NVIDIA’s Transfer Learning Toolkit eliminates the time consuming process of building and fine-tuning Deep Neural Networks from scratch for Intelligent Video Analytics (IVA) applications.

The Transfer Learning Toolkit is a python-based toolkit that enables developers to take advantage of NVIDIA’s pre-trained models and offer capabilities for developers to adapt popular network architectures and backbones for their own data, train, fine-tune, prune and export to deployment. The simple interface and abstraction improve the efficiency of the deep learning workflow.

The pre-trained models accelerate the developer’s deep learning training process and eliminates higher costs associated with large scale data collection, labelling, and training model from scratch. Transfer Learning toolkit enables you to build high performance Intelligent Video Analytics based applications in retail analytics, logistics, smart cities, access control and more.

• What is Transfer Learning? Understanding benefits of leveraging transfer learning for your Deep Learning workflows

• Reduce training time by leverage NVIDIA’s GPU-optimized pre-trained models for Transfer Learning

• Understand End-to-End Deep Learning Workflow using Transfer Learning Toolkit

Content

content goes here