Sam

@esterglez Are you using the pre-trained model? if so you have to stop the last layer to be initialized from the pre-trained model. you have two options for this: define...

I have tried the training on pascal voc with batch size of 2, it requires almost 16 GB memory on GPU and for batch size 3, 18.5 GB. with batch...

@Lokyr I have the same problem and I guess it because my data is heavily unbalanced more towards the background with label 0. But I don't know how to apply...

@Lokyr Thanks for the answer, I get back to work with deeplab, I will try this and update you here.

@lixiang-ucas I am also trying to use this network for organ segmentation, could you manage to train the network on your data? so far all my predictions are in black...

@luciaL I have the same issue, may I know how did you solve it? below is the way that I did it, since My images consist of two class of...

@superxiaoying I have the same problem, I tried to replace the code given by @bittnt in TVG_CRFRNN_new_deploy.prototxt file but still I have the same problem. the running result for crfasrnn_demo.py...

@matthiasmace I have the same problem with loss_from_log. Have you solved it?

@farhanrw if you have a grayscale mask then it should be fine to have one number representing each class. But I'm not sure if we need to put class images...

@wuyang0329 Thanks for your reply.. then why it detects all the samples as sample in class 1? Currently, when I train the network all the predictions are white. (white color...