Object detection with FasterRCNN

Object detection using FasterRCNN model(s) (fasterrcnn_pytorch_api)

Model | Trainable | Inference | Pre-trained

Published by DEEP-Hybrid-DataCloud Consortium
Created: - Updated:

Model Description

Build Status

The module, fasterrcnn_pytorch_api, provides API access to the pipeline [1] for training FasterRCNN [2] models on custom datasets. The pipeline is implemented in PyTorch.

With this pipeline, you have the flexibility to choose between official PyTorch models trained on the COCO dataset [3], use any backbone from Torchvision classification models, or even define your own custom backbones. The trained models can be used for object detection tasks on your specific datasets.

The original pipeline is developed in the external repository [1]


[1] https://github.com/sovit-123/fasterrcnn-pytorch-training-pipeline

[2] Ren, S., et al, Faster R-CNN: Towards real-time object detection with region proposal networks, 2015, https://arxiv.org/abs/1506.01497 [cs.CV]

[3] Lin, T.Y., et al., Microsoft COCO: Common Objects in Context, 2014, http://arxiv.org/abs/1405.0312 [cs.CV]

Test this module

You can test and execute this module in various ways.

Excecute locally on your computer using Docker

You can run this module directly on your computer, assuming that you have Docker installed, by following these steps:

$ docker pull deephdc/deep-oc-fasterrcnn_pytorch_api
$ docker run -ti -p 5000:5000 deephdc/deep-oc-fasterrcnn_pytorch_api

Execute on your computer using udocker

If you do not have Docker available or you do not want to install it, you can use udocker within a Python virtualenv:

$ virtualenv udocker
$ source udocker/bin/activate
(udocker) $ pip install udocker
(udocker) $ udocker pull deephdc/deep-oc-fasterrcnn_pytorch_api
(udocker) $ udocker create deephdc/deep-oc-fasterrcnn_pytorch_api
(udocker) $ udocker run -p 5000:5000  deephdc/deep-oc-fasterrcnn_pytorch_api

In either case, once the module is running, point your browser to and you will see the API documentation, where you can test the module functionality, as well as perform other actions (such as training).

For more information, refer to the user documentation.

Train this module

You can train this model using the DEEP framework. In order to execute this module in our pilot e-Infrastructure you would need to be registered in the DEEP IAM.

Once you are registedered, you can go to our training dashboard to configure and train it.

For more information, refer to the user documentation.