pytorch_segmentation_models_trainer

Framework based on Pytorch, Pytorch Lightning, segmentation_models.pytorch and hydra to train semantic segmentation models using yaml config files as follows:

model:
  _target_: segmentation_models_pytorch.Unet
  encoder_name: resnet34
  encoder_weights: imagenet
  in_channels: 3
  classes: 1

loss:
  _target_: segmentation_models_pytorch.utils.losses.DiceLoss

optimizer:
  _target_: torch.optim.AdamW
  lr: 0.001
  weight_decay: 1e-4

hyperparameters:
  batch_size: 1
  epochs: 2
  max_lr: 0.1

pl_trainer:
  max_epochs: ${hyperparameters.batch_size}
  gpus: 0

train_dataset:
  _target_: pytorch_segmentation_models_trainer.dataset_loader.dataset.SegmentationDataset
  input_csv_path: /path/to/input.csv
  data_loader:
    shuffle: True
    num_workers: 1
    pin_memory: True
    drop_last: True
    prefetch_factor: 1
  augmentation_list:
    - _target_: albumentations.HueSaturationValue
      always_apply: false
      hue_shift_limit: 0.2
      p: 0.5
    - _target_: albumentations.RandomBrightnessContrast
      brightness_limit: 0.2
      contrast_limit: 0.2
      p: 0.5
    - _target_: albumentations.RandomCrop
      always_apply: true
      height: 256
      width: 256
      p: 1.0
    - _target_: albumentations.Flip
      always_apply: true
    - _target_: albumentations.Normalize
      p: 1.0
    - _target_: albumentations.pytorch.transforms.ToTensorV2
      always_apply: true

val_dataset:
  _target_: pytorch_segmentation_models_trainer.dataset_loader.dataset.SegmentationDataset
  input_csv_path: /path/to/input.csv
  data_loader:
    shuffle: True
    num_workers: 1
    pin_memory: True
    drop_last: True
    prefetch_factor: 1
  augmentation_list:
    - _target_: albumentations.Resize
      always_apply: true
      height: 256
      width: 256
      p: 1.0
    - _target_: albumentations.Normalize
      p: 1.0
    - _target_: albumentations.pytorch.transforms.ToTensorV2
      always_apply: true

To train a model with configuration path /path/to/config/folder and name test.yaml:

pytorch-smt --config-dir /path/to/config/folder --config-name test +mode=train

The mode can be stored in configuration yaml as well. In this case, do not pass the +mode= argument. If the mode is stored in the yaml and you want to overwrite the value, do not use the + clause, just mode= .

This module suports hydra features such as configuration composition. For further information, please visit https://hydra.cc/docs/intro

Install

If you are not using docker and if you want to enable gpu acceleration, before installing this package, you should install pytorch_scatter as instructed in https://github.com/rusty1s/pytorch_scatter

After installing pytorch_scatter, just do

pip install pytorch_segmentation_models_trainer

We have a docker container in which all dependencies are installed and ready for gpu usage. You can pull the image from dockerhub:

docker pull phborba/pytorch_segmentation_models_trainer:latest

Citing:


@software{philipe_borba_2021_4574256,
  author       = {Philipe Borba},
  title        = {{phborba/pytorch\_segmentation\_models\_trainer: 
                   Version 0.1.2}},
  month        = mar,
  year         = 2021,
  publisher    = {Zenodo},
  version      = {v0.1.2},
  doi          = {10.5281/zenodo.4574256},
  url          = {https://doi.org/10.5281/zenodo.4574256}
}

Release files for pytorch-segmentation-models-trainer 0.7.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for pytorch-segmentation-models-trainer 0.7.1
File	Size	Uploaded
pytorch_segmentation_models_trainer-0.7.1.tar.gz	81.3 kB	Jul 13, 2021	Details

Built distribution (wheel)

Table of built distributions (wheels) for pytorch-segmentation-models-trainer 0.7.1
File	Interpreter	ABI	Platform	Reset
pytorch_segmentation_models_trainer-0.7.1-py3-none-any.whl 116.7 kB Jul 13, 2021	Python 3	none	any	Details

Total release size: 198.0 kB

Release files / pytorch_segmentation_models_trainer-0.7.1.tar.gz

Download URL	pytorch_segmentation_models_trainer-0.7.1.tar.gz
Size	81.3 kB
Tags	Source
SHA-256 checksum How to use checksums	`7aee4aaed854f6df3f871d5091951cc485ba2886e74c9a2da8625dbbbfecce3d`
BLAKE2b-256 checksum How to use checksums	`395fbfeebc024ab7d8655be63ef628932a06f4a7928fe13072c9c4c1d94e1be0`
Upload date	Jul 13, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.1 importlib_metadata/4.6.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.61.2 CPython/3.9.5`

Release files / pytorch_segmentation_models_trainer-0.7.1-py3-none-any.whl

Download URL	pytorch_segmentation_models_trainer-0.7.1-py3-none-any.whl
Size	116.7 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`c7b898ef1942b0e0f6d653e4de5cd5abe19c62d176648e43fc2e1c4a9789c6e3`
BLAKE2b-256 checksum How to use checksums	`d40de7b07fc703e2b9b7345685308343b4a1936b43c940f1a517f5586f8c8a4e`
Upload date	Jul 13, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.1 importlib_metadata/4.6.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.61.2 CPython/3.9.5`