DFANet

Model description

An extremely efficient CNN architecture named DFANet for semantic segmentation under resource constraints. It starts from a single lightweight backbone and aggregates discriminative features through sub-network and sub-stage cascade respectively. Based on the multi-scale feature propagation, DFANet substantially reduces the number of parameters. But it still obtains sufficient receptive field and enhances the model learning ability, which strikes a balance between the speed and segmentation performance.

Step 1: Installing

Install packages

pip3 install 'scipy' 'matplotlib' 'pycocotools' 'opencv-python' 'easydict' 'tqdm'

Step 2: Training

Preparing datasets

Go to visit COCO official website, then select the COCO dataset you want to download.

Take coco2017 dataset as an example, specify /path/to/coco2017 to your COCO path in later training process, the unzipped dataset path structure sholud look like:

coco2017
├── annotations
│   ├── instances_train2017.json
│   ├── instances_val2017.json
│   └── ...
├── train2017
│   ├── 000000000009.jpg
│   ├── 000000000025.jpg
│   └── ...
├── val2017
│   ├── 000000000139.jpg
│   ├── 000000000285.jpg
│   └── ...
├── train2017.txt
├── val2017.txt
└── ...

Training on COCO dataset

bash train_dfanet_xceptiona_dist.sh --data-path /path/to/coco2017/ --dataset coco

Reference

Ref: https://github.com/LikeLy-Journey/SegmenTron Ref: torchvision