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
| Config | Params(M) | RES | FLOPS (G) | FP32(fps) | FP16(fps) | train-split | mIoU - val | mIoU - test | model |
|---|---|---|---|---|---|---|---|---|---|
| MV3-Small + PSP + FFM | 1.74 | 2048x1024 | 11.63 | 40.85 | 54.50 | train | 0.662 | 0.6388 | file (6.86MB) |
| MV3-Small + PSP + FFM | 1.74 | 1024x512 | 2.91 | 78.79 | 71.74 | train | 0.615 | - | file (6.86MB) |
| MV3-Small + PSP + FFM | 1.74 | 2048x1024 | 11.63 | 40.85 | 54.50 | train + val | 0.717 | 0.6559 | file (6.86MB) |
| MV3-Small + PSP + FFM | 1.74 | 1024x512 | 2.91 | 78.79 | 71.74 | train + val | 0.646 | - | file (6.86MB) |
Note: Params and FLOPS are got using torchstat.
- Add mobilenetv3 large
- Improve performance.
- Add more configurations support.