Completed
- softmax function
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Inference with Torch-TensorRT Deep Learning Prediction for Beginners - CPU vs CUDA vs TensorRT
Automatically move to the next video in the Classroom when playback concludes
- 1 - intro
- 2 - clone Torch-TensorRT
- 3 - install and setup Docker
- 4 - install Nvidia Container Toolkit & Nvidia Docker 2
- 5 - Torch-TensorRT container option #1
- 6 - Torch-TensorRT Nvidia NGC container option #2
- 7 - import Pytorch
- 8 - load ResNet50
- 9 - load sample image
- 10 - sample image transforms
- 11 - batch size
- 12 - prediction with ResNet50
- 13 - softmax function
- 14 - ImageNet class number to name mapping
- 15 - predict top 5 classes of sample image topk
- 16 - speed test benchmark function
- 17 - CPU benchmarks
- 18 - CUDA benchmarks
- 19 - trace model
- 20 - convert traced model into a Torch-TensorRT model
- 21 - TensorRT benchmarks
- 22 - download Jupyter Notebook
- 23 - HOW DID I MISS THIS???
- 24 - thanks for watching!
