FaceBoxes.PyTorch icon indicating copy to clipboard operation
FaceBoxes.PyTorch copied to clipboard

A PyTorch Implementation of FaceBoxes

Results 19 FaceBoxes.PyTorch issues
Sort by recently updated
recently updated
newest added

@zisianw HI I ran it exactly according to the training code. but I only have one card (1080TI), and the other parameters did not change at all. Training 28h. My...

hello. If i want to test with image size 1024x1024. What I must do in this code. {boxes = decode(loc.data.squeeze(0), prior_data, cfg['variance']) boxes = boxes * scale / resize boxes...

hello. thanks for your source code. My English is poor, please sympathize I have run your program. I want to ask about size of image when I test. Why in...

Hi, I want to train this network with landmark task. When will the training code with landmarks be released? Or any advice on how to accomplish this task?

https://github.com/zisianw/FaceBoxes.PyTorch/blob/master/utils/box_utils.py#L102 truths: (tensor) Ground truth boxes, Shape: [num_obj, 4].

The threshold given to NMS (0.3) is far too low and includes many false positives. If someone wanted to see them, they can set the value themselves but I think...

Improves faceboxes test scores on major benchmarks PASCAL: 97.05% -> 97.28% AFW: 98.55% -> 98.83% I really didn't like these magic numbers for each dataset, so instead I targeted a...

Hello, I want to download your pre-trained model but it did not exist. Would you send me or upload it again? I hope I will receive your reply soon.