cory8249 comments

Results 11 comments of


                                            cory8249

Missing Documentation

+1 please help give some hint about how to use the code. Thanks a lot.

Slower than Caffe at test time

I want to build a real-time video object detection system, so input are fed one by one continuously. I originally used "caffe time" script command to benchmark, but I found...

Slower than Caffe at test time

I simply use im_detect() in a for loop. I found that it will create testDB (seemed not necessary for my app), so I am going to modify it myself.

Box_Mask question

I think these codes are not necessary if you follow #23. You can remove all these default number. Just let it initialized to zeros: `_boxes = np.zeros([hw, num_anchors, 4], dtype=np.float)`...

mAP

I slightly change this code (following original YOLO training procedure), and train 160 epoch on VOC07+12, test on VOC07-test, evaluated mAP with 416 x 416 resolution 0.6334, batch size 16...

mAP

@JesseYang Sorry to let you misunderstand, 0.768 mAP is not trained by me. I just mention it as reference.

I fix the [IoU bug](https://github.com/longcw/yolo2-pytorch/issues/19), and train on VOC0712 trainval. Get mAP = 0.6825 (still increase slowly) [https://github.com/cory8249/yolo2-pytorch/blob/master/darknet.py#L120](https://github.com/cory8249/yolo2-pytorch/blob/master/darknet.py#L120)