45ae
179 | a7b9dc38c80e86fbb13604bbce4eb6a8
180 | 1ef03aab18277ff1ef3a2c64cef919d0
181 | 22ca1d5fbd8e6eac7b79156a61ad4c01
182 | cf280bbec8017c26655715f3c8480da5
183 | 1b957f2c258ed744b3c42e318f3affc
184 | d0fde1daedab10365240248232b90795
185 | dfb6553d8e04cbaae1263552aa9a2d35
186 | bece8f6d89e653e6fcb8d8c6d4df8143
187 | f12822778713f5e35b36bbc16e99b441
188 | 255dd61372b3509a41657e31b569b105
189 | d6d7fb290b69e985ee2b478fec745c0a
190 | f5c61ca4acfb7f5435836c728d324152
191 | 97b7d9aabe38f91df11c97be803c47d
192 | 6b9f509d91eeef913efeda73d60343e4
193 | 852feb3fca95b6d5dc3653f8341633a
194 | 38c6b87674e80ee8515596bfc4f5c627
195 | a911474d0fa043e3cf004563556ddb36
196 | a5fc64e1faa85794de03ab2a27ba7531
197 | a0dfc97cf85ddccdac42bdc1d2df4a3
198 | 60fba8438739f3cfba9ea396e14c59f2
199 | 79487b518c97cac315b5ce4486462d3f
200 | 7bc039fffc79dec9e680aea9bdb841f9
201 | cf5b6127ac18e85b6aea2f18ee404fd5
202 | f5a121812ce16ed2578f5640449b6f5
203 | f4e1a4032b1686cec35131da26f8061a
204 | 77883e18cc08859ddb1afe6c464e7652
205 | 967b6aa33d17c109e81edb73cdd34eeb
206 | f8534299ecce5c16eaf14273fa406ffc
207 | dba95c4ca95048982d9c07d3b9171829
208 | 2ed8dcef657845be4a8e02787dff638e
209 | 9fdaafde365beafc37f7ce56c66316ea
210 | e293003f297e155624d1b7c6bfe44fcc
211 | f97506704760741b460fa882e24b7e4a
212 | c97cc6e7fd4b4a07d650f729d0ffe69
213 | 40c778a9ff366c2bf36ea1eb6542fe7e
214 | e98c05f4cc8c7afcf648915c85184f8c
215 | fff6acd5b543ae02a9bdc22a1e02e82
216 | 9b0c6f3ee4a7965644b289cb940133b8
217 | 44cb50f7614a4574d09ae058ff1abff8
218 | df0823f1c81eb6bbfcb8d8c6d4df8143
219 | de5799693fbddbe3c4560b8f156e749
220 | b4b15a84b9067f94a75d03186a0409e2
221 | 330b05e262c93e216078c74a96498820
222 | c904c93a0a1739e5f51f77a6d7299806
223 | 54a7ea6d6e297a849eb34048e600e1ea
224 | e1fe4f81f074abc3e6597d391ab6fcc1
225 | 66acf7f6883db6a377b9297f3055210
226 | 8ce777fa2b40476cfcb8d8c6d4df8143
227 | 9c2699c78add2e5847ecd534f9237f9
228 | 6778917189e50370a894da3d4a669d7b
229 | 61b57e8b5da8fb13d527a9a6f5a872b9
230 | 19654d8fe7090a887eaeab1f0c9120b7
231 | 49cd0dd4d1c008edbbc7a6acbd8f058b
232 | d4bbd93c0d85e77d7934a0d24a61231
233 | 1a3127ade9d7eca4fde8830b9596d8b9
234 | 6b2a590446ad5794b10e111f2d30684d
235 | 45d24c9106f2cd7614cd86cb97af8937
236 | 5a502ebda119949ef7dc60c6a4d98c25
237 | 955143d7f0b5c70fef76898f881b76a
238 | 3bd2db092bede98957e3b0a0099797c
239 | 397f450de4fc6fd4fcb8d8c6d4df8143
240 | d6ebf710756c5839f8d3a35c7c106515
241 | 16327d928854b34ef11c3739edd52fa3
242 | fad0ae547e1facc09f97ca916781e800
243 | b8e26fbbb44def8d1deb48513aeadf93
244 | aff71b0d462342aa4bf6dad97590bf33
245 | 1e0f7ff92144792ac3ab13a0474803d5
246 | d450da2cf4d0b79bb20310112468976b
247 | f01cf64f05572ac4b509f4ddcfa8ca1
248 | f672eccfe1739e962dcf15e1dea29cf0
249 | 8006e3cb3ba934a05b977412e02c412c
250 | c60a072ba63c12cd8ae0d28389a2d006
251 | 18145f4b303c37f11c3739edd52fa3
252 | 6b837caba2f63098360a9d5ff73ffdad
253 | b4e7c74a6e6685d2339c933a8cb966c
254 | 5ed0d3a50d9d77dcf1dc60fdf1e64165
255 | 8f5347fce0d9b517cac7c8ef7fe2392d
256 | 2d638c6b6b2feb9248da169d95204ce2
257 | ab7895189ef13e754f3443b22038d340
258 | 5c8da21eabad2dfe3d59e2f2ea85dc18
259 | ec876529d01d4df490ad276cd2af3a4
260 | ca968e46ba74732551970742dd566321
261 | 2ce7732982343c1d9792f6094a78f8d5
262 | ccd12ea2362ef81d8bb3deb7fab7c9b7
263 | 792c3698dc7d200144175b4dddf5be08
264 | 7869e39e4fcaa1b7ab26a588d1ab0ca4
265 | 1e4fd4cc6fee7cb2fcb8d8c6d4df8143
266 | a4b3971680744f7f1742918a871fc8cf
267 | 348d6ddf9e02cbddf647dc544bb0ab61
268 | b15485a55d855bf980936c51aa7ffcf5
269 | 914a876b24bea577e97426e55fb77981
270 | 3e7ef877f826230dedde7b5a5ea6d004
271 | 26ce3db3122afe74a5f600ed2cf472ac
272 | d13f1adad399c9f1ea93fe4e1ab627a2
273 | dacef14e18d54f3857d60a3bdfb4976c
274 | 956ef7ea0d496de01735ea0e092a805a
275 | 703b4edd4d407a10f8ddacb75f806b29
276 | dc6c499e71d04971d22730b0728b2fc9
277 | 853c5ea3c279b9e9f7887b5467c02fc8
278 | 183e79a892e4294d65666d9a7426c2c8
279 | d6a5a84cc689a2bd620365f6656fe3
280 | 367546484916da6275225719b7a8b341
281 | 1e5e1ff56c27c0d2adc5f5aafedb1c38
282 | acaf95927290a89182bfcd34215ccfc7
283 | 4f62263f7bb10280a5f600ed2cf472ac
284 | 10ba42fc70f16d7f41d86c17c15247b0
285 | 1112f253e122dc8273111597f45b8227
286 | d385523f0cd93d48d6084fb53091249
287 | 31c9507ec40650d0d5506bacc83bff24
288 | a5a31ea56d8fbe0a72ad95ccf7316565
289 | a6ae06e879fcaa019e26fe04e3dd51db
290 | 609dfe9367c0e64e2b520984c067934c
291 | 25427fc8b45e4c6370ad12dcb213189e
292 | ea71ba1d8d8c8e5888a1de3dc61bfeef
293 | 2cc1ea376c68da216502fbbc8833905
294 | 18ed152bad2c123b4b3c42e318f3affc
295 | 53d7272eee54bad2f841233486fac2b
296 | ae37dd444b0813b8fcb8d8c6d4df8143
297 | e487374a244b5f03b428462f49e66329
298 | d3a3d52234e722825208aab875b932bc
299 | 200fe239e1eac6a2651636b7e802cd3e
300 | f36cab1570442a83466f97f37dccbde
301 | 1f4df93fc1ca81c985bde43adc8959db
302 | b10efcf01493c922e7e684d25d4dcaf0
303 | 75c15dd98de4ff17bd4bf7024dfa167d
304 | 16249c6e2a76400dfcb8d8c6d4df8143
305 | 47ff70265cba94df900cbe2c18fd90e9
306 | 8913c3dff1651a316a3d00506cb9ed19
307 | 896abd405c79547086485c798787f66b
308 | 3c4d8c4ebe9dedbc2cd2160e449d45ae
309 | cf280956401024fe92225eae846f578f
310 | 7893d0b50a7b6a768ec45924afa4ac91
311 | 4ffb03a364a13c376b41b8bcd0404ec
312 | f1cc6b6fa75bd67ff51f77a6d7299806
313 | 52cd206dd4674bbd4fbd95145f67665c
314 | 68abd2755ff4588b545bbb1b2e749fb8
315 | 20c9d1713fbc0925c35131da26f8061a
316 | baffbaa9a9338f331735ea0e092a805a
317 | 78c87f00ebe9491e2cd2160e449d45ae
318 | 776e4b38023091002cd2160e449d45ae
319 | 989694b21ed5752d4c61a7cce317bfb7
320 | d9f6bd064c9fd456fcb8d8c6d4df8143
321 | 97c26d66399ecdc973b8ea30c1700f67
322 | ed1de19103e97b74c30ba10ebbf8ea21
323 | 48f878a6176591190c2e24416edfe5b
324 | 6be148a3e219dc68e6597d391ab6fcc1
325 | 3a3d292307c4831f4dc0ed4c2f72c4cf
326 | 60d1a7bf1e70c526befa8f2022732db1
327 | 1728c555de071aad3ea96ac97db63fa8
328 | f049bbd180d89cb5490ad276cd2af3a4
329 | 1b35500ce44ae7e344b6d51c32a5873f
330 | eaca02e8f065925dbaf5b49ad7809302
331 | 4b6ba211c9731d334c614ad0ec154eb5
332 | 574e0de3cea53dd472b623d6378b1581
333 | 4003077668e23d6c9998b4eb812699dd
334 | ad01773f3f53bca3a8ffa3a6526018ac
335 | 8c4539bca010eae1cd74bafe512884c
