├── .gitignore ├── DUNet-retinal-vessel-detection ├── README.md ├── __pycache__ │ ├── loaddata.cpython-36.pyc │ └── models.cpython-36.pyc ├── cut_patches.py ├── data │ ├── CHASE │ │ ├── test │ │ │ ├── 1st_manual │ │ │ │ ├── Image_11L_1stHO.png │ │ │ │ ├── Image_11R_1stHO.png │ │ │ │ ├── Image_12L_1stHO.png │ │ │ │ ├── Image_12R_1stHO.png │ │ │ │ ├── Image_13L_1stHO.png │ │ │ │ ├── Image_13R_1stHO.png │ │ │ │ ├── Image_14L_1stHO.png │ │ │ │ └── Image_14R_1stHO.png │ │ │ └── images │ │ │ │ ├── Image_11L.jpg │ │ │ │ ├── Image_11R.jpg │ │ │ │ ├── Image_12L.jpg │ │ │ │ ├── Image_12R.jpg │ │ │ │ ├── Image_13L.jpg │ │ │ │ ├── Image_13R.jpg │ │ │ │ ├── Image_14L.jpg │ │ │ │ └── Image_14R.jpg │ │ └── train │ │ │ ├── 1st_manual │ │ │ ├── Image_01L_1stHO.png │ │ │ ├── Image_01R_1stHO.png │ │ │ ├── Image_02L_1stHO.png │ │ │ ├── Image_02R_1stHO.png │ │ │ ├── Image_03L_1stHO.png │ │ │ ├── Image_03R_1stHO.png │ │ │ ├── Image_04L_1stHO.png │ │ │ ├── Image_04R_1stHO.png │ │ │ ├── Image_05L_1stHO.png │ │ │ ├── Image_05R_1stHO.png │ │ │ ├── Image_06L_1stHO.png │ │ │ ├── Image_06R_1stHO.png │ │ │ ├── Image_07L_1stHO.png │ │ │ ├── Image_07R_1stHO.png │ │ │ ├── Image_08L_1stHO.png │ │ │ ├── Image_08R_1stHO.png │ │ │ ├── Image_09L_1stHO.png │ │ │ ├── Image_09R_1stHO.png │ │ │ ├── Image_10L_1stHO.png │ │ │ └── Image_10R_1stHO.png │ │ │ └── images │ │ │ ├── Image_01L.jpg │ │ │ ├── Image_01R.jpg │ │ │ ├── Image_02L.jpg │ │ │ ├── Image_02R.jpg │ │ │ ├── Image_03L.jpg │ │ │ ├── Image_03R.jpg │ │ │ ├── Image_04L.jpg │ │ │ ├── Image_04R.jpg │ │ │ ├── Image_05L.jpg │ │ │ ├── Image_05R.jpg │ │ │ ├── Image_06L.jpg │ │ │ ├── Image_06R.jpg │ │ │ ├── Image_07L.jpg │ │ │ ├── Image_07R.jpg │ │ │ ├── Image_08L.jpg │ │ │ ├── Image_08R.jpg │ │ │ ├── Image_09L.jpg │ │ │ ├── Image_09R.jpg │ │ │ ├── Image_10L.jpg │ │ │ └── Image_10R.jpg │ └── DRIVE │ │ ├── test │ │ ├── 1st_manual │ │ │ ├── 01_manual1.gif │ │ │ ├── 02_manual1.gif │ │ │ ├── 03_manual1.gif │ │ │ ├── 04_manual1.gif │ │ │ ├── 05_manual1.gif │ │ │ ├── 06_manual1.gif │ │ │ ├── 07_manual1.gif │ │ │ ├── 08_manual1.gif │ │ │ ├── 09_manual1.gif │ │ │ ├── 10_manual1.gif │ │ │ ├── 11_manual1.gif │ │ │ ├── 12_manual1.gif │ │ │ ├── 13_manual1.gif │ │ │ ├── 14_manual1.gif │ │ │ ├── 15_manual1.gif │ │ │ ├── 16_manual1.gif │ │ │ ├── 17_manual1.gif │ │ │ ├── 18_manual1.gif │ │ │ ├── 19_manual1.gif │ │ │ └── 20_manual1.gif │ │ └── images │ │ │ ├── 01_test.tif │ │ │ ├── 02_test.tif │ │ │ ├── 03_test.tif │ │ │ ├── 04_test.tif │ │ │ ├── 05_test.tif │ │ │ ├── 06_test.tif │ │ │ ├── 07_test.tif │ │ │ ├── 08_test.tif │ │ │ ├── 09_test.tif │ │ │ ├── 10_test.tif │ │ │ ├── 11_test.tif │ │ │ ├── 12_test.tif │ │ │ ├── 13_test.tif │ │ │ ├── 14_test.tif │ │ │ ├── 15_test.tif │ │ │ ├── 16_test.tif │ │ │ ├── 17_test.tif │ │ │ ├── 18_test.tif │ │ │ ├── 19_test.tif │ │ │ └── 20_test.tif │ │ └── train │ │ ├── 1st_manual │ │ ├── 21_manual1.gif │ │ ├── 22_manual1.gif │ │ ├── 23_manual1.gif │ │ ├── 24_manual1.gif │ │ ├── 25_manual1.gif │ │ ├── 26_manual1.gif │ │ ├── 27_manual1.gif │ │ ├── 28_manual1.gif │ │ ├── 29_manual1.gif │ │ ├── 30_manual1.gif │ │ ├── 31_manual1.gif │ │ ├── 32_manual1.gif │ │ ├── 33_manual1.gif │ │ ├── 34_manual1.gif │ │ ├── 35_manual1.gif │ │ ├── 36_manual1.gif │ │ ├── 37_manual1.gif │ │ ├── 38_manual1.gif │ │ ├── 39_manual1.gif │ │ └── 40_manual1.gif │ │ └── images │ │ ├── 21_train.tif │ │ ├── 22_train.tif │ │ ├── 23_train.tif │ │ ├── 24_train.tif │ │ ├── 25_train.tif │ │ ├── 26_train.tif │ │ ├── 27_train.tif │ │ ├── 28_train.tif │ │ ├── 29_train.tif │ │ ├── 30_train.tif │ │ ├── 31_train.tif │ │ ├── 32_train.tif │ │ ├── 33_train.tif │ │ ├── 34_train.tif │ │ ├── 35_train.tif │ │ ├── 36_train.tif │ │ ├── 37_train.tif │ │ ├── 38_train.tif │ │ ├── 39_train.tif │ │ └── 40_train.tif ├── experiment_log.txt ├── finally_evaluate.py ├── get_mask.py ├── loaddata.py ├── merge_imgs.py ├── models.py ├── preprocessing.py ├── show_img │ ├── CHASE_test.png │ ├── DRIVE_test.png │ ├── Unet++.png │ ├── Unet.png │ ├── patchVSpatch_labelVSpatch_predict.png │ └── preprocessing.png ├── train_test_evaluate.py └── 眼底血管分割实验报告.pdf ├── README.md └── Reading-list ├── registration-paper ├── 1903.03545.pdf ├── 1908.02738.pdf ├── An Unsupervised Learning Model for Deformable Medical Image Registration.pdf ├── VoxelMorph A Learning Framework for Deformable Medical Image Registration.pdf └── 医学影像报告-第14组.pdf └── segmentation-paper ├── [10] Deep_Layer_Aggregation_CVPR_2018_paper.pdf ├── [1] Adaptive histogram equalization and its variations-影印版.pdf ├── [1] Adaptive histogram equalization and its variations-扫描版.pdf ├── [2] Contrast Limited Adaptive Histogram Equalization.pdf ├── [3] Adaptive contrast enhancement using local region stretching.pdf ├── [4] 眼底图像检测和分析系统的设计与开发_马青柯.caj ├── [5] 基于改进的U_Net眼底视网膜血管分割_梁礼明.pdf ├── [6] DUNet-A deformable network for retinal vessel segmentation.pdf ├── [7] Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification.pdf ├── [8] UNet.pdf └── [9] UNet++.pdf /.gitignore: -------------------------------------------------------------------------------- 1 | DUNet-retinal-vessel-detection/data_process/ 2 | DUNet-retinal-vessel-detection/data_crop/ 3 | DUNet-retinal-vessel-detection/result/ 4 | DUNet-retinal-vessel-detection/weights_DRIVE_5.pth 5 | DUNet-retinal-vessel-detection/weights_CHASE_5.pth -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/README.md: -------------------------------------------------------------------------------- 1 | # 简介 2 | 3 | ## 一、文件目录 4 | 5 | ```bash 6 | . 7 | │ preprocessing.py # 4步图像增强 8 | │ get_mask.py # 获取感兴趣区域ROI二值化 9 | │ cut_patches.py # 切成很多小图 10 | │ models.py # 存取不同网络模型，暂时用torch写了Unet和Unet++ 11 | │ loaddata.py # 为训练测试加载数据 12 | │ train_test_evaluate.py # 训练、预测、评估 13 | │ merge_imgs.py # 合并预测的小patchs，合并切割后的label（因为合并切割图像与原label大小并不一样 14 | │ finally_evaluate.py # 计算整张图像Dice和accuracy两个评价指标 15 | │ README.md 16 | │ 17 | ├─data 18 | │ ├─CHASE 19 | │ │ ├─test 20 | │ │ │ ├─1st_manual # 4对，8张 21 | │ │ │ └─images 22 | │ │ └─train 23 | │ │ ├─1st_manual # 10对，20张 24 | │ │ └─images 25 | │ └─DRIVE 26 | │ ├─test 27 | │ │ ├─1st_manual # 20张 28 | │ │ └─images 29 | │ └─train 30 | │ ├─1st_manual # 20张 31 | │ └─images 32 | │ 33 | │ ############## 以下文件和文件夹是本人手动加进去的 ############## 34 | │ 35 | ├─show_img 36 | │ └─... # 4张实验结果展示图 37 | │ 38 | ├─experiment_log.txt # 实验运行日志 39 | │ 40 | │ ################ 以下数据集是运行代码后期生成的 ################ 41 | │ 42 | ├─data_process 43 | │ ├─CHASE 44 | │ │ ├─test # 3个文件夹各8张 45 | │ │ │ ├─1st_manual 46 | │ │ │ ├─mask 47 | │ │ │ └─preprocessing 48 | │ │ └─train # 3个文件夹各20张 49 | │ │ ├─1st_manual 50 | │ │ ├─mask 51 | │ │ └─preprocessing 52 | │ └─DRIVE 53 | │ ├─test # 3个文件夹各20张 54 | │ │ ├─1st_manual 55 | │ │ ├─mask 56 | │ │ └─preprocessing 57 | │ └─train # 3个文件夹各20张 58 | │ ├─1st_manual 59 | │ ├─mask 60 | │ └─preprocessing 61 | │ 62 | ├─data_crop 63 | │ ├─CHASE 64 | │ │ ├─test # 8*36*2=576张，增强图+label 65 | │ │ └─train # 20*36*2=1440张 66 | │ └─DRIVE 67 | │ ├─test # 20*9*2=360张 68 | │ └─train # 20*9*2=360张 69 | │ 70 | └─result 71 | ├─CHASE 72 | │ ├─merge # 8张，合并的预测的整个图 73 | │ ├─merge_label # 8张，合并的分割的整个label图 74 | │ └─test # 8*36=288张，预测的单个patch图 75 | └─DRIVE 76 | ├─merge # 20张 77 | ├─merge_label # 20张 78 | └─test # 20*9=180张 79 | ``` 80 | 81 | ## 二、执行顺序 82 | 83 | - [x] preprocessing.py：生成4步（rgb2gray，nomalized，clahe，gamma）图像增强后的图像，保存至 `./data_process/{dataset}/{train_or_test}/preprocessing/{imgname}_gamma.jpg`。 84 | - [x] get_mask.py：生成原始图像的mask，保存至 `./data_process/{dataset}/{train_or_test}/mask/{imgname}_mask.jpg`。 85 | - [x] cut_patches.py：先将`1st_manual`文件夹从`./data/{dataset}/{train_or_test}/`拷贝到`./data_process/{dataset}/{train_or_test}/`，然后将增强图、`1st_manual`（ground_truth）、(mask暂时没切割)分割为指定大小的小patches，分别保存至 `./data_crop/{dataset}/{train_or_test}/{index}`。 86 | - [x] train_test_evaluate.py：调用 models.py，执行网络训练、预测、评估。models.py和loaddata.py是要被调用的两个模块。 87 | - [x] merge_imgs.py: 合并2个数据集的predict和label。 88 | - [x] finally_evaluate.py: 计算 Dice 和Accuracy 测度。 89 | 90 | ```bash 91 | python preprocessing.py 92 | python get_mask.py 93 | python cut_patches.py 94 | 95 | python train_test_evaluate.py train 96 | python train_test_evaluate.py test 97 | python train_test_evaluate.py train --batch_size=8 --ckpt='weights_DRIVE_5.pth' --datasetname='DRIVE' 98 | python train_test_evaluate.py test --ckpt='weights_DRIVE_5.pth' --datasetname='DRIVE' 99 | 100 | python merge_imgs.py # 注意每次修改5处，每次合并一个数据集的预测图or标签 101 | python merge_imgs.py 102 | python merge_imgs.py 103 | python merge_imgs.py 104 | python finally_evaluate.py 105 | ``` 106 | 107 | ## 三、实验思路 108 | 109 | - 1.图像预处理： 110 | - 1）单通道化RGB2Gray 111 | - 2）归一化 112 | - 3）对比度限制自适应直方图均衡化 113 | - 4）伽马校正 114 | - 2.图像分割成小块patch 115 | - 3.torch写网络 116 | - Unet 117 | ![Unet.png](./show_img/Unet.png) 118 | - Unet++ 119 | ![Unet++.png](./show_img/Unet++.png) 120 | - 4.训练与测试，计算每个小patch的train_loss和dice_score 121 | - 5.合并图像 122 | - 6.计算整体测度 123 | 124 | ## 四、实验结果 125 | 126 | 本人运算资源时间有限，暂时没有进行深入对比试验。`torch.__version__=1.4.0`，`torchvision.__version__=0.5.0`，GPU：天池平台的的 `Tesla V100`，显存有时不到1GB，CPU：天池平台的 `2Core4G` 127 | 128 | CHASE数据集用cuda训练batchsize为2，网络采用UNet++，轮数epoch=5，测试集结果： 129 | 130 | avarage Dice: **78.03%**, avarage Accuracy: **96.91%** 131 | 132 | DRIVE数据集用cpu训练batchsize为8，网络采用UNet，轮数epoch=5，测试集结果： 133 | 134 | avarage Dice: **77.45%**, avarage Accuracy: **95.83%** 135 | 136 | 1.预处理增强步骤图 137 | 138 | 1）单通道化RGB2Gray 2）归一化 3）对比度限制自适应直方图均衡化 CLAHE 4）伽马校正 139 | 140 | ![preprocessing.png](./show_img/preprocessing.png) 141 | 142 | 2.切分的增强图小块图，小块标签图，小块预测图patch_labelVSpatch_predict 143 | 144 | ![patchVSpatch_labelVSpatch_predict.png](./show_img/patchVSpatch_labelVSpatch_predict.png) 145 | 146 | 3.CHASE_test 147 | 148 | ![CHASE_test.png](./show_img/CHASE_test.png) 149 | 150 | 4.DRIVE_test 151 | 152 | ![DRIVE_test.png](./show_img/DRIVE_test.png) 153 | 154 | 5.合并后的图计算两个评价指标：Dice 和 Accuracy 155 | 156 | ``` 157 | CHASE No.1, Dice:82.06%, Accuracy:97.71% 158 | CHASE No.2, Dice:81.09%, Accuracy:97.62% 159 | CHASE No.3, Dice:76.20%, Accuracy:96.22% 160 | CHASE No.4, Dice:78.20%, Accuracy:96.52% 161 | CHASE No.5, Dice:77.55%, Accuracy:96.84% 162 | CHASE No.6, Dice:73.54%, Accuracy:96.46% 163 | CHASE No.7, Dice:79.55%, Accuracy:96.93% 164 | CHASE No.8, Dice:76.02%, Accuracy:97.00% 165 | CHASE avarage Dice:78.03%, avarage Accuracy:96.91% 166 | DRIVE No.1, Dice:80.14%, Accuracy:95.85% 167 | DRIVE No.2, Dice:82.00%, Accuracy:96.07% 168 | DRIVE No.3, Dice:75.77%, Accuracy:94.57% 169 | DRIVE No.4, Dice:79.41%, Accuracy:95.84% 170 | DRIVE No.5, Dice:76.71%, Accuracy:95.51% 171 | DRIVE No.6, Dice:74.82%, Accuracy:95.07% 172 | DRIVE No.7, Dice:76.64%, Accuracy:95.71% 173 | DRIVE No.8, Dice:72.05%, Accuracy:95.28% 174 | DRIVE No.9, Dice:70.27%, Accuracy:95.35% 175 | DRIVE No.10, Dice:77.66%, Accuracy:95.96% 176 | DRIVE No.11, Dice:77.46%, Accuracy:95.76% 177 | DRIVE No.12, Dice:76.08%, Accuracy:95.71% 178 | DRIVE No.13, Dice:76.95%, Accuracy:95.40% 179 | DRIVE No.14, Dice:78.46%, Accuracy:96.37% 180 | DRIVE No.15, Dice:79.59%, Accuracy:96.64% 181 | DRIVE No.16, Dice:80.35%, Accuracy:96.23% 182 | DRIVE No.17, Dice:72.79%, Accuracy:95.44% 183 | DRIVE No.18, Dice:77.54%, Accuracy:96.23% 184 | DRIVE No.19, Dice:84.87%, Accuracy:97.00% 185 | DRIVE No.20, Dice:79.51%, Accuracy:96.64% 186 | DRIVE avarage Dice:77.45%, avarage Accuracy:95.83% 187 | ``` 188 | 189 | 6.实验日志见 [./experiment_log.txt](./experiment_log.txt) 190 | 191 | ## 五、参考文献 192 | 193 | - [1] Pizer S M, Amburn E P, Austin J D, et al. Adaptive histogram equalization and its variations[J]. Computer vision, graphics, and image processing, 1987, 39(3): 355-368. 194 | - [2] Zuiderveld K . Contrast Limited Adaptive Histogram Equalization[J]. Graphics Gems, 1994:474-485. 195 | - [3] Srinivasan S, Balram N. Adaptive contrast enhancement using local region stretching[C]//Proceedings of the 9th Asian symposium on information display. 2006: 152-155. 196 | - [4] 马青柯. 眼底图像检测和分析系统的设计与开发[D]. 暨南大学. 197 | - [5] 梁礼明, 盛校棋, 郭凯,等. 基于改进的U-Net眼底视网膜血管分割[J]. 计算机应用研究, 2020, v.37;No.342(04):293-297. 198 | - [6] Jin Q , Meng Z , Pham T D , et al. DUNet: A deformable network for retinal vessel segmentation[J]. Knowledge-Based Systems, 2019, 178(AUG.15):149-162. https://github.com/RanSuLab/DUNet-retinal-vessel-detection 199 | - [7] J.V. Soares, J.J. Leandro, R.M. Cesar, H.F. Jelinek, M.J. Cree, Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification, IEEE Trans. Med. Imaging 25 (9) (2006) 1214–1222. 200 | - [8] Ronneberger O , Fischer P , Brox T . U-Net: Convolutional Networks for Biomedical Image Segmentation[M]. Springer, Cham, 2015. 201 | - [9] Zhou Z , Siddiquee M , Tajbakhsh N , et al. UNet++: A Nested U-Net Architecture for Medical Image Segmentation[C]// 4th Deep Learning in Medical Image Analysis (DLMIA) Workshop. 2018. 202 | - [10] Yu F , Wang D , Shelhamer E , et al. Deep Layer Aggregation[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2018. 203 | - [11] https://github.com/wfdubowen/Retina-Unet 204 | - [12] https://github.com/JavisPeng/u_net_liver 205 | - [13] https://github.com/ainieli/UCAS_retina_seg 206 | -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/__pycache__/loaddata.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/__pycache__/loaddata.cpython-36.pyc -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/__pycache__/models.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/__pycache__/models.cpython-36.pyc -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/cut_patches.py: -------------------------------------------------------------------------------- 1 | # Crop each image to patches to expand the date 2 | import os 3 | import shutil 4 | import argparse 5 | import glob 6 | import numpy as np 7 | from PIL import Image 8 | 9 | 10 | def strided_crop(img, label, mask, name, height, width, m, n, l, stride=1): 11 | # directories = ['./data_crop/' + m + '/' + n + '/Images', './data_crop/' + 12 | # m + '/' + n + '/Labels', './data_crop/' + m + '/' + n + '/Masks'] 13 | directories = ['./data_crop/' + m + '/' + n] 14 | for directory in directories: 15 | if not os.path.exists(directory): 16 | os.makedirs(directory) 17 | max_x = int(((img.shape[0] - height) / stride) + 1) 18 | # print('max_x:',max_x) 19 | max_y = int(((img.shape[1] - width) / stride) + 1) 20 | # print('max_y:',max_y) 21 | max_crops = max_x * max_y 22 | print('max_crops =', max_x, '*', max_y, '=', max_crops) 23 | k = 0 24 | for h in range(max_x): 25 | for w in range(max_y): 26 | k += 1 27 | crop_img_arr = img[h * stride:(h * stride) + 28 | height, w * stride:(w * stride) + width] 29 | crop_label_arr = label[h * stride:(h * stride) + 30 | height, w * stride:(w * stride) + width] 31 | crop_mask_arr = mask[h * stride:(h * stride) + 32 | height, w * stride:(w * stride) + width] 33 | crop_img = Image.fromarray(crop_img_arr) 34 | crop_label = Image.fromarray(crop_label_arr) 35 | crop_mask = Image.fromarray(crop_mask_arr) 36 | # img_name = directories[0] + '/' + name + '_%03d.png' % k 37 | # label_name = directories[0] + '/' + \ 38 | # name + '_%03d_label.png' % k 39 | # mask_name = directories[0] + '/' + \ 40 | # name + '_%03d_mask.png' % k 41 | img_name = directories[0] + '/' + '%03d.png' % (max_crops*l+k) 42 | label_name = directories[0] + '/' + \ 43 | '%03d_label.png' % (max_crops*l+k) 44 | mask_name = directories[0] + '/' + \ 45 | '%03d_mask.png' % (max_crops*l+k) 46 | crop_img.save(img_name) 47 | crop_label.save(label_name) 48 | # crop_mask.save(mask_name) 49 | 50 | 51 | if __name__ == '__main__': 52 | 53 | dataset = ['CHASE', 'DRIVE'] 54 | train_test = ['train', 'test'] 55 | 56 | # Copy 1st_manual from 'data' folder to 'data_process' folder 57 | source_path = ['./data/'+dataset[i]+'/'+train_test[j]+'/1st_manual' 58 | for i in range(len(dataset)) for j in range(len(train_test))] 59 | target_path = ['./data_process/'+dataset[i]+'/'+train_test[j]+'/1st_manual' 60 | for i in range(len(dataset)) for j in range(len(train_test))] 61 | print(source_path, target_path) 62 | for i in range(4): 63 | if not os.path.exists(target_path[i]): 64 | os.makedirs(target_path[i]) 65 | if os.path.exists(source_path[i]): 66 | shutil.rmtree(target_path[i]) 67 | shutil.copytree(source_path[i], target_path[i]) 68 | print('Copy dir finished!') 69 | 70 | # Set some parameters 71 | parser = argparse.ArgumentParser() 72 | parser.add_argument('--side_length', type=int, default=256) 73 | parser.add_argument('--stride', type=int, default=128) 74 | args = parser.parse_args() 75 | 76 | # Crop from images 77 | for m in dataset: 78 | for n in train_test: 79 | img_dir = './data_process/' + m + '/' + n + '/preprocessing/' 80 | img_name = os.listdir(img_dir) 81 | images = [img_dir+img_name[i] for i in range(len(img_name))] 82 | l = 0 83 | for i, j in enumerate(images): 84 | image_name = j.split('/')[-1].split('.')[0][:-6] 85 | # print(image_name) # Image_01L, ..., 20_test 86 | im = Image.open(images[i]) 87 | img_arr = np.asarray(im) 88 | if m == 'CHASE': 89 | label_name = './data_process/' + m + '/' + n + \ 90 | '/1st_manual/' + image_name + '_1stHO.png' 91 | elif m == 'DRIVE': 92 | label_name = './data_process/' + m + '/' + n + \ 93 | '/1st_manual/' + image_name[:2] + '_manual1.gif' 94 | label = Image.open(label_name) 95 | label_arr = np.asarray(label) 96 | mask_name = './data_process/' + m + '/' + \ 97 | n + '/mask/' + image_name + '_mask.jpg' 98 | mask = Image.open(mask_name) 99 | mask_arr = np.asarray(mask) 100 | strided_crop(img_arr, label_arr, mask_arr, image_name, 101 | args.side_length, args.side_length, m, n, l, args.stride) 102 | l += 1 103 | -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_11L_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_11L_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_11R_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_11R_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_12L_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_12L_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_12R_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_12R_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_13L_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_13L_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_13R_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_13R_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_14L_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_14L_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_14R_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/1st_manual/Image_14R_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_11L.