batch_input_cpu::error

[liutianling]

when I test a image, i get error as following:
File "test_on_one_image.py", line 43, in main
_batch_input_cpu[0,:,:,:] = (img)
RuntimeError: The expanded size of the tensor (320) must match the existing size (240) at non-singleton dimension 2
Others, when i solve the size error, it show the model error?
Could you tell me how to solve it ?
And I want to konw the version of the packages you using.
Thank you!

[yifjiang]

I pushed a quick fix. However, running "test_on_one_image.py" should require a GPU and I am currently unable to test it. If "test_on_one_image.py" still doesn't work, please let me know, and you can use "test_on_one_image_cpu.py" for now. That one has been tested with pyTorch ver 0.1.12 and torchvision ver 0.1.18 and only requires CPU.

[HsiaX]

I pushed a quick fix. However, running "test_on_one_image.py" should require a GPU and I am currently unable to test it. If "test_on_one_image.py" still doesn't work, please let me know, and you can use "test_on_one_image_cpu.py" for now. That one has been tested with pyTorch ver 0.1.12 and torchvision ver 0.1.18 and only requires CPU.

I'm sorry but I want to ask that torchvision is 0.1.18 or 0.1.8? I try to search for 0.1.18 but failed.

[FedericoBarone994]

i think is 0.1.8. Sorry for the misunderstanding

…

________________________________ Da: HsiaX <notifications@github.com> Inviato: domenica 7 aprile 2019 15:44 A: yifjiang/relative-depth-using-pytorch Cc: Federico Barone; Manual Oggetto: Re: [yifjiang/relative-depth-using-pytorch] batch_input_cpu::error (#5) I pushed a quick fix. However, running "test_on_one_image.py" should require a GPU and I am currently unable to test it. If "test_on_one_image.py" still doesn't work, please let me know, and you can use "test_on_one_image_cpu.py" for now. That one has been tested with pyTorch ver 0.1.12 and torchvision ver 0.1.18 and only requires CPU. I'm sorry but I want to ask that torchvision is 0.1.18 or 0.1.8? I try to search for 0.1.18 but failed. — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub<#5 (comment)>, or mute the thread<https://github.com/notifications/unsubscribe-auth/ApdGBIlGo8WkCVw7rWowg3WFgpTbA3jIks5vefZOgaJpZM4TrQrU>.