336 | 3bd57e05db01e224e7e684d25d4dcaf0
337 | 456a6dc3d369a749519f3f3e6cd6d1a6
338 | e365a641480635d330c09d86acf3d5c1
339 | 12e8d8176f2bd111978e8f21c8f49a92
340 | eefbd20231e62d535c10b08ea69398c3
341 | b384676ddfb3b657fcb8d8c6d4df8143
342 | 89cb9b2ad175b833cadf6344ec272e8
343 | b9d353635f7e1134e95ee7559a2a873b
344 | f7093dd024fd09fc7219d6d5c4afbaff
345 | ae67ee6392fe8ab94e7cb04dd663c825
346 | 964d3a853d6e5a642b1c313558664cae
347 | f8ca4809b68d1ad6157d629c9921fc15
348 | 93a984496599a5b82b151d8b52c53b90
349 | 27ed76ca359d6eaffcb8d8c6d4df8143
350 | efedd8c990f9926c48d945252c13120a
351 | 930d6656e3df0635fcb8d8c6d4df8143
352 | 102273fdf8d1b90041fbc1e2da054acb
353 | 1efd03d9264973c9f2098a9f7fc86999
354 | 7a3abc9f27ffaa0418a6353ea60f11b6
355 | 185b2436cc0404096ef2faffa907bc32
356 | 30464d7e164a40aa2bc52a80abcabb17
357 | 13badfc11837c16cc01e0156f398b4d2
358 | de93987085cf4dcc5208aab875b932bc
359 | e4d3e153ce7f9904e76bc197b3a3ffc0
360 | d6c6665366854e6abec99d5b4657d5b1
361 | 2f216bc398d3da98cddf96969ede3013
362 | 55de711b4c86b86188e7662971dc736f
363 | 217bf5bf88842058b8a06a6203bc49a9
364 | a06089b2d68c974c6273cbd9c7cef4c
365 | 4f3f01e4b17d018ddaaf0f74e020d2dc
366 | f7495b2e74c906b5922ab3cc7ca1ae2c
367 | 9fbe081afc5868ca5c9ed170ce1aefed
368 | 370ff00dc6f08167c3bd24f986301745
369 | 6e2ccf5c1b61a09b6e56ccb2c92c79c
370 | 169d73f18f7b17bb4a6ecce2eeb45768
371 | d54d7977d760f4c3bd16d4490a10a752
372 | c0a0f01bf127b972257cafc2ddee5167
373 | 9d1e04bd3df11256bef045a510a22fbb
374 | b88ca09d13a5a472e3e80050b31d1851
375 | 833baf068fb6225c99570bac758be6a4
376 | 50a3d09ac90370ec9c48f338871146f5
377 | 6770adca6c298f68fc3f90c1b551a0f7
378 | e37de82cff38f88d1735ea0e092a805a
379 | 6efc48bb9267c2ab4c6deb9ede0648df
380 | e1fedf82bf8fce9eb8b431083b6191e2
381 | e120efa70ef8efa71ce05d96d33be415
382 | 69762de7892483b64fa8d6439169bda4
383 | 2d4c4ceacdd41cf1f8c0f5916f81d758
384 | daaca6107846a666a8737fcf23389014
385 | 608b5df0d5946c68400789f7122dfdab
386 | e053e531fc4341b5fcb8d8c6d4df8143
387 | f9ee021d829cb2ba1cff7132ce500fbb
388 | e0aa085dfdb0ac03ef3a2c64cef919d0
389 | dd284c442afd361e37f2340db925336
390 | cb4b887b5acd27cde76bc197b3a3ffc0
391 | f40c7b19234b07c2c8687ff9b0b4e4ac
392 | d42435906e79e4131de8e551fc6cf2b0
393 | 2ceeb17225f4e460d493bfe20f94b6ab
394 | 9d66a6faebd46b1d68661782af60b711
395 | e94aab17400945413225afab722d9fd2
396 | 551f8026ff0917c781a172d69c52a28a
397 | 5929c6937d617f3acf7d397dd220c7e2
398 | e8c75d7c6f151e2b3d23022ce06f940d
399 | 29f2e3d2815a018ba77f16c25b1f7f4d
400 | d1aed86c38d9ea6761462fc0fa9b0bb4
401 | 684b06c007aa83873c2e0b170f2ad8bc
402 | 3781aa0aaed95b8049244b68aadec703
403 | 8522fb13bfa443d33cabd62faf4bd0f0
404 | 8adca6727b3275cc305056296c226e1f
405 | a0e4661a3c458405899bad344dc01f2f
406 | 774d99cb78b5b82e3a5e6305a3a7adee
407 | c561496324b6d8154c5b22ae639d5204
408 | 4242398ccded25abd3ba76930e17ffc8
409 | 2cba43cc26f174a8f9a65dcd8ee605f
410 | 38eedb7c36b785fda81f841e85c630d5
411 | 5f865b98b4be6abf35836c728d324152
412 | 5580b95ab8e7806c6c5b8009db95f66f
413 | 873aad4a222d541a91c2792fcdc1ca8
414 | cdf8043d57863c1b17b431cae0dd70ed
415 | 13daa0657f5c3e32cb0c0d433974e32b
416 | 9c2a936a664a59823c10371ef1aaa57c
417 | d1dc19013dca2182536407ae4270b9be
418 | c816540b4e0eacd57697d9c3588bbfc5
419 | 78f85448752ae2963873cf6e670bb8b6
420 | e4201614cb3590e41735ea0e092a805a
421 | a138582b1d0b9cbb137af984a9f45d65
422 | e2e7f45670fc5e369a6c869309041adb
423 | e04e5a96efd77a6ed2f5c44a5922d7b9
424 | 21ba9de4d311ff31cdb282e42e89414c
425 | e13a855926f25ffc5285aeabe3f6e218
426 | e35009c75fb246453f02f5b8959142cc
427 | 69ae5e9ce88c9262dd0bffa2f83687b2
428 | c5d999b26cc9ba381735ea0e092a805a
429 | d1b15263933da857784a45ea6efa1d77
430 | 2ee70ee71a0b7caeb15194162f658e87
431 | bf792ee1a5570858d0615e6a68ba2d50
432 | fb8be091d77118ab90fd203f931c9af5
433 | 266d6b136cba49504b3c42e318f3affc
434 | 4d63d3865d635b2be7c7920f6a65a54d
435 | cd05ada0981bd85a2c528d33bca1ac2
436 | dfe800d8d8642e9647bc3701b998a7d5
437 | 7eaa7d0cadf48bbfa9bdc22a1e02e82
438 | 22315c51156a826525b5da4000a94497
439 | ca6812040234d1ecf57534363fbbac3
440 | da4fe1c3d5b1eb6ab2b4f8bf5db83688
441 | 55077c2175d97b8889ab11a408196888
442 | 435600f37bac6ed9a28fe47978e866bb
443 | d939b56b53aa7e7c42f80363988bcb92
444 | 13c127aad3fc8e6af51fa0238791f5dc
445 | 6272bb389bb524f0c8e1fef75f114ecc
446 | 6dcbc7efc9369de386a5dcc6ebde687f
447 | 4c5a9be10106d239b0957d845ac33749
448 | 6267ef99cbfaea7741cf86c757faf4f9
449 | 6f5b104f7c1cb4bc636c7e486232cac1
450 | 3ba4b7bb7b6d89415461e7d030e03e48
451 | d54b55ff9b0923c12cd2160e449d45ae
452 | ac662716b87687be71e364dec61013a6
453 | 375c6cce56f3967ed323d15bd4f8b2d
454 | 36a1e900d1b4d4b287b2013bc93e747c
455 | 24927157e3a53c1f91cb6b6c47a03f13
456 | 54ad0800a524a96ee039576a17a0737d
457 | 8b85d01ba70a09e9a5f600ed2cf472ac
458 | ef40f27470d99d6fcb8d8c6d4df8143
459 | 28d35fb9035fcbfffd5c9a0fa28996b4
460 | 2d3c98d5d85f22a127babbd370e736b
461 | 85335cc8e6ac212a3834555ce6c51ffe
462 | 7d097f4b38f0a8a65b6c7da997b0e5e3
463 | 534c7e2c9495d7987b6fd5468f603b31
464 | e7ffebf4dd9176542cd2160e449d45ae
465 | 


--------------------------------------------------------------------------------
/splits/content_plane_test.txt:
--------------------------------------------------------------------------------
  1 | cfaff76a1503d4f562b600da24e0965
  2 | cfb555a4d82a600aca8607f540cc62ba
  3 | cfc075c635df8a7a94b9c9a92aa36f8c
  4 | cfd42bf49322e79d8deb28944f3f72ef
  5 | d004d0e86ea3d77a65a6ed5c458f6a32
  6 | d01da87ecbc2deea27e33924ab17ba05
  7 | d05cdbdddb68865d2dcd3faa5a0a5f24
  8 | d06035fb4ba89c91f119374ee5d5f944
  9 | d06105ee2a2ae27c51008e496c6cfd2e
 10 | d07277bc3c95a365bd46d022fd7d80aa
 11 | d08471df3e76602427743256ca3834f
 12 | d0ab3ed71a4ac9319d1eb836604648db
 13 | d130dd0c96152140bc0909d98a1ff2b4
 14 | d13d131a649c5df38b96ae1a0a8b84ec
 15 | d171967c6353177bb87697d3904b168b
 16 | d18592d9615b01bbbc0909d98a1ff2b4
 17 | d199612c22fe9313f4fb6842b3610149
 18 | d1a887a47991d1b3bc0909d98a1ff2b4
 19 | d1b28579fde95f19e1873a3963e0d14
 20 | d1cdd239dcbfd018bbf3143b1cb6076a
 21 | d1d308692cb4b6059a6e43b878d5b335
 22 | d1df81e184c71e0f26360e1e29a956c7
 23 | d1e3bba19cb9447dcf6c095014f481a4
