You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Files and versions

Updated 1 year ago


Action Classification with Pytorchvideo

Author: Jael Gu


An action classification operator is able to predict labels of human activities (with corresponding scores) and extracts features given the input video. 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 and maps vectors with labels provided by the Kinetics400 Dataset.

Code Example

Use the pretrained SLOWFAST model ('slowfast_r50') to classify and generate a vector for the given video path './archery.mp4' (download).

Write a pipeline with explicit inputs/outputs name specifications:

from towhee import pipe, ops, DataCollection

p = (
        .map('path', 'frames', ops.video_decode.ffmpeg())
        .map('frames', ('labels', 'scores', 'features'),
        .output('path', 'labels', 'scores', 'features')


Factory Constructor

Create the operator via the following factory method

action_classification.pytorchvideo( model_name='x3d_xs', skip_preprocess=False, classmap=None, topk=5)


model_name: str

​ The name of pre-trained model from pytorchvideo hub.

​ Supported model names:

  • c2d_r50
  • i3d_r50
  • slow_r50
  • slowfast_r50
  • slowfast_r101
  • x3d_xs
  • x3d_s
  • x3d_m
  • mvit_base_16x4
  • mvit_base_32x3

skip_preprocess: bool

​ Flag to control whether to skip UniformTemporalSubsample in video transforms, defaults to False. If set to True, the step of UniformTemporalSubsample will be skipped. In this case, the user should guarantee that all the input video frames are already reprocessed properly, and thus can be fed to model directly.

classmap: Dict[str: int]:

​ Dictionary that maps class names to one hot vectors. If not given, the operator will load the default class map dictionary.

topk: int

​ The topk labels & scores to present in result. The default value is 5.


Given a video data, the video classification operator predicts a list of class labels and generates a video embedding in numpy.ndarray.


frames: List[VideoFrame]

​ Video frames in towhee.types.video_frame.VideoFrame.


labels, scores, features: Tuple(List[str], List[float], numpy.ndarray)

  • labels: predicted class names.
  • scores: possibility scores ranking from high to low corresponding to predicted labels.
  • features: a video embedding in shape of (num_features,) representing features extracted by model.
Jael Gu 4c2989a9db Remove dc2 20 Commits
file-icon .gitattributes
1.1 KiB
Initial commit 2 years ago
file-icon README.md
2.9 KiB
Remove dc2 1 year ago
file-icon __init__.py
696 B
Add files 2 years ago
file-icon kinetics_400.json
10 KiB
Add files 2 years ago
file-icon pytorchvideo.py
5.8 KiB
Enable cuda 2 years ago
file-icon requirements.txt
88 B
Specify pytorchvideo version supporting all models 2 years ago
file-icon result.png
15 KiB
Update README 1 year ago