search

XinyiYing / D3Dnet

Repository for "Deformable 3D Convolution for Video Super-Resolution", SPL, 2020
Apache License 2.0
305 stars 43 forks source link

about dataloader #21

Closed reminayano closed 3 years ago

reminayano commented 3 years ago

after for idx_iter, (LR, HR, SR_buicbic) in enumerate(test_loader):(test.py, line 29) I printed LR.size(), and result was torch.Size([1, 1, 7, 144, 176]). Can you tell me what does each tensor dimension refer to? especially, 1, 1, 7.

XinyiYing commented 3 years ago

[1, 1, 7, 144, 176] represent the batch size, the channel size, the number input frames (temporal length), the height and the width respectively.

reminayano commented 3 years ago

I understood, thank you very much.