ResNet50 to ONNX, TorchScript and TensorRT using Nvidia Container

#sagemaker #pytorch #nvidia

Exclusive Phi AI merch T-shirts is now available here:
https://phiaistore.etsy.com
https://phi-ai-store.printify.me/prod...

This video illustrates how to create ONNX, TorchScript and TensorRT versions of pretrained ResNet50 model from PyTorch model zoo. We start with locating necessary files in AWS Sagemaker repository. Next we discussion each code files. Next we modify original codes by printing out each basic steps. Finally, we user Nvidia PyTorch Docker container to run the scripts and generate deployable model.

Great books about Machine Learning:
https://amzn.to/3Xzy22k Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow
https://amzn.to/4dPv7rS Machine Learning with PyTorch and Scikit-Learn
https://amzn.to/4gaxUxj Designing Machine Learning Systems
https://amzn.to/4gfsYqO Machine Learning Design Patterns


Links:
1. AWS Github Repo:
https://github.com/aws

2. Nvidia PyTorch Container:
https://catalog.ngc.nvidia.com/orgs/n...

4. Triton Charter is generated by Nvidia SDXL-turbo model
https://build.nvidia.com/stabilityai/...