souryuu

I did not use tensorboard to visualize the predicted mask. However it seems that you forget to pass the mask value to the final sigmoid fuction before visualizing it.

I thought tf.sigmoid(outputs['mask']['mask']) should do a fine work. However, it did not work when I tried to visualize masks on tensorboard. So I wrote another visualization function using PIL to...

If you use the code in my fork without any modification, your batch normalization should not be properly trained up until now because update_bn in config_v1.py was set to False....

@realwecan Yes it should be something like that. However, in the latest version on "fix_testing" branch, all "is_training" in train.py and test.py are already set to True and False respectively....

@realwecan Yes I encountered that in the early stage of training. Afterward, it gradually reduced. Setting learning rate and loss weight too high should temporary increase the regular loss. However,...

@realwecan in pyramid_networks line 272, setting only_positive flag in sample_rpn_outputs to False should solve your issue. It is the flag to filter rois with RPN's confidence value < 0.5 for...

@lengly Check if update_bn in config_v1.py is set to True during training. If not, set it to True and train the network again.

It works fine for me. During training, did "target" and "predicted" match ? If no, I think your RCNN did not learn well. you can keep RPN and begin training...

I am not sure about how the original maskrcnn create the target rois for training. From the current version of code, it seems that rois from RPN will be match...

@realwecan For me it seems that large portion of the images contain person in it (both in term of size and frequency). Also after I trained it up to some...