Integrate KEEP model with RunPod Serverless #21
Conversation
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
This commit introduces the necessary files and modifications to enable the KEEP model to run on RunPod Serverless. Key changes: - Added `handler.py`: Contains the serverless handler function to process video URLs using the KEEP model. It includes logic for video downloading, frame processing, model inference, and output generation. - Created `Dockerfile`: Defines the Docker image for the RunPod Serverless environment, including all dependencies, application code, and pre-trained model downloads. - Updated `requirements.txt`: Added `runpod` package and ensured all other necessary dependencies are listed. These changes allow you to deploy the KEEP model as a serverless endpoint on RunPod, accepting video URLs as input and returning processed videos.
This commit updates several model download URLs in the Dockerfile to address build failures due to broken or incorrect links. Changes include: - YOLOv5 face models (yolov5n-face.pth, yolov5l-face.pth) now download from the jnjaby/KEEP GitHub releases. - GMFlow model (gmflow_sintel-0c07dcb3.pth) download has been removed as a reliable URL was not found and handler.py does not strictly require it. - Facelib models (detection_Resnet50_Final.pth, detection_mobilenet0.25_Final.pth, parsing_parsenet.pth) now download from the jnjaby/KEEP GitHub releases. - Download paths for Facelib models standardized. - Retry mechanism (--tries=3) for wget remains in place.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This commit introduces the necessary files and modifications to enable the KEEP model to run on RunPod Serverless.
Key changes:
handler.py: Contains the serverless handler function to process video URLs using the KEEP model. It includes logic for video downloading, frame processing, model inference, and output generation.Dockerfile: Defines the Docker image for the RunPod Serverless environment, including all dependencies, application code, and pre-trained model downloads.requirements.txt: Addedrunpodpackage and ensured all other necessary dependencies are listed.These changes allow you to deploy the KEEP model as a serverless endpoint on RunPod, accepting video URLs as input and returning processed videos.