Preparation
-
Please see dataset/README.md to get more details about our datasets-VIL100
-
Please see INSTALL.md to install environment and evaluation tools
-
Before training, we should download datasets-VIL100 and models
-
datasets : https://pan.baidu.com/s/1NkP_5LMLTn6qsu9pSbyi0g - iy16
-
models : https://pan.baidu.com/s/1_o13TBbTf258-j7iACDS2Q - sgh2
- The first training stage loads the model: initial_STM
- The second training stage loads the model: resume STM and resume ATT
-
-
Put them under this structure
MMA-Net |----INSTALL.md |----README.md |----dataset |------|-----VIL100 |----models |----evaluation |----options.py |----libs |----requirements.txt |----train.py |----test.py
Training and Testing
-
To train the MMA network, run following command
python3 train.py --gpu ${GPU-IDS}
-
To test the MMA network, run following command
python3 test.py
The test results will be saved as indexed png file at
${root}/${output}/${valset}.Additionally, you can modify some setting parameters in
options.pyto change training configuration.
Evaluation
-
generate
accuracy,fp,fppython evaluate_acc.py # Please modify `pre_dir_name` and `json_dir_name` in evaluate_acc.py -
Install
CULane evaluation tools, please see INSTALL.md -
generate
F,mIoUevaluate_acc after the CULane evaluation tools are installed-
all pred txt files will be generated under
MMA-Net/evaluation/txt/pred_txtafter this steppython generate_iou_pred_txt.py # Please modify `pre_dir_name` and `json_path` in `generate_iou_pred_txt.py` -
results_MMAandtemp_MMAwill be generated underMMA-Net/evaluation/txt/results_txtafter this step.results_MMA: evaluation results of each sequencetemp_MMA: temporary files generated during evaluation, you can ignore thempython evaluate_iou.py # `data_root` should be set as your VIL-100 dataset path in `evaluate_iou.py` -
Attention!! if you want to evaluation results one more time, please delete all folders/files under
MMA-Net/evaluation/txt/results_txt.
-
36 Jan 5, 2023
5 Jun 27, 2022
3 Aug 17, 2022
3 Jul 7, 2022
4 Dec 30, 2022
35 Sep 7, 2022
1 Jan 14, 2022
13 Aug 18, 2022
47 Dec 16, 2022
39 Sep 20, 2022
39 Nov 23, 2022
27 Dec 8, 2022
52 Dec 19, 2022
45 Dec 12, 2022
64 Nov 19, 2022
233 Jan 6, 2023