UNet: semantic segmentation with PyTorch

Forked From github.com/milesial

Glomerulus Segmentation Notes

Changes to Repository and Summary

03/20:

Obtained Dice Score > 0.835 via Standard Segmentation of UNET provided by repository .

3/27:

Fixed issue of random-selected Validation images train.py; using roughly 20% of the established training images as the Validation images.
- Validation dataset is roughly 196 images.
Visualized data via tensorboard, image shown here:
Selected best model .pth file to analyze testing with.
Tested data and composed three images together.

Usage

Note : Use Python 3

Prediction

You can easily test the output masks on your images via the CLI.

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

> python predict.py -h
usage: predict.py [-h] [--model FILE] --input INPUT [INPUT ...]
                  [--output INPUT [INPUT ...]] [--viz] [--no-save]
                  [--mask-threshold MASK_THRESHOLD] [--scale SCALE]

Predict masks from input images

optional arguments:
  -h, --help            show this help message and exit
  --model FILE, -m FILE
                        Specify the file in which the model is stored
                        (default: MODEL.pth)
  --input INPUT [INPUT ...], -i INPUT [INPUT ...]
                        filenames of input images (default: None)
  --output INPUT [INPUT ...], -o INPUT [INPUT ...]
                        Filenames of ouput images (default: None)
  --viz, -v             Visualize the images as they are processed (default:
                        False)
  --no-save, -n         Do not save the output masks (default: False)
  --mask-threshold MASK_THRESHOLD, -t MASK_THRESHOLD
                        Minimum probability value to consider a mask pixel
                        white (default: 0.5)
  --scale SCALE, -s SCALE
                        Scale factor for the input images (default: 0.5)

You can specify which model file to use with --model MODEL.pth.

Training

> 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.

Tensorboard

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

aadarshjha / Pytorch-UNet