Charles Shan
Charles Shan
I also encountered this problem!
 Here is mine. I changed a picture and plot the YCbCr: I find it seams Y channel is good:
I FIX IT!!! because it used transform.Normalize We need to use inv_trans! ``` inv_trans = transforms.Compose([ transforms.Normalize(mean=[0., 0., 0.], std=[1/0.229, 1/0.224, 1/0.225]), # Recover the std transforms.Normalize(mean=[-0.485, -0.456, -0.406], std=[1.,...
同问
找到了,https://github.com/yangxue0827/RCNN,这个是更原始的 tensorflow 版本,里边数据是全的