Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[DOC] Add SlowFast example in demo README.md #2867

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[DOC] Add SlowFast example in demo README.md #2867

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 17 additions & 1 deletion demo/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -444,7 +444,7 @@ Examples:

Assume that you are located at `$MMACTION2` .

1. Use the Faster RCNN as the human detector, SlowOnly-8x8-R101 as the action detector. Making predictions per 8 frames, and output 1 frame per 4 frames to the output video. The FPS of the output video is 4.
1. Use the Faster RCNN as the human detector, SlowOnly-8x8-R101 (AVA 2.1) as the action detector. Making predictions per 8 frames, and output 1 frame per 4 frames to the output video. The FPS of the output video is 4.

```shell
python demo/demo_spatiotemporal_det.py demo/demo.mp4 demo/demo_spatiotemporal_det.mp4 \
Expand All @@ -460,6 +460,22 @@ python demo/demo_spatiotemporal_det.py demo/demo.mp4 demo/demo_spatiotemporal_de
--output-fps 6
```

Alternatively, use SlowFast-8x8-R101 (AVA 2.2) as the action detector.

```shell
python demo/demo_spatiotemporal_det.py demo/demo.mp4 demo/demo_spatiotemporal_det.mp4 \
--config configs/detection/slowfast/slowfast_r50-k400-pre-temporal-max-focal-alpha3-gamma1_8xb6-8x8x1-cosine-10e_ava22-rgb.py \
--checkpoint https://download.openmmlab.com/mmaction/v1.0/detection/slowfast/slowfast_r50-k400-pre-temporal-max-focal-alpha3-gamma1_8xb6-8x8x1-cosine-10e_ava22-rgb/slowfast_r50-k400-pre-temporal-max-focal-alpha3-gamma1_8xb6-8x8x1-cosine-10e_ava22-rgb_20220906-dd59e26f.pth \
--det-config demo/demo_configs/faster-rcnn_r50_fpn_2x_coco_infer.py \
--det-checkpoint http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_2x_coco/faster_rcnn_r50_fpn_2x_coco_bbox_mAP-0.384_20200504_210434-a5d8aa15.pth \
--det-score-thr 0.9 \
--action-score-thr 0.5 \
--label-map tools/data/ava/label_map.txt \
--predict-stepsize 8 \
--output-stepsize 4 \
--output-fps 6
```

## SpatioTemporal Action Detection ONNX Video Demo

MMAction2 provides a demo script to predict the SpatioTemporal Action Detection result using the onnx file instead of building the PyTorch models.
Expand Down