search

VIPL-SLP / pointlstm-gesture-recognition-pytorch

This repo holds the codes of paper: An Efficient PointLSTM for Point Clouds Based Gesture Recognition (CVPR 2020).
https://openaccess.thecvf.com/content_CVPR_2020/html/Min_An_Efficient_PointLSTM_for_Point_Clouds_Based_Gesture_Recognition_CVPR_2020_paper.html
Apache License 2.0
121 stars 20 forks source link

Error running file nvidia_process.py #27

Open nemolfie opened 2 years ago

nemolfie commented 2 years ago

When I run the nvidiaprocess.py , program error is "ValueError: too many values to unpack (expected 4) " and the error line is ", npypath, label, = r.split(npy_path) ". Excuse me, what's wrong with this, please.

ycmin95 commented 2 years ago

You can check the return value of r.split(npy_path), npy_path and label are expected to obtain from it.

nemolfie commented 2 years ago

您可以检查 r.split(npy_path) 的返回值，npy_path 和 label 期望从中获得。

Excuse me, there is a another problem , when I run the program "nvidia_dataloader.py" , in the line 106 , it has an unassign variable "BaseFeeder" . I'd like to know if this is a code shortage or something else, please.

ycmin95 commented 2 years ago

It seems that "nvidia_dataloader.py" has 32 lines.

nemolfie commented 2 years ago

似乎“nvidia_dataloader.py”有 32 行。

the error line is "feeder = BaseFeeder(framerate=80)" but I can not find the BaseFeeder before the code.

ycmin95 commented 2 years ago

OK, I got it. It is in the nvidia_dataloader.py file, which is used for debugging in the previous version, you can simply change the BaseFeeder to NvidiaFeeder. But it should only report an error when you run the nvidia_dataloader.py file (nvidia_dataloader.py is not supposed to be run individually expect to debug, which is called during model training).