Tim M
57b5cefde5
Updated all `.md` files to contain newest image
|
2 년 전 | |
|---|---|---|
| .. | ||
| README.md | 2 년 전 | |
| imagenet_classes.txt | 4 년 전 | |
| pytorch_model.py | 4 년 전 | |
| requirements.txt | 4 년 전 | |
| resnet50.onnx | 4 년 전 | |
| trt_inference.py | 4 년 전 | |
| turkish_coffee.jpg | 4 년 전 | |
README.md
How to convert a model from PyTorch to TensorRT and speed up inference
This repository contains code for How to convert a model from PyTorch to TensorRT and speed up inference blogpost.
To run PyTorch part: ```shell script python3 -m pip install -r requirements.txt python3 pytorch_model.py
To run TensorRT part:
1. Download and install NVIDIA CUDA 10.0 or later following by official instruction: [link](https://developer.nvidia.com/cuda-10.0-download-archive)
2. Download and extract CuDNN library for your CUDA version (login required): [link](https://developer.nvidia.com/rdp/cudnn-download)
3. Download and extract NVIDIA TensorRT library for your CUDA version (login required):
[link](https://developer.nvidia.com/nvidia-tensorrt-6x-download).
The minimum required version is 6.0.1.5.
Please follow the [Installation Guide](https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html) for your system and don't forget to install Python's part
4. Add the absolute path to CUDA, TensorRT, CuDNN libs to the environment variable ```PATH``` or ```LD_LIBRARY_PATH```
5. Install [PyCUDA](https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html#installing-pycuda)
```shell script
python3 trt_inference.py
AI Courses by OpenCV
Want to become an expert in AI? AI Courses by OpenCV is a great place to start.
