Closed k-apos closed 3 years ago
Thanks for your interest. Are you using patch-wise learning or a single image?
Thanks for your interest. Are you using patch-wise learning or a single image?
I am testing a single image.
You need to patch your image and then apply the model on patches. Please see the evaluation code to find out more details. The model trained using patches, thus, whole image performance should be weak.
Thank you very much for the immediate response!
When I run evaluate.py I exchange weight_lstm.hdf5 with pretrained weight_retina.hdf5 and I get this error:
Traceback (most recent call last):
File "C:/Users/Asus/PycharmProjects/BCDU-Net-df7258bdfeab3a5258f1d6913182aaab4a0008be/Retina Blood Vessel Segmentation/evaluate.py", line 103, in
'No such file or directory' means that it did not find your weight file. Make sure about the path to weight file
Thank you very much!!
Hello sir,
Thank you very much for this great repository. I used pretrained models for DRIVE dataset but i received a wrong mask. I have done the image grayscale before input and then I take this result. Αm i doing something wrong?
Thank you in advance