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_11L.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_11R.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_11R.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_12L.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_12L.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_12R.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_12R.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_13L.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_13L.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_13R.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_13R.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_14L.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_14L.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_14R.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/test/images/Image_14R.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_01L_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_01L_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_01R_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_01R_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_02L_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_02L_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_02R_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_02R_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_03L_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_03L_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_03R_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_03R_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_04L_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_04L_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_04R_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_04R_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_05L_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_05L_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_05R_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_05R_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_06L_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_06L_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_06R_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_06R_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_07L_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_07L_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_07R_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_07R_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_08L_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_08L_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_08R_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_08R_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_09L_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_09L_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_09R_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_09R_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_10L_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_10L_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_10R_1stHO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/1st_manual/Image_10R_1stHO.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_01L.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_01L.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_01R.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_01R.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_02L.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_02L.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_02R.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_02R.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_03L.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_03L.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_03R.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_03R.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_04L.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_04L.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_04R.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_04R.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_05L.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_05L.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_05R.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_05R.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_06L.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_06L.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_06R.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_06R.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_07L.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_07L.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_07R.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_07R.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_08L.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_08L.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_08R.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_08R.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_09L.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_09L.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_09R.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_09R.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_10L.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_10L.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_10R.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/CHASE/train/images/Image_10R.jpg -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/01_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/01_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/02_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/02_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/03_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/03_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/04_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/04_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/05_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/05_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/06_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/06_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/07_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/07_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/08_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/08_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/09_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/09_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/10_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/10_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/11_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/11_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/12_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/12_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/13_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/13_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/14_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/14_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/15_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/15_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/16_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/16_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/17_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/17_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/18_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/18_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/19_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/19_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/20_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/1st_manual/20_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/01_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/01_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/02_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/02_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/03_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/03_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/04_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/04_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/05_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/05_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/06_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/06_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/07_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/07_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/08_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/08_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/09_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/09_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/10_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/10_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/11_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/11_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/12_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/12_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/13_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/13_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/14_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/14_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/15_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/15_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/16_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/16_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/17_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/17_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/18_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/18_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/19_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/19_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/test/images/20_test.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/test/images/20_test.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/21_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/21_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/22_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/22_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/23_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/23_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/24_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/24_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/25_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/25_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/26_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/26_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/27_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/27_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/28_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/28_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/29_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/29_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/30_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/30_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/31_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/31_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/32_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/32_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/33_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/33_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/34_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/34_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/35_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/35_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/36_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/36_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/37_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/37_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/38_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/38_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/39_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/39_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/40_manual1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/1st_manual/40_manual1.gif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/21_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/21_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/22_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/22_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/23_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/23_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/24_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/24_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/25_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/25_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/26_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/26_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/27_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/27_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/28_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/28_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/29_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/29_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/30_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/30_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/31_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/31_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/32_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/32_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/33_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/33_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/34_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/34_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/35_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/35_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/36_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/36_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/37_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/37_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/38_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/38_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/39_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/39_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/data/DRIVE/train/images/40_train.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/data/DRIVE/train/images/40_train.tif -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/experiment_log.txt: -------------------------------------------------------------------------------- 1 | DRIVE, Unet 2 | train_num=20*9=180, batch_size=8; 3 | test_num=20*9=180, batch_size=1 4 | 5 | %run train_test_evaluate train --datasetname='DRIVE' 6 | 7 | Epoch 1/5 8 | ---------- 9 | 1/23,train_loss:0.736 10 | 2/23,train_loss:0.662 11 | 3/23,train_loss:0.623 12 | 4/23,train_loss:0.516 13 | 5/23,train_loss:0.492 14 | 6/23,train_loss:0.465 15 | 7/23,train_loss:0.460 16 | 8/23,train_loss:0.428 17 | 9/23,train_loss:0.387 18 | 10/23,train_loss:0.385 19 | 11/23,train_loss:0.368 20 | 12/23,train_loss:0.359 21 | 13/23,train_loss:0.377 22 | 14/23,train_loss:0.354 23 | 15/23,train_loss:0.359 24 | 16/23,train_loss:0.323 25 | 17/23,train_loss:0.330 26 | 18/23,train_loss:0.318 27 | 19/23,train_loss:0.315 28 | 20/23,train_loss:0.311 29 | 21/23,train_loss:0.309 30 | 22/23,train_loss:0.303 31 | 23/23,train_loss:0.319 32 | epoch 1 loss:0.413 33 | Epoch 2/5 34 | ---------- 35 | 1/23,train_loss:0.293 36 | 2/23,train_loss:0.289 37 | 3/23,train_loss:0.277 38 | 4/23,train_loss:0.276 39 | 5/23,train_loss:0.266 40 | 6/23,train_loss:0.258 41 | 7/23,train_loss:0.273 42 | 8/23,train_loss:0.279 43 | 9/23,train_loss:0.255 44 | 10/23,train_loss:0.257 45 | 11/23,train_loss:0.249 46 | 12/23,train_loss:0.260 47 | 13/23,train_loss:0.252 48 | 14/23,train_loss:0.239 49 | 15/23,train_loss:0.269 50 | 16/23,train_loss:0.245 51 | 17/23,train_loss:0.234 52 | 18/23,train_loss:0.231 53 | 19/23,train_loss:0.232 54 | 20/23,train_loss:0.224 55 | 21/23,train_loss:0.236 56 | 22/23,train_loss:0.222 57 | 23/23,train_loss:0.213 58 | epoch 2 loss:0.253 59 | Epoch 3/5 60 | ---------- 61 | 1/23,train_loss:0.217 62 | 2/23,train_loss:0.218 63 | 3/23,train_loss:0.238 64 | 4/23,train_loss:0.211 65 | 5/23,train_loss:0.210 66 | 6/23,train_loss:0.208 67 | 7/23,train_loss:0.205 68 | 8/23,train_loss:0.208 69 | 9/23,train_loss:0.212 70 | 10/23,train_loss:0.193 71 | 11/23,train_loss:0.203 72 | 12/23,train_loss:0.234 73 | 13/23,train_loss:0.197 74 | 14/23,train_loss:0.201 75 | 15/23,train_loss:0.193 76 | 16/23,train_loss:0.234 77 | 17/23,train_loss:0.185 78 | 18/23,train_loss:0.185 79 | 19/23,train_loss:0.209 80 | 20/23,train_loss:0.198 81 | 21/23,train_loss:0.184 82 | 22/23,train_loss:0.180 83 | 23/23,train_loss:0.174 84 | epoch 3 loss:0.204 85 | Epoch 4/5 86 | ---------- 87 | 1/23,train_loss:0.192 88 | 2/23,train_loss:0.189 89 | 3/23,train_loss:0.183 90 | 4/23,train_loss:0.183 91 | 5/23,train_loss:0.195 92 | 6/23,train_loss:0.173 93 | 7/23,train_loss:0.174 94 | 8/23,train_loss:0.186 95 | 9/23,train_loss:0.185 96 | 10/23,train_loss:0.164 97 | 11/23,train_loss:0.177 98 | 12/23,train_loss:0.169 99 | 13/23,train_loss:0.156 100 | 14/23,train_loss:0.164 101 | 15/23,train_loss:0.158 102 | 16/23,train_loss:0.163 103 | 17/23,train_loss:0.164 104 | 18/23,train_loss:0.159 105 | 19/23,train_loss:0.165 106 | 20/23,train_loss:0.179 107 | 21/23,train_loss:0.157 108 | 22/23,train_loss:0.191 109 | 23/23,train_loss:0.169 110 | epoch 4 loss:0.174 111 | Epoch 5/5 112 | ---------- 113 | 1/23,train_loss:0.156 114 | 2/23,train_loss:0.184 115 | 3/23,train_loss:0.152 116 | 4/23,train_loss:0.164 117 | 5/23,train_loss:0.150 118 | 6/23,train_loss:0.155 119 | 7/23,train_loss:0.144 120 | 8/23,train_loss:0.181 121 | 9/23,train_loss:0.159 122 | 10/23,train_loss:0.179 123 | 11/23,train_loss:0.175 124 | 12/23,train_loss:0.148 125 | 13/23,train_loss:0.150 126 | 