logo
Browse Source

Update README

Signed-off-by: Jael Gu <mengjia.gu@zilliz.com>
main
Jael Gu 2 years ago
parent
commit
bf8f12596f
  1. 10
      README.md

10
README.md

@ -1,4 +1,4 @@
# Video Classification with Pytorchvideo
# Action Classification with Pytorchvideo
*Author: [Jael Gu](https://github.com/jaelgu)* *Author: [Jael Gu](https://github.com/jaelgu)*
@ -6,7 +6,7 @@
## Description ## Description
A video classification operator is able to predict labels (and corresponding scores)
An action classification operator is able to predict labels of human activities (with corresponding scores)
and extracts features given the input video. and extracts features given the input video.
It preprocesses video frames with video transforms and then loads pre-trained models by model names. It preprocesses video frames with video transforms and then loads pre-trained models by model names.
This operator has implemented pre-trained models from [Pytorchvideo](https://github.com/facebookresearch/pytorchvideo) This operator has implemented pre-trained models from [Pytorchvideo](https://github.com/facebookresearch/pytorchvideo)
@ -27,7 +27,7 @@ import towhee
( (
towhee.glob('./archery.mp4') towhee.glob('./archery.mp4')
.video_decode.ffmpeg() .video_decode.ffmpeg()
.video_classification.pytorchvideo(model_name='slowfast_r50')
.action_classification.pytorchvideo(model_name='slowfast_r50')
.show() .show()
) )
``` ```
@ -41,7 +41,7 @@ import towhee
( (
towhee.glob['path']('./archery.mp4') towhee.glob['path']('./archery.mp4')
.video_decode.ffmpeg['path', 'frames']() .video_decode.ffmpeg['path', 'frames']()
.video_classification.pytorchvideo['frames', ('labels', 'scores', 'features')](
.action_classification.pytorchvideo['frames', ('labels', 'scores', 'features')](
model_name='slowfast_r50') model_name='slowfast_r50')
.select['labels', 'scores', 'features']() .select['labels', 'scores', 'features']()
.show(formatter={'path':'video_path'}) .show(formatter={'path':'video_path'})
@ -55,7 +55,7 @@ import towhee
Create the operator via the following factory method Create the operator via the following factory method
***video_classification.pytorchvideo(
***action_classification.pytorchvideo(
model_name='x3d_xs', skip_preprocess=False, classmap=None, topk=5)*** model_name='x3d_xs', skip_preprocess=False, classmap=None, topk=5)***
**Parameters:** **Parameters:**

Loading…
Cancel
Save