[Torch-TensorRT](https://pytorch.org/TensorRT/) is an integration of the [PyTorch](https://pytorch.org/docs/stable/index.html) deep learning framework and the [TensorRT](https://developer.nvidia.com/tensorrt) inference acceleration framework. With this toolkit, users can generate an optimized TensorRT engine from a trained PyTorch model with a single line of code. The tutorial notebooks included here illustrate the inference optimization procedure (and benchmark the results) for the following networks and applications: 
- **Hugging Face BERT**: Masked Language Modeling
- **EfficientNet**: Image Classification
- **Resnet50**: Image Classification
- **SSD**: Object Detection

torch_tensorrt_notebooks

Collection of Jupyter Notebooks illustrating how Torch-TensorRT can optimize inference with several well-known deep learning models

Torch-TensorRT Notebooks