Last active
September 29, 2024 14:11
-
-
Save maulikmadhavi/7da97c8754ba23ad90c7a9543afd03b3 to your computer and use it in GitHub Desktop.
decord efficient video reading
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import decord | |
| import numpy as np | |
| class EfficientVideoReader: | |
| def __init__(self, video_path, skip_frames=1, max_frames=None, batch_size=32): | |
| """ | |
| Initialize the EfficientVideoReader. | |
| Args: | |
| video_path (str): Path to the video file | |
| skip_frames (int): Number of frames to skip between reads | |
| max_frames (int): Maximum number of frames to read (None for all frames) | |
| batch_size (int): Number of frames to read in each batch | |
| """ | |
| decord.bridge.set_bridge('numpy') | |
| self.vr = decord.VideoReader(video_path) | |
| self.total_frames = len(self.vr) | |
| self.skip_frames = skip_frames | |
| self.max_frames = min(max_frames or self.total_frames, self.total_frames) | |
| self.batch_size = batch_size | |
| self.indices = np.arange(0, self.max_frames, skip_frames) | |
| def __iter__(self): | |
| """Make the class iterable.""" | |
| self.current_index = 0 | |
| return self | |
| def __next__(self): | |
| """Get the next frame.""" | |
| if self.current_index >= len(self.indices): | |
| raise StopIteration | |
| batch_end = min(self.current_index + self.batch_size, len(self.indices)) | |
| batch_indices = self.indices[self.current_index:batch_end] | |
| frames = self.vr.get_batch(batch_indices).asnumpy() | |
| self.current_index = batch_end | |
| return frames | |
| def __len__(self): | |
| """Return the total number of frames to be read.""" | |
| return len(self.indices) | |
| @property | |
| def frame_shape(self): | |
| """Return the shape of the video frames.""" | |
| return self.vr[0].shape | |
| def reset(self): | |
| """Reset the reader to the beginning of the video.""" | |
| self.current_index = 0 | |
| # Usage example | |
| def process_video(video_path, model): | |
| reader = EfficientVideoReader(video_path, skip_frames=2, max_frames=1000, batch_size=32) | |
| print(f"Processing {len(reader)} frames, shape: {reader.frame_shape}") | |
| for batch in reader: | |
| for frame in batch: | |
| # Your ML model inference here | |
| # result = model.predict(frame) | |
| pass | |
| # Assuming you have a ML model | |
| # model = load_your_ml_model() | |
| # process_video('path/to/your/video.mp4', model) | |
| # To use this in your ML demonstration: | |
| # 1. Create an instance of `EfficientVideoReader` with your desired parameters. | |
| # 2. Iterate over the reader to process frames in batches. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment