I have a pytorch tensor, let’s say
images, of type
<class 'torch.Tensor'> and of size
torch.Size([32, 3, 300, 300]), so that
images[i, :, :, :] represents the i-th out of 32 rgb 300x300 images.
I would like to plot some of these images, let’s say the first one, i.e.,
images[0, :, :, :] using opencv (
cv2.imshow()). Could you help? Thank you!
You can call
images.numpy() to get the numpy array, which can be visualized using OpenCV.
Thanks for your response. I tried that but I got an opencv error (
Source image must have 1, 3 or 4 channels in function cvConvertImage)… It seemed to me that it would be trivial, but it isn’t…
Sorry, my bad. You have to permute the axis:
images.numpy().transpose(1, 2, 0)
images.permute(1, 2, 0).numpy()
I see. Thank you very much, it worked!
Why can’t we use torch tensors directly with Open cv without converting them to numpy? I run cv2.kmeans on large images and they’re very slow. Wondering if being able to run them on Tensors would be faster.
after converting your torch tensor back to opencv ndarray, if you do an imshow the image will appear slightly darker due to standard normalization.
def inverse_normalize(tensor, mean, std):
for t, m, s in zip(tensor, mean, std):
input = inverse_normalize(tensor=input, mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225))
you should inverse normalize your torch tensor before converting to numpy array if the image colours matter to you
I think opencv-python package support CPU-only. So, we need to change cuda tensor to cpu.