 24 | d20e3ed9b3430672bbf3143b1cb6076a
 25 | d21c556af88582754c3a35cee92bb95b
 26 | d221f607d5b5c553faac198e88c3dbb7
 27 | d22521d217d89f8d5b1bb801ea1e2db7
 28 | d2412f19d33572dc4c3a35cee92bb95b
 29 | d24e6c81b5261fe5ca2bd098b9203af
 30 | d25572a7c7bd40a72d716a8ba99beff8
 31 | d2815b419e61dbb0b87697d3904b168b
 32 | d2842bc324b3dac5bc0909d98a1ff2b4
 33 | d28a3cd771b2bf1e71d03b466c72ce41
 34 | d2bf5f39131584c0a8cba409c4409ba9
 35 | d2e2e23f5be557e2d1ab3b031c100cb1
 36 | d2faf50d6d88dd0690baeef8ba5b93e5
 37 | d353b227b279804190b1d6deb98feec6
 38 | d3580448933d00fd90b1d6deb98feec6
 39 | d38922599bc74f6da30fd8ce49679098
 40 | d39075b8eb890a898deb28944f3f72ef
 41 | d390f0246fd43cc8bd46d022fd7d80aa
 42 | d3b39374c97d39da7dc01d89d8a05b74
 43 | d3dcf83f03c7ad2bbc0909d98a1ff2b4
 44 | d3ecaf6bb9395131d563154e026c3490
 45 | d3f93b6da62fae46a98ae8c73b190485
 46 | d458335c758930c210b8e0008ef5faf6
 47 | d4849eddcd93569ac119f94203b4868c
 48 | d4a8134b2463a8bca8607f540cc62ba
 49 | d4aec2680be68c813a116bc3efac4e3b
 50 | d4d61a35e8b568fb7f1f82f6fc8747b8
 51 | d4dac019726e980e203936772104a82d
 52 | d4ed7de4aa7799f066cf1b4a8fc3914e
 53 | d51bd83c27fc3167ba4ae55719e5e195
 54 | d532a5abb756ebebcc14f1e6f4f4f49b
 55 | d581b2e10f8bc6aecc1d733a19631a1
 56 | d583d6f23c590f3ec672ad25c77a396
 57 | d59cd5f2012a1ca1aae46a5cc955c766
 58 | d5a94c9f09d238c4c3a35cee92bb95b
 59 | d5ad529ad399086e4e9a6f7cd468e49d
 60 | d5b08d1355502d325f83a2299c09f64
 61 | d5b78307fd9a0764bc97347c46fe15e1
 62 | d5f01e2aa54bbf28ca8607f540cc62ba
 63 | d605a53c0917acada80799ffaf21ea7d
 64 | d629589ee52d48ee4d210d9468aedaf2
 65 | d639c8d2f55982558b96ae1a0a8b84ec
 66 | d6ca5966c5ed5b86da2b0f839aba40f9
 67 | d6cc7ffd165de05e2e2de556c136fbc8
 68 | d70d648947c65b1eca8607f540cc62ba
 69 | d7287ce98d521db5ca8607f540cc62ba
 70 | d72a483cf8a0cf2bbbf3143b1cb6076a
 71 | d75ce9ee8a64adfd98459325335edae9
 72 | d81042a53dd1cc5bd90bfc986bc4c94d
 73 | d83300deab42c100eb9db4e832a6dd82
 74 | d8452d4fe51f2bab3554ccf8c30febe7
 75 | d84bb293898861ed9b2acbfd8323f804
 76 | d8a8e238987fed8dbc0909d98a1ff2b4
 77 | d8d9de967255b4c562b600da24e0965
 78 | d919249737749c36417568af9ae9577f
 79 | d99ddce71988c822475045ea78b20eb7
 80 | d9d282f79262ebd4c3a35cee92bb95b
 81 | d9d39f688eb9ba58b3f2b01de37c0b29
 82 | d9dd8dd2c422dadaad70e50d5d7d02a5
 83 | da12fdb456d5fb588b96ae1a0a8b84ec
 84 | da26509e7d1864a162b600da24e0965
 85 | da67955425ffe66071d03b466c72ce41
 86 | da6faddc7079ce8ab6befd5df74fffa2
 87 | da9d111e1175d318bbf3143b1cb6076a
 88 | dac25e0fbef7dabaf1692146d36a4a3d
 89 | dacb447d7820e7f7ca8607f540cc62ba
 90 | dadf41579d385b0aacf77e718d93f3e1
 91 | daf0298bbe90dff19751c7a6f15617f4
 92 | db02eb57817e4b4d22362be7f5226e91
 93 | db4079b8c7d3d674ca8607f540cc62ba
 94 | db5fa6a73bbe6d35ca8607f540cc62ba
 95 | dbab9feed7e936cfa87372b03d6dc78b
 96 | dbc521b1d4c2d308303d346f4be7d4f
 97 | dc344ae06e26aa55615ba7bf3620290d
 98 | dc3bfc83bc2d1db643afdb9c81ff2967
 99 | dc7c5d12854b9467b96212c8f6cd06e
100 | dc8d9003cde43b66c8727b27ee96a4b7
101 | dcb5bded8772135b4295343ee7255799
102 | dd465efdee6a57e966cf1b4a8fc3914e
103 | dd48aa92170bdde04c3a35cee92bb95b
104 | dd4da4309c12d47bc2c2c81e2232aa95
105 | dd9e42969d34463aca8607f540cc62ba
106 | ddb96cc263869979f446f92b52bbd82a
107 | ddec69970cbc4d29112a90660b187a10
108 | ddf4aa5f68f89616bce962d6c4b37336
109 | de001f9e2311dffb7209009cfb89d4bd
110 | de3a0bb3f0ca87a5674fc9582804ad0a
111 | de45798ef57fe2d131b4f9e586a6d334
112 | de543fb92592aa48236a74f773a58aa
113 | de65da5cdc92b4aebc0909d98a1ff2b4
114 | de72864008c4db8bdeadc9ca0263db5a
115 | de776175878f17d1f4c1adce71073351
116 | de863b025e53c9a63554ccf8c30febe7
117 | dea43c46fdbe84511adbb4c4e06ad649
118 | deb9d02cd1eda25270c4138179d9ed97
119 | ded529516b4362c9f019a51d1a3b2e07
120 | df1c68e94259c6cf5c7319b71bdce6e
121 | df6aae66a8c378ae9029a69fa5fc9ad
122 | df7313e87ef2905d37678474be485ca
123 | df8bb967a346ccc25e9e2656aff7dd5b
124 | df990580230f0254d21176457f0be3a
125 | dfa310706fad49d873ec74c119307b9
126 | dfa36bffe436a98ee0534173b9189765
127 | dfa5d6ed898152d34210bb5f1b1324bb
128 | dfed744828fceb4d28cd0e56fe42c08
129 | e0058b4948f87d3b87697d3904b168b
130 | e005d8b297850d483a99ba0078ef7bd1
131 | e00b89bc338348caa42c49797afd1f5c
132 | e00d7bd590ac129bbc0909d98a1ff2b4
133 | e025a1fc1bd71c2aacf77e718d93f3e1
134 | e0385af10bddc6a0ca8607f540cc62ba
135 | e039c9760ca026cc6aa3bf023a2b42a5
136 | e08402fb1e5953a2a93f0f952e72609
137 | e09c32b947e33f619ba010ddb4974fe
138 | e0aec5757f7a907d647cd52f13caf24b
139 | e0bb0ddf67462f4a8b686f76be476fe0
140 | e0cc4f538a8da2d65d3bbd70fc7759b7
141 | e0e0d713c8969b52ca8607f540cc62ba
142 | e1225308d6c26c862b600da24e0965
143 | e127b1f5ead603f9a5a118bd15e6e34f
144 | e1324a093b45645c5a5672eede2b271f
145 | e160529ef50ae4dbb819cac660ba383c
146 | e18b6350437cfe0d727249e8d9a90100
147 | e1a8e2f93abfc7d590baeef8ba5b93e5
148 | e1fbbf2ea1989b49fb2ad20449a93a60
149 | e2116e0b34db656dfca1f1143bb6bc17
150 | e283e3825d66a985b87697d3904b168b
151 | e28e5714139535e7a9b2becd26dc2fc1
152 | e2f91794c302f5c03221f63172285740
153 | e31da3ac74fa3c0c23db3adbb2f1dce
154 | e33fbcf5b616d6f9f44f89e40af48618
155 | e3473fc8fffca7d4d972c9dd75ed77d4
156 | e380f6fa720e1c15560a4691498bd2fc
157 | e3bdca8304aa6593c503a3776fc280fe
158 | e3e6cbc295806a47cf0420e0d05f48de
159 | e42443669339a6c1a5a118bd15e6e34f
160 | e45d71c7afb3cb1c67629418bd553f95
161 | e49d1e1d176ec1dfbc0909d98a1ff2b4
162 | e4ac77fdf28116232fa725d7a62a02a
163 | e4d902abdf9481558caa71b1fbf7fb98
164 | e4e98f8654d29536dc858dada15498d2
165 | e501a0327ab3731d0f859db45b95a2d
166 | e50f001069380884b87697d3904b168b
167 | e51b620853f2cc0137678474be485ca
168 | e51bd7d434d1ee6622096c1bee7ddc7a
169 | e521828113e1e0c45e28caa3b26a73fd
170 | e523ba4e79a48d31bd46d022fd7d80aa
171 | e52f08852429e6117dc01d89d8a05b74
172 | e52f809111bb75692b5a1d128057b6a4
173 | e559a626d0ef8b4f982014dd9aabdeeb
174 | e5610bbacaf098508b96ae1a0a8b84ec
175 | e594754cc2a264d63da2ae40e7681e7e
176 | e59c4f290d8585a862b600da24e0965
177 | e5af05179ffeb8fcbd46d022fd7d80aa
178 | e5bb559c00276ad354eba1f1b35fb0c1
179 | e5c98b67c146cd61e816c75152573ee0
180 | e5f08a5e3dad6cdff810506e9ae2dcc2
181 | e5fe5ed2cdc8b11d62b600da24e0965
