Complete User's Guide
environmental preparation
- clone warehouse::
git clone https://github.com/zuruoke/watermark-removal - Installation of dependencies: requires a specific version of TensorFlow and additional libraries
pip install tensorflow==1.15.0pip install git+https://github.com/JiahuiYu/neuralgym - Download model: Get the pre-trained model and put it in the model/ directory
Practical steps
- Prepare the image: Place the image to be processed in the project directory
- execute a command::
python main.py --image 输入路径 --output 输出路径 --checkpoint_dir model/ --watermark_type istock - Parameter description::
- -image: Specify the path of the input image
- -output: Setting the save path after repairing
- -watermark_type: support different types of watermark processing
caveat
First time use is recommended to run in Google Colab cloud environment, which can avoid local environment configuration issues. For complex watermarks, model parameters may need to be adjusted or retrained.
This answer comes from the articleWatermark Removal: open source image watermark removal tool, picture watermark recovery original imageThe































