diff --git a/README.md b/README.md index 2928a75..cc3000e 100644 --- a/README.md +++ b/README.md @@ -19,36 +19,22 @@ and maps vectors with labels. Use the pretrained VideoSwinTransformer model ('swin_t_k400_1k') to classify and generate a vector for the given video path './archery.mp4' ([download](https://dl.fbaipublicfiles.com/pytorchvideo/projects/archery.mp4)). - *Write the pipeline in simplified style*: +*Write a pipeline with explicit inputs/outputs name specifications:* ```python -import towhee - -( - towhee.glob('./archery.mp4') - .video_decode.ffmpeg() - .action_classification.video_swin_transformer(model_name='swin_t_k400_1k') - .show() +from towhee.dc2 import pipe, ops, DataCollection + +p = ( + pipe.input('path') + .map('path', 'frames', ops.video_decode.ffmpeg()) + .map('frames', ('labels', 'scores', 'features'), + ops.action_classification.video_swin_transformer(model_name='swin_t_k400_1k')) + .output('path', 'labels', 'scores', 'features') ) -``` - - -
-*Write a same pipeline with explicit inputs/outputs name specifications:* - -```python -import towhee - -( - towhee.glob['path']('./archery.mp4') - .video_decode.ffmpeg['path', 'frames']() - .action_classification.video_swin_transformer['frames', ('labels', 'scores', 'features')](model_name='swin_t_k400_1k') - .select['path', 'labels', 'scores', 'features']() - .show(formatter={'path': 'video_path'}) -) +DataCollection(p('./archery.mp4')).show() ``` - +
diff --git a/result.png b/result.png new file mode 100644 index 0000000..9038c6d Binary files /dev/null and b/result.png differ diff --git a/result1.png b/result1.png deleted file mode 100644 index 95a6897..0000000 Binary files a/result1.png and /dev/null differ diff --git a/result2.png b/result2.png deleted file mode 100644 index 0807a75..0000000 Binary files a/result2.png and /dev/null differ