This repository contains the implementation for a dual-path network with mobilenetv3-small backbone. I have used PSP module as the context aggregation block.

The Cityscapes dataset, which can be downloaded here.

NOTE: The code has been tested in Ubuntu 18.04, and requirements.txt contains all the nessary packages.

To train the model, we run train.py

python3 train.py --root Cityscapes_root_directory --model_path optional_param, to resume training from a checkpoint.

The trainer, also evaluates the model for every save and logs the results, but if evaluation needs to be done for a particular model, we run evaluate.py

python3 evaluate.py --root Cityscapes_root_directory --model_path saved_model_path_to_evaluate.

The evaluate_server.py evaluates the model, and store the segmentation masks in cityscapes_results folder created in the root path of the script. This is used for submiting the results to Cityscapes evaluation server.

python3 evaluate_server.py --root Cityscapes_root_directory --model_path saved_model_path_to_evaluate.

To visulaize the results, we run demo.py.

python3 demo.py --root Cityscapes_root_directory --model_path saved_model_path_to_run_demo.

To run inference on a single image, we run demo_single.py. Can run inference to any image given by img_path.

python3 demo_single.py --model_path saved_model_path_to_run_demo. --img_path optional_param, default is images/demo.png. 

The FPS metrics are evaluated on a RTX2070. And evaluation was done by single scale input images.

• Cityscapes

Note: Params and FLOPS are got using torchstat.

• Add mobilenetv3 large
• Improve performance.
• Add more configurations support.