Welcome to MMPose’s documentation!¶
Datasets
Model Zoo
- Overview
- Top Down Models
- Imagenet classification with deep convolutional neural networks
- Convolutional pose machines
- Distribution-aware coordinate representation for human pose estimation
- Stacked hourglass networks for human pose estimation
- Deep high-resolution representation learning for human pose estimation
- Mobilenetv2: Inverted residuals and linear bottlenecks
- Rethinking on multi-stage networks for human pose estimation
- ResNeSt: Split-Attention Networks
- Simple baselines for human pose estimation and tracking
- ResNetV1D
- Aggregated residual transformations for deep neural networks
- Learning delicate local representations for multi-person pose estimation
- Improving Convolutional Networks with Self-Calibrated Convolutions
- Squeeze-and-excitation networks
- Shufflenet: An extremely efficient convolutional neural network for mobile devices
- Shufflenet v2: Practical guidelines for efficient cnn architecture design
- The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Bottom Up Models
- Hand Models
- Mesh Models
Tutorials
Useful Tools and Scripts
Notes