TPN

TPN copied to clipboard

how to download ckpt

1


RERRRER

Expected 5-dimensional input for 5-dimensional weight 64 3 1 7 7, but got 4-dimensional input of size [8, 3, 256, 256] instead

2

I have downloaded kinetics400_tpn_r50f32s2.pth in google drive which is provided and run this command: `python ./test_video.py config_files/kinetics400/tpn/r50f32s2.py ckpt/kinetics400_tpn_r50f32s2.pth` it showed this: `Expected 5-dimensional input for 5-dimensional weight 64 3 1...

MichaelWU0726

What role does this module play? The input and output data have not changed after processing by the module. looking forward to your replay ,thanks.

tvshow5727

img_group shape=`(4, 3, 10, 224, 224)` # NCTHW After operator: [img_group.reshape((-1,) + img_group.shape[2:])](https://github.com/decisionforce/TPN/blob/117a4d187517f51ea914b17be8ac59ef1a36b594/mmaction/models/recognizers/TSN3D.py#L94), the shape of x is: `(12, 10, 224, 224)`, and leads to the error above in [here](https://github.com/decisionforce/TPN/blob/117a4d187517f51ea914b17be8ac59ef1a36b594/mmaction/models/tenons/backbones/resnet_slow.py#L397)....

Tramac

When I use the code to train, I met the problem. Traceback (most recent call last): File "/home/liuyh/pycharm-community-2021.2.2/plugins/python-ce/helpers/pydev/pydevd.py", line 1483, in _exec pydev_imports.execfile(file, globals, locals) # execute the script File...

liu0527aa

RuntimeError: Legacy autograd function with non-static forward method is deprecated

2

RuntimeError: Legacy autograd function with non-static forward method is deprecated. Please use new-style autograd function with static forward method. (Example: https://pytorch.org/docs/stable/autograd.html#torch.autograd.Function)

Note-Liu

Thanks for your contribution! But i still have some questions ,like this ! why training code different from the test code in the cls_head.py's forward method? ``` def forward(self, x):...

784682065

在PyTorch 1.7下,运行test_video.py报错:RuntimeError: Legacy autograd function with non-static forward method is deprecated.

4

# 运行环境: - CPU: Intel i7-10700K - GPU: RTX3090 - RAM: 64GB - 操作系统:Ubuntu 20.04.1 LTS - Python 3.6 - Pytorch 1.7.0 with CUDA 11.0 # 背景&现象: 由于Pytorch 1.3以下版本,不支持CUDA11,无法兼容30系GPU,所以使用了Pytorch1.7,运行demo时,输出如下错误: >...

HYJJJJJJJJ

Update _SimpleConsensus to use static autograd methods (for PyTorch >1.3)

4

Thank you so much for sharing your implementation of TPN! ## Problem I've been trying to get it to work in one of my own projects -- however, I ran...

tchang1997

Thanks for your contribution. In your paper there are 32 frames when evaluating Kinetics-400, both in R-50 and R-101. Could you please tell me did you also use 32 frames...

liming-ai