... Sample a given number of frame indices from the video. ... Args: ... clip_len (`int`): Total number of frames to sample. ... frame_sample_rate (`int`): Sample every n-th frame. ... seg_len (`int`): Maximum allowed index of sample's last frame. ... Returns: ... indices (`List[int]`): List of sampled frame indices ... ''' ... converted_len = int(clip_len * frame_sample_rate) ... end_idx = np.random.randint(converted_len, seg_len) ... start_idx = end_idx - converted_len ... indices = np.linspace(start_idx, end_idx, num=clip_len) ... indices = np.clip(indices, start_idx, end_idx - 1).astype(np.int64) ... return indices >>> # video clip consists of 300 frames (10 seconds at 30 FPS) >>> file_path = hf_hub_download( ... repo_id="nielsr/video-demo", filename="eating_spaghetti.mp4", repo_type="dataset" ... ) >>> container = av.open(file_path) >>> # sample 8 frames >>> indices = sample_frame_indices(clip_len=8, frame_sample_rate=1, seg_len=container.streams.video[0].frames) >>> video = read_video_pyav(container, indices) >>> processor = AutoProcessor.from_pretrained("microsoft/xclip-base-patch32") >>> model = AutoModel.from_pretrained("microsoft/xclip-base-patch32") >>> inputs = processor(videos=list(video), return_tensors="pt") >>> video_features = model.get_video_features(**inputs) ```NrP