182 | e60b86c7a4015490e5a760ec65004efd
183 | e6236c5ec784a48111dcece1819895c0
184 | e66692f2ec8ea898874f1daffc45b57c
185 | e66996d97d9f553939e75b12f2e5480
186 | e6d6e9544e353f9f75e49fe23848bbe5
187 | e6e8f0e244efac73da2b0f839aba40f9
188 | e777a6a46ae240a7bd46d022fd7d80aa
189 | e7c1bb596e9a1ce9ca8607f540cc62ba
190 | e805624480f632ebcc14f1e6f4f4f49b
191 | e812f54386acd072d44f37c9e0fb10d0
192 | e8409b544c626028a9b2becd26dc2fc1
193 | e841e17e3256acf38699933784576e73
194 | e85cd06b4a14d3ffbc0909d98a1ff2b4
195 | e88a8692a22d548e1ec438f11f5ea1c3
196 | e88e090caa1ccc5d187bd96066d7269e
197 | e899c19c87245ac94c3a35cee92bb95b
198 | e8b4bac72559c097e8f5e45871fbc77c
199 | e8d5a3e98c222583d972c9dd75ed77d4
200 | e8de6c58f4a772d771d03b466c72ce41
201 | e93a2143cbec37a173fac4529123dfb2
202 | e94ad5f8e53a255a8fc2d09ac4aa4e78
203 | e954dc13308e6756308fc4195afc19d3
204 | e9bbeedf2681b8ad154c6bbaeb7d331f
205 | e9c78deefc2950be62b600da24e0965
206 | e9dcdcd8963ba18f42bc0eea174f82b
207 | e9f39176973edd33a8cba409c4409ba9
208 | ea6ccb2dfb61484caaa29616be3e223b
209 | eac05be6e7f3bfa99a6e43b878d5b335
210 | eaccb2ca303223afc503a3776fc280fe
211 | eae54f8d47cf07c0aeec93871310e650
212 | eae845d4a7945ecaf2e466e56cb8c63f
213 | eb2fbd46563e23635fc197bbabcd5bd
214 | eb43db95d804f40d66cf1b4a8fc3914e
215 | eb5baf7bb88c1499873ec74c119307b9
216 | eb60d49fd5cdb809e6a2524c335c48f9
217 | ebb5a048015c13cd35fc197bbabcd5bd
218 | ebe0d0bfa6ec36edd88eab18f1be033b
219 | ebedcd06f1770cd4bbf3143b1cb6076a
220 | ebf8011ea1f4b4190b1d6deb98feec6
221 | ec03d76cbd50314f5c7319b71bdce6e
222 | ec4cd947eb2ee3103554ccf8c30febe7
223 | ec4f0bfd77978a1cca8607f540cc62ba
224 | ec531add757ad0fa9a51282fb89c35c1
225 | ecb4ae05d7dd135a619550d2af0b6117
226 | ece25d89898c7d9090b1d6deb98feec6
227 | ed0a9a32a8e35f21ca8607f540cc62ba
228 | ed35478403ae873943cf31d2bcc8f4
229 | ed709305e61acf6a9b017c80f62649a0
230 | ed73e946a138f3cfbc0909d98a1ff2b4
231 | ed7e1a38fe33830b87697d3904b168b
232 | ed95d9219432bbdbbf3143b1cb6076a
233 | edc185566c1df89c35fc197bbabcd5bd
234 | edd9f45c7c927032db5e5b1ef1010d8b
235 | ee562cc82d73ab212135f3a0e614f115
236 | ee672fc1455b9fc43523242fdf9b75a7
237 | eed299b690be51ffbd931fcaa69140
238 | ef0d51f895cee0e04485f82d9fa383bf
239 | efc7d4fb87937413dc13452e3008005b
240 | f009f3112625ee00b8cf782e8c539948
241 | f0137228f926dd464f8327dbe71ce85c
242 | f0b22be59432dc8bca8607f540cc62ba
243 | f0fb27f3a597838feb1a0518c224975f
244 | f11d14402a759a1465f50257ecdfa5c7
245 | f1210d8f895e40b663c15773e7567372
246 | f12eefbbefabe566ca8607f540cc62ba
247 | f1384d3fd2d59e63f4d6518603e8629
248 | f1a917846d46b61f71d03b466c72ce41
249 | f1b3408a3ba452d0c1ccec171a275967
250 | f1b407dd7f610bb1a266a0298675ed53
251 | f1df46c588524ee76aa3bf023a2b42a5
252 | f1f12c4408b0b4ee445d150719ce97db
253 | f2171bb2d715140c8b96ae1a0a8b84ec
254 | f222d51d7c6fedc2db73445864b72015
255 | f258c40371334a4e90b1d6deb98feec6
256 | f27927b066b0696d1f95d2b537942ba5
257 | f2d4b8440d4bde5330afbcb38d77d0c3
258 | f2f779b4f12ea6d67209009cfb89d4bd
259 | f2fda88e9688fd81d972c9dd75ed77d4
260 | f3463eac7325b600d01b5600c06c528d
261 | f34a66147493f0633d5158710d6fb8
262 | f3660119189d3eca4c3a35cee92bb95b
263 | f39985959d394f8c863ab010b80d9ed
264 | f3cc7d5c4089b842df6e254b0245ddcb
265 | f405858991b190173af8c56bd4352c9
266 | f40fe7461dc4e3396b7bd17e458d0dcb
267 | f4453381943f6039eba96cf317eae721
268 | f55390ed02c0b2b36aa3bf023a2b42a5
269 | f57c74e194cd2b2bc8727b27ee96a4b7
270 | f59a2be8fd084418bbf3143b1cb6076a
271 | f5a667f5796b9a0b9a6e43b878d5b335
272 | f5a8cae96024e709c1ccec171a275967
273 | f5cc091bacb338c6951971f8370d9050
274 | f613ace665da5e3e8b96ae1a0a8b84ec
275 | f6b7f7695d091b9bc0909d98a1ff2b4
276 | f6ea6663b48bf78261f1ef59130c405d
277 | f6f2905883c49d179e0d0faf84afc607
278 | f70e5f2568e927147d755f57c8fea340
279 | f7160900b6ce7bc4e63e266a803d9270
280 | f7298a13f6d1644472a4466eb772f128
281 | f79fce6480d9276facf77e718d93f3e1
282 | f7bf32d3aecd197360c9b6e4c75a092a
283 | f7c11b5e07e9ccab3a116bc3efac4e3b
284 | f7f915160c0e1f6f42bc0eea174f82b
285 | f80343ac3064e74862347b4731688b0f
286 | f8038d33c212f81fe99ea3c41458bc01
287 | f88be1c8e93fbfecba0d990ae229b477
288 | f8ceed6c984895079a6e43b878d5b335
289 | f8d7d8331fe29f247209009cfb89d4bd
290 | f8f4cccabf7ac33b199dff268d0aba38
291 | f8fa93d7b17fe6126bded4fd00661977
292 | f944c570191885e8ca8607f540cc62ba
293 | f9505b01e3ea959cf9700e397b8b4e4d
294 | f986604528abe35554eefcdc602d4520
295 | f98964dc88c44a2c863ab010b80d9ed
296 | f998bb1b62da4d06d3a1a47fb9b678
297 | f9cd8293c30f1aaab87697d3904b168b
298 | f9d30b24d9651ee476c772fd813166d
299 | f9e80ce23d9536623fddedb0bf24c68a
300 | f9f4daf3015b5ece5e9e2656aff7dd5b
301 | f9fb41a3b1f59bb027745e9b6b461e93
302 | fa5c740ca9192b708e8131a047a07ce1
303 | faa361f642620bb72def37e9c0b35d0e
304 | fabe8fdc617e3aca2bd098b9203af
305 | fad346b02d91348bbbf3143b1cb6076a
306 | fae6ae6ef62cfa107b164268a44f7712
307 | fb110c5d01f1b3fc59dcf12563d8fce3
308 | fb2204e98090448ebbf3143b1cb6076a
309 | fb2e4eb19ba19bde5fe6cff21a9e8496
310 | fb92c2e96fdf6c37595dc3191c718398
311 | fbb2e9c15888afcaca504cdc40c452de
312 | fbe788465e564e46bc0909d98a1ff2b4
313 | fc25e0cdcb2ecf1ca2bd098b9203af
314 | fc2c9fd0bbd77dac4d210d9468aedaf2
315 | fc5d7c28e254a0d84c3a35cee92bb95b
316 | fc6decc887f6d8a0bbf3143b1cb6076a
317 | fc7387d630c84bb9c863ab010b80d9ed
318 | fc7c3ccb57f65337209009cfb89d4bd
319 | fc7fda7232bedd84bbf3143b1cb6076a
320 | fc9f6bc1ba1cb7c1c3fe7930fce05ded
321 | fcc94cf74fb886b7bbf3143b1cb6076a
322 | fd41d04f1aabbaea3fddedb0bf24c68a
323 | fd425567d79a43d14f8a08a5e6b028e7
324 | fd528602cbde6f11bbf3143b1cb6076a
325 | fd7c74a05072d3befef192e05c55dcd3
326 | fd9f1cdaa381599bca8607f540cc62ba
327 | fdb107ea7a600f5fe3f3aec01b086ba
328 | fdc1a422b48a16f67341d39902b9e2e1
329 | fdcb11fa39661f0fb08f81d66e854bfa
330 | fe0c4db38fb6399990b1d6deb98feec6
331 | fe0eb72a9fb21dd62b600da24e0965
332 | fe1d825ce462c3e7b96212c8f6cd06e
333 | fe23572aac36c84761cfaa00f7177470
334 | fe3aa0ec747c12c0ca8607f540cc62ba
335 | fe4ad5664773074cb536c73c7d134340
336 | fe82a9934a38997866cf1b4a8fc3914e
337 | ff13be97bdfa45f8254dc1d04198881
338 | ff28d340bf0b5d9387b2a887422ab97
