Chestnut

I happend to this problem too

I have found that error comes from that maybe you did not generate the right format of json file.

but if we have two class to classified, the patches for training sometimes just have class 1, so the weights of class 2 will be zero. because the samples are...

@hgaiser hi~ I am now following this work and I also use resnet50 to replace the VGG16. I wonder the 5stage is trainable now? will it came to the out...

@Oh233 hi~ i am train on my own data. about 12s/iter on K80, is it something wrong happend?

@Oh233 thank you ! i set a timer in mnc_data_layer to see which part to slow speed but in show that get_next_minibatch did not take too long. i wonder if...

@Oh233 hi~ I wonder why the cfg.GPU_ID would influence the values output from the nms? thank you in advance !

thank you！ I just replace the VGG with the resnet50