3D-ResNets-PyTorch

3D-ResNets-PyTorch copied to clipboard

can not find opts.json

4

HI, when I run the main.py it show me: that I "can not find opts.json in results path". I also can not run following command: "python main.lua -h"

Atrin4000

I don't have the JSON file

7

I'd like to use this model using the Japanese dataset as follows: https://actions.stair.center/ But I don't have an annotation JSON file for the below option. --annotation_path kinetics.json Please tell me...

kpis-msa

I want to test the accuracy of the training model with my own video. I tried to write the code that can load the model and test my own video,...

harddrad

Is there a simple way to get inference results on video files that are not part of the considered data sets?

2

Any hint would be welcome, including, if necessary, how to patch the code for that. Thanks for sharing this excellent work. Best regards, Georges.

quenot

visualization！！！

1

How to visualize 3D CNN? For example, the visualization of thermodynamic diagram.

slighting666

Hi, Thanks for your source it was awesome. But I need to train action for new videos. It is possible to train our custom videos with these models. If possible...

suravijayjilla

GPU utilization rate and distribution training

1

when I use distribution training on GPUs, the process ids are the same and the GPU utilization rate is zero.  

byrsongyuxin

how to predict the label using webcam

5

I want to predict the class label using webcam. so I got the frame of webcam image, then put it to model. ``` frame = torch.tensor(frame) output = model(frame) ```...

junmin98

RUN```util_scripts/generate_video_jpgs.py```,but get nothing.

5

I obey the code in README.md to run ``util_scripts/generate_video_jpgs.py``, but the new floder I created to put jpgs has nothing. whether the path of floder l created is wrong. Can...

huamgmin

error in generating ucf101.json

1

When I generated ucf101.json, the following problems occurred “pandas.errors.ParserError : Error tokenizing data. C error: Expected 9 fields in line 3, saw 13” then I changed here： def load_ labels(label_...

N00k0428