MobilePose
MobilePose is a Tiny PyTorch implementation of single person 2D pose estimation framework. The aim is to provide the interface of the training/inference/evaluation, and the dataloader with various data augmentation options. And final trained model can satisfy basic requirements(speed+size+accuracy) for mobile device.
Some codes for networks and display are brought from:
NEWS!
Mar 2019: Support running on MacBook with decent FPS!
Feb 2019: ALL the pretrained model files are avaliable!
Requirements
Python 3.7
PyTorch 1.0
Evaluation Results
Model(+DUC+DSNTNN)
Parmas(M)
Flops(G)
AP@0.5:0.95
AP@0.5
AR@0.5:0.95
AR@0.5
Link
ResNet18
12.26
1.64
68.2
93.9
79.7
96.7
MobileNetV2
3.91