-
-
My code runs and display two images but the segmentation is just very very poor similar to issue #24, can you see if I am calling the routines incorrectly.
```
image_batch_tensor = tf.expand_dims…
-
Thanks for your great code. I can reach 64% with FCN8sAtOnce. However, when I try to use the FCN8sAtOnce model for my task(only part of the code related to the use the FCN8sAtOnce), I get the ValueEr…
-
I have the same problem, all output results are zeros. Anyone can help ?
_Originally posted by @prfans in https://github.com/wkentaro/pytorch-fcn/issues/113#issuecomment-555805034_
I used the pr…
-
I have 2000 gray pictures. I need to segment the image to two parts,object and background.Now I want to use fcn to do the image segment.How can I fine tune the pretrained fcn models,like pascal-fcn8s-…
HLinn updated
6 years ago
-
When I try to train fcn8s_pascal.py, it always appears this issue. But if I train segnet_pacal.py, it works normally. Can anyone help me? I didn't change the .yml file provided by author.
-
When I trying to import FCN8s onnx model generated from PyTorch, the following error occurs:
"op_type {} is currently not supported for NNP conversion".
After checking the code, we found that this …
-
after the fcn32 was trained for 9 epochs, the output value score of it is still zero.
however, the weight of each layers are not zero. i am wondering if somebody has suggestions to fix this problem.
-
How can I load FCN8 weights for a network with a different ouput than the one used to train original FCN8 on VOC dataset?
I downloaded the `fcn8s_from_caffe.pth` file and I want to load those weigh…
-
Why ？When I finished training， the runs dir have no pkl file generated？Just a events file， a yml file， a log file。