hub / github.com/LAION-AI/watermark-detection

github.com/LAION-AI/watermark-detection @main

Chat with this repo

repository ↗ · DeepWiki ↗ · + Follow

64 symbols 166 edges 7 files 22 documented · 34%

What it actually does AI analysis from the code graph — generated when you open this

loading…

README

watermark-detection

A repository containing datasets and tools to train a watermark classifier.

Datasets

The datasets folder contains WebDataset files using the following keys: - key: A unique identifier within the dataset - url: The URL of the image data - caption: The caption describing the images

Dataset annotation

Preliminary dataset annotations and WIP tools can be found on https://github.com/robvanvolt/DALLE-tools. More mature tools and completely annotated datasets will be transferred to this repository. Feel free to adjust the structure, upload new annotations or annotation tools.

Web Annotator

WIP - A tool to annotate the url-caption datasets online will be shortly uploaded.

Core symbols most depended-on inside this repo

step

called by 3

training/scalable_shampoo/shampoo.py

get_dataset

called by 2

training/train_watermark.py

num_to_sym

called by 2

training/train_watermark.py

parse_output

called by 2

training/train_watermark.py

add_statistics

called by 2

training/scalable_shampoo/shampoo.py

partition

called by 2

training/scalable_shampoo/shampoo.py

get_load_mapping

called by 1

training/train_watermark.py

get_process_map

called by 1

training/train_watermark.py

Shape

Function 34

Method 22

Class 8

Languages

Python100%

Modules by API surface

training/scalable_shampoo/shampoo.py31 symbols

training/train_watermark.py15 symbols

training/eval_watermark.py11 symbols

training/scalable_shampoo/shampoo_utils.py4 symbols

training/scalable_shampoo/matrix_functions.py3 symbols

For agents

$ claude mcp add watermark-detection \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact