Passing batch of images for faster processing #9
Comments
|
Hello @Neltherion . Right now there isn't a way to process a batch of images, but I'll work on it. |
|
@ipazc Thanks. I'll be watching your progress... |
|
I'm curious, how fast is it on GPU, without batches? |
|
@Vermeille something like 40-60ms on 1920x1080 |
|
I also want this features, when will batch of images support be available? |
|
@ipazc are you still woking on it, or its a dead thing ? |
I tried on GPU instance on Google-colab. For 1280x720 image it took around a second, not at all fast as I was expecting initially %time _ = face_detector.detect_faces(image) CPU times: user 1.11 s, sys: 56.2 ms, total: 1.17 s Is it ok to have this high number?? |
Hi @ipazc, if possible will you be able to suggest by when we can expect this feature? |
|
@ipazc Still waiting for Batch level implementation, see if you can help |
…tch processing support - Completely refactored the MTCNN implementation following best coding practices. - Optimized code by removing unnecessary transpositions, resulting in faster computation. Fixes #22. - Transposed convolutional layer weights to eliminate the need for additional transpositions during preprocessing and postprocessing, improving overall efficiency. - Converted preprocessing and postprocessing functions into matrix operations to accelerate computation. Fixes #14, #110. - Added batch processing support to enhance performance for multiple input images. Fixes #9, #71. - Migrated network architecture to TensorFlow >= 2.12 for improved compatibility and performance. Fixes #80, #82, #90, #91, #93, #98, #104, #112, #114, #115, #116. - Extensively documented the project with detailed explanations of thresholds and parameters. Fixes #12, #41, #52, #57, #99, #122, #117. - Added support for selecting computation backends (CPU, GPU, etc.) with the `device` parameter. Fixes #23. - Added new parameters to control the result format (support for x1, y1, x2, y2 instead of x1, y1, width, height) and the ability to return tensors instead of dictionaries. Fixes #72. - Configured PyLint support to ensure code quality and style adherence. - Organized functions into specific modules (`mtcnn.utils.*` and `mtcnn.stages.*`) for better modularity. - Created Jupyter notebooks for visualization and ablation studies of each stage, allowing detailed exploration of layers, weights, and intermediate results. Fixes #88, #102. - Added a comprehensive training guide for the model. Fixes #35, #39. - Updated README with information on the new version, including the complete Read the Docs documentation that describes the process, theoretical background, and usage examples. Fixes #53, #73. - Configured GitHub Actions for continuous integration and delivery (CI/CD). - Fixed memory leak by switching to a more efficient TensorFlow method (`model(tensor)` instead of `model.predict(tensor)`). Fixes #87, #109, #121, #125, #128. - Made TensorFlow an optional dependency to prevent conflicts with user-installed versions. Fixes #95. - Added comprehensive unit tests for increased reliability and coverage.
Hi, First of all thanks so much for your effort in bringing MTCNN to Python in an easy usable way.
I wanted to know if there is a way to pass a batch of images (instead of just one image) to the GPU to increase the overall speed of face detections for lots of images.
Thanks again
The text was updated successfully, but these errors were encountered: