wmrenr

Thank you for great contribution! I want to know how I can apply it to some mainstream cnn network, such as Mask RCNN.

I found a problem, it is that there are several large occluded objects in my test set, and the model I trained cannot recognize and segment them.

Train with my own dataset

1

Thank you for your contribution! I use my own data set (about 1000 pieces) to train this network. and the AP verified by epochs previous times is 0. Is this...

Experiment on your own dataset

2

I want to conduct a single pixel attack experiment on my own data set. What should I do?

The training set and validation of Places2 dataset were not found!

Exception in Thread: ValueError: signal number 32 out of range

1

The online query said that the bug was a pit in Python 3.6？ What should I do ?

When I modify the loss function of loss_ bbox_ Init and loss_ bbox_ from GIoULoss to CIoULoss, which can be trained but the evaluation result is null . Can you...

what 's the mean of loss_sem?

Thank you for your great contribution! How can the central keypoints be visualized during testing？