3df2eaf74d8f2299ca05e3e98cab5bf89dafc249,cnn_visualisation.py,,preprocess_image,#Any#,91

Before Change

    means = [0.485, 0.456, 0.406]
    stds = [0.229, 0.224, 0.225]

    preprocessed_img = img.copy()[:, :, ::-1]
    for i in range(3):
        preprocessed_img[:, :, i] = preprocessed_img[:, :, i] - means[i]
        preprocessed_img[:, :, i] = preprocessed_img[:, :, i] / stds[i]
    preprocessed_img = \
        np.ascontiguousarray(np.transpose(preprocessed_img, (2, 0, 1)))
    preprocessed_img = torch.from_numpy(preprocessed_img)
    preprocessed_img.unsqueeze_(0)
    input = Variable(preprocessed_img, requires_grad=True)
    return input

After Change

    // Transpose to obtain D-W-H
    im_as_arr = im_as_arr.transpose(2, 0, 1)
    // Normalize the channels
    for channel, _ in enumerate(im_as_arr):
        im_as_arr[channel] /= 255
        im_as_arr[channel] -= mean[channel]
        im_as_arr[channel] /= std[channel]
    // Convert to float tensor
    im_as_ten = torch.from_numpy(im_as_arr).float()
    // Add one more channel to the beginning. Tensor shape = 1,3,224,224
    im_as_ten.unsqueeze_(0)
    // Convert to Pytorch variable

Instances