inputing numpy array images into pytorch neural net

Question

I have a numpy array representation of an image and I want to turn it into a tensor so I can feed it through my pytorch neural network.

I understand that the neural networks take in transformed tensors which are not arranged in [100,100,3] but [3,100,100] and the pixels are rescaled and the images must be in batches.

So I did the following:

import cv2
my_img = cv2.imread('testset/img0.png')
my_img.shape #reuturns [100,100,3] a 3 channel image with 100x100 resolution
my_img = np.transpose(my_img,(2,0,1))
my_img.shape #returns [3,100,100] 
#convert the numpy array to tensor
my_img_tensor = torch.from_numpy(my_img)
#rescale to be [0,1] like the data it was trained on by default 
my_img_tensor *= (1/255)
#turn the tensor into a batch of size 1
my_img_tensor = my_img_tensor.unsqueeze(0)
#send image to gpu 
my_img_tensor.to(device)
#put forward through my neural network.
net(my_img_tensor)

However this returns the error:

RuntimeError: _thnn_conv2d_forward is not implemented for type torch.ByteTensor

Piyush Chauhan · Accepted Answer · 2018-12-13 19:40:56Z

4

The problem is that the input you give to your network is of type ByteTensor while only float operations are implemented for conv like operations. Try the following

my_img_tensor = my_img_tensor.type('torch.DoubleTensor')
# for converting to double tensor

Source PyTorch Discussion Forum

Thanks to AlbanD

answered Dec 13, 2018 at 19:40

Piyush Chauhan

8361 gold badge9 silver badges21 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

wawawewa Over a year ago

It was actually FloatTensor, but thank you, your comment lead me to finding the answer.

Collectives™ on Stack Overflow

inputing numpy array images into pytorch neural net

1 Answer 1

1 Comment

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

1 Comment

Your Answer

Sign up or log in

Post as a guest

Related