14/23,train_loss:0.155 127 | 15/23,train_loss:0.148 128 | 16/23,train_loss:0.157 129 | 17/23,train_loss:0.139 130 | 18/23,train_loss:0.157 131 | 19/23,train_loss:0.149 132 | 20/23,train_loss:0.156 133 | 21/23,train_loss:0.175 134 | 22/23,train_loss:0.132 135 | 23/23,train_loss:0.134 136 | epoch 5 loss:0.157 137 | 138 | 139 | %run train_test_evaluate test --datasetname='DRIVE' 140 | 141 | index:1 dice score:0.8297099055045265 142 | index:2 dice score:0.8287949542118989 143 | index:3 dice score:0.7990722446525212 144 | index:4 dice score:0.7737353239599942 145 | index:5 dice score:0.7501107665042092 146 | index:6 dice score:0.736418905667778 147 | index:7 dice score:0.7807346326836582 148 | index:8 dice score:0.811734443900049 149 | index:9 dice score:0.7925742574257426 150 | index:10 dice score:0.7724620770128354 151 | index:11 dice score:0.8142943184099578 152 | index:12 dice score:0.8366117531349889 153 | index:13 dice score:0.752596874717731 154 | index:14 dice score:0.7819158791921438 155 | index:15 dice score:0.8407057446274772 156 | index:16 dice score:0.790240760125614 157 | index:17 dice score:0.8055893074119077 158 | index:18 dice score:0.8419537472411477 159 | index:19 dice score:0.8048796658489691 160 | index:20 dice score:0.7675104448267388 161 | index:21 dice score:0.7180045531030387 162 | index:22 dice score:0.7561423873089572 163 | index:23 dice score:0.6703225806451613 164 | index:24 dice score:0.6476319089418346 165 | index:25 dice score:0.7377244213714038 166 | index:26 dice score:0.7472294926769505 167 | index:27 dice score:0.7632150615496017 168 | index:28 dice score:0.8383145516903479 169 | index:29 dice score:0.8286048932847475 170 | index:30 dice score:0.7994041064835805 171 | index:31 dice score:0.7959802201308024 172 | index:32 dice score:0.8460909388289173 173 | index:33 dice score:0.8226716645384521 174 | index:34 dice score:0.6729400410182169 175 | index:35 dice score:0.8071216617210683 176 | index:36 dice score:0.8198539869157107 177 | index:37 dice score:0.8110170138094148 178 | index:38 dice score:0.810272134917593 179 | index:39 dice score:0.7870073624945864 180 | index:40 dice score:0.7710793879018178 181 | index:41 dice score:0.7117437722419929 182 | index:42 dice score:0.6714681440443213 183 | index:43 dice score:0.7521124856350977 184 | index:44 dice score:0.7454962787786047 185 | index:45 dice score:0.7106001629401647 186 | index:46 dice score:0.7016634851377147 187 | index:47 dice score:0.7469930365055919 188 | index:48 dice score:0.7577943513877002 189 | index:49 dice score:0.6237424547283702 190 | index:50 dice score:0.6715496666940992 191 | index:51 dice score:0.737471663531568 192 | index:52 dice score:0.6584392919471453 193 | index:53 dice score:0.7385019710906702 194 | index:54 dice score:0.7957613734780172 195 | index:55 dice score:0.7159673175460463 196 | index:56 dice score:0.7263157894736842 197 | index:57 dice score:0.7859102064385737 198 | index:58 dice score:0.6218989479153136 199 | index:59 dice score:0.6277504270069326 200 | index:60 dice score:0.7933511614493209 201 | index:61 dice score:0.7073670585697336 202 | index:62 dice score:0.7300138538016462 203 | index:63 dice score:0.8008331456879081 204 | index:64 dice score:0.6968174204355109 205 | index:65 dice score:0.7107327658153898 206 | index:66 dice score:0.7116939890710382 207 | index:67 dice score:0.5217391304347826 208 | index:68 dice score:0.5316423589093215 209 | index:69 dice score:0.6872949501447411 210 | index:70 dice score:0.6649980239757608 211 | index:71 dice score:0.7245220282626766 212 | index:72 dice score:0.7662030006681649 213 | index:73 dice score:0.7430568328122126 214 | index:74 dice score:0.7651911788037442 215 | index:75 dice score:0.7073257048484134 216 | index:76 dice score:0.7066019295037518 217 | index:77 dice score:0.6698645598194131 218 | index:78 dice score:0.6029132362254591 219 | index:79 dice score:0.6875153902979562 220 | index:80 dice score:0.6874564459930314 221 | index:81 dice score:0.6774159553166825 222 | index:82 dice score:0.7912149795860904 223 | index:83 dice score:0.8141836173721825 224 | index:84 dice score:0.8191653786707882 225 | index:85 dice score:0.6580751302440362 226 | index:86 dice score:0.7039848197343453 227 | index:87 dice score:0.7602943654850851 228 | index:88 dice score:0.6683537897001138 229 | index:89 dice score:0.7610169491525424 230 | index:90 dice score:0.788251441119956 231 | index:91 dice score:0.8344713915705204 232 | index:92 dice score:0.7584920956627482 233 | index:93 dice score:0.7026369168356998 234 | index:94 dice score:0.8349673202614379 235 | index:95 dice score:0.7376069756176328 236 | index:96 dice score:0.6556103108415466 237 | index:97 dice score:0.8137147284819526 238 | index:98 dice score:0.7343868841375814 239 | index:99 dice score:0.7167332445628052 240 | index:100 dice score:0.7576724772894672 241 | index:101 dice score:0.7737153445941131 242 | index:102 dice score:0.7791081750619323 243 | index:103 dice score:0.7381283298586981 244 | index:104 dice score:0.6950860608222599 245 | index:105 dice score:0.6792710706150342 246 | index:106 dice score:0.7914163090128755 247 | index:107 dice score:0.7807892149978936 248 | index:108 dice score:0.7079326923076923 249 | index:109 dice score:0.6867088607594937 250 | index:110 dice score:0.766517921404923 251 | index:111 dice score:0.78824095061474 252 | index:112 dice score:0.6331141661685594 253 | index:113 dice score:0.7044676276180616 254 | index:115 dice score:0.747887323943662 255 | index:116 dice score:0.7850209781451563 256 | index:117 dice score:0.7975151452921244 257 | index:118 dice score:0.7663934426229508 258 | index:119 dice score:0.7870156734823773 259 | index:120 dice score:0.7933170099380671 260 | index:121 dice score:0.6776306992913491 261 | index:122 dice score:0.6527592231014284 262 | index:123 dice score:0.7640910548252645 263 | index:124 dice score:0.6801795280150572 264 | index:125 dice score:0.710610002891009 265 | index:126 dice score:0.8234587189039779 266 | index:127 dice score:0.8329795918367346 267 | index:128 dice score:0.8262011026516146 268 | index:129 dice score:0.7653206650831353 269 | index:130 dice score:0.8199233716475096 270 | index:131 dice score:0.8383784048119712 271 | index:132 dice score:0.7911357340720222 272 | index:133 dice score:0.7666254253015775 273 | index:134 dice score:0.8187051290343444 274 | index:135 dice score:0.8165790287658522 275 | index:136 dice score:0.7533045089561458 276 | index:137 dice score:0.7914235310082779 277 | index:138 dice score:0.8171975324184817 278 | index:139 dice score:0.7228680277425027 279 | index:140 dice score:0.7452861178634781 280 | index:141 dice score:0.8137283376899991 281 | index:142 dice score:0.7383646331505891 282 | index:143 dice score:0.7892099663669435 283 | index:144 dice score:0.846106338779406 284 | index:145 dice score:0.7633114062306069 285 | index:146 dice score:0.7449642084235059 286 | index:147 dice score:0.7424896197997232 287 | index:148 dice score:0.6029718776863564 288 | index:149 dice score:0.6120414673046252 289 | index:150 dice score:0.7445219430899327 290 | index:151 dice score:0.49935242480932507 291 | index:152 dice score:0.6701644479248238 292 | index:153 dice score:0.7998323955465102 293 | index:154 dice score:0.7153024911032029 294 | index:155 dice score:0.7268623024830699 295 | index:156 dice score:0.8005720414730068 296 | index:157 dice score:0.6539608453260729 297 | index:158 dice score:0.6671505599336375 298 | index:159 dice score:0.8052051823526054 299 | index:160 dice score:0.6401679916004199 300 | index:161 dice score:0.7497205743272289 301 | index:162 dice score:0.8321235165341629 302 | index:163 dice score:0.8326001389210466 303 | index:164 dice score:0.8502375542243338 304 | index:165 dice score:0.8595675132009052 305 | index:166 dice score:0.7839273640490679 306 | index:167 dice score:0.8214912615431581 307 | index:168 dice score:0.8560377737592928 308 | index:169 dice score:0.7936410256410257 309 | index:170 dice score:0.8444845039173542 310 | index:171 dice score:0.8760182012246504 311 | index:172 dice score:0.7836360951115049 312 | index:173 dice score:0.8184245660881175 313 | index:174 dice score:0.8071322899634041 314 | index:175 dice score:0.7032585083272991 315 | index:176 dice score:0.720252878753669 316 | index:177 dice score:0.7804011838211115 317 | index:178 dice score:0.7365003006614552 318 | index:179 dice score:0.791427163737888 319 | index:180 dice score:0.8211850380668653 320 | Average Dice Score: 75.1572% 321 | 322 | 323 | 324 | CHASE, Unet++ 325 | train_num=20*36=720, batch_size=2; 326 | test_num=8*36=288, batch_size=1 327 | 328 | %run train_test_evaluate train 329 | 330 | Epoch 1/5 331 | ---------- 332 | 1/360,train_loss:0.696 333 | 2/360,train_loss:0.674 334 | 3/360,train_loss:0.611 335 | 4/360,train_loss:0.554 336 | 5/360,train_loss:0.480 337 | 6/360,train_loss:0.459 338 | 7/360,train_loss:0.398 339 | 8/360,train_loss:0.338 340 | 9/360,train_loss:0.385 341 | 10/360,train_loss:0.368 342 | 11/360,train_loss:0.424 343 | 12/360,train_loss:0.279 344 | 13/360,train_loss:0.310 345 | 14/360,train_loss:0.353 346 | 15/360,train_loss:0.416 347 | 16/360,train_loss:0.354 348 | 17/360,train_loss:0.396 349 | 18/360,train_loss:0.319 350 | 19/360,train_loss:0.227 351 | 20/360,train_loss:0.148 352 | 21/360,train_loss:0.250 353 | 22/360,train_loss:0.504 354 | 23/360,train_loss:0.264 355 | 24/360,train_loss:0.152 356 | 25/360,train_loss:0.347 357 | 26/360,train_loss:0.213 358 | 27/360,train_loss:0.237 359 | 28/360,train_loss:0.202 360 | 29/360,train_loss:0.202 361 | 30/360,train_loss:0.313 362 | 31/360,train_loss:0.170 363 | 32/360,train_loss:0.162 364 | 33/360,train_loss:0.251 365 | 34/360,train_loss:0.208 366 | 35/360,train_loss:0.192 367 | 36/360,train_loss:0.341 368 | 37/360,train_loss:0.189 369 | 38/360,train_loss:0.151 370 | 39/360,train_loss:0.279 371 | 40/360,train_loss:0.166 372 | 41/360,train_loss:0.168 373 | 42/360,train_loss:0.191 374 | 43/360,train_loss:0.228 375 | 44/360,train_loss:0.143 376 | 45/360,train_loss:0.138 377 | 46/360,train_loss:0.151 378 | 47/360,train_loss:0.422 379 | 48/360,train_loss:0.155 380 | 49/360,train_loss:0.187 381 | 50/360,train_loss:0.271 382 | 51/360,train_loss:0.137 383 | 52/360,train_loss:0.235 384 | 53/360,train_loss:0.167 385 | 54/360,train_loss:0.325 386 | 55/360,train_loss:0.207 387 | 56/360,train_loss:0.192 388 | 57/360,train_loss:0.285 389 | 58/360,train_loss:0.292 390 | 59/360,train_loss:0.225 391 | 60/360,train_loss:0.182 392 | 61/360,train_loss:0.348 393 | 62/360,train_loss:0.191 394 | 63/360,train_loss:0.190 395 | 64/360,train_loss:0.176 396 | 65/360,train_loss:0.177 397 | 66/360,train_loss:0.257 398 | 67/360,train_loss:0.174 399 | 68/360,train_loss:0.161 400 | 69/360,train_loss:0.244 401 | 70/360,train_loss:0.231 402 | 71/360,train_loss:0.241 403 | 72/360,train_loss:0.356 404 | 73/360,train_loss:0.168 405 | 74/360,train_loss:0.199 406 | 75/360,train_loss:0.174 407 | 76/360,train_loss:0.172 408 | 77/360,train_loss:0.145 409 | 78/360,train_loss:0.242 410 | 79/360,train_loss:0.200 411 | 80/360,train_loss:0.326 412 | 81/360,train_loss:0.271 413 | 82/360,train_loss:0.218 414 | 83/360,train_loss:0.165 415 | 84/360,train_loss:0.150 416 | 85/360,train_loss:0.249 417 | 86/360,train_loss:0.134 418 | 87/360,train_loss:0.265 419 | 88/360,train_loss:0.356 420 | 89/360,train_loss:0.179 421 | 90/360,train_loss:0.112 422 | 91/360,train_loss:0.246 423 | 92/360,train_loss:0.266 424 | 93/360,train_loss:0.145 425 | 94/360,train_loss:0.200 426 | 95/360,train_loss:0.204 427 | 96/360,train_loss:0.196 428 | 97/360,train_loss:0.257 429 | 98/360,train_loss:0.137 430 | 99/360,train_loss:0.125 431 | 100/360,train_loss:0.149 432 | 101/360,train_loss:0.157 433 | 102/360,train_loss:0.237 434 | 103/360,train_loss:0.225 435 | 104/360,train_loss:0.221 436 | 105/360,train_loss:0.205 437 | 106/360,train_loss:0.157 438 | 107/360,train_loss:0.218 439 | 108/360,train_loss:0.164 440 | 109/360,train_loss:0.381 441 | 110/360,train_loss:0.226 442 | 111/360,train_loss:0.210 443 | 112/360,train_loss:0.205 444 | 113/360,train_loss:0.171 445 | 114/360,train_loss:0.184 446 | 115/360,train_loss:0.170 447 | 116/360,train_loss:0.208 448 | 117/360,train_loss:0.225 449 | 118/360,train_loss:0.117 450 | 119/360,train_loss:0.175 451 | 120/360,train_loss:0.233 452 | 121/360,train_loss:0.301 453 | 122/360,train_loss:0.128 454 | 123/360,train_loss:0.182 455 | 124/360,train_loss:0.190 456 | 125/360,train_loss:0.203 457 | 126/360,train_loss:0.170 458 | 127/360,train_loss:0.169 459 | 128/360,train_loss:0.269 460 | 129/360,train_loss:0.151 461 | 130/360,train_loss:0.100 462 | 131/360,train_loss:0.197 463 | 132/360,train_loss:0.221 464 | 133/360,train_loss:0.346 465 | 134/360,train_loss:0.333 466 | 135/360,train_loss:0.141 467 | 136/360,train_loss:0.230 468 | 137/360,train_loss:0.151 469 | 138/360,train_loss:0.158 470 | 139/360,train_loss:0.176 471 | 140/360,train_loss:0.170 472 | 141/360,train_loss:0.229 473 | 142/360,train_loss:0.373 474 | 143/360,train_loss:0.125 475 | 144/360,train_loss:0.123 476 | 145/360,train_loss:0.225 477 | 146/360,train_loss:0.182 478 | 147/360,train_loss:0.203 479 | 148/360,train_loss:0.209 480 | 149/360,train_loss:0.206 481 | 150/360,train_loss:0.105 482 | 151/360,train_loss:0.136 483 | 152/360,train_loss:0.127 484 | 153/360,train_loss:0.218 485 | 154/360,train_loss:0.221 486 | 155/360,train_loss:0.131 487 | 156/360,train_loss:0.290 488 | 157/360,train_loss:0.142 489 | 158/360,train_loss:0.144 490 | 159/360,train_loss:0.166 491 | 160/360,train_loss:0.211 492 | 161/360,train_loss:0.173 493 | 162/360,train_loss:0.172 494 | 163/360,train_loss:0.158 495 | 164/360,train_loss:0.103 496 | 165/360,train_loss:0.143 497 | 166/360,train_loss:0.130 498 | 167/360,train_loss:0.121 499 | 168/360,train_loss:0.245 500 | 169/360,train_loss:0.112 501 | 170/360,train_loss:0.201 502 | 171/360,train_loss:0.090 503 | 172/360,train_loss:0.131 504 | 173/360,train_loss:0.245 505 | 174/360,train_loss:0.110 506 | 175/360,train_loss:0.238 507 | 176/360,train_loss:0.118 508 | 177/360,train_loss:0.106 509 | 178/360,train_loss:0.185 510 | 179/360,train_loss:0.184 511 | 180/360,train_loss:0.242 512 | 181/360,train_loss:0.120 513 | 182/360,train_loss:0.261 514 | 183/360,train_loss:0.101 515 | 184/360,train_loss:0.219 516 | 185/360,train_loss:0.190 517 | 186/360,train_loss:0.192 518 | 187/360,train_loss:0.173 519 | 188/360,train_loss:0.172 520 | 189/360,train_loss:0.189 521 | 190/360,train_loss:0.113 522 | 191/360,train_loss:0.158 523 | 192/360,train_loss:0.173 524 | 193/360,train_loss:0.187 525 | 194/360,train_loss:0.106 526 | 195/360,train_loss:0.158 527 | 196/360,train_loss:0.153 528 | 197/360,train_loss:0.205 529 | 198/360,train_loss:0.166 530 | 199/360,train_loss:0.119 531 | 200/360,train_loss:0.147 532 | 201/360,train_loss:0.228 533 | 202/360,train_loss:0.114 534 | 203/360,train_loss:0.155 535 | 204/360,train_loss:0.184 536 | 205/360,train_loss:0.136 537 | 206/360,train_loss:0.161 538 | 207/360,train_loss:0.143 539 | 208/360,train_loss:0.130 540 | 209/360,train_loss:0.135 541 | 210/360,train_loss:0.127 542 | 211/360,train_loss:0.135 543 | 212/360,train_loss:0.091 544 | 213/360,train_loss:0.114 545 | 214/360,train_loss:0.182 546 | 215/360,train_loss:0.301 547 | 216/360,train_loss:0.122 548 | 217/360,train_loss:0.361 549 | 218/360,train_loss:0.163 550 | 219/360,train_loss:0.128 551 | 220/360,train_loss:0.115 552 | 221/360,train_loss:0.128 553 | 222/360,train_loss:0.132 554 | 223/360,train_loss:0.107 555 | 224/360,train_loss:0.124 556 | 225/360,train_loss:0.128 557 | 226/360,train_loss:0.210 558 | 227/360,train_loss:0.151 559 | 228/360,train_loss:0.111 560 | 229/360,train_loss:0.111 561 | 230/360,train_loss:0.120 562 | 231/360,train_loss:0.161 563 | 232/360,train_loss:0.209 564 | 233/360,train_loss:0.152 565 | 234/360,train_loss:0.128 566 | 235/360,train_loss:0.220 567 | 236/360,train_loss:0.161 568 | 237/360,train_loss:0.127 569 | 238/360,train_loss:0.197 570 | 239/360,train_loss:0.119 571 | 240/360,train_loss:0.134 572 | 241/360,train_loss:0.138 573 | 242/360,train_loss:0.251 574 | 243/360,train_loss:0.150 575 | 244/360,train_loss:0.094 576 | 245/360,train_loss:0.156 577 | 246/360,train_loss:0.130 578 | 247/360,train_loss:0.182 579 | 248/360,train_loss:0.110 580 | 249/360,train_loss:0.096 581 | 250/360,train_loss:0.128 582 | 251/360,train_loss:0.098 583 | 252/360,train_loss:0.169 584 | 253/360,train_loss:0.104 585 | 254/360,train_loss:0.252 586 | 255/360,train_loss:0.247 587 | 256/360,train_loss:0.140 588 | 257/360,train_loss:0.140 589 | 258/360,train_loss:0.110 590 | 259/360,train_loss:0.151 591 | 260/360,train_loss:0.171 592 | 261/360,train_loss:0.140 593 | 262/360,train_loss:0.163 594 | 263/360,train_loss:0.138 595 | 264/360,train_loss:0.258 596 | 265/360,train_loss:0.133 597 | 266/360,train_loss:0.090 598 | 267/360,train_loss:0.221 599 | 268/360,train_loss:0.135 600 | 269/360,train_loss:0.168 601 | 270/360,train_loss:0.105 602 | 271/360,train_loss:0.222 603 | 272/360,train_loss:0.322 604 | 273/360,train_loss:0.142 605 | 274/360,train_loss:0.135 606 | 275/360,train_loss:0.183 607 | 276/360,train_loss:0.215 608 | 277/360,train_loss:0.192 609 | 278/360,train_loss:0.110 610 | 279/360,train_loss:0.144 611 | 280/360,train_loss:0.138 612 | 281/360,train_loss:0.158 613 | 282/360,train_loss:0.254 614 | 283/360,train_loss:0.135 615 | 284/360,train_loss:0.150 616 | 285/360,train_loss:0.161 617 | 286/360,train_loss:0.108 618 | 287/360,train_loss:0.112 619 | 288/360,train_loss:0.258 620 | 289/360,train_loss:0.143 621 | 290/360,train_loss:0.227 622 | 291/360,train_loss:0.118 623 | 292/360,train_loss:0.099 624 | 293/360,train_loss:0.193 625 | 294/360,train_loss:0.221 626 | 295/360,train_loss:0.133 627 | 296/360,train_loss:0.113 628 | 297/360,train_loss:0.087 629 | 298/360,train_loss:0.116 630 | 299/360,train_loss:0.138 631 | 300/360,train_loss:0.127 632 | 301/360,train_loss:0.155 633 | 302/360,train_loss:0.201 634 | 303/360,train_loss:0.164 635 | 304/360,train_loss:0.119 636 | 305/360,train_loss:0.146 637 | 306/360,train_loss:0.140 638 | 307/360,train_loss:0.138 639 | 308/360,train_loss:0.100 640 | 309/360,train_loss:0.114 641 | 310/360,train_loss:0.115 642 | 311/360,train_loss:0.103 643 | 312/360,train_loss:0.111 644 | 313/360,train_loss:0.278 645 | 314/360,train_loss:0.123 646 | 315/360,train_loss:0.136 647 | 316/360,train_loss:0.089 