339 | ff2f975a23b78bc78caa71b1fbf7fb98
340 | ff52c059efaca3c1ca8607f540cc62ba
341 | ff6f81eba664481126360e1e29a956c7
342 | ff725af6df1b76207b164268a44f7712
343 | ff77ea82fb4a5f92da9afa637af35064
344 | ff7c22a964a5a54e3bb4b8f3758b3c41
345 | ffbc31352a34c3e1ffb94dfdd6ddfaf0
346 | ffc1b82bec23a50995b8d6bdd18d56e8
347 | ffccda82ecc0d0f71740529c616cd4c7
348 | ffd13ca14b85fec66cf1b4a8fc3914e
349 | ffef991d85e3136a9a6e43b878d5b335
350 | 


--------------------------------------------------------------------------------
/splits/content_table_test.txt:
--------------------------------------------------------------------------------
  1 | cd106955d3bdf8e751c4deb11af7079e
  2 | cd2ad198854d47c6e5e7067ae780b222
  3 | cd413f0540b54bc1fcf003a332eb3241
  4 | cd44665771f7b7d2b2000d40d3899456
  5 | cd4e8748514e028642d23b95defe1ce5
  6 | cd762ebd8c8ab61361a38c5058945a3a
  7 | cd82d526e58e3e7f4fb85ea6fd426098
  8 | cd895c35fff495cdd0b93fa304cfa755
  9 | cd94233033b1d958ef2438b4b778b7f8
 10 | cda580f16378e12c3002761e7a3ba3bd
 11 | cdb0bd21fd5d075bbd1f60c111786ed
 12 | cdbe8e456a3e3202c55161a63fbd109a
 13 | cdf0a34dc3504e40643beaf431c0975a
 14 | ce1e09dec6387f715fcce4c360a80a36
 15 | ce2d3e0b58bb1244700ade95b2f08044
 16 | ce4e075487aa05ecdcfcef693e7ec696
 17 | ce6e4aa17c710b3cd6d67789347621
 18 | cea242a600c342fd33891f25755e1e1c
 19 | cf046edeff204b81cdf7280ff8af6720
 20 | cf076ced8264a480cce90f0d61ed7a70
 21 | cf10ac71297ae632f44880b8ee951142
 22 | cf24f0128755080569080f7eaa8f3e1d
 23 | cf2ea610fbafece363944951133f1c85
 24 | cf37563a68edc94bd71ce74ab5e9c1b5
 25 | cf46448f9ef495c81d022067655f6c16
 26 | cf52e17b21021ad9490ad276cd2af3a4
 27 | cf5a0589134088ba37e5c2aed7049b42
 28 | cfa43d56d70e530160dc76a524f85955
 29 | cfa823ee81496f5912b57997414c1d71
 30 | cfb7e0b0f44819c5e2f409c9efab99cd
 31 | cfe4e4fb603b99c77843fb4efdc19510
 32 | cfefed4429defd86febdb1f263373824
 33 | d007026a83d6be854e48282b72e69035
 34 | d05ff7b47febe58a656db3f863b4b796
 35 | d064b468c3cf683cedf48f9fa39262b
 36 | d06d27bc9ad1faabd7bf6fb68df7f786
 37 | d073f58c96c17aca95786b1c8687acc
 38 | d08a421a6362b4bcb000f20a5153622c
 39 | d0a4d46fd42a0c3df6cfab91d65bb91
 40 | d0b6d6210a65f1e4e50369287c07141d
 41 | d11363fff4e2dc6589cc5332e945f058
 42 | d1296da8d3a45ac88aaae3d020f5ddf8
 43 | d1457e572ef95ddbd2096b2fa6f98cc7
 44 | d1494e0665f06507b79de6fdd84b2221
 45 | d14a4b797fec250b83768a4ac1607d73
 46 | d14dfaade3e105306ebc5c7b8e36e351
 47 | d151d9f45d8b14536cd661fb5fd95741
 48 | d1525a08cc96beeec786af79f5203d8e
 49 | d1611599e3dad7292f4c88fd91c6b1b
 50 | d177f7632a4bb3405073c32a9cf4a6a9
 51 | d1807006e89f9e7c3087f84b199fd297
 52 | d19b4bde0766723c9b3bb0ef2a08be04
 53 | d19c946f825a9786db6175ef18ad3f80
 54 | d1a0b26d98ee4a877fa6d07b5977c143
 55 | d1b44c2dc663cca6b8baed360b6cc5ee
 56 | d1b4a4f43818c34e490ad276cd2af3a4
 57 | d1d9e395bff3d3a7c8fc6229eb64e56a
 58 | d1ef95530469a1de1fc4857cc94b6562
 59 | d1f808613f6dd787a2c8f09e8ae34f27
 60 | d1fe23dc2b62082121f2d1de8124ec62
 61 | d20562f6f18add5c7dcd20e7ddd78bc8
 62 | d20dbb223dc5e26e6e4d44229ea605db
 63 | d20e0f359f37f7f5648b060eabbed82f
 64 | d21ad1e0d76175e3486040c0d9e85846
 65 | d22e15286d0d99ec52d2de7b04447df3
 66 | d237260f66c00364dfe9cab879fd37e8
 67 | d26eacf8d87a522647839bae1bc65257
 68 | d26f2c85a4aafa72db6f3ca49e992ad8
 69 | d27130df514414d1d8c46a3a266762d7
 70 | d291243cfb51ea7dcb25d116843b43a4
 71 | d2a3193796284084e8775b281dde57f
 72 | d2a331898525d0d1c955e5ed03ef3a2f
 73 | d2b7b34e176262513521fe8ac6222005
 74 | d2cc7d1f7fff8488698b889b37529d3f
 75 | d312c70dfc7017e9c55161a63fbd109a
 76 | d31b0d2a41051f2c7b79156a61ad4c01
 77 | d330377051e6180319fb4103277a6b93
 78 | d35a2fb01107b6178727c7a6ed7a8927
 79 | d37560b9ea27af4efe354164024016d6
 80 | d37fd2ce56b3340eaccac37ae24b8e2
 81 | d382d9e34f365544278d386bfa54545
 82 | d3a72603f65b921b391e4d6c585a697a
 83 | d3a8019633567d71b20716e5484f7807
 84 | d3aeb75da27b505f1c9acd0bdfdc9f62
 85 | d3b7021f03ecd58d2585ba435c7d1fcc
 86 | d3c31829b1295d0abf22a5ca4fa4678e
 87 | d4054b29b329a700490ad276cd2af3a4
 88 | d416139067bf7db337b2bb75885cfc44
 89 | d41c8af82fe98a019fb4103277a6b93
 90 | d43664b8f4df83341ee9d48493ad639
 91 | d43d8df70f357bcb83776366d314ddd7
 92 | d458bc90f183605119fb4103277a6b93
 93 | d45cb36eb4c38786b9a7614f2da8d7ae
 94 | d46537f513283d6cdcfcef693e7ec696
 95 | d481ee7e971849339db8ad97fd392b59
 96 | d48ceb6fe098d078f0cfa7d27eaf1bef
 97 | d497f192ea400165da22561748cba914
 98 | d4acb5110512f5c38369c37b40e82efa
 99 | d4b3c13ec756196f94b77d9f59f49ab0
100 | d4bf9872856d6fc2b300c4ca2f51c01b
101 | d4de4deff5410e2be499c77acfcee9f4
102 | d5402d5be271438ef51fa0238791f5dc
103 | d578287c4a9452efa9af104529ef47c3
104 | d58af24ca497ba8c4b3c42e318f3affc
105 | d5a7ae84e93368c28b015826dff11d35
106 | d5b21d6154c0795813dd6eafe1477be1
107 | d5c3aa73e043303b7ff6ace05b36a5
108 | d5ca71b9b9ca6e5041b73991ca70550f
109 | d5d7324c2233d6edf51f77a6d7299806
110 | d5de572c3f6517374b3c42e318f3affc
111 | d5deca423faade89bb814dc1a3fcda86
112 | d5e79960180078237062f2d72cde5c95
113 | d5f5388411866fcd6f349f21cf5447af
114 | d5f55cf498a7562eb000f20a5153622c
115 | d60054176a178d18febad4f49b26ec52
116 | d6064ca673a721ee44175b4dddf5be08
117 | d60a87c721416783ec7a87c695ada295
118 | d62f718a14db87cdb40f0ac0fb9a650d
119 | d6577674aee8f8cbe986c6d94503b284
120 | d6728931be54e6924b3c42e318f3affc
121 | d679b6e72d6c0ead391e4d6c585a697a
122 | d69a4fe99afe6e0097a5b791ac4ae3c8
123 | d6acd7d7c9e0deaacc963bba1556032a
124 | d6c68f9d1844c3bfcb002c1e2b5fc68b
125 | d6ef0aa7b674c171fb4f26e87f6a6814
126 | d7576f0e6f9acba7d261e17fa0c462a7
127 | d77287719eb7bf0d66ef9dd2f3ef27d3
128 | d7792a9c16aaf16d98e0d1738edd4f19
129 | d77f7643e6e34ac91933ffef19678834
130 | d78d509ada047f34e1a714ee619465a
131 | d799cc222f34fc0879bb09dc5605a57
132 | d7c40ca08579ba4e664b3b9b23ddfcbc
133 | d7cde91c536c6502d7a1dc9bb68fc381
134 | d7edd292f614e9dc58b7984178830447
135 | d81df8f708d4360c5e05d85b12fbe60c
136 | d821813cdad2ca93183128a5e9c4cbee
137 | d828c9f6c3e9f67367d177b869ee03bf
138 | d8bd55abd721dc0c99860e9353bb52a1
139 | d8c35b0ed66cfafa426c7177f78cd656
140 | d8f851bbc98dccc23fa92d98173c06f
141 | d903be5d4ceb3fd56eceb9b47ba95c
