I’m struggling on how to train my network on images without normalizing them first ? Because when I use ToTensor as a transform, it normalizes the images automatically.
Can anyone PLEASE help me out?
I’m struggling on how to train my network on images without normalizing them first ? Because when I use ToTensor as a transform, it normalizes the images automatically.
Can anyone PLEASE help me out?
Hi,
I think it can help:
try:
import accimage
except ImportError:
accimage = None
def _is_pil_image(img):
if accimage is not None:
return isinstance(img, (Image.Image, accimage.Image))
else:
return isinstance(img, Image.Image)
def _is_tensor_image(img):
return torch.is_tensor(img) and img.ndimension() == 3
def _is_numpy_image(img):
return isinstance(img, np.ndarray) and (img.ndim in {2, 3})
def my_to_tensor(pic):
"""Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor.
See ``ToTensor`` for more details.
Args:
pic (PIL Image or numpy.ndarray): Image to be converted to tensor.
Returns:
Tensor: Converted image.
"""
if not(_is_pil_image(pic) or _is_numpy_image(pic)):
raise TypeError('pic should be PIL Image or ndarray. Got {}'.format(type(pic)))
if isinstance(pic, np.ndarray):
# handle numpy array
if pic.ndim == 2:
pic = pic[:, :, None]
img = torch.from_numpy(pic.transpose((2, 0, 1)))
# backward compatibility
if isinstance(img, torch.ByteTensor):
return img.float() ###### removed .div(255)
else:
return img
if accimage is not None and isinstance(pic, accimage.Image):
nppic = np.zeros([pic.channels, pic.height, pic.width], dtype=np.float32)
pic.copyto(nppic)
return torch.from_numpy(nppic)
# handle PIL Image
if pic.mode == 'I':
img = torch.from_numpy(np.array(pic, np.int32, copy=False))
elif pic.mode == 'I;16':
img = torch.from_numpy(np.array(pic, np.int16, copy=False))
elif pic.mode == 'F':
img = torch.from_numpy(np.array(pic, np.float32, copy=False))
elif pic.mode == '1':
img = 255 * torch.from_numpy(np.array(pic, np.uint8, copy=False))
else:
img = torch.ByteTensor(torch.ByteStorage.from_buffer(pic.tobytes()))
# PIL image mode: L, LA, P, I, F, RGB, YCbCr, RGBA, CMYK
if pic.mode == 'YCbCr':
nchannel = 3
elif pic.mode == 'I;16':
nchannel = 1
else:
nchannel = len(pic.mode)
img = img.view(pic.size[1], pic.size[0], nchannel)
# put it from HWC to CHW format
# yikes, this transpose takes 80% of the loading time/CPU
img = img.transpose(0, 1).transpose(0, 2).contiguous()
if isinstance(img, torch.ByteTensor):
return img.float() ###### removed .div(255)
else:
return img
### test
class MyToTensor(object):
def __call__(self, pic):
return my_to_tensor(pic)
Note that, I have just copy pasted source code of ToTensor and removed the lines where images have been normalized using .div(255)
.
You can use this MyToTensor
instead of default ToTensor
in transofrms
.
Or another way will be to unnormalize tensors after using ToTensor
in transforms. Here it is:
def unnormalize(tensor):
return tensor.mul(255)
class Unnormalize(object):
def __call__(self, tensor):
return unnormalize(tensor)
img = Image.open('img.jpg')
img_tensor_normalized = transforms.ToTensor()(img)
img_tensor = Unnormalize()(img_tensor_normalized)
As before, you can add Unnormalize
in your transforms pipepline after ToTensor()
.
Bests