We uploaded the pretrained models described in this paper including ResNet-50 pretrained on the combined dataset with Kinetics-700 and Moments in Time. We significantly updated our scripts. If you want to use older versions to reproduce our CVPR2018 paper, you should use the scripts in the CVPR2018 branch.
Features
- Pre-trained models
- Requires PyTorch (ver. 0.4+ required)
- Requires FFmpeg, FFprobe
- Requires Python 3
- Download videos and train/test splits
- Generate annotation file in json format similar to ActivityNet
Categories
Machine LearningLicense
MIT LicenseFollow 3D ResNets for Action Recognition
You Might Also Like
Act! Premium is perfect for small and midsize businesses looking to market better, sell more, and create customers for life. With unparalleled flexibility and freedom of choice, Act! Premium accommodates the unique ways you do business. Whether it’s customizations to fit your specific business or industry processes or your preferences for deployment and access, the possibilities with Act! Premium are limitless.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of 3D ResNets for Action Recognition!