Glone this repo// //Download the pretrained model and dataset from my baidunetdisk below //Put them into the project content //Create an environment and run:
pip install -r requirements.txt
To predict a single image and save it:
python predict.py -i image.jpg -o output.jpg
To predict a multiple images and show them without saving them:
python predict.py -i image1.jpg image2.jpg --viz --no-save
You can specify which model file to use with --model MODEL.pth/pt.
> python train.py -h
usage: train.py [-h] [-e E] [-b [B]] [-l [LR]] [-f LOAD] [-s SCALE] [-v VAL]
Train the UNet on images and target masks
optional arguments:
-h, --help show this help message and exit
-e E, --epochs E Number of epochs (default: 5)
-b [B], --batch-size [B]
Batch size (default: 1)
-l [LR], --learning-rate [LR]
Learning rate (default: 0.1)
-f LOAD, --load LOAD Load model from a .pth file (default: False)
-s SCALE, --scale SCALE
Downscaling factor of the images (default: 0.5)
-v VAL, --validation VAL
Percent of the data that is used as validation (0-100)
(default: 15.0)
By default, the scale is 0.5, so if you wish to obtain better results (but use more memory), set it to 1.
The input images and target masks should be in the data/imgs and data/masks folders respectively.
You can visualize in real time the train and test losses, the weights and gradients, along with the model predictions with tensorboard:
tensorboard --logdir=runs
You can find a reference training run with the Caravana dataset on TensorBoard.dev (only scalars are shown currently).