search

leeyeehoo / CSRNet-pytorch

CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
642 stars 259 forks source link

how are normalized parameters calculated? #33

Closed rongliangzi closed 4 years ago

rongliangzi commented 5 years ago

Thanks for the released code! we can see there are normalization in both train and test as follows:

transforms.Compose([
                       transforms.ToTensor(),transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                     std=[0.229, 0.224, 0.225]),
                   ])

so why do we need normalization? how are the parameters 'mean' & 'std' calculated?

rongliangzi commented 5 years ago

I get it. It's illustrated in pytorch tutorial as here