Computer Vision Toolbox Model for Inflated-3D Video Classification
Pretrained Inflated-3D model for Video Classification
The model is pre-trained on the Kinetics-400 dataset that contains the Inception-V1 network as the backbone architecture with separate models for RGB and Optical Flow video data. Out-of-the-box video classification support for 400 action classes from Kinetics-400 dataset.
MATLAB 版本兼容性
- 兼容 R2021b 到 R2026a 的版本
平台兼容性
- Windows
- macOS (Apple 芯片)
- macOS (Intel)
- Linux
