[INFO] Saving Training Data
Traceback (most recent call last):
File "main_train.py", line 54, in
main_train()
File "main_train.py", line 35, in main_train
dataloader.prepare_dataset()
File "/home/mir/Optic-Disc-Unet/experiments/data_loaders/standard_loader.py", line 69, in prepare_dataset
imgs_val, groundTruth = self._access_dataset(self.val_img_path, self.val_groundtruth_path, self.val_type)
File "/home/mir/Optic-Disc-Unet/experiments/data_loaders/standard_loader.py", line 48, in _access_dataset
imgs[index,:,:,0]=np.asarray(orgImg[:,:,1]*0.75+orgImg[:,:,0]*0.25)
ValueError: could not broadcast input array from shape (400,599) into shape (400,600)

thank you for your share, i try to run your code, but it appear one error:
first,i want to know your image, gt are 1D in your dataset?
In standard_loader.py , 47 line code : orgImg=plt.imread(orgPath) ,it will produce 2D array,
but 48 line code : imgs[index,:,:,0]=np.asarray(orgImg[:,:,1]*0.75+orgImg[:,:,0]*0.25), it appear one
error , too many index! and i don't know what you want in this line code?

Traceback (most recent call last):
File "main_test.py", line 40, in
main_test()
File "main_test.py", line 28, in main_test
infer.predict()
File "C:\Users\vcvis\Desktop\Optic-Disc-Unet-master\perception\infers\segmention_infer.py", line 51, in predict
_, contours, _ = cv2.findContours(binaryResult, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
ValueError: not enough values to unpack (expected 3, got 2)

please help
thank you

Why is the probability output of the test results almost close to 1 when I am training with your project, the test picture is close to white paper?

Thanks for sharing your work.
Please share your Pretrained Weights for this work for further analysis, as it would help me and verify your results.
I really appreciate it if you answer these questions. Thanks very much.

Hi!
First of all, thank you very much for sharing your code!

I would to train it with my own data set. Could you explain me what things should I change?
Only in segmention_config.json? And what mean each variable?
Sorry for so much question!

This is the error i get when testing the code. I am using the specified version of libraries as mentioned in the segmentation template.

how to train on my own dataset?