Mask R-CNN for Fine-Grained segmentation
Project description
# fine-grained-segmentation library
Python library for segmenting clothing items in images, implemented in Python 3 and ONNX. A deep learning model generates bounding boxes and segmentation masks for each instance of an object in the image. It’s based on [Matterport Mask R-CNN](https://github.com/matterport/Mask_RCNN)
The library is also available on the [Python Package Index](https://pypi.org/project/fine-grained-segmentation/)
A demo web app is up at https://fine-grained-segmentation.vinnypalumbo.com
## Requirements
Python 3.5, ONNX runtime, and other common packages listed in requirements.txt.
## Installation
Clone this repository
Run setup to install the library `bash python3 setup.py install ` If it failed to install the dependencies, run `bash pip3 install -r requirements.txt `
Download pre-trained weights (mrcnn.onnx) from the [releases page](https://github.com/vinny-palumbo/fine_grained_segmentation/releases)
## Usage
Here is how to use the library from the command line: `bash fashion-segmentator --image=<path/to/image/file> ` This will generate a `result.png` file in the current directory
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for fine_grained_segmentation-0.1.9.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | aa106918410a4a56682d68164749d6e43f457bc02b6a44cffdc5108a9760de7c |
|
MD5 | 277de9e48755d72137576e49eb7cc8fc |
|
BLAKE2b-256 | f7f83c41e9e8ff5dbd61a9edd96820298eec177e9bd09d322f6a1901bad8f0c6 |
Hashes for fine_grained_segmentation-0.1.9-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1644acfd3bf8380e0dc8cede3b50ccd659b0f81583616c6eb463fcc89e8d6209 |
|
MD5 | 9f51c7a6eeb51b0a3673b08835df4064 |
|
BLAKE2b-256 | 8b6c266af4330aef00cbda8259b6b625c34885a146f38a87dce66c915eb439c2 |