facebookresearch / facebookresearch/SlowFast

Run the Demo on Videos/Camera

Open
#330 2 comments 4 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
7.4k
Forks
1.3k
PR merge metrics
No merged PRs in 30d

Description

When I was running the video visualization, I use the pre-training model and was prompted to complete the demo. However, when I observed the output video, there was no category label, which was no different from the original video. Could you tell me why?Looking forward to your reply.
Tip is:
2it [00:16, 11.43s/it][11/17 19:09:28][INFO] predictor.py: 47: Finish loading model weights
4it [00:17, 4.30s/it]
[11/17 19:09:28][INFO] demo_net.py: 119: Finish demo in: 17.204275846481323
My configuration is your original configuration,demo/Kinetics/Slowfast_8x8_R50.yaml.I added the configuration at the end:
DEMO:
ENABLE: True
LABEL_FILE_PATH: /home/pjw/dataset/kinetics_classnames.json # Add local label file path here.
#WEBCAM: 0
INPUT_VIDEO: /home/pjw/dataset/eating_hotdog/0G27MoNN_iM_000192_000202.mp4
OUTPUT_FILE: 5.mp4
NUM_VIS_INSTANCES: 2
NUM_CLIPS_SKIP: 5
NUM_GPUS: 2
NUM_SHARDS: 1
RNG_SEED: 0
OUTPUT_DIR: /home/pjw/output

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.