WangDong

training data selection

1

In the function *get_top_confidences* in *matcher.py*, you choose the top_k confidences bounding boxes including background, I think it is not a good strategy, it may lead to train negative examples...

How to generate prior_boxes_ssd300.pkl

4

Hi, your implementation is really great! But I have a question. If I want to detect some small objects and I want to detect from conv3, should I change prior_boxes_ssd300.pkl?...

advice for the way of naming weights

1

Thanks for your great work. In your provided pre-trained weights for detectron2, I notice that the names of tensors start with `backbone.bottom_up` (eg. `backbone.bottom_up.stem.conv1_1.weight`), and I can not directly use...