ram-api.mp4
This project is a Web API for Urban Scene Segmentation for Autonomous Car, using two models `Baseline` and `MTKT`, that can handle unsupervised domain adaptation (UDA) problem for multi-target datasets.
It is built upon the ResNet-101 backbone initialized with ImageNet pre-trained weights, conducted with PyTorch.
Our first Model `Baseline` strategy is to merge all target datasets into a single one and then deal as a single target.
our second model `MTKT` is a multi-target knowledge transfer, which has a target-specific teacher for each specific target that learns a target-agnostic model thanks to a multi-teacher/single-student distillation mechanism.
The UI for this api is found in Web-Application-Client-Flask repo.
✔️ Fine Segmentation for unlabeled or coarse segmentated image.
✔️ Segmentation with calculation of mIOU for labeled image.
The following tools were used in the REST-API project:
Before starting, you need to have Git, Python 3.7, torch and cuda installed.
Also pre-trained models can be downloaded here(https://github.com/valeoai/MTAF/releases) and put in <root_dir>/model
# Clone this project
$ git clone https://github.com/mohamedelmesawy/Web-API-FastAPI
# install FastAPI :
$ pip install fastapi
# Also install uvicorn to work as the server:
$ pip install "uvicorn[standard]"
# Run the Application main.py
$ uvicorn main:app --reloadBy RAM-Team: MOhamed ElMesawy, Afnan Hamdy, Rowan ElMahalawy, Ali Hassanin, and MOhamed Samaha
The pretrained models are borrowed from MTAF.