https://github.com/ternaus/cloths_segmentation

Code for binary segmentation of cloths
https://github.com/ternaus/cloths_segmentation

computer-vision deep-learning image-segmentation

Last synced: about 1 year ago
JSON representation

Code for binary segmentation of cloths

• Host: GitHub
• URL: https://github.com/ternaus/cloths_segmentation
• Owner: ternaus
• License: mit
• Created: 2020-10-29T22:16:13.000Z (over 5 years ago)
• Default Branch: main
• Last Pushed: 2020-11-09T00:21:26.000Z (over 5 years ago)
• Last Synced: 2025-03-30T11:06:57.921Z (about 1 year ago)
• Topics: computer-vision, deep-learning, image-segmentation
• Language: Python
• Homepage:
• Size: 20.5 KB
• Stars: 234
• Watchers: 4
• Forks: 40
• Open Issues: 7
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE

Awesome Lists containing this project

README

          
![](https://habrastorage.org/webt/gu/wi/lq/guwilqwsfru7hc5rkxhxsj_nl_u.jpeg)

# Code for binary segmentation of various cloths

## Installation

`pip install -U cloths_segmentation`

### Example inference

Jupyter notebook with the example: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/18RenTYhuPVip9SHdMLn-vnK0K57B--um#scrollTo=D0h2Y-oOCnXJ)

### WebApp

[https://clothssegmentation.herokuapp.com/](https://clothssegmentation.herokuapp.com/)

## Data Preparation

Download the dataset from [https://www.kaggle.com/c/imaterialist-fashion-2019-FGVC6](https://www.kaggle.com/c/imaterialist-fashion-2019-FGVC6)

Process the data using [script](https://github.com/ternaus/iglovikov_helper_functions/tree/master/iglovikov_helper_functions/data_processing/prepare_cloths_segmentation)

The script will create process the data and store images to folder `images` and binary masks to folder `labels`.

## Training

### Define the config.

Example at [cloths_segmentation/configs](cloths_segmentation/configs)

You can enable / disable datasets that are used for training and validation.

### Define the environmental variable `IMAGE_PATH` that points to the folder with images.

Example:

```bash

export IMAGE_PATH=

```

### Define the environmental variable `LABEL_PATH` that points to the folder with masks.

Example:

```bash

export MASK_PATH=

```

### Training

```

python -m cloths_segmentation.train -c 

```

### Inference

```bash

python -m torch.distributed.launch --nproc_per_node= cloths_segmentation/inference.py \

                                   -i  \

                                   -c  \

                                   -w  \

                                   -o  \

                                   --fp16