Chen-Lin Zhang

Hi, I just downloaded the feature from Google Drive. And when use tar to extract features, it looks like: `tar: This does not look like a tar archive` Do you...

Training Error

8

Hi, I tried your code to reproduce the coviar result in your paper. I followed all your instructions in GET_START.md But I met this error: ` v_frame_idx = random.randint(seg_begin,seg_end -...

Problems in Converting PNASNet_mobile to pytorch

1

Hi, I just want to use your code to convert PNASNet_mobile models to PyTorch. After modifiing your code with both PNASNet.pytorch and PNASNet.TF, I find that the accuracy is slow...

Machine Translation Save and Load model problem

10

Hello, While playing with the machine translation example I came across an unexpected crash. I can't reload the previous train model and see Warning. When I come across the code...

multi-gpu or distributed training failed

1

Hi, I try to use pynvvl to do multi-GPU training. But it seems that it will fail. `CUDA runtime error 3 at line 15 in file /nvvl/src/detail/Decoder.cpp: initialization error CUDA...

Variable Type Error

2

When I tried to run this example, it get the following error: _v = _l2normalize(torch.matmul(_u, W.data), eps=1e-12) return torch.mm(tensor1, tensor2) RuntimeError: mm(): argument 'mat2' (position 1) must be Variable, not...

add the first verson custom dataset.md

2

Add a guide with custom dataset (using THUMOS14 as the example)

slow speed on torch.DataParallel models

1

Hi, I try to use this framework to compute FFT with torch.DataParallel(model) but it seems that with the same batch_size in one GPU and 4 GPUs, the fft will consume...