vendor/ViTPose/demo/docs/2d_human_pose_demo.md

2D Human Pose Demo

2D Human Pose Top-Down Image Demo

Using gt human bounding boxes as input

We provide a demo script to test a single image, given gt json file.

python demo/top_down_img_demo.py \
    ${MMPOSE_CONFIG_FILE} ${MMPOSE_CHECKPOINT_FILE} \
    --img-root ${IMG_ROOT} --json-file ${JSON_FILE} \
    --out-img-root ${OUTPUT_DIR} \
    [--show --device ${GPU_ID or CPU}] \
    [--kpt-thr ${KPT_SCORE_THR}]

Examples:

python demo/top_down_img_demo.py \
    configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/coco/hrnet_w48_coco_256x192.py \
    https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w48_coco_256x192-b9e0b3ab_20200708.pth \
    --img-root tests/data/coco/ --json-file tests/data/coco/test_coco.json \
    --out-img-root vis_results

To run demos on CPU:

python demo/top_down_img_demo.py \
    configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/coco/hrnet_w48_coco_256x192.py \
    https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w48_coco_256x192-b9e0b3ab_20200708.pth \
    --img-root tests/data/coco/ --json-file tests/data/coco/test_coco.json \
    --out-img-root vis_results \
    --device=cpu

Using mmdet for human bounding box detection

We provide a demo script to run mmdet for human detection, and mmpose for pose estimation.

Assume that you have already installed mmdet.

python demo/top_down_img_demo_with_mmdet.py \
    ${MMDET_CONFIG_FILE} ${MMDET_CHECKPOINT_FILE} \
    ${MMPOSE_CONFIG_FILE} ${MMPOSE_CHECKPOINT_FILE} \
    --img-root ${IMG_ROOT} --img ${IMG_FILE} \
    --out-img-root ${OUTPUT_DIR} \
    [--show --device ${GPU_ID or CPU}] \
    [--bbox-thr ${BBOX_SCORE_THR} --kpt-thr ${KPT_SCORE_THR}]

Examples:

python demo/top_down_img_demo_with_mmdet.py \
    demo/mmdetection_cfg/faster_rcnn_r50_fpn_coco.py \
    https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth \
    configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/coco/hrnet_w48_coco_256x192.py \
    https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w48_coco_256x192-b9e0b3ab_20200708.pth \
    --img-root tests/data/coco/ \
    --img 000000196141.jpg \
    --out-img-root vis_results

2D Human Pose Top-Down Video Demo

We also provide a video demo to illustrate the results.

Assume that you have already installed mmdet.

python demo/top_down_video_demo_with_mmdet.py \
    ${MMDET_CONFIG_FILE} ${MMDET_CHECKPOINT_FILE} \
    ${MMPOSE_CONFIG_FILE} ${MMPOSE_CHECKPOINT_FILE} \
    --video-path ${VIDEO_FILE} \
    --out-video-root ${OUTPUT_VIDEO_ROOT} \
    [--show --device ${GPU_ID or CPU}] \
    [--bbox-thr ${BBOX_SCORE_THR} --kpt-thr ${KPT_SCORE_THR}]

Examples:

python demo/top_down_video_demo_with_mmdet.py \
    demo/mmdetection_cfg/faster_rcnn_r50_fpn_coco.py \
    https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth \
    configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/coco/hrnet_w48_coco_256x192.py \
    https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w48_coco_256x192-b9e0b3ab_20200708.pth \
    --video-path demo/resources/demo.mp4 \
    --out-video-root vis_results

2D Human Pose Bottom-Up Image Demo

We provide a demo script to test a single image.

python demo/bottom_up_img_demo.py \
    ${MMPOSE_CONFIG_FILE} ${MMPOSE_CHECKPOINT_FILE} \
    --img-path ${IMG_PATH}\
    --out-img-root ${OUTPUT_DIR} \
    [--show --device ${GPU_ID or CPU}] \
    [--kpt-thr ${KPT_SCORE_THR} --pose-nms-thr ${POSE_NMS_THR}]

Examples:

python demo/bottom_up_img_demo.py \
    configs/body/2d_kpt_sview_rgb_img/associative_embedding/coco/hrnet_w32_coco_512x512.py \
    https://download.openmmlab.com/mmpose/bottom_up/hrnet_w32_coco_512x512-bcb8c247_20200816.pth \
    --img-path tests/data/coco/ \
    --out-img-root vis_results

2D Human Pose Bottom-Up Video Demo

We also provide a video demo to illustrate the results.

python demo/bottom_up_video_demo.py \
    ${MMPOSE_CONFIG_FILE} ${MMPOSE_CHECKPOINT_FILE} \
    --video-path ${VIDEO_FILE} \
    --out-video-root ${OUTPUT_VIDEO_ROOT} \
    [--show --device ${GPU_ID or CPU}] \
    [--kpt-thr ${KPT_SCORE_THR} --pose-nms-thr ${POSE_NMS_THR}]

Examples:

python demo/bottom_up_video_demo.py \
    configs/body/2d_kpt_sview_rgb_img/associative_embedding/coco/hrnet_w32_coco_512x512.py \
    https://download.openmmlab.com/mmpose/bottom_up/hrnet_w32_coco_512x512-bcb8c247_20200816.pth \
    --video-path demo/resources/demo.mp4 \
    --out-video-root vis_results

Speed Up Inference

Some tips to speed up MMPose inference:

For top-down models, try to edit the config file. For example,

1. set flip_test=False in topdown-res50.
2. set post_process='default' in topdown-res50.
3. use faster human bounding box detector, see MMDetection.

For bottom-up models, try to edit the config file. For example,

1. set flip_test=False in AE-res50.
2. set adjust=False in AE-res50.
3. set refine=False in AE-res50.
4. use smaller input image size in AE-res50.