Metadata-Version: 2.1
Name: gray2color
Version: 0.1.1
Summary: Convert your grayscale semantic masks (vistas/cityscape style) to RGB colored masks wiht built-in or custom pallets
Home-page: https://github.com/Mr-TalhaIlyas/Converting-Grayscale-Semantic-Masks-to-Color
Author: Talha Ilyas
Author-email: mr.talhailyas@gmail.com
License: UNKNOWN
Description: [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![PyPI version](https://badge.fury.io/py/0.0.1.svg)](https://badge.fury.io/py/0.0.1) [![DOI](https://zenodo.org/badge/357129295.svg)](https://zenodo.org/badge/latestdoi/357129295)
        # Grayscale to Color Semantic Mask Converotr
        
        This `lib` converts the grayscale semantic masks obtained at the output a CNN and fills it with colors for example in case of 
        `cityscape` dataset you have 30 channels at the output of CNN and after using `argmax` to create one channel semantic mask you
        get the following output
        
        ![alt text](https://github.com/Mr-TalhaIlyas/Converting-Grayscale-Semantic-Masks-to-Color/raw/master/screens/gray.png?raw=true)
        which you can use for measuring `IOU`, `Dice` or other evaluation metrics. But it is a bit difficult for human visualization so this package 
        converts the above output to following ouptut easy to visualize.
        ![alt text](https://github.com/Mr-TalhaIlyas/Converting-Grayscale-Semantic-Masks-to-Color/raw/master/screens/rgb.png)
        ## Usage
        
        ```python
        import cv2
        from gray2rgb import gray2rgb
        
        mask = cv2.imread('../gray.png', 0)
        rgb = gray2rgb(mask, use_pallet='cityscape', custom_pallet=None)
        
        ```
        ## Available Pallets
        Available Pallets are `ade20k`, `cityscape`, `lip`, `pannuke`, `pascal`, `vistas`
        
        You can also define your custom color Pallets as follows
        
        ```python
        
        # values are in order [R, G, B] ranging from [0, 255]
        
        pallet_cityscape = np.array([[[128, 64, 128],
                                    [244, 35, 232],
                                    [70, 70, 70],
                                    [102, 102, 156],
                                    [190, 153, 153]]], np.uint8) / 255
        ```
        
        ## Returns
        
        A `uint8` image with values ranging from [0, 255] you can save via
        
        ```python
        import cv2
        
        rgb = cv2.cvtColor(rgb, cv2.COLOR_BGR2RGB)  #   becaues cv2 will change color channels before writing
        cv2.imwrite('../rgb.png', rgb)
        ```
        
        
        ## Raises Errors
        
        ```python
        
        PalletNotDefined: if pallet is not specified
        
        NotEnoughColors: if grayscale mask has more classes present than the colors in the pallet
        
        ```
        
Keywords: python,gray2rgb,gray2color,grayscale to rgb,color pallets,cityscapevistas,lip,ade20k,pannuke,pascal_voc
Platform: UNKNOWN
Classifier: Intended Audience :: Education
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
