Getting -1 for map using VOC07+12 Trainval

[Alina-liu]

Hi,thank you for your code,I'm new on this ,I use your net and change the baseline to resnext using resnext50 which is convertied from caffe model ,but I get -1 mAP for all classes,can you tell me why? Thank you and please forgive my poor English!

[liusai92]

I encounted this issue too, I checked the weights I trained, there are lots of nan in the scope of res3_5, Top-Down, RPN, Fast-RCNN, is it just a hyperparameter problem? I also found that I didn't restore all weights in Resnet50.npy, especially batch-normalization layer's weights 'mean, variance', should them be restored to graph variables beta, gamma?

[imyhxy]

The same problem here, which version of tensorflow you are using?

[rxqy]

there might some difference between these models ie, maybe caffe pretrain model requires input normalization. while the origin one doesn't

[Alina-liu]

I used the tensorflow 1.0.1,does this version lead to the problem? @imyhxy

[imyhxy]

@Alina-liu I am not sure, but I used the tensorflow 1.8.

[zhangtongton]

The same problem here, has it solved? thx @Alina-liu @imyhxy