deepdetect
Deep Learning Server and CLI for Torch and TensorRT
What is deepdetect?
Deep Learning Server and CLI for Torch and TensorRT
Overview of deepdetect
What it is
DeepDetect is a deep learning runtime, command-line tool, and REST server for training and inference. The Python wheel embeds the DeepDetect runtime in the current Python environment and provides the deepdetect CLI for repeatable model workflows. The server remains available for long-running REST services, containerized serving, and integrations that need a dedicated process. It supports images, text, CSV/tabular data, time series, sparse/SVM-style data, object-detection boxes, and segmentation masks through a single API surface.
Key features
- Train and run inference from the
deepdetectCLI or the REST API. - Create model services backed by local model repositories.
- Run asynchronous training jobs and inspect their status.
- Work with image classification, object detection, semantic segmentation, language models, tabular data, time series, and sparse data.
- Use filesystem-based model storage without a database dependency.
- Emit structured CLI events for automation and human-readable terminal output.
- Use JSON request and response payloads for server integrations.
Use cases
DeepDetect is suitable for practical model operations: create services, train models, run predictions, monitor jobs, and keep model repositories organized on the filesystem. It can be used for local training, in-process inference, and automation-friendly workflows. The server is appropriate when a long-running REST service, remote clients, asynchronous jobs behind an HTTP API, or a dedicated serving process is needed. Docker can be used for containerized serving and reproducible service environments.
Getting started
Install one wheel variant in a Python environment. deepdetect-cpu and deepdetect-gpu both provide import deepdetect, so they are mutually exclusive in the same environment. bash python -m pip install --extra-index-url https://www.deepdetect.com/download/wheels/simple deepdetect-cpu For a CUDA-enabled environment, install the GPU package instead: bash python -m pip install --extra-index-url https://www.deepdetect.com/download/wheels/simple deepdetect-gpu Inspect the packaged CLI profiles and command options: bash deepdetect inspect models deepdetect train yolox --help deepdetect infer segformer --help
License and pricing
DeepDetect is distributed under the GNU Lesser General Public License v3.0. The project is open source. Pricing is not stated.
Based on the project's public README and repository metadata.