Features

Our community edition provides all the important features to experience the power and usability of model optimization with Neutrino. With the community version, engineers and researchers can verify the seamless integration of Neutrino into standard AI processes, test compatibility with existing model development and explore the benefits of optimization to various products. Feel free to use it as you please! The aim of the community edition is multifold, with examples such as:

  • Provide hands-on experience with automated model architecture optimization and see first-hand the possibilities with Deeplite Neutrino

  • Compare and complement the results obtained using Deeplite Neutrino with other open-source and industry model architecture optimization frameworks

  • Export an optimized model to test integration with endpoint applications

  • Verify the integration of Deeplite Neutrino within industry and production pipelines

  • Utilize Deeplite Neutrino to accelerate academic research, expedite results and share your achievements in research papers

  • Have fun! Users can play around with Deeplite Neutrino and enjoy the advantages of model architecture optimization in various use-cases

However, for production-grade models and to access some advanced features, we recommend to use the production edition of Neutrino. The production edition is ideal under the following scenarios:

  • For using a stable, support-friendly production environment with access to Deeplite’s experts

  • Optimizing advanced, state-of-the-art, and complex deep learning architectures such as object detection and semantic segmentation

  • Export and consume your optimized models along with trained weights in ONNX or PyTorch JIT format

  • To be able to use Neutrino in a private or secure environment with no external internet support



Community Edition Production Edition
Monthly Price
Free!
Optimization
Optimize classification CNN models
Type of models to optimize
Optimize for a specific `delta` accuracy
Optimize Object Detection (OD) CNN models
Optimize Segmentation CNN models
Model Quantization
Distributed optimization and training
Exporting options
Export format: ONNX
Export format: TorchScript (.pt)
Export an FP16 quantized ONNX model
Get all the optimization metrics and results
Export the second best optimized model
Export the best optimized model
Caching and Logging
Locally caching and checkpointing through the optimization process
Cloud logging of experimental details
Local(air-gapped) logging of experimental detail
Support and Updates
Free updates and new features
Active support for bugs and requests

(via github)

(via email, call)