pra-dan
commented
4 years ago I can help you with the first part, the second part is a problem for me too! The results are divided between these 2 layers, the feature map dimensions of which, you have mentioned above. But I got the following for v3-tiny
| Layer | Feature map shape |
|---|---|
| detector/yolo-v3-tiny/Conv_12/BiasAdd/YoloRegion | (1, 255, 26, 26) |
| detector/yolo-v3-tiny/Conv_9/BiasAdd/YoloRegion | (1, 255, 13, 13) |
If you can justify why you don't get 255 and get 18, I can help you understanding the 255 value.
Hello @PINTO0309,
outputs = exec_net.infer(inputs={input_blob: prepimg}) I got two outputs and it's shape like (1,18,13,13) and (1,18,26,26). I want to know each number means. I also want to know how EntryIndex function work. I will appreciate your help with this question.