A repo about simple usecase of CLIP (Contrastive Language-Image Pre-Training) of Open AI

1. main Demo code for using library open_clip
   Try to predict the text based on image
2. video_to_frame Simple code for cutting frames from a video
   The function extract_and_save_frames is used to cut some range of frames from a videos
3. VIFI_CLIP Demo code for using VIFI_CLIP, predict the text based on video
   Original notebook is run on Colab