142 | d92354e060c98854b0ffd7a60ee2298f
143 | d93d1957e7a38a6619fb4103277a6b93
144 | d9467c88e3e26d3c4b3c42e318f3affc
145 | d94de64641651a2079b3e1be3524f72f
146 | d956062bec339ab6c67bebb34dbddc1a
147 | d97819998f885d54fb977fd7ef10cdde
148 | d97e2a50640387adf90c06a14471bc6
149 | d9a0b526a354225dad1da5f59ea6f4e3
150 | d9b82ebcd756397c371fff21f277e702
151 | d9c11381adf0cf48f1783a44a88d6274
152 | d9c75799ff9ff74664b3b9b23ddfcbc
153 | d9daa0e33f695897136d9cfd13835101
154 | d9faa371af8e7f443fa7114f9b06aaa5
155 | d9fb408a6fd11e6c22ce72a02bf771ea
156 | da09745bd5be34b9aaff8bf395bfe94
157 | da0def87fd8cd658da094b3bbad5f5e4
158 | da234c874b8beef22e1a5fb6897c8678
159 | da2a145da58d39c7aa5ceeb306445170
160 | da3e68c20b832c47a3b06ba374e12b77
161 | da5d6d0da4ed0c1cea65c47b660136e7
162 | da84e4621c255691490ad276cd2af3a4
163 | da9676ff70b2e78a0a7b8ecc42036d5
164 | da96905b5b3c821c8cbb8bac2032149c
165 | da9d681e20d2c123604b3895514420b1
166 | daaa70967da2bad4e80de6380bdd8c21
167 | dade0594e68e2250be6c545952e7fa4a
168 | daf4f3295db84cd39420b255bb5956f0
169 | db09ccbc677e2afc9f60147421585c0d
170 | db0c430a51ac45c19d2be74cfb51ade1
171 | db32d69c5b2c77ba51b5726fdf67f095
172 | db406d9b2a94bce5622d7484764b58f
173 | db454c99849016f8febad4f49b26ec52
174 | db6561b883e56b9072c6d81e4b9f21e4
175 | db77ba0cf616e2908369c37b40e82efa
176 | db9458fd1459982347b1b3e368e511da
177 | dbb28a435349c9c76b1cb83d86c19bfc
178 | dbf2123ee206a81b8b00eeaf68a1358
179 | dc3fba5ae5e86e62416e6e65da17ce54
180 | dc49259a117af8f1d200faae04ce3f8
181 | dc5a136f23bd3f31c710d14956729baa
182 | dc5b7cbcf45e557f310af74324aae27f
183 | dcc24b55654a9e6bb65b71636c46ae49
184 | dcca76b81c747e76a65e19246f8119cb
185 | dccb87aacbcb40a4f1783a44a88d6274
186 | dcf246280361e20d1bf2b66b52bf6885
187 | dd0377d3a40b57c360885f79b3a5579a
188 | dd0521f27114171e492d9da2668ec34c
189 | dd0c4018a8b310edafaeb6535dda1ed
190 | dd2238408ee5d84d8d1c97149a00bd19
191 | dd276ac55465f51e1457f3eb061a2fca
192 | dd2c3ff28a34556a47839bae1bc65257
193 | dd35a3f0ba7c5f2e73ea70c16ec9e2b7
194 | dd363031a195991631b72d9d4e0e505a
195 | dd3de76ab27a6aee8141276dba5d99db
196 | dd468c350fc655eafebad4f49b26ec52
197 | dd4f28a0e0d3f93c614a26402360d21a
198 | dd543a069376134aba5342d638d0c267
199 | dd86b0fcacb9990914038d588fd1342f
200 | ddc16ae1263d506c955e5ed03ef3a2f
201 | dddd611b4262ede6e3b9db784be35882
202 | dde92f6460b1d7b2b4cb6dc412eb15ce
203 | de10ce891b1cd33635836c728d324152
204 | de2f120b21e228c2e6c5cd45aa112726
205 | de551ddcab968586a90dd8e076a5a7f9
206 | de5de9cd2d952cc5278f90ef85162deb
207 | de9b2870157cdba6f83df7938e45b43c
208 | dec1d2cf8a4563d36cb02543e4df83bf
209 | decb34ff7d69d024e6c5cd45aa112726
210 | decd9ab8c2714f2e7235016c2c2c8150
211 | dee160f20e1195a4b2cf6e4d01862bc5
212 | df2244d33847f7cc4802d94e40825ea
213 | df297071493f894e79b3e1be3524f72f
214 | df38d8c2f3b36ff76e4b69f8ed4dc344
215 | df4593480b94850bbf6d78b1e39e2718
216 | df5ac7a785ab39fbb5677466d30ffffb
217 | df63a11436240ec7fb906a2c84fd375f
218 | df74203c0a1585f9a29294366c3334b2
219 | df7f8b7ea0e2c4ee55f46d55537192b6
220 | df811f7a858750875634c21965ee6bab
221 | dfafa039da1cf318a42557fe008dfc94
222 | dfdef0c8739cdd0944b0115560181a7a
223 | dfe0eb3f446059d0500cffceffd2bd2b
224 | dfef8f26e9a8437782db9fca4b68095
225 | dff5b7cb4f72def6641f7a370ac2809e
226 | dff9b5c37bedc55e9f011a37a96f51f
227 | e004afd245bd06337e2a6b10ca75153d
228 | e0229fb0e8d85e1fbfd790572919a77f
229 | e026b4997f7d037c39d3717288022c20
230 | e03d534f3ce3c77d19fb4103277a6b93
231 | e05344d8bd3ef63c5b7bf37141f96eae
232 | e053e9199d9d7f2d276b6f6d90ee3a83
233 | e055a8a5d8ca0b9869df3aa2bce421f5
234 | e056700bca093e0c1cf96a5dc33e37f1
235 | e07c83841b933e74c5facc3cc8dc041e
236 | e0940f2229e42007d98e761e6d91dfc8
237 | e0aec1747c4d7c11f24f0645d0949356
238 | e0aee89fa986647257256b1738023f7b
239 | e0caa2e794d98c814c9587cb3f654544
240 | e104beba32cf40bee369d8ecc5b0e866
241 | e1581daad0ddbbe4465d230735fb8831
242 | e15a28c0743ded35673b9aac59c306c4
243 | e18c2cce4bbab2e45b7bf37141f96eae
244 | e1a8e9e2059f4792fbb8cbddab1c2002
245 | e1b3412d67d2c18c59f8e31ca87c470e
246 | e1b85df09d33ddea3e43be0b542efff8
247 | e20f1fff2b84f8ea71ba8e8bdf40d1ea
248 | e2807c8c5f5653d4bd91edd7a65c1323
249 | e28354127815445a83e5416284930195
250 | e285d68fe197f968492d9da2668ec34c
251 | e28af7dd5593fe6f820018801b237b3d
252 | e2a2fe3713803e9e04e2b29e7a72f7
253 | e2a56bcdb18d820047ad57fbec8be0bc
254 | e2a940682bf386d166e77edacd2d5e3a
255 | e2cb95f03f5dedf9f198b94f669bca91
256 | e2f60503a4fabc4aed20ed9a17aa05a4
257 | e34d1be103e9d88145a1bc3ecd3d162f
258 | e35d752ecf4e205ab40f0ac0fb9a650d
259 | e36dc839d70d3bb927445c0c7cf3becc
260 | e39bfe8848fbf76540a98a90bd0efcca
261 | e39d56046b309a64229048a9abc3ab6
262 | e3c8c6e7bc421e52e4721974983917c4
263 | e3da34a62e53689e82028a475156419
264 | e3e1762fa7f935b3f6287cb48a47c45c
265 | e3fc414b6b9b52ac50d71b436e21a7da
266 | e41da371550711697062f2d72cde5c95
267 | e44531f7204b6fb9fe43ff1e45af424d
268 | e448e3e40395d4d679414e04132a8bef
269 | e469e53c260a5ca47d2695833906aa3a
270 | e490518bf6d40e138288267d39a90f5
271 | e4947c9bc17eed10e54cb890e8682c84
272 | e4c8211dafa5b903febad4f49b26ec52
273 | e4dc0ff7a1f3151814f68a949b9a6baf
274 | e5261b63c63b226bf7e56c1f3346606a
275 | e52a290532a567aefa10901ed3f9da3
276 | e537c592fdd7f7b7c3bd24f986301745
277 | e53f5f3d4b20df8176331cff7db8f268
278 | e5567a82c577e8af83ab2e8865eef185
279 | e55dde3c1153ae5d7eb43b1b22d3185e
280 | e563bbcb07d70dcc3321831d2245cf06
281 | e59fa20a6988b93e29e4b5aa807bb4e7
282 | e5c44394471f29d874739c2c9ecfb3ee
283 | e65cd563d3a74dd4c0a61ad1cf92b694
284 | e699d5904e00a6ab748c0b14b00bc019
285 | e6a188bbf8315d11f1783a44a88d6274
286 | e6a89aaa226b116a60885f79b3a5579a
287 | e6b3255eb51908a53c99073e1068144
288 | e6b84acd543ebf20662cdc2f77e49a85
289 | e6cb8965b985b8a07eec403e4de3e723
290 | e6d8569c0957e7453002761e7a3ba3bd
291 | e6da3e780a427429791f2019e8710746
292 | e6ddcae1c08b880811d3792a7f546aa8
293 | e702f89ce87a0b6579368d1198f406e7
294 | e7045bfa00de20a39a0d3e7e907e5b53
295 | e70d9645a26a4e941832ad614f693f66
296 | e7169243daef074dc82dc2efb3363de1
297 | e731318d8d28bd585913832d290e62af
298 | e74841627e110e98d9de0de5dc66ab1
