Tool to remove the background from the portrait using Tensorflow

A tool to remove a background from a portrait image using Tensorflow

---

Description:

The program removes the background from portrait photos

---

Differences from the original script:

• Tensorflow 2.0 compatible
• Added comments to the code.
• Added tqdm progress bar.
• Removes background from image without loss of image resolution.
• The script now not only processes a single file, but can also process all images from the input folder and save them in the output folder with the same name.
• New sample images.

---

Dependencies:

wget for setup.py!
tensorflow, pillow, tqdm, numpy, scipy for main.py!

---

Setup for Windows:

• Clone this repository
• Install all the dependencies from requirements.txt via pip3 install -r requirements.txt
• Run ./setup.bat
  This setup.bat script loads the trained model.

Setup for Linux:

• Clone repository: git clone https://github.com/OPHoperHPO/image-background-remove-tool
• Install all the dependencies from requirements.txt: pip3 install -r requirements.txt
• Run ./setup.sh
  This setup.sh script loads the trained model.

---

Running the script:

• python3 main.py <input_path> <output_path> <model_type>

Explanation of variables:

• <input_path> - path to input file or dir.
• <output_path> - path to output file or dir.
• <model_type> - can be xception_model or mobile_net_model. The first model has better quality, but it runs much slower than the second.

Note: See sample scripts for more information on using the program.

---

TODO:

1) Add a graphical interface. (0% done)

Sample Result:

• More sample images in docs/imgs/input/ and docs/imgs/examples/ folders

• Input:

• 

• Output:

• 

---