modifty output from video-decode from Image to VideoFrame

README.md

@@ -29,11 +29,11 @@ import towhee
 towhee.dc(['./demo_video.mp4']) \
         .video_decode.ffmpeg(sample_type='uniform_temporal_subsample', args={'num_samples': 12}) \
         .runas_op(func=lambda x: [y for y in x]) \
-        .clip4clip(model_name='clip_vit_b32', modality='video', weight_path='./pytorch_model.bin.1') \
+        .clip4clip(model_name='clip_vit_b32', modality='video', weight_path='./pytorch_model.bin.1', device='cpu') \
         .show()
 
 towhee.dc(['kids feeding and playing with the horse']) \
-      .clip4clip(model_name='clip_vit_b32', modality='text', weight_path='./pytorch_model.bin.1') \
+      .clip4clip(model_name='clip_vit_b32', modality='text', weight_path='./pytorch_model.bin.1', device='cpu') \
       .show()
 ```
 ![](vect_simplified_video.png)   
@@ -47,11 +47,11 @@ import towhee
 towhee.dc['path'](['./demo_video.mp4']) \
         .video_decode.ffmpeg['path', 'frames'](sample_type='uniform_temporal_subsample', args={'num_samples': 12}) \
         .runas_op['frames', 'frames'](func=lambda x: [y for y in x]) \
-        .clip4clip['frames', 'vec'](model_name='clip_vit_b32', modality='video', weight_path='./pytorch_model.bin.1') \
+        .clip4clip['frames', 'vec'](model_name='clip_vit_b32', modality='video', weight_path='./pytorch_model.bin.1', device='cpu') \
         .show()
 
 towhee.dc['text'](["kids feeding and playing with the horse"]) \
-      .clip4clip['text','vec'](model_name='clip_vit_b32', modality='text', weight_path='./pytorch_model.bin.1') \
+      .clip4clip['text','vec'](model_name='clip_vit_b32', modality='text', weight_path='./pytorch_model.bin.1', device='cpu') \
       .select['text', 'vec']() \
       .show()
 ```