lity

@ruotianluo Thank you very much. I get this point. I have trained res101 on COCO with your scripts(using tf pretrained model). However, I got 32 mAP. It seems a little...

@ruotianluo Besides, I checked the original paper of ResNet and found the result on COCO 2015 competition was about 27.2(without any tricks). So I feel confused about what result should...

@Superlee506 Thanks a lot. In fact, I want to use mask rcnn to predict keypoints in clothes. I have two questions: 1. Due to the different formats of train/test data,...

@Superlee506 Sorry, I cannot find the ‘issue’ in your repository. Do you open the issue function in your setting?