pytorch-yolo-v3

pytorch-yolo-v3 copied to clipboard

I see that `letterbox_image` are used in both `detect.py` and `video_demo.py`. But in the `cam_demo.py`, images are simply resized without keeping the aspect ratio. Anybody knows the reason? Thanks!

bearpaw

Performance fps?

2

Has anyone tested the performance of the pytorch implementation where the C implementation using the same configuration?

apiszcz

fix #66

bearpaw

Traceback (most recent call last): File "detect.py", line 118, in model.load_weights(args.weightsfile) File "D:\Skripsi\pytorch-yolo-v3\darknet.py", line 477, in load_weights conv_weights = conv_weights.view_as(conv.weight.data) RuntimeError: shape '[1024, 512, 3, 3]' is invalid for input...

miscla

The separator in Windows is "\\" and in Linux is "/", so this line will be invalid on Win system ``` det_names = pd.Series(imlist).apply(lambda x: "{}/det_{}".format(args.det,x.split("/")[-1])) ``` and I modified...

liuslnlp

I'm on windows and i read that i had to change line 306 of detect.py , and that's what i'v done. , but how or where can i see the...

AntoineMath

about the training code

2

Hello,When will the training code be published?

strive1127

rambo

How to load pre-trained model

3

Hi, I do like your code which help me understand the YOLO framework. But it is regretful that there are no training process. Now I'm trying to write the training...

liliangqi

S601327412