https://github.com/princep/automatic-garbanzo
Preprocessing and inferencing kernel in cuda
https://github.com/princep/automatic-garbanzo
Last synced: 3 months ago
JSON representation
Preprocessing and inferencing kernel in cuda
- Host: GitHub
- URL: https://github.com/princep/automatic-garbanzo
- Owner: PrinceP
- Created: 2022-02-13T07:03:43.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2022-07-19T06:37:39.000Z (almost 3 years ago)
- Last Synced: 2025-01-04T14:57:15.833Z (4 months ago)
- Language: Python
- Size: 14.5 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Python C++ CUDA Inference
### Steps to run the workspace
1. Clone the repo
```
git clone https://github.com/PrinceP/automatic-garbanzo
```
2. Move to automatic-garbanzo
```
cd automatic-garbanzo
```
3. Run on the workspace docker and execute the test
```
sudo docker run -v {$PWD}:/app -it cuda_kernel_workspace bash
cd /app
make clean
make
```
### For generating and testing Engine [trtexec]
```
trtexec --onnx=bcc.onnx --verbose --explicitBatch --minShapes=input0:1x3x224x224 --maxShapes=input0:10x3x224x224 --optShapes=input0:5x3x224x224 --saveEngine=bcc.trt
trtexec --loadEngine=bcc.trt --shapes='input0':2x3x224x224
```