648 | 317/360,train_loss:0.125 649 | 318/360,train_loss:0.178 650 | 319/360,train_loss:0.125 651 | 320/360,train_loss:0.231 652 | 321/360,train_loss:0.134 653 | 322/360,train_loss:0.128 654 | 323/360,train_loss:0.136 655 | 324/360,train_loss:0.112 656 | 325/360,train_loss:0.149 657 | 326/360,train_loss:0.138 658 | 327/360,train_loss:0.136 659 | 328/360,train_loss:0.146 660 | 329/360,train_loss:0.152 661 | 330/360,train_loss:0.157 662 | 331/360,train_loss:0.130 663 | 332/360,train_loss:0.144 664 | 333/360,train_loss:0.120 665 | 334/360,train_loss:0.084 666 | 335/360,train_loss:0.209 667 | 336/360,train_loss:0.142 668 | 337/360,train_loss:0.114 669 | 338/360,train_loss:0.090 670 | 339/360,train_loss:0.133 671 | 340/360,train_loss:0.132 672 | 341/360,train_loss:0.162 673 | 342/360,train_loss:0.149 674 | 343/360,train_loss:0.108 675 | 344/360,train_loss:0.126 676 | 345/360,train_loss:0.145 677 | 346/360,train_loss:0.132 678 | 347/360,train_loss:0.163 679 | 348/360,train_loss:0.143 680 | 349/360,train_loss:0.126 681 | 350/360,train_loss:0.130 682 | 351/360,train_loss:0.102 683 | 352/360,train_loss:0.106 684 | 353/360,train_loss:0.182 685 | 354/360,train_loss:0.115 686 | 355/360,train_loss:0.167 687 | 356/360,train_loss:0.100 688 | 357/360,train_loss:0.091 689 | 358/360,train_loss:0.134 690 | 359/360,train_loss:0.105 691 | 360/360,train_loss:0.084 692 | epoch 1 loss:0.188 693 | Epoch 2/5 694 | ---------- 695 | 1/360,train_loss:0.224 696 | 2/360,train_loss:0.108 697 | 3/360,train_loss:0.228 698 | 4/360,train_loss:0.088 699 | 5/360,train_loss:0.092 700 | 6/360,train_loss:0.134 701 | 7/360,train_loss:0.101 702 | 8/360,train_loss:0.154 703 | 9/360,train_loss:0.124 704 | 10/360,train_loss:0.179 705 | 11/360,train_loss:0.057 706 | 12/360,train_loss:0.099 707 | 13/360,train_loss:0.132 708 | 14/360,train_loss:0.106 709 | 15/360,train_loss:0.109 710 | 16/360,train_loss:0.059 711 | 17/360,train_loss:0.181 712 | 18/360,train_loss:0.246 713 | 19/360,train_loss:0.114 714 | 20/360,train_loss:0.090 715 | 21/360,train_loss:0.093 716 | 22/360,train_loss:0.117 717 | 23/360,train_loss:0.141 718 | 24/360,train_loss:0.132 719 | 25/360,train_loss:0.129 720 | 26/360,train_loss:0.107 721 | 27/360,train_loss:0.114 722 | 28/360,train_loss:0.153 723 | 29/360,train_loss:0.088 724 | 30/360,train_loss:0.080 725 | 31/360,train_loss:0.147 726 | 32/360,train_loss:0.132 727 | 33/360,train_loss:0.236 728 | 34/360,train_loss:0.098 729 | 35/360,train_loss:0.113 730 | 36/360,train_loss:0.064 731 | 37/360,train_loss:0.118 732 | 38/360,train_loss:0.109 733 | 39/360,train_loss:0.089 734 | 40/360,train_loss:0.230 735 | 41/360,train_loss:0.187 736 | 42/360,train_loss:0.096 737 | 43/360,train_loss:0.112 738 | 44/360,train_loss:0.096 739 | 45/360,train_loss:0.222 740 | 46/360,train_loss:0.112 741 | 47/360,train_loss:0.141 742 | 48/360,train_loss:0.129 743 | 49/360,train_loss:0.113 744 | 50/360,train_loss:0.079 745 | 51/360,train_loss:0.145 746 | 52/360,train_loss:0.122 747 | 53/360,train_loss:0.123 748 | 54/360,train_loss:0.071 749 | 55/360,train_loss:0.109 750 | 56/360,train_loss:0.093 751 | 57/360,train_loss:0.196 752 | 58/360,train_loss:0.104 753 | 59/360,train_loss:0.152 754 | 60/360,train_loss:0.146 755 | 61/360,train_loss:0.127 756 | 62/360,train_loss:0.106 757 | 63/360,train_loss:0.145 758 | 64/360,train_loss:0.122 759 | 65/360,train_loss:0.082 760 | 66/360,train_loss:0.141 761 | 67/360,train_loss:0.096 762 | 68/360,train_loss:0.122 763 | 69/360,train_loss:0.248 764 | 70/360,train_loss:0.156 765 | 71/360,train_loss:0.114 766 | 72/360,train_loss:0.071 767 | 73/360,train_loss:0.144 768 | 74/360,train_loss:0.193 769 | 75/360,train_loss:0.137 770 | 76/360,train_loss:0.113 771 | 77/360,train_loss:0.164 772 | 78/360,train_loss:0.111 773 | 79/360,train_loss:0.190 774 | 80/360,train_loss:0.137 775 | 81/360,train_loss:0.121 776 | 82/360,train_loss:0.144 777 | 83/360,train_loss:0.146 778 | 84/360,train_loss:0.054 779 | 85/360,train_loss:0.141 780 | 86/360,train_loss:0.106 781 | 87/360,train_loss:0.145 782 | 88/360,train_loss:0.107 783 | 89/360,train_loss:0.105 784 | 90/360,train_loss:0.108 785 | 91/360,train_loss:0.090 786 | 92/360,train_loss:0.122 787 | 93/360,train_loss:0.091 788 | 94/360,train_loss:0.210 789 | 95/360,train_loss:0.159 790 | 96/360,train_loss:0.154 791 | 97/360,train_loss:0.126 792 | 98/360,train_loss:0.149 793 | 99/360,train_loss:0.109 794 | 100/360,train_loss:0.183 795 | 101/360,train_loss:0.137 796 | 102/360,train_loss:0.197 797 | 103/360,train_loss:0.187 798 | 104/360,train_loss:0.217 799 | 105/360,train_loss:0.136 800 | 106/360,train_loss:0.147 801 | 107/360,train_loss:0.121 802 | 108/360,train_loss:0.153 803 | 109/360,train_loss:0.168 804 | 110/360,train_loss:0.134 805 | 111/360,train_loss:0.102 806 | 112/360,train_loss:0.106 807 | 113/360,train_loss:0.073 808 | 114/360,train_loss:0.074 809 | 115/360,train_loss:0.164 810 | 116/360,train_loss:0.079 811 | 117/360,train_loss:0.208 812 | 118/360,train_loss:0.101 813 | 119/360,train_loss:0.166 814 | 120/360,train_loss:0.172 815 | 121/360,train_loss:0.201 816 | 122/360,train_loss:0.102 817 | 123/360,train_loss:0.119 818 | 124/360,train_loss:0.178 819 | 125/360,train_loss:0.087 820 | 126/360,train_loss:0.082 821 | 127/360,train_loss:0.101 822 | 128/360,train_loss:0.118 823 | 129/360,train_loss:0.142 824 | 130/360,train_loss:0.194 825 | 131/360,train_loss:0.166 826 | 132/360,train_loss:0.147 827 | 133/360,train_loss:0.079 828 | 134/360,train_loss:0.130 829 | 135/360,train_loss:0.120 830 | 136/360,train_loss:0.107 831 | 137/360,train_loss:0.102 832 | 138/360,train_loss:0.086 833 | 139/360,train_loss:0.155 834 | 140/360,train_loss:0.142 835 | 141/360,train_loss:0.179 836 | 142/360,train_loss:0.115 837 | 143/360,train_loss:0.124 838 | 144/360,train_loss:0.117 839 | 145/360,train_loss:0.146 840 | 146/360,train_loss:0.106 841 | 147/360,train_loss:0.085 842 | 148/360,train_loss:0.164 843 | 149/360,train_loss:0.107 844 | 150/360,train_loss:0.174 845 | 151/360,train_loss:0.121 846 | 152/360,train_loss:0.146 847 | 153/360,train_loss:0.133 848 | 154/360,train_loss:0.169 849 | 155/360,train_loss:0.103 850 | 156/360,train_loss:0.163 851 | 157/360,train_loss:0.119 852 | 158/360,train_loss:0.169 853 | 159/360,train_loss:0.090 854 | 160/360,train_loss:0.163 855 | 161/360,train_loss:0.112 856 | 162/360,train_loss:0.151 857 | 163/360,train_loss:0.087 858 | 164/360,train_loss:0.095 859 | 165/360,train_loss:0.099 860 | 166/360,train_loss:0.091 861 | 167/360,train_loss:0.099 862 | 168/360,train_loss:0.087 863 | 169/360,train_loss:0.088 864 | 170/360,train_loss:0.157 865 | 171/360,train_loss:0.106 866 | 172/360,train_loss:0.103 867 | 173/360,train_loss:0.087 868 | 174/360,train_loss:0.153 869 | 175/360,train_loss:0.099 870 | 176/360,train_loss:0.079 871 | 177/360,train_loss:0.148 872 | 178/360,train_loss:0.143 873 | 179/360,train_loss:0.075 874 | 180/360,train_loss:0.076 875 | 181/360,train_loss:0.078 876 | 182/360,train_loss:0.168 877 | 183/360,train_loss:0.118 878 | 184/360,train_loss:0.097 879 | 185/360,train_loss:0.158 880 | 186/360,train_loss:0.222 881 | 187/360,train_loss:0.129 882 | 188/360,train_loss:0.120 883 | 189/360,train_loss:0.141 884 | 190/360,train_loss:0.073 885 | 191/360,train_loss:0.098 886 | 192/360,train_loss:0.153 887 | 193/360,train_loss:0.110 888 | 194/360,train_loss:0.054 889 | 195/360,train_loss:0.120 890 | 196/360,train_loss:0.167 891 | 197/360,train_loss:0.135 892 | 198/360,train_loss:0.073 893 | 199/360,train_loss:0.178 894 | 200/360,train_loss:0.170 895 | 201/360,train_loss:0.122 896 | 202/360,train_loss:0.089 897 | 203/360,train_loss:0.043 898 | 204/360,train_loss:0.053 899 | 205/360,train_loss:0.094 900 | 206/360,train_loss:0.153 901 | 207/360,train_loss:0.135 902 | 208/360,train_loss:0.151 903 | 209/360,train_loss:0.109 904 | 210/360,train_loss:0.115 905 | 211/360,train_loss:0.151 906 | 212/360,train_loss:0.158 907 | 213/360,train_loss:0.110 908 | 214/360,train_loss:0.113 909 | 215/360,train_loss:0.151 910 | 216/360,train_loss:0.156 911 | 217/360,train_loss:0.118 912 | 218/360,train_loss:0.109 913 | 219/360,train_loss:0.091 914 | 220/360,train_loss:0.112 915 | 221/360,train_loss:0.145 916 | 222/360,train_loss:0.102 917 | 223/360,train_loss:0.105 918 | 224/360,train_loss:0.095 919 | 225/360,train_loss:0.129 920 | 226/360,train_loss:0.089 921 | 227/360,train_loss:0.089 922 | 228/360,train_loss:0.188 923 | 229/360,train_loss:0.132 924 | 230/360,train_loss:0.103 925 | 231/360,train_loss:0.159 926 | 232/360,train_loss:0.167 927 | 233/360,train_loss:0.120 928 | 234/360,train_loss:0.099 929 | 235/360,train_loss:0.087 930 | 236/360,train_loss:0.178 931 | 237/360,train_loss:0.175 932 | 238/360,train_loss:0.107 933 | 239/360,train_loss:0.143 934 | 240/360,train_loss:0.123 935 | 241/360,train_loss:0.088 936 | 242/360,train_loss:0.192 937 | 243/360,train_loss:0.075 938 | 244/360,train_loss:0.095 939 | 245/360,train_loss:0.093 940 | 246/360,train_loss:0.128 941 | 247/360,train_loss:0.148 942 | 248/360,train_loss:0.066 943 | 249/360,train_loss:0.080 944 | 250/360,train_loss:0.123 945 | 251/360,train_loss:0.090 946 | 252/360,train_loss:0.133 947 | 253/360,train_loss:0.127 948 | 254/360,train_loss:0.142 949 | 255/360,train_loss:0.090 950 | 256/360,train_loss:0.105 951 | 257/360,train_loss:0.068 952 | 258/360,train_loss:0.106 953 | 259/360,train_loss:0.084 954 | 260/360,train_loss:0.120 955 | 261/360,train_loss:0.147 956 | 262/360,train_loss:0.346 957 | 263/360,train_loss:0.159 958 | 264/360,train_loss:0.085 959 | 265/360,train_loss:0.133 960 | 266/360,train_loss:0.143 961 | 267/360,train_loss:0.137 962 | 268/360,train_loss:0.135 963 | 269/360,train_loss:0.086 964 | 270/360,train_loss:0.117 965 | 271/360,train_loss:0.071 966 | 272/360,train_loss:0.112 967 | 273/360,train_loss:0.065 968 | 274/360,train_loss:0.073 969 | 275/360,train_loss:0.075 970 | 276/360,train_loss:0.109 971 | 277/360,train_loss:0.131 972 | 278/360,train_loss:0.244 973 | 279/360,train_loss:0.151 974 | 280/360,train_loss:0.123 975 | 281/360,train_loss:0.121 976 | 282/360,train_loss:0.108 977 | 283/360,train_loss:0.063 978 | 284/360,train_loss:0.129 979 | 285/360,train_loss:0.139 980 | 286/360,train_loss:0.080 981 | 287/360,train_loss:0.098 982 | 288/360,train_loss:0.107 983 | 289/360,train_loss:0.053 984 | 290/360,train_loss:0.148 985 | 291/360,train_loss:0.126 986 | 292/360,train_loss:0.127 987 | 293/360,train_loss:0.150 988 | 294/360,train_loss:0.134 989 | 295/360,train_loss:0.081 990 | 296/360,train_loss:0.121 991 | 297/360,train_loss:0.086 992 | 298/360,train_loss:0.111 993 | 299/360,train_loss:0.133 994 | 300/360,train_loss:0.104 995 | 301/360,train_loss:0.087 996 | 302/360,train_loss:0.090 997 | 303/360,train_loss:0.148 998 | 304/360,train_loss:0.157 999 | 305/360,train_loss:0.168 1000 | 306/360,train_loss:0.093 1001 | 307/360,train_loss:0.147 1002 | 308/360,train_loss:0.146 1003 | 309/360,train_loss:0.125 1004 | 310/360,train_loss:0.112 1005 | 311/360,train_loss:0.086 1006 | 312/360,train_loss:0.109 1007 | 313/360,train_loss:0.113 1008 | 314/360,train_loss:0.118 1009 | 315/360,train_loss:0.122 1010 | 316/360,train_loss:0.214 1011 | 317/360,train_loss:0.252 1012 | 318/360,train_loss:0.124 1013 | 319/360,train_loss:0.102 1014 | 320/360,train_loss:0.108 1015 | 321/360,train_loss:0.142 1016 | 322/360,train_loss:0.104 1017 | 323/360,train_loss:0.106 1018 | 324/360,train_loss:0.180 1019 | 325/360,train_loss:0.104 1020 | 326/360,train_loss:0.136 1021 | 327/360,train_loss:0.105 1022 | 328/360,train_loss:0.077 1023 | 329/360,train_loss:0.153 1024 | 330/360,train_loss:0.120 1025 | 331/360,train_loss:0.120 1026 | 332/360,train_loss:0.109 1027 | 333/360,train_loss:0.093 1028 | 334/360,train_loss:0.108 1029 | 335/360,train_loss:0.110 1030 | 336/360,train_loss:0.070 1031 | 337/360,train_loss:0.080 1032 | 338/360,train_loss:0.144 1033 | 339/360,train_loss:0.156 1034 | 340/360,train_loss:0.088 1035 | 341/360,train_loss:0.090 1036 | 342/360,train_loss:0.103 1037 | 343/360,train_loss:0.121 1038 | 344/360,train_loss:0.098 1039 | 345/360,train_loss:0.087 1040 | 346/360,train_loss:0.098 1041 | 347/360,train_loss:0.102 1042 | 348/360,train_loss:0.086 1043 | 349/360,train_loss:0.114 1044 | 350/360,train_loss:0.138 1045 | 351/360,train_loss:0.121 1046 | 352/360,train_loss:0.095 1047 | 353/360,train_loss:0.154 1048 | 354/360,train_loss:0.175 1049 | 355/360,train_loss:0.082 1050 | 356/360,train_loss:0.152 1051 | 357/360,train_loss:0.189 1052 | 358/360,train_loss:0.170 1053 | 359/360,train_loss:0.091 1054 | 360/360,train_loss:0.200 1055 | epoch 2 loss:0.125 1056 | Epoch 3/5 1057 | ---------- 1058 | 1/360,train_loss:0.139 1059 | 2/360,train_loss:0.125 1060 | 3/360,train_loss:0.075 1061 | 4/360,train_loss:0.091 1062 | 5/360,train_loss:0.118 1063 | 6/360,train_loss:0.178 1064 | 7/360,train_loss:0.102 1065 | 8/360,train_loss:0.084 1066 | 9/360,train_loss:0.087 1067 | 10/360,train_loss:0.142 1068 | 11/360,train_loss:0.079 1069 | 12/360,train_loss:0.130 1070 | 13/360,train_loss:0.114 1071 | 14/360,train_loss:0.108 1072 | 15/360,train_loss:0.145 1073 | 16/360,train_loss:0.097 1074 | 17/360,train_loss:0.102 1075 | 18/360,train_loss:0.158 1076 | 19/360,train_loss:0.162 1077 | 20/360,train_loss:0.120 1078 | 21/360,train_loss:0.116 1079 | 22/360,train_loss:0.072 1080 | 23/360,train_loss:0.119 1081 | 24/360,train_loss:0.095 1082 | 25/360,train_loss:0.108 1083 | 26/360,train_loss:0.106 1084 | 27/360,train_loss:0.112 1085 | 28/360,train_loss:0.085 1086 | 29/360,train_loss:0.096 1087 | 30/360,train_loss:0.094 1088 | 31/360,train_loss:0.179 1089 | 32/360,train_loss:0.098 1090 | 33/360,train_loss:0.101 1091 | 34/360,train_loss:0.155 1092 | 35/360,train_loss:0.121 1093 | 36/360,train_loss:0.115 1094 | 37/360,train_loss:0.088 1095 | 38/360,train_loss:0.234 1096 | 39/360,train_loss:0.106 1097 | 40/360,train_loss:0.085 1098 | 41/360,train_loss:0.109 1099 | 42/360,train_loss:0.101 1100 | 43/360,train_loss:0.104 1101 | 44/360,train_loss:0.060 1102 | 45/360,train_loss:0.155 1103 | 46/360,train_loss:0.093 1104 | 47/360,train_loss:0.144 1105 | 48/360,train_loss:0.086 1106 | 49/360,train_loss:0.114 1107 | 50/360,train_loss:0.122 1108 | 51/360,train_loss:0.099 1109 | 52/360,train_loss:0.131 1110 | 53/360,train_loss:0.128 1111 | 54/360,train_loss:0.089 1112 | 55/360,train_loss:0.055 1113 | 56/360,train_loss:0.097 1114 | 57/360,train_loss:0.046 1115 | 58/360,train_loss:0.159 1116 | 59/360,train_loss:0.131 1117 | 60/360,train_loss:0.104 1118 | 61/360,train_loss:0.085 1119 | 62/360,train_loss:0.095 1120 | 63/360,train_loss:0.088 1121 | 64/360,train_loss:0.104 1122 | 65/360,train_loss:0.224 1123 | 66/360,train_loss:0.164 1124 | 67/360,train_loss:0.194 1125 | 68/360,train_loss:0.184 1126 | 69/360,train_loss:0.079 1127 | 70/360,train_loss:0.130 1128 | 71/360,train_loss:0.118 1129 | 72/360,train_loss:0.107 1130 | 73/360,train_loss:0.148 1131 | 74/360,train_loss:0.131 1132 | 75/360,train_loss:0.100 1133 | 76/360,train_loss:0.099 1134 | 77/360,train_loss:0.092 1135 | 78/360,train_loss:0.102 1136 | 79/360,train_loss:0.097 1137 | 80/360,train_loss:0.070 1138 | 81/360,train_loss:0.129 1139 | 82/360,train_loss:0.074 1140 | 83/360,train_loss:0.070 1141 | 84/360,train_loss:0.157 1142 | 85/360,train_loss:0.116 1143 | 86/360,train_loss:0.067 1144 | 87/360,train_loss:0.105 1145 | 88/360,train_loss:0.104 1146 | 89/360,train_loss:0.086 1147 | 90/360,train_loss:0.139 1148 | 91/360,train_loss:0.095 1149 | 92/360,train_loss:0.081 1150 | 93/360,train_loss:0.115 1151 | 94/360,train_loss:0.099 1152 | 95/360,train_loss:0.124 1153 | 96/360,train_loss:0.101 1154 | 97/360,train_loss:0.084 1155 | 98/360,train_loss:0.070 1156 | 99/360,train_loss:0.095 1157 | 100/360,train_loss:0.089 1158 | 101/360,train_loss:0.062 1159 | 102/360,train_loss:0.096 1160 | 103/360,train_loss:0.095 1161 | 104/360,train_loss:0.073 1162 | 105/360,train_loss:0.183 1163 | 106/360,train_loss:0.120 1164 | 107/360,train_loss:0.121 1165 | 108/360,train_loss:0.145 1166 | 109/360,train_loss:0.144 1167 | 110/360,train_loss:0.080 1168 | 111/360,train_loss:0.121 1169 | 112/360,train_loss:0.117 1170 | 113/360,train_loss:0.131 1171 | 114/360,train_loss:0.074 1172 | 115/360,train_loss:0.120 1173 | 116/360,train_loss:0.092 1174 | 117/360,train_loss:0.096 1175 | 118/360,train_loss:0.106 1176 | 119/360,train_loss:0.114 1177 | 120/360,train_loss:0.104 1178 | 121/360,train_loss:0.071 1179 | 122/360,train_loss:0.096 1180 | 123/360,train_loss:0.098 1181 | 124/360,train_loss:0.099 1182 | 125/360,train_loss:0.244 1183 | 126/360,train_loss:0.112 1184 | 127/360,train_loss:0.106 1185 | 128/360,train_loss:0.124 1186 | 129/360,train_loss:0.075 1187 | 130/360,train_loss:0.078 1188 | 131/360,train_loss:0.128 1189 | 132/360,train_loss:0.096 1190 | 133/360,train_loss:0.111 1191 | 134/360,train_loss:0.103 1192 | 135/360,train_loss:0.175 1193 | 136/360,train_loss:0.131 1194 | 137/360,train_loss:0.158 1195 | 138/360,train_loss:0.135 1196 | 139/360,train_loss:0.071 1197 | 140/360,train_loss:0.178 1198 | 141/360,train_loss:0.133 1199 | 142/360,train_loss:0.075 1200 | 143/360,train_loss:0.095 1201 | 144/360,train_loss:0.100 1202 | 145/360,train_loss:0.096 1203 | 146/360,train_loss:0.080 1204 | 147/360,train_loss:0.161 1205 | 148/360,train_loss:0.124 1206 | 149/360,train_loss:0.035 1207 | 150/360,train_loss:0.146 1208 | 151/360,train_loss:0.111 1209 | 152/360,train_loss:0.135 1210 | 153/360,train_loss:0.060 1211 | 154/360,train_loss:0.084 1212 | 155/360,train_loss:0.265 1213 | 156/360,train_loss:0.107 1214 | 157/360,train_loss:0.090 1215 | 158/360,train_loss:0.124 1216 | 159/360,train_loss:0.128 1217 | 160/360,train_loss:0.088 1218 | 161/360,train_loss:0.163 1219 | 162/360,train_loss:0.093 1220 | 163/360,train_loss:0.113 1221 | 164/360,train_loss:0.051 1222 | 165/360,train_loss:0.075 1223 | 166/360,train_loss:0.102 1224 | 167/360,train_loss:0.103 1225 | 168/360,train_loss:0.073 1226 | 169/360,train_loss:0.071 1227 | 170/360,train_loss:0.138 1228 | 171/360,train_loss:0.094 1229 | 172/360,train_loss:0.105 1230 | 173/360,train_loss:0.097 1231 | 174/360,train_loss:0.153 1232 | 175/360,train_loss:0.097 1233 | 176/360,train_loss:0.144 1234 | 177/360,train_loss:0.077 1235 | 178/360,train_loss:0.083 1236 | 179/360,train_loss:0.250 1237 | 180/360,train_loss:0.098 1238 | 181/360,train_loss:0.072 1239 | 182/360,train_loss:0.111 1240 | 183/360,train_loss:0.094 1241 | 184/360,train_loss:0.090 1242 | 185/360,train_loss:0.099 1243 | 186/360,train_loss:0.123 1244 | 187/360,train_loss:0.137 1245 | 188/360,train_loss:0.100 1246 | 189/360,train_loss:0.088 1247 | 190/360,train_loss:0.064 1248 | 191/360,train_loss:0.101 1249 | 192/360,train_loss:0.074 1250 | 193/360,train_loss:0.152 1251 | 194/360,train_loss:0.096 1252 | 195/360,train_loss:0.170 1253 | 196/360,train_loss:0.076 1254 | 197/360,train_loss:0.078 1255 | 198/360,train_loss:0.077 1256 | 199/360,train_loss:0.111 1257 | 200/360,train_loss:0.179 1258 | 201/360,train_loss:0.161 1259 | 202/360,train_loss:0.129 1260 | 203/360,train_loss:0.110 1261 | 204/360,train_loss:0.096 1262 | 205/360,train_loss:0.107 1263 | 206/360,train_loss:0.125 1264 | 207/360,train_loss:0.122 1265 | 208/360,train_loss:0.151 1266 | 209/360,train_loss:0.105 1267 | 210/360,train_loss:0.078 1268 | 211/360,train_loss:0.117 1269 | 212/360,train_loss:0.097 1270 | 213/360,train_loss:0.094 1271 | 214/360,train_loss:0.055 1272 | 215/360,train_loss:0.102 1273 | 216/360,train_loss:0.103 1274 | 217/360,train_loss:0.145 1275 | 218/360,train_loss:0.079 1276 | 219/360,train_loss:0.157 1277 | 220/360,train_loss:0.090 1278 | 221/360,train_loss:0.101 1279 | 222/360,train_loss:0.070 1280 | 223/360,train_loss:0.086 1281 | 224/360,train_loss:0.136 1282 | 225/360,train_loss:0.080 1283 | 226/360,train_loss:0.093 1284 | 227/360,train_loss:0.092 1285 | 228/360,train_loss:0.163 1286 | 229/360,train_loss:0.067 1287 | 230/360,train_loss:0.173 1288 | 231/360,train_loss:0.130 1289 | 232/360,train_loss:0.173 1290 | 233/360,train_loss:0.086 1291 | 234/360,train_loss:0.161 1292 | 235/360,train_loss:0.085 1293 | 236/360,train_loss:0.114 1294 | 237/360,train_loss:0.091 1295 | 238/360,train_loss:0.118 1296 | 239/360,train_loss:0.094 1297 | 240/360,train_loss:0.153 1298 | 241/360,train_loss:0.086 1299 | 242/360,train_loss:0.109 1300 | 243/360,train_loss:0.188 1301 | 244/360,train_loss:0.121 1302 | 245/360,train_loss:0.132 1303 | 246/360,train_loss:0.113 1304 | 247/360,train_loss:0.078 1305 | 248/360,train_loss:0.149 1306 | 249/360,train_loss:0.101 1307 | 250/360,train_loss:0.135 1308 | 251/360,train_loss:0.073 1309 | 252/360,train_loss:0.131 1310 | 253/360,train_loss:0.071 1311 | 254/360,train_loss:0.106 1312 | 255/360,train_loss:0.117 1313 | 256/360,train_loss:0.149 1314 | 257/360,train_loss:0.121 1315 | 258/360,train_loss:0.097 1316 | 259/360,train_loss:0.097 1317 | 260/360,train_loss:0.133 1318 | 261/360,train_loss:0.149 1319 | 262/360,train_loss:0.081 1320 | 263/360,train_loss:0.105 1321 | 264/360,train_loss:0.157 1322 | 265/360,train_loss:0.143 1323 | 266/360,train_loss:0.119 1324 | 267/360,train_loss:0.074 1325 | 268/360,train_loss:0.095 1326 | 269/360,train_loss:0.100 1327 | 270/360,train_loss:0.086 1328 | 271/360,train_loss:0.153 1329 | 272/360,train_loss:0.076 1330 | 273/360,train_loss:0.096 1331 | 274/360,train_loss:0.086 1332 | 275/360,train_loss:0.138 1333 | 276/360,train_loss:0.089 1334 | 277/360,train_loss:0.124 1335 | 278/360,train_loss:0.101 1336 | 279/360,train_loss:0.087 1337 | 280/360,train_loss:0.041 1338 | 281/360,train_loss:0.124 1339 | 282/360,train_loss:0.102 1340 | 283/360,train_loss:0.054 1341 | 284/360,train_loss:0.105 1342 | 285/360,train_loss:0.089 1343 | 286/360,train_loss:0.090 1344 | 287/360,train_loss:0.149 1345 | 288/360,train_loss:0.122 1346 | 289/360,train_loss:0.116 1347 | 290/360,train_loss:0.068 1348 | 291/360,train_loss:0.094 1349 | 292/360,train_loss:0.169 1350 | 293/360,train_loss:0.101 1351 | 294/360,train_loss:0.133 1352 | 295/360,train_loss:0.151 1353 | 296/360,train_loss:0.106 1354 | 297/360,train_loss:0.106 1355 | 298/360,train_loss:0.073 1356 | 299/360,train_loss:0.101 1357 | 300/360,train_loss:0.050 1358 | 301/360,train_loss:0.170 1359 | 302/360,train_loss:0.073 1360 | 303/360,train_loss:0.096 1361 | 304/360,train_loss:0.102 1362 | 305/360,train_loss:0.063 1363 | 306/360,train_loss:0.058 1364 | 307/360,train_loss:0.082 1365 | 308/360,train_loss:0.055 1366 | 309/360,train_loss:0.118 1367 | 310/360,train_loss:0.099 1368 | 311/360,train_loss:0.118 1369 | 312/360,train_loss:0.089 1370 | 313/360,train_loss:0.068 1371 | 314/360,train_loss:0.096 1372 | 315/360,train_loss:0.092 1373 | 316/360,train_loss:0.069 1374 | 317/360,train_loss:0.129 1375 | 318/360,train_loss:0.202 1376 | 319/360,train_loss:0.094 1377 | 320/360,train_loss:0.065 1378 | 321/360,train_loss:0.056 1379 | 322/360,train_loss:0.119 1380 | 323/360,train_loss:0.116 1381 | 324/360,train_loss:0.151 1382 | 325/360,train_loss:0.122 1383 | 326/360,train_loss:0.116 1384 | 327/360,train_loss:0.090 1385 | 328/360,train_loss:0.114 1386 | 329/360,train_loss:0.100 1387 | 330/360,train_loss:0.091 1388 | 331/360,train_loss:0.109 1389 | 332/360,train_loss:0.096 1390 | 333/360,train_loss:0.074 1391 | 334/360,train_loss:0.154 1392 | 335/360,train_loss:0.099 1393 | 336/360,train_loss:0.116 1394 | 337/360,train_loss:0.111 1395 | 338/360,train_loss:0.099 1396 | 339/360,train_loss:0.063 1397 | 340/360,train_loss:0.169 1398 | 341/360,train_loss:0.096 1399 | 342/360,train_loss:0.077 1400 | 343/360,train_loss:0.208 1401 | 344/360,train_loss:0.131 1402 | 345/360,train_loss:0.102 1403 | 346/360,train_loss:0.100 1404 | 347/360,train_loss:0.056 1405 | 348/360,train_loss:0.116 1406 | 349/360,train_loss:0.151 1407 | 350/360,train_loss:0.157 1408 | 351/360,train_loss:0.075 1409 | 352/360,train_loss:0.167 1410 | 353/360,train_loss:0.105 1411 | 354/360,train_loss:0.094 1412 | 355/360,train_loss:0.074 1413 | 356/360,train_loss:0.126 1414 | 357/360,train_loss:0.090 1415 | 358/360,train_loss:0.126 1416 | 359/360,train_loss:0.067 1417 | 360/360,train_loss:0.110 1418 | epoch 3 loss:0.110 1419 | Epoch 4/5 1420 | ---------- 1421 | 1/360,train_loss:0.098 1422 | 2/360,train_loss:0.085 1423 | 3/360,train_loss:0.048 1424 | 4/360,train_loss:0.173 1425 | 5/360,train_loss:0.100 1426 | 6/360,train_loss:0.126 1427 | 7/360,train_loss:0.068 1428 | 8/360,train_loss:0.067 1429 | 9/360,train_loss:0.096 1430 | 10/360,train_loss:0.084 1431 | 11/360,train_loss:0.115 1432 | 12/360,train_loss:0.166 1433 | 13/360,train_loss:0.067 1434 | 14/360,train_loss:0.090 1435 | 15/360,train_loss:0.109 1436 | 16/360,train_loss:0.104 1437 | 17/360,train_loss:0.128 1438 | 18/360,train_loss:0.070 1439 | 19/360,train_loss:0.080 1440 | 20/360,train_loss:0.107 1441 | 21/360,train_loss:0.086 1442 | 22/360,train_loss:0.051 1443 | 23/360,train_loss:0.101 1444 | 24/360,train_loss:0.122 1445 | 25/360,train_loss:0.070 1446 | 26/360,train_loss:0.076 1447 | 27/360,train_loss:0.085 1448 | 28/360,train_loss:0.096 1449 | 29/360,train_loss:0.078 1450 | 30/360,train_loss:0.079 1451 | 31/360,train_loss:0.080 1452 | 32/360,train_loss:0.154 1453 | 33/360,train_loss:0.144 1454 | 34/360,train_loss:0.097 1455 | 35/360,train_loss:0.071 1456 | 36/360,train_loss:0.130 1457 | 37/360,train_loss:0.079 1458 | 38/360,train_loss:0.083 1459 | 39/360,train_loss:0.202 1460 | 40/360,train_loss:0.080 1461 | 41/360,train_loss:0.105 1462 | 42/360,train_loss:0.094 1463 | 43/360,train_loss:0.132 1464 | 44/360,train_loss:0.070 1465 | 45/360,train_loss:0.108 1466 | 46/360,train_loss:0.209 1467 | 47/360,train_loss:0.085 1468 | 48/360,train_loss:0.075 1469 | 49/360,train_loss:0.160 1470 | 50/360,train_loss:0.080 1471 | 51/360,train_loss:0.109 1472 | 52/360,train_loss:0.085 1473 | 53/360,train_loss:0.148 1474 | 54/360,train_loss:0.110 1475 | 55/360,train_loss:0.051 1476 | 56/360,train_loss:0.104 1477 | 57/360,train_loss:0.082 1478 | 58/360,train_loss:0.116 1479 | 59/360,train_loss:0.129 1480 | 60/360,train_loss:0.097 1481 | 61/360,train_loss:0.085 1482 | 62/360,train_loss:0.091 1483 | 63/360,train_loss:0.103 1484 | 64/360,train_loss:0.071 1485 | 65/360,train_loss:0.116 1486 | 66/360,train_loss:0.134 1487 | 67/360,train_loss:0.117 1488 | 68/360,train_loss:0.111 1489 | 69/360,train_loss:0.154 1490 | 70/360,train_loss:0.146 1491 | 71/360,train_loss:0.191 1492 | 72/360,train_loss:0.103 1493 | 73/360,train_loss:0.120 1494 | 74/360,train_loss:0.133 1495 | 75/360,train_loss:0.078 1496 | 76/360,train_loss:0.082 1497 | 77/360,train_loss:0.110 1498 | 78/360,train_loss:0.109 1499 | 79/360,train_loss:0.107 1500 | 80/360,train_loss:0.081 1501 | 81/360,train_loss:0.117 1502 | 82/360,train_loss:0.112 1503 | 83/360,train_loss:0.111 1504 | 84/360,train_loss:0.072 1505 | 85/360,train_loss:0.082 1506 | 86/360,train_loss:0.097 1507 | 87/360,train_loss:0.123 1508 | 88/360,train_loss:0.153 1509 | 89/360,train_loss:0.051 1510 | 90/360,train_loss:0.140 1511 | 91/360,train_loss:0.065 1512 | 92/360,train_loss:0.081 1513 | 93/360,train_loss:0.092 1514 | 94/360,train_loss:0.097 1515 | 95/360,train_loss:0.075 1516 | 96/360,train_loss:0.115 1517 | 97/360,train_loss:0.197 1518 | 98/360,train_loss:0.105 1519 | 99/360,train_loss:0.138 1520 | 100/360,train_loss:0.134 1521 | 101/360,train_loss:0.067 1522 | 102/360,train_loss:0.106 1523 | 103/360,train_loss:0.116 1524 | 104/360,train_loss:0.172 1525 | 105/360,train_loss:0.117 1526 | 106/360,train_loss:0.092 1527 | 107/360,train_loss:0.107 1528 | 108/360,train_loss:0.137 1529 | 109/360,train_loss:0.080 1530 | 110/360,train_loss:0.099 1531 | 111/360,train_loss:0.092 1532 | 112/360,train_loss:0.109 1533 | 113/360,train_loss:0.085 1534 | 114/360,train_loss:0.122 1535 | 115/360,train_loss:0.075 1536 | 116/360,train_loss:0.119 1537 | 117/360,train_loss:0.068 1538 | 118/360,train_loss:0.078 1539 | 119/360,train_loss:0.114 1540 | 120/360,train_loss:0.130 1541 | 121/360,train_loss:0.080 1542 | 122/360,train_loss:0.089 1543 | 123/360,train_loss:0.089 1544 | 124/360,train_loss:0.160 1545 | 125/360,train_loss:0.080 1546 | 126/360,train_loss:0.070 1547 | 127/360,train_loss:0.099 1548 | 128/360,train_loss:0.097 1549 | 129/360,train_loss:0.134 1550 | 130/360,train_loss:0.083 1551 | 131/360,train_loss:0.083 1552 | 132/360,train_loss:0.145 1553 | 133/360,train_loss:0.098 1554 | 134/360,train_loss:0.110 1555 | 135/360,train_loss:0.103 1556 | 136/360,train_loss:0.083 1557 | 137/360,train_loss:0.116 1558 | 138/360,train_loss:0.093 1559 | 139/360,train_loss:0.100 1560 | 140/360,train_loss:0.120 1561 | 141/360,train_loss:0.113 1562 | 142/360,train_loss:0.104 1563 | 143/360,train_loss:0.096 1564 | 144/360,train_loss:0.105 1565 | 145/360,train_loss:0.079 1566 | 146/360,train_loss:0.099 1567 | 147/360,train_loss:0.155 1568 | 148/360,train_loss:0.084 1569 | 149/360,train_loss:0.143 1570 | 150/360,train_loss:0.158 1571 | 151/360,train_loss:0.071 1572 | 152/360,train_loss:0.069 1573 | 153/360,train_loss:0.124 1574 | 154/360,train_loss:0.071 1575 | 155/360,train_loss:0.134 1576 | 156/360,train_loss:0.106 1577 | 157/360,train_loss:0.093 1578 | 158/360,train_loss:0.223 1579 | 159/360,train_loss:0.101 1580 | 160/360,train_loss:0.094 1581 | 161/360,train_loss:0.088 1582 | 162/360,train_loss:0.077 1583 | 163/360,train_loss:0.114 1584 | 164/360,train_loss:0.081 1585 | 165/360,train_loss:0.080 1586 | 166/360,train_loss:0.155 1587 | 167/360,train_loss:0.108 1588 | 168/360,train_loss:0.122 1589 | 169/360,train_loss:0.094 1590 | 170/360,train_loss:0.043 1591 | 171/360,train_loss:0.117 1592 | 172/360,train_loss:0.122 1593 | 173/360,train_loss:0.081 1594 | 174/360,train_loss:0.127 1595 | 175/360,train_loss:0.096 1596 | 176/360,train_loss:0.107 1597 | 177/360,train_loss:0.081 1598 | 178/360,train_loss:0.100 1599 | 179/360,train_loss:0.118 1600 | 180/360,train_loss:0.116 1601 | 181/360,train_loss:0.105 1602 | 182/360,train_loss:0.103 1603 | 183/360,train_loss:0.057 1604 | 184/360,train_loss:0.060 1605 | 185/360,train_loss:0.153 1606 | 186/360,train_loss:0.090 1607 | 187/360,train_loss:0.167 1608 | 188/360,train_loss:0.092 1609 | 189/360,train_loss:0.094 1610 | 190/360,train_loss:0.087 1611 | 191/360,train_loss:0.105 1612 | 192/360,train_loss:0.106 1613 | 193/360,train_loss:0.037 1614 | 194/360,train_loss:0.112 1615 | 195/360,train_loss:0.074 1616 | 196/360,train_loss:0.100 1617 | 197/360,train_loss:0.127 1618 | 198/360,train_loss:0.111 1619 | 199/360,train_loss:0.069 1620 | 200/360,train_loss:0.146 1621 | 201/360,train_loss:0.126 1622 | 202/360,train_loss:0.085 1623 | 203/360,train_loss:0.107 1624 | 204/360,train_loss:0.098 1625 | 205/360,train_loss:0.039 1626 | 206/360,train_loss:0.084 1627 | 207/360,train_loss:0.114 1628 | 208/360,train_loss:0.116 1629 | 209/360,train_loss:0.120 1630 | 210/360,train_loss:0.053 1631 | 211/360,train_loss:0.084 1632 | 212/360,train_loss:0.087 1633 | 213/360,train_loss:0.087 1634 | 214/360,train_loss:0.109 1635 | 215/360,train_loss:0.089 1636 | 216/360,train_loss:0.093 1637 | 217/360,train_loss:0.067 1638 | 218/360,train_loss:0.120 1639 | 219/360,train_loss:0.066 1640 | 220/360,train_loss:0.067 1641 | 221/360,train_loss:0.120 1642 | 222/360,train_loss:0.105 1643 | 223/360,train_loss:0.128 1644 | 224/360,train_loss:0.100 1645 | 225/360,train_loss:0.122 1646 | 226/360,train_loss:0.070 1647 | 227/360,train_loss:0.125 1648 | 228/360,train_loss:0.095 1649 | 229/360,train_loss:0.047 1650 | 230/360,train_loss:0.119 1651 | 231/360,train_loss:0.072 1652 | 232/360,train_loss:0.090 1653 | 233/360,train_loss:0.100 1654 | 234/360,train_loss:0.125 1655 | 235/360,train_loss:0.124 1656 | 236/360,train_loss:0.148 1657 | 237/360,train_loss:0.063 1658 | 238/360,train_loss:0.113 1659 | 239/360,train_loss:0.082 1660 | 240/360,train_loss:0.061 1661 | 241/360,train_loss:0.107 1662 | 242/360,train_loss:0.101 1663 | 243/360,train_loss:0.061 1664 | 244/360,train_loss:0.087 1665 | 245/360,train_loss:0.198 1666 | 246/360,train_loss:0.075 1667 | 247/360,train_loss:0.076 1668 | 248/360,train_loss:0.091 1669 | 249/360,train_loss:0.147 1670 | 250/360,train_loss:0.115 1671 | 251/360,train_loss:0.062 1672 | 252/360,train_loss:0.077 1673 | 253/360,train_loss:0.106 1674 | 254/360,train_loss:0.088 1675 | 255/360,train_loss:0.100 1676 | 256/360,train_loss:0.128 1677 | 257/360,train_loss:0.101 1678 | 258/360,train_loss:0.151 1679 | 259/360,train_loss:0.088 1680 | 260/360,train_loss:0.083 1681 | 261/360,train_loss:0.134 1682 | 262/360,train_loss:0.049 1683 | 263/360,train_loss:0.130 1684 | 264/360,train_loss:0.093 1685 | 265/360,train_loss:0.042 1686 | 266/360,train_loss:0.062 1687 | 267/360,train_loss:0.091 1688 | 268/360,train_loss:0.100 1689 | 269/360,train_loss:0.125 1690 | 270/360,train_loss:0.071 1691 | 271/360,train_loss:0.136 1692 | 272/360,train_loss:0.080 1693 | 273/360,train_loss:0.061 1694 | 274/360,train_loss:0.079 1695 | 275/360,train_loss:0.077 1696 | 276/360,train_loss:0.085 1697 | 277/360,train_loss:0.069 1698 | 278/360,train_loss:0.106 1699 | 279/360,train_loss:0.048 1700 | 280/360,train_loss:0.130 1701 | 281/360,train_loss:0.095 1702 | 282/360,train_loss:0.123 1703 | 283/360,train_loss:0.045 1704 | 284/360,train_loss:0.079 1705 | 285/360,train_loss:0.098 1706 | 286/360,train_loss:0.076 1707 | 287/360,train_loss:0.092 1708 | 288/360,train_loss:0.128 1709 | 289/360,train_loss:0.091 1710 | 290/360,train_loss:0.083 1711 | 291/360,train_loss:0.108 1712 | 292/360,train_loss:0.079 1713 | 293/360,train_loss:0.081 1714 | 294/360,train_loss:0.081 1715 | 295/360,train_loss:0.092 1716 | 296/360,train_loss:0.095 1717 | 297/360,train_loss:0.117 1718 | 298/360,train_loss:0.086 1719 | 299/360,train_loss:0.091 1720 | 300/360,train_loss:0.061 1721 | 301/360,train_loss:0.067 1722 | 302/360,train_loss:0.080 1723 | 303/360,train_loss:0.062 1724 | 304/360,train_loss:0.049 1725 | 305/360,train_loss:0.230 1726 | 306/360,train_loss:0.047 1727 | 307/360,train_loss:0.123 1728 | 308/360,train_loss:0.075 1729 | 309/360,train_loss:0.071 1730 | 310/360,train_loss:0.062 1731 | 311/360,train_loss:0.091 1732 | 312/360,train_loss:0.170 1733 | 313/360,train_loss:0.045 1734 | 314/360,train_loss:0.083 1735 | 315/360,train_loss:0.129 1736 | 316/360,train_loss:0.102 1737 | 317/360,train_loss:0.096 1738 | 318/360,train_loss:0.098 1739 | 319/360,train_loss:0.063 1740 | 320/360,train_loss:0.146 1741 | 321/360,train_loss:0.092 1742 | 322/360,train_loss:0.122 1743 | 323/360,train_loss:0.094 1744 | 324/360,train_loss:0.078 1745 | 325/360,train_loss:0.121 1746 | 326/360,train_loss:0.108 1747 | 327/360,train_loss:0.053 1748 | 328/360,train_loss:0.069 1749 | 329/360,train_loss:0.065 1750 | 330/360,train_loss:0.132 1751 | 331/360,train_loss:0.056 1752 | 332/360,train_loss:0.104 1753 | 333/360,train_loss:0.093 1754 | 334/360,train_loss:0.126 1755 | 335/360,train_loss:0.066 1756 | 336/360,train_loss:0.135 1757 | 337/360,train_loss:0.075 1758 | 338/360,train_loss:0.133 1759 | 339/360,train_loss:0.102 1760 | 340/360,train_loss:0.084 1761 | 341/360,train_loss:0.116 1762 | 342/360,train_loss:0.077 1763 | 343/360,train_loss:0.157 1764 | 344/360,train_loss:0.073 1765 | 345/360,train_loss:0.077 1766 | 346/360,train_loss:0.091 1767 | 347/360,train_loss:0.073 1768 | 348/360,train_loss:0.045 1769 | 349/360,train_loss:0.101 1770 | 350/360,train_loss:0.143 1771 | 351/360,train_loss:0.089 1772 | 352/360,train_loss:0.116 1773 | 353/360,train_loss:0.055 1774 | 354/360,train_loss:0.079 1775 | 355/360,train_loss:0.055 1776 | 356/360,train_loss:0.056 1777 | 357/360,train_loss:0.090 1778 | 358/360,train_loss:0.087 1779 | 359/360,train_loss:0.139 1780 | 360/360,train_loss:0.090 1781 | epoch 4 loss:0.100 1782 | Epoch 5/5 1783 | ---------- 1784 | 1/360,train_loss:0.097 1785 | 2/360,train_loss:0.067 1786 | 3/360,train_loss:0.113 1787 | 4/360,train_loss:0.079 1788 | 5/360,train_loss:0.092 1789 | 6/360,train_loss:0.067 1790 | 7/360,train_loss:0.060 1791 | 8/360,train_loss:0.080 1792 | 9/360,train_loss:0.069 1793 | 10/360,train_loss:0.107 1794 | 11/360,train_loss:0.099 1795 | 12/360,train_loss:0.159 1796 | 13/360,train_loss:0.104 1797 | 14/360,train_loss:0.109 1798 | 15/360,train_loss:0.087 1799 | 16/360,train_loss:0.184 1800 | 17/360,train_loss:0.121 1801 | 18/360,train_loss:0.091 1802 | 19/360,train_loss:0.099 1803 | 20/360,train_loss:0.075 1804 | 21/360,train_loss:0.042 1805 | 22/360,train_loss:0.081 1806 | 23/360,train_loss:0.092 1807 | 24/360,train_loss:0.095 1808 | 25/360,train_loss:0.093 1809 | 26/360,train_loss:0.107 1810 | 27/360,train_loss:0.119 1811 | 28/360,train_loss:0.068 1812 | 29/360,train_loss:0.097 1813 | 30/360,train_loss:0.076 1814 | 31/360,train_loss:0.066 1815 | 32/360,train_loss:0.147 1816 | 33/360,train_loss:0.077 1817 | 34/360,train_loss:0.109 1818 | 35/360,train_loss:0.099 1819 | 36/360,train_loss:0.109 1820 | 37/360,train_loss:0.073 1821 | 38/360,train_loss:0.091 1822 | 39/360,train_loss:0.139 1823 | 40/360,train_loss:0.083 1824 | 41/360,train_loss:0.098 1825 | 42/360,train_loss:0.050 