wfdubowen / retina-unet

眼底图像的血管分割

Retina-Unet

来源：https://github.com/orobix/retina-unet

此代码已经针对Python3进行了优化，数据集下载：http://www.isi.uu.nl/Research/Databases/DRIVE/
百度网盘数据集下载：https://pan.baidu.com/s/1UpQtbhgtVdlqc0QGbESx3A 密码：4l7v

有关代码内容讲解，请参见CSDN博客：
基于UNet的眼底图像血管分割实例：https://blog.csdn.net/u013063099/article/details/79981097

【注意】run_training.py与run_testing.py的实际作用为了让程序在后台运行，如果运行出现错误，可以运行src目录下的训练与预测文件。

retina-unet's Issues

dismatch of the data_format

Hello:
Thanks for your code. When i train as your code, i print the model and found your data_format is channel_first, but maxpooling is channel_last, so your channel dims is dismatch, i correct it and when i training, the loss can be down, but the val_acc always didn't change! Do you know why? i have check the input data and the mask groundtruth like you, and ensure it is no problem.

FileNotFoundError

执行 python retinaNN_tranning.py 报错

Traceback (most recent call last):
  File "retinaNN_training.py", line 100, in <module>
    visualize(group_images(patches_imgs_train[0:N_sample,:,:,:],5),'./'+name_experiment+'/'+"sample_input_imgs")#.show()
  File "C:\Users\user\Documents\repo\Retina-Unet\lib\help_functions.py", line 49, in visualize
    img.save(filename + '.png')
  File "C:\Users\user\unet\lib\site-packages\PIL\Image.py", line 2085, in save
    fp = builtins.open(filename, "w+b")
FileNotFoundError: [Errno 2] No such file or directory: './test/sample_input_imgs.png'