299 | e750a8adb862c9f654f948e69de0f232
300 | e751c765bfb096da43f06ece0b2b5196
301 | e7580c72525b4bb1cc786970133d7717
302 | e758e1b760f185e2593ebeeedbff73b
303 | e75ddddd62dac8a119fb4103277a6b93
304 | e777df6ffb40e3a1853d412328e7e7a6
305 | e77bdb7d3e12d6231eb51344489c49f3
306 | e79b8e7272ea19ca2112c05ea370d321
307 | e7abab128d0edb033396b0dbcf4d4bc7
308 | e7b0ff6ffeb24ac2cfde2e560cf498ca
309 | e7b41a39388925c364f6d058992c3399
310 | e7b76d66231ad077cf004563556ddb36
311 | e7bf775ba6774a2e278d386bfa54545
312 | e7eb326a867912fe16b2b5432674ae6
313 | e801542eb03f6e3b96d5fa1ee6ada8d1
314 | e809af47a0255110855931d119219022
315 | e811612c42cf5c5ae0cc7e7449604bbc
316 | e81af191bb828526815b2b467e8e2eac
317 | e834ef941f7bc9c9e7df9f1005942e3d
318 | e83930a4a62413e1187ef2b10c31bd17
319 | e8502118aeed3381d5b708f09789d978
320 | e8599df1d0465e3811f3906fc1b00350
321 | e86ddb9617b8c44758b3fd27263469a1
322 | e87136a7996cc5c82d6b4fb79c7b302b
323 | e881a6fa6c3443ad5d28221e3b996124
324 | e8870f3190f6b8d4bd1025bd755a15aa
325 | e8afe4f07f221087620018391309f97
326 | e8b3da6a6d938b475966c5a46a5a6ec8
327 | e8ba9621aef9395a3019620286259e2c
328 | e8ce7c3e66e6aec08ee0a9ed0efc243f
329 | e90b641f8f1489d44b5e2e6b95708893
330 | e920d6df55f51b9d3abfc4d0a5688916
331 | e92bd321064e981e5208aab875b932bc
332 | e9383126d043156fc1302d82d108316
333 | e94b1ab02a3264c89eaa55bb236fb6e1
334 | e9546947de34dde213a5873d239ac557
335 | e96bc1b7f02caf77eaf288f952624966
336 | e97089561bcb8e85833c6c72c4b62a4d
337 | e97156fd53e88e27be2d01aee0780473
338 | e9871fd4c45b34148737eef0436997
339 | e98dcd0334fa639fef9f898cda0ff409
340 | e99f7a450afce3b62553cc33364504d5
341 | e9a1325245afff7c405d9b5bb7b18be5
342 | e9cbfadc69d199c6368aec320face349
343 | e9d6ce5bdae4462aa187e6150daf1a0
344 | ea093e60ddd1c7467afee304cce81d6f
345 | ea367e390741fc38dcfcef693e7ec696
346 | ea45801f26b84935d0ebb3b81115ac90
347 | ea559127f7f21405372d8d157558385e
348 | ea5e7b13d0eda809663191fd557d3a61
349 | ea60054e04139d95b90b5e5b769a3ec0
350 | ea6b9474514df497febad4f49b26ec52
351 | ea7dcf537a18150cd3dad974dc098fa1
352 | ea96b8a866121d1abed1bd9593e318c
353 | eabe7e2ee9547616214a15a5a42c49c0
354 | ead000700697a012310af74324aae27f
355 | ead93856b735ec90f0aeabfdcb4e1dd9
356 | eb00a4e8b33d257cad16260d4d73b56
357 | eb363770ee36b0309a79b01b89f55c86
358 | eb54a7a886da95f69223fc014b68160f
359 | eb6f0eab4203ca0e1c19e7863a1c200b
360 | eb8a34ab2eb9a26fe93eff560d16430
361 | ebae52c84acf994e9e4da01b847d5cb2
362 | ebc897217df591d73542091189dc62b5
363 | ebd353db403531b4257d13bddbc14c41
364 | ebece7c581e3a42c32ba69f5f654ada
365 | ebfc108a60197d8d55f46d55537192b6
366 | ec1e1abd7c9f2eaf5dc565f18990abf4
367 | ec6de49b6fee801a4b3c42e318f3affc
368 | ec7795f1efb90af9f37db3b69001ec04
369 | ec8efc59f0e8c0fa97b2fb14fbcb9c20
370 | ec98b08c2093d435f51f77a6d7299806
371 | eca46f21f2893069c0a61ad1cf92b694
372 | ecdcc12d56c119c5a67f11eba80d4fdd
373 | ecdebac7ddf6ef0011c50f6f633c5e38
374 | ece1e39b8c5f851b9eea323f522c6486
375 | ecf3f077d30540fe5d5ac0a8c21f0bd4
376 | ecfb5ad31b6e40b72b70eac6546e93fd
377 | ed0b1bd723063c8ee1be359afa82825
378 | ed1e06e886b5514fe8f49d7c9e73ab9
379 | ed20a233783090839039bc4ea22a379b
380 | ed2d5ed8ad10f323593ebeeedbff73b
381 | ed2d7f09d80ec3a259577d199a67fd7
382 | ed320d80089655bedf6cfab91d65bb91
383 | ed554b9e04b7f7eee7be13c697329304
384 | ed59907918516bbb4c24aa998833ed98
385 | ed73c41dcfe9170119cc3eaf35cd388f
386 | ed8dd7ac0d865ac686f1a0f58f951001
387 | ed964779023b7af85f6276ff8d24e520
388 | ed9dc0937009dc031311158f08f2982a
389 | edb32ed999f08ed4a12cedd896805aef
390 | edb69ee3e3e66e9bc242632b2a8c3129
391 | edb7dfd7fe00c08e25c8be43ebcd1add
392 | edc14df2b7e3bed1b15370175a9d2c81
393 | edfc8ca3568153d7e8ee6c6df61c5951
394 | edfd25e28cc7b003869c91937070800b
395 | ee00ed62953f4bd280afdc8bd41edec3
396 | eeb23be65d6c76123199fadac163f8c6
397 | eece94f60e91c3d819fb4103277a6b93
398 | eecec73da85e87ccf008d8a3590fb522
399 | eee6cf14a56af26ad71f17d6e8238d04
400 | eef0387bc4e72a1efebad4f49b26ec52
401 | ef29c3dcc28f4e314785a5d3b6c47521
402 | ef3ae300317c571b490ad276cd2af3a4
403 | ef4bc194041cb83759b7deb32c0c31a
404 | ef62dad7755794a47558b47f7ba0b0c
405 | ef873c6f267860cd43ac09133d4c1d60
406 | efc01209cfa158eadbbc9440457e303e
407 | efc9a32719fc71962c95e86abe3e6416
408 | eff1bc2f644be748490ad276cd2af3a4
409 | f01ca36bab1a7a1d9e9583a661702ed4
410 | f023a5489450b924520ad20925ff9d2d
411 | f026d1e8b71bd18e97f16d67bfc59c23
412 | f03a86b27bd0a6b3d86234e915108e6a
413 | f06857189fae823f35836c728d324152
414 | f0735e59fa7222f9fe8adc3c073336
415 | f073fc78c930ca06f777b6b1bae343f6
416 | f09cdde03794151a17be1b91fdcd9df
417 | f0a7dba4e3c7c1e4ffa178ce1c2c6b13
418 | f0b044c592e19f3d8dab161b48d8b921
419 | f0b827eed9f044bdcdcd8e1ae308f03a
420 | f0cee441d88de6dafebad4f49b26ec52
421 | f0d8620b49ea76db83130614d8020b3
422 | f0e18881d2d01e91286a9d56d8187adc
423 | f10936939b1c9277d6134c153bee8ea0
424 | f166eeb3434b9ea4d79a1acd1a8c2d4e
425 | f17661552a06bf85282d5d529f9dee5b
426 | f17e630571a76d4f4b8710a3469971b1
427 | f1bfec97b7e9f7b776a402eb60ff1f9d
428 | f1c17621d394670b48d1a35afd3934
429 | f1c3fdbbba8e36bf62a510b8f97c658e
430 | f1c64d90ecf5212fac0d0a08bc077486
431 | f1fa3fac81269971820018801b237b3d
432 | f2087cbd26a910355c16106acf3e4b14
433 | f21154a95d49ca29e6c5cd45aa112726
434 | f220f4b4c7b79d7ab54f2a7bd7b06a98
435 | f22cffb7f3ca2ea1d719cc16de395dac
436 | f22dc1d847c5b82f585f699d798e7ecf
437 | f252711946bff75aa5234533e6540c01
438 | f25cf833c2200fef239d0ce9a68d2afa
439 | f27a46a8dce3b811707cdefe012d0353
440 | f2893a87ec37f8b3781cb4570305e329
441 | f28a91c02b1f32c7126e8f891cf24099
442 | f294a34bf1c9ebb7f12d7184a2ad3430
443 | f29863d2fe8863d4195b8ea6a366e14d
444 | f2ac49e7de8898d6782db34fbe677487
445 | f2ba8040ab2d2745febad4f49b26ec52
446 | f2c4fbc0c7c9b87d961b3f02493c4f73
447 | f2d39c20369e9c524b1c88aaac3e0ad7
448 | f2e1735aa2cba97222fbb0d1d627b825
449 | f2e6820ca69d9b7719fb4103277a6b93
450 | f2fee52b9098c13fdcfa6f33a3c5eb83
451 | f3164e1781a296597f6f00dc967c386
452 | f34a17d1b45ccc541763ab8766fa2282
453 | f38a18709e55e4647ee217c21e683487
454 | f3efcbd9745da90619fb4103277a6b93
455 | f3f6e3dc8c3b0eaf97b6421ec010dd0d
456 | f408befab026f5001e5e1a907376dffc
