how to run the this code using gpu

[sunguwei]

I found that it is a bit slow when I run this code. Then I check the usage of gpu and I found this code was run on the cpu. So I want to change the code to run on the gpu. But I found the type of weight of this model is torch.FloatTensor. Is that mean I cannot use the gpu to run this code directly? Is that any solution can help me to run this code on gpu?

Here is the error:
RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument #2 'weight'

[oyxhust]

I also meet this issue. Have you solve it?

[lianuo]

same issue

[BrightXiaoHan]

You can call .cuda() or to('gpu:0') to move model to gpu.
For example:

pnet = Pnet().cuda()
output = pnet(input_tensor)

[fuxuliu]

Like this, For example:
pnet.cuda() rnet.cuda() onet.cuda() offsets = output[0].cpu().data.numpy() probs = output[1].cpu().data.numpy()

finish the rest like that

[mayuanjason]

Hi sunguwei,

I just refactor this repo, you can check it in https://github.com/mayuanjason/MTCNN_face_detection_alignment_pytorch

It can run on GPU.

Here are some improvments I made:
• Transfer all numpy operation to torch operation, so that it can benefit from GPU acceleration.
• Automatic run on 'CPU' or 'GPU'.
• Based on the latest version of pytorch (1.3)
• Real-time face tracking