janicevidal / PyTorchCV

Repo for most of CV problems, such as image classification, object detection, pose estimation, segmentation, and so on.

Source code for Deep Learning Based CV Problems(Pytorch)

@misc{CV2018,
  author =       {Donny You ([e-mail])},
  howpublished = {\url{https://github.com/CVBox/PytorchCV}},
  year =         {2018}
}

This repository provides source code for some deep learning based cv problems. We'll do our best to keep this repository up to date. If you do find a problem about this repository, please raise it as an issue. We will fix it immediately.

Details:

• Pose Estimation

  • Convolutional Pose Machines
  • Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
  • Associative Embedding: End-to-End Learning for Joint Detection and Grouping

• Object Detection

  • SSD: Single Shot MultiBox Detector

• Semantic Segmentation

  • Efficient ConvNet for Real-time Semantic Segmentation

• Image Classification

  • Densely Connected Convolutional Networks

Examples

• Train the openpose model

python main.py  --hypes hypes/pose/coco/op_coco_pose.json \
                --base_lr 0.001 \
                --phase train

• Finetune the openpose model

python main.py  --hypes hypes/pose/coco/op_coco_pose.json \
                --base_lr 0.001 \
                --phase train \
                --resume checkpoints/pose/coco/coco_open_pose_65000.pth

• Test the openpose model(test_img):

python main.py  --hypes hypes/pose/coco/op_coco_pose.json \
                --phase test \
                --resume checkpoints/pose/coco/coco_open_pose_65000.pth \
                --test_img val/samples/ski.jpg

• Test the openpose model(test_dir):

python main.py  --hypes hypes/pose/coco/op_coco_pose.json \
                --phase test \
                --resume checkpoints/pose/coco/coco_open_pose_65000.pth \
                --test_dir val/samples

• Attention: Other command line parameters are showed in main file. You can refer & use them.