457 | f41e9600bd8bcb92716a0dc6cbf69f91
458 | f41ead4917ec05a149524cfd5973a145
459 | f434ad9d54919c9029d8eecf3827c486
460 | f44c91626e4900a5a26aea0642029fc
461 | f46c84466664f3162f023f89cad43868
462 | f46d7f7da9a056d7fff16555386d173d
463 | f46f68598988b922eede8c01bbe6592b
464 | f46fe188be699e5c593ebeeedbff73b
465 | f48d32cd065088b6a6551b53c4ec69b3
466 | f48e40d7f7b07b8ae0c7300d2b2cc1d
467 | f4976e80b8533bcf85518f8659f21d56
468 | f4b5313a0bc95a48da7c128b58fc7554
469 | f4f000158796b9593002ed4dcf002f44
470 | f4f168b88686872f785f45147f3e474
471 | f511c1d4356a6a7ac0a61ad1cf92b694
472 | f52b167d756420c83e5f17778b45d37e
473 | f52e33287b89f0109bbfb8262cd69a18
474 | f5529ea819c6e97decdeb21614063c36
475 | f580dcfbb898139df6cfab91d65bb91
476 | f5aecb6607876495e03eb69820d1aaf2
477 | f5d97731def4d875f51f77a6d7299806
478 | f5fa9f592d891083996915f7802ec40
479 | f60960ae4dc8e293c8ce22a41ea48e48
480 | f621e2ad900ad48535836c728d324152
481 | f64138f5515e5031f785f45147f3e474
482 | f64617385056e0b1beedb4c8fd29e2d1
483 | f65decafeb2b8518dcfcef693e7ec696
484 | f66d010471970cf0391e4d6c585a697a
485 | f69b664bb78a4c2f7537eb150af3dadf
486 | f6b3638983b0effaf3bf08ec218707d
487 | f6c5bf92d03a93e247839bae1bc65257
488 | f6cd420f08155054803d0f5bac2abe4c
489 | f6e14672ef1ca30130aad3a2f98e3b63
490 | f6ec4343f78b94b42553cc33364504d5
491 | f6f180c3e72caacb5077539b37310c29
492 | f6f3b8e08af617e44733824eae5cd9ae
493 | f70b502758db5927be2f6e4bb98bc38c
494 | f7196ec7d732af5166decb1b3cdc5557
495 | f73cc62cf8ca9d954c7384dbb75cab0d
496 | f7477e845dad9568b0aa15078ea6f391
497 | f7574c55aa4d5c80cba9caf4d254cef0
498 | f772e5b89475fd2e4719088c8e42c6ab
499 | f77643cf323921d7c6542d86974f9497
500 | f78e16c1dbc4dbd31349824369d952b3
501 | f7b8a1d716dc1725aa7cb30470f3273c
502 | f7dc5f5fde343cc5c955e5ed03ef3a2f
503 | f7ddd0ae5b0107efdde6d22342684df5
504 | f7fea253245d97786c02d42bfa6c5667
505 | f7ff2f9bb62a9f5c96de5fa2ca080bfe
506 | f80cce35d167ff9b855931d119219022
507 | f82473746c17ef04f2baf097673c64e5
508 | f850a69b0d308fbc19fb4103277a6b93
509 | f85a362c7607921a7aeca7115f6949c7
510 | f86ad1699aa2da6dc955e5ed03ef3a2f
511 | f875ff7c72fdada820768660cf080d12
512 | f89a468c302c89d9534fa06200d07790
513 | f8e8b0059395805d9bd3e6056359bce9
514 | f8f22279842d9b8bfc6d85675a0e869f
515 | f90bf59515aa8368e42c56c78fb88524
516 | f910c50ed20073928be66dc0939fd23
517 | f917474a20558aa33bbab77a66bc3671
518 | f92b1c64b0306322de6ff974c28c2f8b
519 | f94b4fa5703a0d96983ba8b03ccecdb9
520 | f94bd6bbed8fd60614038d588fd1342f
521 | f9509165955416a79b4cf10910d2df7e
522 | f9597fd50738ba45ba5342d638d0c267
523 | f979c7a650d29ea819fb4103277a6b93
524 | f995c1239510cf8b5d009c98a5b96836
525 | f9add10d9e9f13f413ee1dc69b2c2bdc
526 | f9bac9ba3b878cf23a6e0d0a575f76a3
527 | f9bbfd8acdee30158a63c123f2a561a6
528 | f9beeefdebf70350f4b6538438a0b930
529 | f9c98f76522d375d20bac10b01e55c85
530 | f9ca8f7549af695a5aad165050e534c
531 | f9d405eae2dd08fd12439bb9f264f4d9
532 | f9d9ef770e04c5772b3242897b354191
533 | f9e126d15c5761b29af4053b8815b239
534 | f9ed6c993f7d65e2e5f83d0df19ff934
535 | fa29ae17ed1482ed8aaae3d020f5ddf8
536 | fa83ef67ce97491ac955e5ed03ef3a2f
537 | faa05897ccdaa0e4f51f77a6d7299806
538 | faa5d5ba2a002922511e5b9dc733c75c
539 | fad62f2339aefa8f9d86e5f05f1da2b7
540 | fb0459ca3947e2fecf5d00de99803a2b
541 | fb32e9a7a8c2dfad74eb542502c2205f
542 | fb3816ce98c668157e22078abbbc121d
543 | fb4d71ac2bbefa2297936c81e7f6629
544 | fb50672ad3f7b196cae684aee7caa8d9
545 | fb5e8a6361262c26acf7920879052e93
546 | fb91ba29b46a519f8f37c398c1a74a0f
547 | fb9e9c0767a92d2e923b3c05c4c4fae
548 | fba0f822f16932aa10566a0096ed09d
549 | fbdd516e90ad48902872e9c941f7c819
550 | fbf9ef8784c0cb8485c1a9fb01e08349
551 | fc2ae302325d2c796820bd77cbfc18d6
552 | fc472163ea149f8e19fb4103277a6b93
553 | fc8b1310927ce3e6d8d12f352b5e1839
554 | fc9f18e509b363fcac7bed72580dc30f
555 | fcc0737ae08a9cfb63eca8f941f00cca
556 | fcc387cf43f5c63855931d119219022
557 | fcc3a9a4e880b5f35966c5a46a5a6ec8
558 | fccd86d2aa3c565334aff3344c00890c
559 | fcd4d0e1777f4841dcfcef693e7ec696
560 | fcf216336b414bfd2ea86336b05b146a
561 | fd07e0a8265d1e15db11d29991a4fad8
562 | fd1573fb1fc4a99b4c161851ed2b4e4
563 | fd57354b70d416386086aaeef17e8c87
564 | fd5c4da3a081cf115ec69be1b6d2571
565 | fd7a579772b195532de421c2ab5cfb52
566 | fdc04ac9fe8dd6db04cb542e2c50eb4
567 | fdf1cbe0d8aeba868c1cf3f7d7f0373
568 | fe0e7198411fc340c057222d6d091c56
569 | fe167899fda76d1e88dcbe86402c7c15
570 | fe25a9fdbf70cc25f81ed792b3a38b04
571 | fe2e9385283b62922de0bc4fc4d02dd6
572 | fe38d140fa386ed4c434c6fce2e7773
573 | fe4bcffc64838402684b7bc3f8a9aa55
574 | fe4c20766801dc98bc2e5d5fd57660fe
575 | fe5e1df0653804d6ce4670b160b81e9
576 | fe5f543fd0c6b34edbbc9440457e303e
577 | fe621b83750698a6855931d119219022
578 | fe710962895c20914476c40fec27b24f
579 | fe82d64b0268ba75febad4f49b26ec52
580 | fe9d363792ee708b35836c728d324152
581 | fed87d16ece9ac0ad42ec7e303174a87
582 | ff127b5ab0e36faec3bec646284d5a6a
583 | ff1c8d1e157f3b74b0ceed2c36e897b8
584 | ff212e47775ea7fe6a3056c8cad72d81
585 | ff2b5b315173f3244fb315ce917a9ec2
586 | ff32ec299e6c37e767d783b4714d4324
587 | ff404f70bb77a5a876e4a31295619fa6
588 | ff42855b8cd62a1060fdcc1483180fd1
589 | ff9bb9597cac5ef17a50afc9c93f8a50
590 | ffb5e48fde2cca54518bdb78540c51ed
591 | ffe2bf44f5d9760b9a8ef44e1d2c5b75
592 | 


--------------------------------------------------------------------------------
/splits/merge_splits.py:
--------------------------------------------------------------------------------
 1 | import os
 2 | 
 3 | cats = ['chair', 'plane', 'car', 'table', 'cabinet', 'lamp', 'boat', 'couch']
 4 | names = ['03001627', '02691156', '02958343', '04379243', '02933112', '03636649', '04530566', '04256520']
 5 | fout = open('content_total_test.txt', 'w')
 6 | for i, cat in enumerate(cats):
 7 |     fin = open("content_%s_test.txt"%(cat))
 8 |     dataset_names = [name.strip() for name in fin.readlines()]
 9 |     fin.close()
10 |     for model_name in dataset_names:
11 |         fout.write("%s/%s\n"%(names[i], model_name))
12 | fout.close()
13 | 
14 | 
15 | 


--------------------------------------------------------------------------------