U-Help

Does the weighted sum of APr, APc, APf equal to AP?

Hi, I use the pretrain_model in this Github repository to test mask_rcnn_r50_fpn_1x_lvis_agnostic, however, I get only very bad result, can you give some suggestion? 

About classification accuracy

1

Hello, I'm confused that how you get the curve of classificaiton accuracy per class in inference. Can you give me some suggestions or share the code?

About baseline model

4

I have great interest in your work, and I want to ask a question. Does the baseline model also use sigmoid loss function rather than softmax loss function?

Well, in your paper, there are results on different frameworks and models, including R-50-C4 and R-101-C4. But in this repo, you don't provide relevant results. I try to implement this...

I follow your install guide and run the training code with "./tools/dist_train.sh configs/lvis/forest_rcnn_r50_fpn.py 1 --validate". However, it always ends with the following error:  Can you explain the reason?

NMS Resampling-Linear

1

In the paper, the equation for NMS Resampling-Linear is as following:  But, in my opinion, for xi in frequent classes, threshold should be alpha_f+...