Codes-for-Lane-Detection/ENet-Label-Torch at master · cardwing/Codes-for-Lane-Detection

README.md

Torch, please follow the installation instructions at fb.resnet.torch.
Matlab (for tools/prob2lines), version R2014a or later.
Opencv (for tools/lane_evaluation), version 2.4.8 (later 2.4.x should also work).
Hardware: For testing, GPU with 3G memory suffices. For training, we recommend 4xGPU with 12G memory.

Please follow SCNN-Torch to put CULane in the desired folder. We'll call the directory that you cloned ENet-Label-Torch as $ENet_ROOT.

Download our trained models to ./experiments/pretrained
```
cd $ENet_ROOT/experiments/pretrained
```
Download the trained model here.
Run test script
```
cd $ENet_ROOT
sh ./experiments/test.sh
```
Testing results (probability map of lane markings) are saved in experiments/predicts/ by default.
Get curve line from probability map
```
cd tools/prob2lines
matlab -nodisplay -r "main;exit"  # or you may simply run main.m from matlab interface
```
The generated line coordinates would be saved in tools/prob2lines/output/ by default.
Calculate precision, recall, and F-measure
```
cd $ENet_ROOT/tools/lane_evaluation
make
sh Run.sh   # it may take over 30min to evaluate
```
Note: Run.sh evaluate each scenario separately while run.sh evaluate the whole. You may use calTotal.m to calculate overall performance from all senarios.
By now, you should be able to reproduce the result (F1-measure: 72.0).

Download the pre-trained model
```
cd $ENet_ROOT/experiments/models
```
Download the pre-trained model here and move it to $ENet_ROOT/experiments/models/vgg_SCNN_DULR_w9.
Training ENet-Label model
```
cd $ENet_ROOT
sh ./experiments/train.sh
```
The training process should start and trained models would be saved in experiments/models/vgg_SCNN_DULR_w9 by default.
Then you can test the trained model following the Testing steps above. If your model position or name is changed, remember to set them to yours accordingly.