1826 | 43/360,train_loss:0.065 1827 | 44/360,train_loss:0.097 1828 | 45/360,train_loss:0.145 1829 | 46/360,train_loss:0.073 1830 | 47/360,train_loss:0.096 1831 | 48/360,train_loss:0.063 1832 | 49/360,train_loss:0.100 1833 | 50/360,train_loss:0.122 1834 | 51/360,train_loss:0.067 1835 | 52/360,train_loss:0.056 1836 | 53/360,train_loss:0.074 1837 | 54/360,train_loss:0.088 1838 | 55/360,train_loss:0.053 1839 | 56/360,train_loss:0.082 1840 | 57/360,train_loss:0.054 1841 | 58/360,train_loss:0.061 1842 | 59/360,train_loss:0.102 1843 | 60/360,train_loss:0.072 1844 | 61/360,train_loss:0.095 1845 | 62/360,train_loss:0.106 1846 | 63/360,train_loss:0.196 1847 | 64/360,train_loss:0.095 1848 | 65/360,train_loss:0.125 1849 | 66/360,train_loss:0.071 1850 | 67/360,train_loss:0.082 1851 | 68/360,train_loss:0.109 1852 | 69/360,train_loss:0.070 1853 | 70/360,train_loss:0.086 1854 | 71/360,train_loss:0.083 1855 | 72/360,train_loss:0.082 1856 | 73/360,train_loss:0.068 1857 | 74/360,train_loss:0.083 1858 | 75/360,train_loss:0.175 1859 | 76/360,train_loss:0.077 1860 | 77/360,train_loss:0.089 1861 | 78/360,train_loss:0.081 1862 | 79/360,train_loss:0.100 1863 | 80/360,train_loss:0.114 1864 | 81/360,train_loss:0.132 1865 | 82/360,train_loss:0.062 1866 | 83/360,train_loss:0.089 1867 | 84/360,train_loss:0.064 1868 | 85/360,train_loss:0.138 1869 | 86/360,train_loss:0.068 1870 | 87/360,train_loss:0.083 1871 | 88/360,train_loss:0.098 1872 | 89/360,train_loss:0.122 1873 | 90/360,train_loss:0.074 1874 | 91/360,train_loss:0.071 1875 | 92/360,train_loss:0.084 1876 | 93/360,train_loss:0.062 1877 | 94/360,train_loss:0.123 1878 | 95/360,train_loss:0.137 1879 | 96/360,train_loss:0.126 1880 | 97/360,train_loss:0.062 1881 | 98/360,train_loss:0.079 1882 | 99/360,train_loss:0.146 1883 | 100/360,train_loss:0.068 1884 | 101/360,train_loss:0.103 1885 | 102/360,train_loss:0.084 1886 | 103/360,train_loss:0.115 1887 | 104/360,train_loss:0.129 1888 | 105/360,train_loss:0.085 1889 | 106/360,train_loss:0.114 1890 | 107/360,train_loss:0.172 1891 | 108/360,train_loss:0.096 1892 | 109/360,train_loss:0.053 1893 | 110/360,train_loss:0.088 1894 | 111/360,train_loss:0.124 1895 | 112/360,train_loss:0.119 1896 | 113/360,train_loss:0.090 1897 | 114/360,train_loss:0.087 1898 | 115/360,train_loss:0.097 1899 | 116/360,train_loss:0.086 1900 | 117/360,train_loss:0.064 1901 | 118/360,train_loss:0.093 1902 | 119/360,train_loss:0.089 1903 | 120/360,train_loss:0.127 1904 | 121/360,train_loss:0.115 1905 | 122/360,train_loss:0.107 1906 | 123/360,train_loss:0.093 1907 | 124/360,train_loss:0.122 1908 | 125/360,train_loss:0.151 1909 | 126/360,train_loss:0.135 1910 | 127/360,train_loss:0.118 1911 | 128/360,train_loss:0.076 1912 | 129/360,train_loss:0.093 1913 | 130/360,train_loss:0.080 1914 | 131/360,train_loss:0.097 1915 | 132/360,train_loss:0.075 1916 | 133/360,train_loss:0.087 1917 | 134/360,train_loss:0.092 1918 | 135/360,train_loss:0.158 1919 | 136/360,train_loss:0.067 1920 | 137/360,train_loss:0.083 1921 | 138/360,train_loss:0.067 1922 | 139/360,train_loss:0.130 1923 | 140/360,train_loss:0.106 1924 | 141/360,train_loss:0.091 1925 | 142/360,train_loss:0.108 1926 | 143/360,train_loss:0.067 1927 | 144/360,train_loss:0.089 1928 | 145/360,train_loss:0.081 1929 | 146/360,train_loss:0.066 1930 | 147/360,train_loss:0.111 1931 | 148/360,train_loss:0.098 1932 | 149/360,train_loss:0.134 1933 | 150/360,train_loss:0.129 1934 | 151/360,train_loss:0.102 1935 | 152/360,train_loss:0.138 1936 | 153/360,train_loss:0.141 1937 | 154/360,train_loss:0.095 1938 | 155/360,train_loss:0.064 1939 | 156/360,train_loss:0.047 1940 | 157/360,train_loss:0.137 1941 | 158/360,train_loss:0.074 1942 | 159/360,train_loss:0.108 1943 | 160/360,train_loss:0.123 1944 | 161/360,train_loss:0.094 1945 | 162/360,train_loss:0.051 1946 | 163/360,train_loss:0.050 1947 | 164/360,train_loss:0.095 1948 | 165/360,train_loss:0.123 1949 | 166/360,train_loss:0.048 1950 | 167/360,train_loss:0.093 1951 | 168/360,train_loss:0.112 1952 | 169/360,train_loss:0.093 1953 | 170/360,train_loss:0.074 1954 | 171/360,train_loss:0.086 1955 | 172/360,train_loss:0.057 1956 | 173/360,train_loss:0.109 1957 | 174/360,train_loss:0.077 1958 | 175/360,train_loss:0.059 1959 | 176/360,train_loss:0.099 1960 | 177/360,train_loss:0.088 1961 | 178/360,train_loss:0.112 1962 | 179/360,train_loss:0.084 1963 | 180/360,train_loss:0.074 1964 | 181/360,train_loss:0.102 1965 | 182/360,train_loss:0.118 1966 | 183/360,train_loss:0.117 1967 | 184/360,train_loss:0.093 1968 | 185/360,train_loss:0.078 1969 | 186/360,train_loss:0.053 1970 | 187/360,train_loss:0.103 1971 | 188/360,train_loss:0.085 1972 | 189/360,train_loss:0.079 1973 | 190/360,train_loss:0.091 1974 | 191/360,train_loss:0.060 1975 | 192/360,train_loss:0.066 1976 | 193/360,train_loss:0.071 1977 | 194/360,train_loss:0.109 1978 | 195/360,train_loss:0.152 1979 | 196/360,train_loss:0.125 1980 | 197/360,train_loss:0.120 1981 | 198/360,train_loss:0.076 1982 | 199/360,train_loss:0.101 1983 | 200/360,train_loss:0.108 1984 | 201/360,train_loss:0.149 1985 | 202/360,train_loss:0.105 1986 | 203/360,train_loss:0.115 1987 | 204/360,train_loss:0.078 1988 | 205/360,train_loss:0.084 1989 | 206/360,train_loss:0.090 1990 | 207/360,train_loss:0.065 1991 | 208/360,train_loss:0.146 1992 | 209/360,train_loss:0.080 1993 | 210/360,train_loss:0.126 1994 | 211/360,train_loss:0.104 1995 | 212/360,train_loss:0.088 1996 | 213/360,train_loss:0.104 1997 | 214/360,train_loss:0.100 1998 | 215/360,train_loss:0.097 1999 | 216/360,train_loss:0.119 2000 | 217/360,train_loss:0.080 2001 | 218/360,train_loss:0.077 2002 | 219/360,train_loss:0.085 2003 | 220/360,train_loss:0.096 2004 | 221/360,train_loss:0.134 2005 | 222/360,train_loss:0.081 2006 | 223/360,train_loss:0.108 2007 | 224/360,train_loss:0.063 2008 | 225/360,train_loss:0.096 2009 | 226/360,train_loss:0.117 2010 | 227/360,train_loss:0.067 2011 | 228/360,train_loss:0.095 2012 | 229/360,train_loss:0.048 2013 | 230/360,train_loss:0.107 2014 | 231/360,train_loss:0.055 2015 | 232/360,train_loss:0.098 2016 | 233/360,train_loss:0.078 2017 | 234/360,train_loss:0.075 2018 | 235/360,train_loss:0.131 2019 | 236/360,train_loss:0.095 2020 | 237/360,train_loss:0.117 2021 | 238/360,train_loss:0.118 2022 | 239/360,train_loss:0.065 2023 | 240/360,train_loss:0.085 2024 | 241/360,train_loss:0.087 2025 | 242/360,train_loss:0.116 2026 | 243/360,train_loss:0.101 2027 | 244/360,train_loss:0.134 2028 | 245/360,train_loss:0.085 2029 | 246/360,train_loss:0.102 2030 | 247/360,train_loss:0.084 2031 | 248/360,train_loss:0.057 2032 | 249/360,train_loss:0.081 2033 | 250/360,train_loss:0.104 2034 | 251/360,train_loss:0.145 2035 | 252/360,train_loss:0.072 2036 | 253/360,train_loss:0.080 2037 | 254/360,train_loss:0.046 2038 | 255/360,train_loss:0.087 2039 | 256/360,train_loss:0.101 2040 | 257/360,train_loss:0.066 2041 | 258/360,train_loss:0.136 2042 | 259/360,train_loss:0.071 2043 | 260/360,train_loss:0.085 2044 | 261/360,train_loss:0.106 2045 | 262/360,train_loss:0.068 2046 | 263/360,train_loss:0.045 2047 | 264/360,train_loss:0.060 2048 | 265/360,train_loss:0.085 2049 | 266/360,train_loss:0.043 2050 | 267/360,train_loss:0.084 2051 | 268/360,train_loss:0.095 2052 | 269/360,train_loss:0.061 2053 | 270/360,train_loss:0.082 2054 | 271/360,train_loss:0.090 2055 | 272/360,train_loss:0.052 2056 | 273/360,train_loss:0.088 2057 | 274/360,train_loss:0.075 2058 | 275/360,train_loss:0.062 2059 | 276/360,train_loss:0.087 2060 | 277/360,train_loss:0.052 2061 | 278/360,train_loss:0.090 2062 | 279/360,train_loss:0.108 2063 | 280/360,train_loss:0.109 2064 | 281/360,train_loss:0.057 2065 | 282/360,train_loss:0.098 2066 | 283/360,train_loss:0.135 2067 | 284/360,train_loss:0.117 2068 | 285/360,train_loss:0.093 2069 | 286/360,train_loss:0.065 2070 | 287/360,train_loss:0.115 2071 | 288/360,train_loss:0.097 2072 | 289/360,train_loss:0.113 2073 | 290/360,train_loss:0.058 2074 | 291/360,train_loss:0.062 2075 | 292/360,train_loss:0.109 2076 | 293/360,train_loss:0.083 2077 | 294/360,train_loss:0.130 2078 | 295/360,train_loss:0.110 2079 | 296/360,train_loss:0.117 2080 | 297/360,train_loss:0.059 2081 | 298/360,train_loss:0.073 2082 | 299/360,train_loss:0.086 2083 | 300/360,train_loss:0.095 2084 | 301/360,train_loss:0.058 2085 | 302/360,train_loss:0.104 2086 | 303/360,train_loss:0.142 2087 | 304/360,train_loss:0.109 2088 | 305/360,train_loss:0.107 2089 | 306/360,train_loss:0.098 2090 | 307/360,train_loss:0.083 2091 | 308/360,train_loss:0.109 2092 | 309/360,train_loss:0.080 2093 | 310/360,train_loss:0.090 2094 | 311/360,train_loss:0.106 2095 | 312/360,train_loss:0.086 2096 | 313/360,train_loss:0.081 2097 | 314/360,train_loss:0.101 2098 | 315/360,train_loss:0.082 2099 | 316/360,train_loss:0.107 2100 | 317/360,train_loss:0.112 2101 | 318/360,train_loss:0.077 2102 | 319/360,train_loss:0.110 2103 | 320/360,train_loss:0.072 2104 | 321/360,train_loss:0.079 2105 | 322/360,train_loss:0.137 2106 | 323/360,train_loss:0.077 2107 | 324/360,train_loss:0.106 2108 | 325/360,train_loss:0.085 2109 | 326/360,train_loss:0.161 2110 | 327/360,train_loss:0.089 2111 | 328/360,train_loss:0.079 2112 | 329/360,train_loss:0.092 2113 | 330/360,train_loss:0.105 2114 | 331/360,train_loss:0.077 2115 | 332/360,train_loss:0.079 2116 | 333/360,train_loss:0.095 2117 | 334/360,train_loss:0.150 2118 | 335/360,train_loss:0.093 2119 | 336/360,train_loss:0.057 2120 | 337/360,train_loss:0.058 2121 | 338/360,train_loss:0.141 2122 | 339/360,train_loss:0.090 2123 | 340/360,train_loss:0.066 2124 | 341/360,train_loss:0.106 2125 | 342/360,train_loss:0.077 2126 | 343/360,train_loss:0.075 2127 | 344/360,train_loss:0.110 2128 | 345/360,train_loss:0.078 2129 | 346/360,train_loss:0.085 2130 | 347/360,train_loss:0.064 2131 | 348/360,train_loss:0.070 2132 | 349/360,train_loss:0.037 2133 | 350/360,train_loss:0.076 2134 | 351/360,train_loss:0.067 2135 | 352/360,train_loss:0.074 2136 | 353/360,train_loss:0.084 2137 | 354/360,train_loss:0.115 2138 | 355/360,train_loss:0.076 2139 | 356/360,train_loss:0.137 2140 | 357/360,train_loss:0.156 2141 | 358/360,train_loss:0.086 2142 | 359/360,train_loss:0.071 2143 | 360/360,train_loss:0.111 2144 | epoch 5 loss:0.093 2145 | 2146 | 2147 | %run train_test_evaluate test 2148 | 2149 | index:1 dice score:0.820403825717322 2150 | index:2 dice score:0.738973897389739 2151 | index:3 dice score:0.7310826542491269 2152 | index:4 dice score:0.795852430686002 2153 | index:5 dice score:0.8096716947648624 2154 | index:6 dice score:0.7986829727187206 2155 | index:7 dice score:0.8293856402664693 2156 | index:8 dice score:0.8324828435685377 2157 | index:9 dice score:0.8512766517504606 2158 | index:10 dice score:0.8600508905852418 2159 | index:11 dice score:0.8019665683382498 2160 | index:12 dice score:0.6867182846932698 2161 | index:13 dice score:0.7369542066027689 2162 | index:14 dice score:0.8323271665043817 2163 | index:15 dice score:0.8830804947364208 2164 | index:16 dice score:0.8848778165661695 2165 | index:17 dice score:0.7917096501922536 2166 | index:18 dice score:0.5888149790588815 2167 | index:19 dice score:0.6724678036895232 2168 | index:20 dice score:0.7387145494210438 2169 | index:21 dice score:0.8501159592255002 2170 | index:22 dice score:0.8670608946869498 2171 | index:23 dice score:0.8210278682591386 2172 | index:24 dice score:0.7168597168597168 2173 | index:25 dice score:0.764270925761609 2174 | index:26 dice score:0.7994513867723255 2175 | index:27 dice score:0.8355581634149919 2176 | index:28 dice score:0.8660820367751061 2177 | index:29 dice score:0.8501790998286871 2178 | index:30 dice score:0.7699353448275862 2179 | index:31 dice score:0.7508667657256067 2180 | index:32 dice score:0.8163526030022357 2181 | index:33 dice score:0.8074742028446593 2182 | index:34 dice score:0.8293415819708352 2183 | index:35 dice score:0.8673496191226687 2184 | index:36 dice score:0.8655406304029791 2185 | index:37 dice score:0.857516339869281 2186 | index:38 dice score:0.7367969085444397 2187 | index:39 dice score:0.8345186285956905 2188 | index:40 dice score:0.8327148807269974 2189 | index:41 dice score:0.8087767648929405 2190 | index:42 dice score:0.7999263758512792 2191 | index:43 dice score:0.7442063839090511 2192 | index:44 dice score:0.7573943661971831 2193 | index:45 dice score:0.8289445965873183 2194 | index:46 dice score:0.8928246013667426 2195 | index:47 dice score:0.8692388530250713 2196 | index:48 dice score:0.8052234688247195 2197 | index:49 dice score:0.650534255185418 2198 | index:50 dice score:0.7001258653241033 2199 | index:51 dice score:0.7498889382496668 2200 | index:52 dice score:0.8448919052541687 2201 | index:53 dice score:0.8542641237855344 2202 | index:54 dice score:0.8038342108815985 2203 | index:55 dice score:0.44061302681992337 2204 | index:56 dice score:0.6001890359168242 2205 | index:57 dice score:0.7697344488905057 2206 | index:58 dice score:0.8437310438150343 2207 | index:59 dice score:0.8470169541792298 2208 | index:60 dice score:0.8281844468117486 2209 | index:61 dice score:0.03496503496503497 2210 | index:62 dice score:0.6191129401005944 2211 | index:63 dice score:0.8083661848445028 2212 | index:64 dice score:0.846827687477847 2213 | index:65 dice score:0.8506835469971807 2214 | index:66 dice score:0.8306118787008793 2215 | index:67 dice score:0.18466898954703834 2216 | index:68 dice score:0.644569097399286 2217 | index:69 dice score:0.8039050664871233 2218 | index:70 dice score:0.8123002173635085 2219 | index:71 dice score:0.802805049088359 2220 | index:72 dice score:0.8211992897145198 2221 | index:73 dice score:0.6484322881921281 2222 | index:74 dice score:0.6710427606901725 2223 | index:75 dice score:0.6961852861035422 2224 | index:76 dice score:0.7451025317905832 2225 | index:77 dice score:0.7972517671929709 2226 | index:78 dice score:0.7700138824618232 2227 | index:79 dice score:0.5066991473812423 2228 | index:80 dice score:0.6958301907122078 2229 | index:81 dice score:0.7829374420429417 2230 | index:82 dice score:0.799851506151888 2231 | index:83 dice score:0.7959317917320244 2232 | index:84 dice score:0.7451623483109217 2233 | index:85 dice score:0.3309066843150232 2234 | index:86 dice score:0.6465728274173806 2235 | index:87 dice score:0.7683670715249663 2236 | index:88 dice score:0.7787923195430805 2237 | index:89 dice score:0.7048042584731488 2238 | index:90 dice score:0.5389920424403183 2239 | index:91 dice score:0.6575901974132062 2240 | index:92 dice score:0.6744993324432577 2241 | index:93 dice score:0.8034070377699389 2242 | index:94 dice score:0.8199800585378405 2243 | index:95 dice score:0.7188089200962227 2244 | index:96 dice score:0.47264856355765444 2245 | index:97 dice score:0.7351937984496124 2246 | index:98 dice score:0.7396655994308076 2247 | index:99 dice score:0.8183835452760946 2248 | index:100 dice score:0.8671862573564498 2249 | index:101 dice score:0.8339425293819941 2250 | index:102 dice score:0.7074592074592074 2251 | index:103 dice score:0.6324015629696423 2252 | index:104 dice score:0.6973963355834137 2253 | index:105 dice score:0.7915567282321899 2254 | index:106 dice score:0.8546117769671704 2255 | index:107 dice score:0.8541866028708134 2256 | index:108 dice score:0.8334194659776055 2257 | index:109 dice score:0.7865590388586446 2258 | index:110 dice score:0.8132663316582914 2259 | index:111 dice score:0.7872543407746613 2260 | index:112 dice score:0.8058139534883721 2261 | index:113 dice score:0.8303718471006327 2262 | index:114 dice score:0.7230443974630021 2263 | index:115 dice score:0.769642474844787 2264 | index:116 dice score:0.7960569814269399 2265 | index:117 dice score:0.8485591661557327 2266 | index:118 dice score:0.8741624908507404 2267 | index:119 dice score:0.8509195977107296 2268 | index:120 dice score:0.7595523742312733 2269 | index:121 dice score:0.6786258250126925 2270 | index:122 dice score:0.703923900118906 2271 | index:123 dice score:0.7921849331142924 2272 | index:124 dice score:0.8484759131620655 2273 | index:125 dice score:0.7886280501921563 2274 | index:126 dice score:0.6535044422507403 2275 | index:127 dice score:0.47204354280059374 2276 | index:128 dice score:0.564278368186493 2277 | index:129 dice score:0.6783879603501918 2278 | index:132 dice score:0.7038129575002732 2279 | index:133 dice score:0.22388059701492538 2280 | index:134 dice score:0.4948791478902089 2281 | index:135 dice score:0.7338282078472959 2282 | index:136 dice score:0.8320242414576772 2283 | index:137 dice score:0.8545714870116589 2284 | index:138 dice score:0.8138758160012145 2285 | index:139 dice score:0.45690973992860784 2286 | index:140 dice score:0.7020082693443591 2287 | index:141 dice score:0.8437396762471093 2288 | index:142 dice score:0.8442500533390228 2289 | index:143 dice score:0.8173308371222252 2290 | index:144 dice score:0.8080612134928333 2291 | index:145 dice score:0.7481636935991606 2292 | index:146 dice score:0.808818214672931 2293 | index:147 dice score:0.8072536922789306 2294 | index:148 dice score:0.818716675859533 2295 | index:149 dice score:0.8568847852268165 2296 | index:150 dice score:0.8326672458731538 2297 | index:151 dice score:0.7365843705366252 2298 | index:152 dice score:0.8140238476597259 2299 | index:153 dice score:0.7977740445191096 2300 | index:154 dice score:0.7745710602003372 2301 | index:155 dice score:0.7721426483484362 2302 | index:156 dice score:0.6794121843344272 2303 | index:157 dice score:0.6238030095759234 2304 | index:158 dice score:0.755711318795431 2305 | index:159 dice score:0.7728839525086174 2306 | index:160 dice score:0.7973688189928928 2307 | index:161 dice score:0.762745885186672 2308 | index:162 dice score:0.3566753926701571 2309 | index:163 dice score:0.7749174917491749 2310 | index:164 dice score:0.8147288457480482 2311 | index:165 dice score:0.8149509803921569 2312 | index:166 dice score:0.7963553189095954 2313 | index:167 dice score:0.7867708486903533 2314 | index:168 dice score:0.6835354067826392 2315 | index:169 dice score:0.8415072902859307 2316 | index:170 dice score:0.8127439411818099 2317 | index:171 dice score:0.8106308724832215 2318 | index:172 dice score:0.7714617811479493 2319 | index:173 dice score:0.7614512775803098 2320 | index:174 dice score:0.7556479305982288 2321 | index:175 dice score:0.7426924660354055 2322 | index:176 dice score:0.7184721764899572 2323 | index:177 dice score:0.7805777504609711 2324 | index:178 dice score:0.8004889056036104 2325 | index:179 dice score:0.7470164244357793 