R2Plus1D-C3D icon indicating copy to clipboard operation
R2Plus1D-C3D copied to clipboard

Published 20 hours ago • verified publisher icon leftthomas
→

Metadata

A PyTorch implementation of R2Plus1D and C3D based on CVPR 2017 paper "A Closer Look at Spatiotemporal Convolutions for Action Recognition" and CVPR 2014 paper "Learning Spatiotemporal Features with 3...

Results 4 R2Plus1D-C3D issues
Sort by recently updated
recently updated
newest added

where is the split1 file?

lilinhan1998 avatar lilinhan1998

请问这个有解决办法吗

![image](https://user-images.githubusercontent.com/22213368/140634300-dc4e8461-2f03-4cc5-a718-d04c838f0f62.png)

Heroism502 avatar Heroism502

I train R2Plus1D on the UCF101(I only select 51 classes) from scratch. The val acc is only 40%.

I train it on a sigle gpu(v100), and I don't adjust the parameter settings in the code.

hhc1997 avatar hhc1997

KeyError: 'calligraphy'

Hi, I want tot train codes with kinetics600, but when I run `!visdom -logging_level WARNING & python train.py --batch_size 2 --num_epochs 1 --data_type 'kinetics600'` I faced with this error: "KeyError:...

tahiira avatar tahiira

← Metadata

57
Stars
14
Forks
Watchers

Owner

verified publisher icon leftthomas

Metadata

A PyTorch implementation of R2Plus1D and C3D based on CVPR 2017 paper "A Closer Look at Spatiotemporal Convolutions for Action Recognition" and CVPR 2014 paper "Learning Spatiotemporal Features with 3...

Back