Sinapsis Anomaly Detection

Monorepo with packages to provide anomaly detection training, inference and export for computer vision.

🐍 Installation • 📦 Packages • 🌐 Webapp • 📙 Documentation • 🔍 License

🐍 Installation

This monorepo currently consists of the following packages for anomaly detection:

• sinapsis-anomalib

Install using your package manager of choice. We encourage the use of uv

Example with uv:

  uv pip install sinapsis-anomalib --extra-index-url https://pypi.sinapsis.tech

or with raw pip:

  pip install sinapsis-anomalib --extra-index-url https://pypi.sinapsis.tech

with uv:

  uv pip install sinapsis-anomalib[all] --extra-index-url https://pypi.sinapsis.tech

or with raw pip:

  pip install sinapsis-anomalib[all] --extra-index-url https://pypi.sinapsis.tech

  uv pip install sinapsis-anomaly-detection[all] --extra-index-url https://pypi.sinapsis.tech

📦 Packages

For example, for AnomalibTorchInference use sinapsis info --example-template-config AnomalibTorchInference to produce the following example config:

agent:
  name: my_test_agent
templates:
- template_name: InputTemplate
  class_name: InputTemplate
  attributes: {}
- template_name: AnomalibTorchInference
  class_name: AnomalibTorchInference
  template_input: InputTemplate
  attributes:
    model_path: '/path/to/model.pt'
    transforms: null
    device: cuda

🌐 Webapp

The webapp offers an interface for anomaly detection on images using pretrained models. Upload images and visualize results (labels, bboxes, or masks) based on the provided agent configuration.

git clone git@github.com:Sinapsis-ai/sinapsis-anomaly-detection.git
cd sinapsis-anomaly-detection

docker compose -f docker/compose.yaml build

docker compose -f docker/compose_apps.yaml up sinapsis-anomalib-gradio -d

docker logs -f sinapsis-anomalib-gradio

Running on local URL:  http://127.0.0.1:7860

docker compose -f docker/compose_apps.yaml down

AGENT_CONFIG_PATH: "/app/configs/inference/custom_torch_demo_agent.yml"

TRAINING_CONFIG: "/app/configs/custom_train_export_agent.yaml"

MODEL_PATH: "/app/artifacts/exported_models/weights/torch/custom_model.pt"

TEST_DIR: "/app/artifacts/data/custom_test_data"

uv sync --frozen

uv pip install sinapsis-anomaly-detection[all] --extra-index-url https://pypi.sinapsis.tech

uv run webapps/anomalib_gradio_app.py

Running on local URL:  http://127.0.0.1:7860

export AGENT_CONFIG_PATH="packages/sinapsis_anomalib/src/sinapsis_anomalib/configs/inference/custom_torch_demo_agent.yml"

export TRAINING_CONFIG="packages/sinapsis_anomalib/src/sinapsis_anomalib/configs/custom_train_export_agent.yaml"

export MODEL_PATH="artifacts/exported_models/weights/torch/custom_model.pt"

export TEST_DIR="artifacts/data/custom_test_data"

📙 Documentation

Documentation for this and other sinapsis packages is available on the sinapsis website

Tutorials for different projects within sinapsis are available at sinapsis tutorials page

🔍 License

This project is licensed under the AGPLv3 license, which encourages open collaboration and sharing. For more details, please refer to the LICENSE file.

For commercial use, please refer to our official Sinapsis website for information on obtaining a commercial license.