2326 | index:181 dice score:0.38952687184198437 2327 | index:182 dice score:0.6987834549878346 2328 | index:183 dice score:0.7424071991001124 2329 | index:184 dice score:0.5731610862114421 2330 | index:185 dice score:0.7544338335607094 2331 | index:186 dice score:0.7662366061666303 2332 | index:187 dice score:0.426078971533517 2333 | index:188 dice score:0.700477960701009 2334 | index:189 dice score:0.7579102281089036 2335 | index:190 dice score:0.7321834244846445 2336 | index:191 dice score:0.75991454132728 2337 | index:192 dice score:0.7363246785984371 2338 | index:193 dice score:0.40179372197309415 2339 | index:194 dice score:0.562375249500998 2340 | index:195 dice score:0.6811567842851947 2341 | index:196 dice score:0.8019435223938038 2342 | index:197 dice score:0.8187565858798735 2343 | index:198 dice score:0.7260586891583202 2344 | index:199 dice score:0.19517102615694165 2345 | index:200 dice score:0.5692682926829268 2346 | index:201 dice score:0.605122268846766 2347 | index:202 dice score:0.7855785717595811 2348 | index:203 dice score:0.8333192460485166 2349 | index:204 dice score:0.8164920581277458 2350 | index:205 dice score:0.37488457987072943 2351 | index:206 dice score:0.6134651600753296 2352 | index:207 dice score:0.7316671809112414 2353 | index:208 dice score:0.7338392194899298 2354 | index:209 dice score:0.7725459782849545 2355 | index:210 dice score:0.834318006678654 2356 | index:211 dice score:0.47074010327022375 2357 | index:212 dice score:0.5578541874732487 2358 | index:213 dice score:0.7769775882929078 2359 | index:214 dice score:0.7805317710680487 2360 | index:215 dice score:0.6193161790623899 2361 | index:216 dice score:0.764757095594637 2362 | index:217 dice score:0.7914110429447853 2363 | index:218 dice score:0.8067688747468904 2364 | index:219 dice score:0.7494722026741731 2365 | index:220 dice score:0.8285295554469956 2366 | index:221 dice score:0.8584918571233064 2367 | index:222 dice score:0.8014796547472256 2368 | index:223 dice score:0.7951985226223454 2369 | index:224 dice score:0.8563673026213743 2370 | index:225 dice score:0.8167330677290837 2371 | index:226 dice score:0.8353840316548322 2372 | index:227 dice score:0.8471289210818389 2373 | index:228 dice score:0.7490738453939244 2374 | index:229 dice score:0.7054820415879017 2375 | index:230 dice score:0.8163002483672155 2376 | index:231 dice score:0.8214635968803997 2377 | index:232 dice score:0.8062891161654709 2378 | index:233 dice score:0.7538755250095456 2379 | index:234 dice score:0.3861955628594905 2380 | index:235 dice score:0.6887062870246512 2381 | index:236 dice score:0.7497351694915254 2382 | index:237 dice score:0.8390919048093199 2383 | index:238 dice score:0.8259390503189228 2384 | index:239 dice score:0.7553025763930498 2385 | index:240 dice score:0.48535564853556484 2386 | index:241 dice score:0.7834471675371635 2387 | index:242 dice score:0.778254972875226 2388 | index:243 dice score:0.8644941976321651 2389 | index:244 dice score:0.8458145152820082 2390 | index:245 dice score:0.7807911556400069 2391 | index:246 dice score:0.7519731787385625 2392 | index:247 dice score:0.6151603498542274 2393 | index:248 dice score:0.7819262782401902 2394 | index:249 dice score:0.8726344050815271 2395 | index:250 dice score:0.8815432968462122 2396 | index:251 dice score:0.8078029260972864 2397 | index:252 dice score:0.8043714023525486 2398 | index:253 dice score:0.6852331606217616 2399 | index:254 dice score:0.6935603256846781 2400 | index:255 dice score:0.5803305337306963 2401 | index:256 dice score:0.7288958907706446 2402 | index:257 dice score:0.7018301982714794 2403 | index:258 dice score:0.535855697316322 2404 | index:259 dice score:0.5285624607658506 2405 | index:260 dice score:0.7077474496829336 2406 | index:261 dice score:0.7728146382716998 2407 | index:262 dice score:0.7987992732443321 2408 | index:263 dice score:0.7599787120808941 2409 | index:264 dice score:0.6447882481637756 2410 | index:265 dice score:0.26609442060085836 2411 | index:266 dice score:0.659902516661693 2412 | index:267 dice score:0.7857185503612156 2413 | index:268 dice score:0.8371262829094155 2414 | index:269 dice score:0.8255831452219714 2415 | index:270 dice score:0.7930706665258266 2416 | index:271 dice score:0.12307692307692308 2417 | index:272 dice score:0.5438813349814586 2418 | index:273 dice score:0.7199939228198116 2419 | index:274 dice score:0.8061976123952248 2420 | index:275 dice score:0.8256840823073911 2421 | index:276 dice score:0.7995637949836423 2422 | index:277 dice score:0.26421404682274247 2423 | index:278 dice score:0.6479338842975206 2424 | index:279 dice score:0.7158030254264564 2425 | index:280 dice score:0.7872676947410043 2426 | index:281 dice score:0.8048538591680765 2427 | index:282 dice score:0.7389476366416105 2428 | index:283 dice score:0.5844155844155844 2429 | index:284 dice score:0.5103821847727956 2430 | index:285 dice score:0.6971131532535041 2431 | index:286 dice score:0.8394667321988082 2432 | index:287 dice score:0.8766066838046273 2433 | index:288 dice score:0.7398648648648649 2434 | Average Dice Score: 73.4771% 2435 | -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/finally_evaluate.py: -------------------------------------------------------------------------------- 1 | import os 2 | import numpy as np 3 | from PIL import Image 4 | 5 | 6 | def Dice(y_true, y_pred): 7 | # input is array 8 | if np.max(y_true) > 1: 9 | y_true = y_true / 255. 10 | if np.max(y_pred) > 1: 11 | y_pred = y_pred / 255. 12 | return 2 * np.sum(y_true * y_pred) / (np.sum(y_pred) + np.sum(y_true)) 13 | 14 | 15 | def Accuracy(y_true, y_pred): 16 | # input is array 17 | if np.max(y_true) > 1: 18 | y_true = y_true / 255. 19 | if np.max(y_pred) > 1: 20 | y_pred = y_pred / 255. 21 | acc_sum = 0 22 | sum = 0 23 | for i in range(len(y_true)): 24 | for j in range(len(y_true[i])): 25 | sum += 1 26 | if y_true[i][j] == y_pred[i][j]: 27 | acc_sum += 1 28 | accuracy = acc_sum/sum 29 | return accuracy 30 | 31 | 32 | if __name__ == '__main__': 33 | CHASE_predict_path = './result/CHASE/merge/' 34 | CHASE_label_path = './result/CHASE/merge_label/' 35 | DRIVE_predict_path = './result/DRIVE/merge/' 36 | DRIVE_label_path = './result/DRIVE/merge_label/' 37 | 38 | Dice_CHASE_sum = 0 39 | Accuracy_CHASE_sum = 0 40 | num_CHASE = len(os.listdir(CHASE_predict_path)) 41 | for i in range(num_CHASE): 42 | x = np.asarray(Image.open(CHASE_predict_path+'%03d.png' % (i+1))) 43 | y = np.asarray(Image.open(CHASE_label_path+'%03d.png' % (i+1))) 44 | Dice_i = Dice(x, y) 45 | Accuracy_i = Accuracy(x, y) 46 | print('CHASE No.{}, Dice:{:.2f}%, Accuracy:{:.2f}%'.format( 47 | i+1, Dice_i*100, Accuracy_i*100)) 48 | Dice_CHASE_sum += Dice_i 49 | Accuracy_CHASE_sum += Accuracy_i 50 | avg_dice = Dice_CHASE_sum*100/num_CHASE 51 | avg_accuracy = Accuracy_CHASE_sum*100/num_CHASE 52 | print('CHASE avarage Dice:{:.2f}%, avarage Accuracy:{:.2f}%'.format( 53 | avg_dice, avg_accuracy)) 54 | 55 | Dice_DRIVE_sum = 0 56 | Accuracy_DRIVE_sum = 0 57 | num_DRIVE = len(os.listdir(DRIVE_predict_path)) 58 | for i in range(num_DRIVE): 59 | x = np.asarray(Image.open(DRIVE_predict_path+'%03d.png' % (i+1))) 60 | y = np.asarray(Image.open(DRIVE_label_path+'%03d.png' % (i+1))) 61 | Dice_i = Dice(x, y) 62 | Accuracy_i = Accuracy(x, y) 63 | print('DRIVE No.{}, Dice:{:.2f}%, Accuracy:{:.2f}%'.format( 64 | i+1, Dice_i*100, Accuracy_i*100)) 65 | Dice_DRIVE_sum += Dice_i 66 | Accuracy_DRIVE_sum += Accuracy_i 67 | avg_dice = Dice_DRIVE_sum*100/num_DRIVE 68 | avg_accuracy = Accuracy_DRIVE_sum*100/num_DRIVE 69 | print('DRIVE avarage Dice:{:.2f}%, avarage Accuracy:{:.2f}%'.format( 70 | avg_dice, avg_accuracy)) 71 | -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/get_mask.py: -------------------------------------------------------------------------------- 1 | # Get masks of each image 2 | import os 3 | import numpy as np 4 | from PIL import Image 5 | 6 | 7 | if __name__ == '__main__': 8 | 9 | dataset = ['CHASE', 'DRIVE'] 10 | train_test = ['train', 'test'] 11 | for m in dataset: 12 | for n in train_test: 13 | img_dir = './data/' + m + '/' + n + '/images/' 14 | img_name = os.listdir(img_dir) 15 | images = [img_dir+img_name[i] for i in range(len(img_name))] 16 | # print(images) 17 | directory = './data_process/' + m + '/' + n + '/mask/' 18 | if not os.path.exists(directory): 19 | os.makedirs(directory) 20 | for i in images: 21 | image_name = i.split('/')[-1].split('.')[0] 22 | # print(image_name) 23 | im = Image.open(i) 24 | im_gray = im.convert('L') 25 | np_im = np.array(im_gray) 26 | np_mask = np.zeros((np_im.shape[0], np_im.shape[1])) 27 | if m == 'CHASE': 28 | np_mask[np_im[:, :] > 5] = 255 29 | elif m == 'DRIVE': 30 | np_mask[np_im[:, :] > 20] = 255 31 | mask = Image.fromarray(np_mask) 32 | mask = mask.convert('L') 33 | mask_name = directory + image_name + '_mask.jpg' 34 | mask.save(mask_name) 35 | -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/loaddata.py: -------------------------------------------------------------------------------- 1 | import os 2 | import PIL.Image as Image 3 | from torch.utils.data import Dataset 4 | 5 | 6 | def make_dataset(root): 7 | imgs = [] 8 | n = len(os.listdir(root))//2 9 | for i in range(n): 10 | img = os.path.join(root, '%03d.png' % (i+1)) 11 | label = os.path.join(root, '%03d_label.png' % (i+1)) 12 | imgs.append((img, label)) 13 | return imgs 14 | 15 | 16 | class LoadDataset(Dataset): 17 | def __init__(self, root, transform=None, target_transform=None): 18 | imgs = make_dataset(root) 19 | self.imgs = imgs 20 | self.transform = transform 21 | self.target_transform = target_transform 22 | 23 | def __getitem__(self, index): 24 | x_path, y_path = self.imgs[index] 25 | img_x = Image.open(x_path) 26 | img_y = Image.open(y_path) 27 | if self.transform is not None: 28 | img_x = self.transform(img_x) 29 | if self.target_transform is not None: 30 | img_y = self.target_transform(img_y) 31 | return img_x, img_y 32 | 33 | def __len__(self): 34 | return len(self.imgs) 35 | -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/merge_imgs.py: -------------------------------------------------------------------------------- 1 | import os 2 | import numpy as np 3 | from PIL import Image 4 | 5 | # No1toChange.merge predict 6 | # source_path = ['./result/CHASE/test/', './result/DRIVE/test/'] 7 | # merge_path = ['./result/CHASE/merge/', './result/DRIVE/merge/'] 8 | # No1toChange.merge mask. Why don not we use raw mask? Because the size of merged croped mask & raw mask are not equail. 9 | source_path = ['./data_crop/CHASE/test/', './data_crop/DRIVE/test/'] 10 | merge_path = ['./result/CHASE/merge_label/', './result/DRIVE/merge_label/'] 11 | for i in range(len(merge_path)): 12 | if not os.path.exists(merge_path[i]): 13 | os.makedirs(merge_path[i]) 14 | 15 | 16 | def merge(path_in, path_out, row, col, idx, side_length, stride, size): 17 | merged_img_arr = np.zeros(size) 18 | l = 0 19 | for i in range(row): 20 | for j in range(col): 21 | l += 1 22 | # print(path_in+'%03d_predict.png' % 23 | # (idx*row*col+l)) 24 | # No2toChange.predict patches path 25 | # img_ij = Image.open(path_in+'%03d_predict.png' % 26 | # (idx*row*col+l)) 27 | # No2toChange.label patches path 28 | img_ij = Image.open(path_in+'%03d_label.png' % 29 | (idx*row*col+l)) 30 | img_ij = np.asarray(img_ij) 31 | # print(img_ij.shape) 32 | print(str(idx+1)+'-'+str(l)) 33 | if idx == 0 and l == 1: 34 | print(img_ij) 35 | print([i*stride, i*stride+side_length, 36 | j*stride, j*stride+side_length]) 37 | # No3toChange. CHASE_prediction*1 or DRIVE_prediction*1 38 | # merged_img_arr[int(i*stride):int(i*stride+side_length), 39 | # int(j*stride):int(j*stride+side_length)] = img_ij 40 | # No3toChange. CHASE_label*255 or DRIVE_label*1 41 | # merged_img_arr[int(i*stride):int(i*stride+side_length), 42 | # int(j*stride):int(j*stride+side_length)] = img_ij*255 43 | merged_img_arr[int(i*stride):int(i*stride+side_length), 44 | int(j*stride):int(j*stride+side_length)] = img_ij 45 | merged_img = Image.fromarray(merged_img_arr).convert('L') 46 | merged_img.save(path_out+'%03d.png' % (idx+1)) 47 | 48 | 49 | if __name__ == '__main__': 50 | 51 | # No4toChange. CHASE 0 52 | # dataset = 0 53 | # No4toChange. DRIVE 1 54 | dataset = 1 55 | side_length = 256 56 | stride = 128 57 | path_in = source_path[dataset] 58 | path_out = merge_path[dataset] 59 | # No5toChange.predict 60 | # files_num = len(os.listdir(source_path[dataset])) 61 | # No5toChange.label 62 | files_num = len(os.listdir(source_path[dataset]))//2 63 | if dataset == 0: 64 | row, col = 6, 6 65 | # size = (999, 960) 66 | size = (6*stride+side_length-stride, 6*stride+side_length-stride) 67 | elif dataset == 1: 68 | row, col = 3, 3 69 | # size = (565, 584) 70 | size = (3*stride+side_length-stride, 3*stride+side_length-stride) 71 | idx_all = files_num/row/col 72 | 73 | for idx in range(int(idx_all)): 74 | merge(path_in, path_out, int(row), int(col), 75 | int(idx), side_length, stride, size) 76 | -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/models.py: -------------------------------------------------------------------------------- 1 | import torch 2 | from torch import nn 3 | 4 | 5 | class DoubleConv(nn.Module): 6 | def __init__(self, in_ch, out_ch): 7 | super(DoubleConv, self).__init__() 8 | self.conv = nn.Sequential( 9 | nn.Conv2d(in_ch, out_ch, 3, padding=1), 10 | nn.BatchNorm2d(out_ch), 11 | nn.ReLU(inplace=True), 12 | nn.Conv2d(out_ch, out_ch, 3, padding=1), 13 | nn.BatchNorm2d(out_ch), 14 | nn.ReLU(inplace=True) 15 | ) 16 | 17 | def forward(self, input): 18 | return self.conv(input) 19 | 20 | 21 | class Unet(nn.Module): 22 | def __init__(self, in_ch, out_ch): 23 | super(Unet, self).__init__() 24 | 25 | self.conv1 = DoubleConv(in_ch, 64) 26 | self.pool1 = nn.MaxPool2d(2) 27 | self.conv2 = DoubleConv(64, 128) 28 | self.pool2 = nn.MaxPool2d(2) 29 | self.conv3 = DoubleConv(128, 256) 30 | self.pool3 = nn.MaxPool2d(2) 31 | self.conv4 = DoubleConv(256, 512) 32 | self.pool4 = nn.MaxPool2d(2) 33 | self.conv5 = DoubleConv(512, 1024) 34 | self.up6 = nn.ConvTranspose2d(1024, 512, 2, stride=2) 35 | self.conv6 = DoubleConv(1024, 512) 36 | self.up7 = nn.ConvTranspose2d(512, 256, 2, stride=2) 37 | self.conv7 = DoubleConv(512, 256) 38 | self.up8 = nn.ConvTranspose2d(256, 128, 2, stride=2) 39 | self.conv8 = DoubleConv(256, 128) 40 | self.up9 = nn.ConvTranspose2d(128, 64, 2, stride=2) 41 | self.conv9 = DoubleConv(128, 64) 42 | self.conv10 = nn.Conv2d(64, out_ch, 1) 43 | 44 | def forward(self, x): 45 | c1 = self.conv1(x) 46 | p1 = self.pool1(c1) 47 | c2 = self.conv2(p1) 48 | p2 = self.pool2(c2) 49 | c3 = self.conv3(p2) 50 | p3 = self.pool3(c3) 51 | c4 = self.conv4(p3) 52 | p4 = self.pool4(c4) 53 | c5 = self.conv5(p4) 54 | up_6 = self.up6(c5) 55 | merge6 = torch.cat([up_6, c4], dim=1) 56 | c6 = self.conv6(merge6) 57 | up_7 = self.up7(c6) 58 | merge7 = torch.cat([up_7, c3], dim=1) 59 | c7 = self.conv7(merge7) 60 | up_8 = self.up8(c7) 61 | merge8 = torch.cat([up_8, c2], dim=1) 62 | c8 = self.conv8(merge8) 63 | up_9 = self.up9(c8) 64 | merge9 = torch.cat([up_9, c1], dim=1) 65 | c9 = self.conv9(merge9) 66 | c10 = self.conv10(c9) 67 | out = nn.Sigmoid()(c10) 68 | # return out 69 | return c10 70 | 71 | 72 | class Unet_plus_plus(nn.Module): 73 | def __init__(self, in_ch, out_ch): 74 | super(Unet_plus_plus, self).__init__() 75 | 76 | self.conv00 = DoubleConv(in_ch, 64) 77 | self.pool00 = nn.MaxPool2d(2) 78 | 79 | self.conv10 = DoubleConv(64, 128) 80 | self.pool10 = nn.MaxPool2d(2) 81 | self.up10 = nn.ConvTranspose2d(128, 64, 2, stride=2) 82 | self.conv01 = DoubleConv(64*2, 64) 83 | 84 | self.conv20 = DoubleConv(128, 256) 85 | self.pool20 = nn.MaxPool2d(2) 86 | self.up20 = nn.ConvTranspose2d(256, 128, 2, stride=2) 87 | self.conv11 = DoubleConv(128*2, 128) 88 | self.up11 = nn.ConvTranspose2d(128, 64, 2, stride=2) 89 | self.conv02 = DoubleConv(64*3, 64) 90 | 91 | self.conv30 = DoubleConv(256, 512) 92 | self.pool30 = nn.MaxPool2d(2) 93 | self.up30 = nn.ConvTranspose2d(512, 256, 2, stride=2) 94 | self.conv21 = DoubleConv(256*2, 256) 95 | self.up21 = nn.ConvTranspose2d(256, 128, 2, stride=2) 96 | self.conv12 = DoubleConv(128*3, 128) 97 | self.up12 = nn.ConvTranspose2d(128, 64, 2, stride=2) 98 | self.conv03 = DoubleConv(64*4, 64) 99 | 100 | self.conv40 = DoubleConv(512, 1024) 101 | self.up40 = nn.ConvTranspose2d(1024, 512, 2, stride=2) 102 | self.conv31 = DoubleConv(512*2, 512) 103 | self.up31 = nn.ConvTranspose2d(512, 256, 2, stride=2) 104 | self.conv22 = DoubleConv(256*3, 256) 105 | self.up22 = nn.ConvTranspose2d(256, 128, 2, stride=2) 106 | self.conv13 = DoubleConv(128*4, 128) 107 | self.up13 = nn.ConvTranspose2d(128, 64, 2, stride=2) 108 | self.conv04 = DoubleConv(64*5, 64) 109 | 110 | self.conv_out = nn.Conv2d(64, out_ch, 1) 111 | self.conv_out_cat = nn.Conv2d(64*4, out_ch, 1) 112 | 113 | def forward(self, x): 114 | c00 = self.conv00(x) 115 | p00 = self.pool00(c00) 116 | 117 | c10 = self.conv10(p00) 118 | p10 = self.pool10(c10) 119 | up10 = self.up10(c10) 120 | merge00_10 = torch.cat([c00, up10], 1) 121 | c01 = self.conv01(merge00_10) 122 | cout01 = self.conv_out(c01) 123 | out01 = nn.Sigmoid()(cout01) 124 | 125 | c20 = self.conv20(p10) 126 | p20 = self.pool20(c20) 127 | up20 = self.up20(c20) 128 | merge10_20 = torch.cat([c10, up20], 1) 129 | c11 = self.conv11(merge10_20) 130 | up11 = self.up11(c11) 131 | merge00_01_11 = torch.cat([c00, c01, up11], 1) 132 | c02 = self.conv02(merge00_01_11) 133 | cout02 = self.conv_out(c02) 134 | out02 = nn.Sigmoid()(cout02) 135 | 136 | c30 = self.conv30(p20) 137 | p30 = self.pool30(c30) 138 | up30 = self.up30(c30) 139 | merge20_30 = torch.cat([c20, up30], 1) 140 | c21 = self.conv21(merge20_30) 141 | up21 = self.up21(c21) 142 | merge10_11_21 = torch.cat([c10, c11, up21], 1) 143 | c12 = self.conv12(merge10_11_21) 144 | up12 = self.up12(c12) 145 | merge00_01_02_12 = torch.cat([c00, c01, c02, up12], 1) 146 | c03 = self.conv03(merge00_01_02_12) 147 | cout03 = self.conv_out(c03) 148 | out03 = nn.Sigmoid()(cout03) 149 | 150 | c40 = self.conv40(p30) 151 | up40 = self.up40(c40) 152 | merge30_40 = torch.cat([c30, up40], 1) 153 | c31 = self.conv31(merge30_40) 154 | up31 = self.up31(c31) 155 | merge20_21_31 = torch.cat([c20, c21, up31], 1) 156 | c22 = self.conv22(merge20_21_31) 157 | up22 = self.up22(c22) 158 | merge10_11_12_22 = torch.cat([c10, c11, c12, up22], 1) 159 | c13 = self.conv13(merge10_11_12_22) 160 | up13 = self.up13(c13) 161 | merge00_01_02_03_13 = torch.cat([c00, c01, c02, c03, up13], 1) 162 | c04 = self.conv04(merge00_01_02_03_13) 163 | cout04 = self.conv_out(c04) 164 | out04 = nn.Sigmoid()(cout04) 165 | 166 | merge_c01_to_c04 = torch.cat([c01, c02, c03, c04], 1) 167 | cout_cat = self.conv_out_cat(merge_c01_to_c04) 168 | out_cat = nn.Sigmoid()(cout_cat) 169 | 170 | # return cout01, cout02, cout03, cout04, cout_cat 171 | # return out01, out02, out03, out04, out_cat 172 | return cout_cat 173 | -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/preprocessing.py: -------------------------------------------------------------------------------- 1 | # 4 steps to enhance image 2 | import cv2 3 | import os 4 | import numpy as np 5 | 6 | 7 | # Step1.Convert RGB to gray 8 | def rgb2gray(rgb): 9 | assert (len(rgb.shape) == 4) # 4D arrays 10 | assert (rgb.shape[1] == 3) 11 | bn_imgs = rgb[:, 0, :, :]*0.299 + \ 12 | rgb[:, 1, :, :]*0.587 + rgb[:, 2, :, :]*0.114 13 | bn_imgs = np.reshape( 14 | bn_imgs, (rgb.shape[0], 1, rgb.shape[2], rgb.shape[3])) 15 | return bn_imgs 16 | 17 | 18 | # Step2.Normalize over the dataset 19 | def dataset_normalized(imgs): 20 | assert (len(imgs.shape) == 4) # 4D arrays 21 | assert (imgs.shape[1] == 1) # check the channel is 1 22 | imgs_normalized = np.empty(imgs.shape) 23 | imgs_std = np.std(imgs) 24 | imgs_mean = np.mean(imgs) 25 | imgs_normalized = (imgs-imgs_mean)/imgs_std 26 | for i in range(imgs.shape[0]): 27 | imgs_normalized[i] = ((imgs_normalized[i] - np.min(imgs_normalized[i])) / ( 28 | np.max(imgs_normalized[i])-np.min(imgs_normalized[i])))*255 29 | return imgs_normalized 30 | 31 | 32 | # Step3.CLAHE (Contrast Limited Adaptive Histogram Equalization) 33 | # In this, image is divided into small blocks called "tiles" (tileSize is 8x8 by default in OpenCV). Then each of these blocks are histogram equalized as usual. So in a small area, histogram would confine to a small region (unless there is noise). If noise is there, it will be amplified. To avoid this, contrast limiting is applied. If any histogram bin is above the specified contrast limit (by default 40 in OpenCV), those pixels are clipped and distributed uniformly to other bins before applying histogram equalization. After equalization, to remove artifacts in tile borders, bilinear interpolation is applied. 34 | def clahe_equalized(imgs): 35 | assert (len(imgs.shape) == 4) 36 | assert (imgs.shape[1] == 1) 37 | # create a CLAHE object (Arguments are optional). 38 | clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8)) 39 | imgs_equalized = np.empty(imgs.shape) 40 | for i in range(imgs.shape[0]): 41 | imgs_equalized[i, 0] = clahe.apply( 42 | np.array(imgs[i, 0], dtype=np.uint8)) 43 | return imgs_equalized 44 | 45 | 46 | # Step4.Adjust gamma 47 | def adjust_gamma(imgs, gamma=1.0): 48 | assert (len(imgs.shape) == 4) 49 | assert (imgs.shape[1] == 1) 50 | # build a lookup table mapping the pixel values [0, 255] to 51 | # their adjusted gamma values 52 | invGamma = 1.0 / gamma 53 | table = np.array([((i / 255.0) ** invGamma) * 54 | 255 for i in np.arange(0, 256)]).astype("uint8") 55 | # apply gamma correction using the lookup table 56 | new_imgs = np.empty(imgs.shape) 57 | for i in range(imgs.shape[0]): 58 | new_imgs[i, 0] = cv2.LUT(np.array(imgs[i, 0], dtype=np.uint8), table) 59 | return new_imgs 60 | 61 | 62 | # Combine process: input: imgs[image_number, channel, height, width] 63 | def combine_process(imgs): 64 | assert(len(imgs.shape) == 4) 65 | assert(imgs.shape[1] == 3) 66 | # global gray_imgs, normalized_imgs, clahe_imgs, gamma_imgs, finally_imgs 67 | gray_imgs = rgb2gray(imgs) 68 | normalized_imgs = dataset_normalized(gray_imgs) 69 | clahe_imgs = clahe_equalized(normalized_imgs) 70 | gamma_imgs = adjust_gamma(clahe_imgs, 1.2) 71 | finally_imgs = gamma_imgs/255. # reduce to 0-1 range 72 | return gray_imgs, normalized_imgs, clahe_imgs, gamma_imgs, finally_imgs 73 | 74 | 75 | # Main process 76 | def main_process(): 77 | 78 | # Step0.Set original & preprocessed image path 79 | dataset = ['CHASE', 'DRIVE'] 80 | train_test = ['train', 'test'] 81 | img_folder_path = ['./data/'+dataset[i]+'/' + train_test[j] + 82 | '/images/' for i in range(2) for j in range(2)] 83 | img_name = [os.listdir(img_folder_path[i]) for i in range(4)] 84 | img_path = [[img_folder_path[i]+img_name[i][j] 85 | for j in range(len(img_name[i]))] for i in range(4)] 86 | # print(img_path) # [[20img_path],[8],[20],[20]] 87 | preprocessing_folder_path = ['./data_process/'+dataset[i]+'/' + train_test[j] + 88 | '/preprocessing/' for i in range(2) for j in range(2)] 89 | for val in preprocessing_folder_path: 90 | if not os.path.exists(val): 91 | os.makedirs(val) 92 | 93 | def new_path(name): 94 | return [[preprocessing_folder_path[i]+os.path.splitext(img_name[i][j])[0]+'_'+name+'.jpg' 95 | for j in range(len(img_name[i]))] for i in range(4)] 96 | gray_path = new_path('gray') 97 | normalized_path = new_path('normalized') 98 | clahe_path = new_path('clahe') 99 | gamma_path = new_path('gamma') 100 | finally_path = new_path('finally') 101 | gray_imgs, normalized_imgs, clahe_imgs, gamma_imgs, finally_imgs = [ 102 | [[] for x in range(4)] for y in range(5)] 103 | 104 | # 1).Read images using cv2; bgr -> rgb; (0, 1, 2, 3) -> (0, 3, 1, 2)(img_number, channel, height, width) 105 | imgs = [np.array([cv2.imread(img_path[i][j]) 106 | for j in range(len(img_path[i]))]) for i in range(4)] 107 | for i in range(len(imgs)): 108 | for j in range(len(imgs[i])): 109 | B, G, R = cv2.split(imgs[i][j]) 110 | img_merge = cv2.merge((R, G, B)) 111 | imgs[i][j] = img_merge 112 | 113 | def change_dim(which, order): 114 | return [np.transpose(which[i], order) for i in range(4)] 115 | imgs = change_dim(imgs, (0, 3, 1, 2)) 116 | # print(len(imgs)) 117 | # for i in range(4): 118 | # print(imgs[i].shape) 119 | # 4 (20, 3, 960, 999) (8, 3, 960, 999) (20, 3, 584, 565) (20, 3, 584, 565) 120 | 121 | # 2).Step1~4: rgb2gray, dataset_normalized, clahe_equalized, adjust_gamma 122 | # global gray_imgs, normalized_imgs, clahe_imgs, gamma_imgs, finally_imgs 123 | for i in range(4): 124 | gray_imgs[i], normalized_imgs[i], clahe_imgs[i], gamma_imgs[i], finally_imgs[i] = combine_process( 125 | imgs[i]) 126 | 127 | # 3).Step5~8: save img_gray, img_normalized, img_clahe, img_clahe, img_gamma, gamma00.txt, finally00.txt 128 | gray_imgs = change_dim(gray_imgs, (0, 2, 3, 1)) 129 | normalized_imgs = change_dim(normalized_imgs, (0, 2, 3, 1)) 130 | clahe_imgs = change_dim(clahe_imgs, (0, 2, 3, 1)) 131 | gamma_imgs = change_dim(gamma_imgs, (0, 2, 3, 1)) 132 | finally_imgs = change_dim(finally_imgs, (0, 2, 3, 1)) 133 | for i in range(len(gray_imgs)): 134 | for j in range(len(gray_imgs[i])): 135 | # print(gray_imgs[i][j].shape) # (960, 999, 1)*2*2, (584, 565, 1)*2*2 136 | # cv2.imwrite(gray_path[i][j], gray_imgs[i][j]) 137 | # cv2.imwrite(normalized_path[i][j], normalized_imgs[i][j]) 138 | # cv2.imwrite(clahe_path[i][j], clahe_imgs[i][j]) 139 | cv2.imwrite(gamma_path[i][j], gamma_imgs[i][j]) 140 | # cv2.imwrite(finally_path[i][j], finally_imgs[i][j]) # The images(0~1) will be black to see, so we haven't saven them. 141 | # np.savetxt('gamma00.txt', gamma_imgs[0][0] 142 | # [:, :, 0], fmt="%.3f", delimiter=',') 143 | # np.savetxt('finally00.txt', finally_imgs[0][0] 144 | # [:, :, 0], fmt="%.3f", delimiter=',') 145 | return gamma_imgs, finally_imgs 146 | 147 | 148 | if __name__ == '__main__': 149 | 150 | gamma_imgs, finally_imgs = main_process() 151 | print(type(gamma_imgs), len(gamma_imgs), 152 | gamma_imgs[0].shape, gamma_imgs[0][0].shape) 153 | -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/show_img/CHASE_test.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/show_img/CHASE_test.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/show_img/DRIVE_test.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/show_img/DRIVE_test.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/show_img/Unet++.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/show_img/Unet++.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/show_img/Unet.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/show_img/Unet.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/show_img/patchVSpatch_labelVSpatch_predict.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/show_img/patchVSpatch_labelVSpatch_predict.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/show_img/preprocessing.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/show_img/preprocessing.png -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/train_test_evaluate.py: -------------------------------------------------------------------------------- 1 | import os 2 | import torch 3 | import argparse 4 | import numpy as np 5 | import PIL.Image as Image 6 | from torch import nn, optim 7 | from torch._C import device 8 | from torch.utils.data import DataLoader 9 | from torchvision.transforms import transforms 10 | from models import Unet, Unet_plus_plus 11 | from loaddata import LoadDataset 12 | 13 | 14 | device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') 15 | # device = torch.device('cpu') 16 | x_transforms = transforms.Compose([ 17 | transforms.ToTensor(), 18 | transforms.Normalize([0.5], [0.5]) 19 | ]) 20 | y_transforms = transforms.ToTensor() 21 | 22 | 23 | def Dice(y_true, y_pred): 24 | # input is array 25 | if np.max(y_true) > 1: 26 | y_true = y_true / 255. 27 | if np.max(y_pred) > 1: 28 | y_pred = y_pred / 255. 29 | return 2 * np.sum(y_true * y_pred) / (np.sum(y_pred) + np.sum(y_true)) 30 | 31 | 32 | def train_model(model, criterion, optimizer, dataloader, args, num_epochs=5): 33 | for epoch in range(num_epochs): 34 | print('Epoch {}/{}'.format(epoch+1, num_epochs)) 35 | print('-' * 10) 36 | dt_size = len(dataloader.dataset) 37 | epoch_loss = 0 38 | step = 0 39 | for x, y in dataloader: 40 | step += 1 41 | inputs = x.to(device) 42 | labels = y.to(device) 43 | optimizer.zero_grad() 44 | outputs = model(inputs) 45 | # print(type(outputs)) 46 | # print(outputs.shape) 47 | # print(outputs) 48 | # print(type(labels)) 49 | # print(labels.shape) 50 | # print(labels) 51 | loss = criterion(outputs, labels) 52 | loss.backward() 53 | optimizer.step() 54 | epoch_loss += loss.item() 55 | print('%d/%d,train_loss:%0.3f' % 56 | (step, (dt_size - 1) // dataloader.batch_size + 1, loss.item())) 57 | print('epoch %d loss:%0.3f' % (epoch+1, epoch_loss/step)) 58 | torch.save(model.state_dict(), 'weights_{}_{}.pth'.format( 59 | args.datasetname, (epoch+1))) 60 | return model 61 | 62 | 63 | def train(args): 64 | model = Unet_plus_plus(1, 1).to(device) 65 | batch_size = args.batch_size 66 | # BCELoss = − 1/n ∑ ( y_n × ln ⁡ x_n + ( 1 − y_n ) × ln ⁡ ( 1 − x_n ) ) 67 | # BCEWithLogitsLoss 就是把 Sigmoid 和 BCELoss 合成一步 68 | criterion = nn.BCEWithLogitsLoss() 69 | # criterion = nn.CrossEntropyLoss() 70 | optimizer = optim.Adam(model.parameters()) 71 | load_dataset = LoadDataset( 72 | 'data_crop/'+args.datasetname+'/train/', transform=x_transforms, target_transform=y_transforms) 73 | dataloaders = DataLoader( 74 | load_dataset, batch_size=batch_size, shuffle=True, num_workers=4) 75 | train_model(model, criterion, optimizer, dataloaders, args) 76 | 77 | 78 | def test(args): 79 | model = Unet_plus_plus(1, 1) 80 | model.load_state_dict(torch.load(args.ckpt, map_location='cpu')) 81 | batch_size = 1 82 | load_dataset = LoadDataset( 83 | 'data_crop/'+args.datasetname+'/test/', transform=x_transforms, target_transform=y_transforms) 84 | dataloaders = DataLoader(load_dataset, batch_size=batch_size) 85 | model.eval() 86 | Dice_score_all = 0 87 | idx = 0 88 | threshold = 0.5 89 | for x, y_true in dataloaders: 90 | idx += 1 91 | y_pred = model(x).sigmoid() 92 | y_pred = y_pred.detach().numpy().reshape((256, 256)) 93 | # print(max([item for sublist in y_pred for item in sublist])) 94 | # print(min([item for sublist in y_pred for item in sublist])) 95 | y_pred = np.int64(y_pred > threshold) 96 | # print(max([item for sublist in y_pred for item in sublist])) 97 | # print(min([item for sublist in y_pred for item in sublist])) 98 | y_true = y_true.detach().numpy().reshape((256, 256)) 99 | # print(y_pred) 100 | # print(type(y_pred)) 101 | # print(y_pred.shape) 102 | # print(y_true) 103 | # print(type(y_true)) 104 | # print(y_true.shape) 105 | Dice_score = Dice(y_true, y_pred) 106 | Dice_score_all += Dice_score 107 | print('index:'+str(idx)+' dice score:'+str(Dice_score)) 108 | # y_pred = torch.squeeze(y_pred).numpy() 109 | y_pred_img = Image.fromarray(np.uint8(y_pred*255)) 110 | if y_pred_img.mode == "F": 111 | y_pred_img = y_pred_img.convert('1') 112 | if not os.path.exists('result/'+args.datasetname + '/test/'): 113 | os.makedirs('result/'+args.datasetname + '/test/') 114 | y_pred_img.save('result/'+args.datasetname + 115 | '/test/%03d_predict.png' % idx) 116 | Dice_score_average = Dice_score_all/(len(dataloaders.dataset)*batch_size) 117 | print('Average Dice Score: {:.4f}%'.format(Dice_score_average*100)) 118 | 119 | 120 | if __name__ == '__main__': 121 | 122 | parse = argparse.ArgumentParser() 123 | parse = argparse.ArgumentParser() 124 | parse.add_argument('action', type=str, 125 | help='train or test', default='train') 126 | parse.add_argument('--batch_size', type=int, default=8) 127 | parse.add_argument('--ckpt', type=str, 128 | help='the path of model weight file', default='weights_CHASE_5.pth') 129 | parse.add_argument('--datasetname', type=str, 130 | help='CHASE or DRIVE', default='CHASE') 131 | args = parse.parse_args() 132 | 133 | if args.action == 'train': 134 | train(args) 135 | elif args.action == 'test': 136 | test(args) 137 | -------------------------------------------------------------------------------- /DUNet-retinal-vessel-detection/眼底血管分割实验报告.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/DUNet-retinal-vessel-detection/眼底血管分割实验报告.pdf -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # 医学影像作业 2 | 3 | - 医学影像配准，读论文作报告 4 | - 眼底血管分割，读论文做实验 -------------------------------------------------------------------------------- /Reading-list/registration-paper/1903.03545.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/registration-paper/1903.03545.pdf -------------------------------------------------------------------------------- /Reading-list/registration-paper/1908.02738.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/registration-paper/1908.02738.pdf -------------------------------------------------------------------------------- /Reading-list/registration-paper/An Unsupervised Learning Model for Deformable Medical Image Registration.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/registration-paper/An Unsupervised Learning Model for Deformable Medical Image Registration.pdf -------------------------------------------------------------------------------- /Reading-list/registration-paper/VoxelMorph A Learning Framework for Deformable Medical Image Registration.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/registration-paper/VoxelMorph A Learning Framework for Deformable Medical Image Registration.pdf -------------------------------------------------------------------------------- /Reading-list/registration-paper/医学影像报告-第14组.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/registration-paper/医学影像报告-第14组.pdf -------------------------------------------------------------------------------- /Reading-list/segmentation-paper/[10] Deep_Layer_Aggregation_CVPR_2018_paper.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/segmentation-paper/[10] Deep_Layer_Aggregation_CVPR_2018_paper.pdf -------------------------------------------------------------------------------- /Reading-list/segmentation-paper/[1] Adaptive histogram equalization and its variations-影印版.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/segmentation-paper/[1] Adaptive histogram equalization and its variations-影印版.pdf -------------------------------------------------------------------------------- /Reading-list/segmentation-paper/[1] Adaptive histogram equalization and its variations-扫描版.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/segmentation-paper/[1] Adaptive histogram equalization and its variations-扫描版.pdf -------------------------------------------------------------------------------- /Reading-list/segmentation-paper/[2] Contrast Limited Adaptive Histogram Equalization.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/segmentation-paper/[2] Contrast Limited Adaptive Histogram Equalization.pdf -------------------------------------------------------------------------------- /Reading-list/segmentation-paper/[3] Adaptive contrast enhancement using local region stretching.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/segmentation-paper/[3] Adaptive contrast enhancement using local region stretching.pdf -------------------------------------------------------------------------------- /Reading-list/segmentation-paper/[4] 眼底图像检测和分析系统的设计与开发_马青柯.caj: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/segmentation-paper/[4] 眼底图像检测和分析系统的设计与开发_马青柯.caj -------------------------------------------------------------------------------- /Reading-list/segmentation-paper/[5] 基于改进的U_Net眼底视网膜血管分割_梁礼明.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/segmentation-paper/[5] 基于改进的U_Net眼底视网膜血管分割_梁礼明.pdf -------------------------------------------------------------------------------- /Reading-list/segmentation-paper/[6] DUNet-A deformable network for retinal vessel segmentation.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/segmentation-paper/[6] DUNet-A deformable network for retinal vessel segmentation.pdf -------------------------------------------------------------------------------- /Reading-list/segmentation-paper/[7] Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/segmentation-paper/[7] Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification.pdf -------------------------------------------------------------------------------- /Reading-list/segmentation-paper/[8] UNet.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/segmentation-paper/[8] UNet.pdf -------------------------------------------------------------------------------- /Reading-list/segmentation-paper/[9] UNet++.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Allenem/MedicalImage/ababe10703629e44ce2aeddbe4405cab3ff1d55d/Reading-list/segmentation-paper/[9] UNet++.pdf --------------------------------------------------------------------------------