Name: MAX-Sports-Video-Classifier
Owner: International Business Machines
Description: Classify sport videos
Created: 2018-03-09 23:20:35.0
Updated: 2018-05-17 20:39:18.0
Pushed: 2018-03-20 23:09:27.0
Homepage: null
Size: 3265
Language: Python
GitHub Committers
User | Most Recent Commit | # Commits |
---|
Other Committers
User | Most Recent Commit | # Commits |
---|
This repository contains code to instantiate and deploy a video classification model. The model recognizes the 487 different classes of sports activities in the Sports-1M Dataset. The model consists of a deep 3-D convolutional net that was trained on the Sports-1M dataset. The input to the model is a video, and the output is a list of estimated class probabilities.
The model is based on the C3D TensorFlow Model. The model files are hosted on IBM Cloud Object Storage. The code in this repository deploys the model as a web service in a Docker container. This repository was developed as part of the IBM Code Model Asset Exchange.
| Domain | Application | Industry | Framework | Training Data | Input Data Format | | ————- | ——– | ——– | ——— | ——— | ————– | | Vision | Video Classification | General | TensorFlow | Sports-1M | Video (MPEG-4)|
| Component | License | Link | | ————- | ——– | ——– | | This repository | Apache 2.0 | LICENSE | | Model Weights | MIT | C3D-TensorFlow | | Model Code (3rd party) | MIT | C3D-TensorFlow | | Test assets | Various | Asset README |
docker
: The Docker command-line interface. Follow the installation instructions for your system.Clone this repository locally. In a terminal, run the following command:
t clone https://github.com/IBM/MAX-Sports-Video-Classifier.git
Change directory into the repository base folder:
MAX-Sports-Video-Classifier
To build the docker image locally, run:
cker build -t max-tf-c3d .
All required model assets will be downloaded during the build process. Note that currently this docker image is CPU only (we will add support for GPU images later).
To run the docker image, which automatically starts the model serving API, run:
cker run -it -p 5000:5000 max-tf-c3d
The API server automatically generates an interactive Swagger documentation page. Go to http://localhost:5000
to load it. From there you can explore the API and also create test requests.
Use the model/predict
endpoint to load a test video file and get predicted labels for the video from the API.
You can also test it on the command line, for example:
rl -F "video=@assets/basketball.mp4" -XPOST http://127.0.0.1:5000/model/predict
son
tatus": "ok",
redictions": [
{
"label_id": "367",
"label": "basketball",
"probability": 0.39916181564331
},
{
"label_id": "370",
"label": "streetball",
"probability": 0.16513635218143
},
{
"label_id": "369",
"label": "3x3 (basketball)",
"probability": 0.11865037679672
}
To run the Flask API app in debug mode, edit config.py
to set DEBUG = True
under the application settings. You will then need to rebuild the docker image (see step 1).