https://github.com/xx025/flyorbird
Use cifar10 dataset bird and airplane to train a model, then convert the model to onnx format, and deploy the model with gradio.
https://github.com/xx025/flyorbird
Last synced: 7 months ago
JSON representation
Use cifar10 dataset bird and airplane to train a model, then convert the model to onnx format, and deploy the model with gradio.
- Host: GitHub
- URL: https://github.com/xx025/flyorbird
- Owner: xx025
- Created: 2024-06-13T07:46:09.000Z (over 1 year ago)
- Default Branch: master
- Last Pushed: 2024-06-13T08:02:53.000Z (over 1 year ago)
- Last Synced: 2024-10-14T07:28:24.867Z (about 1 year ago)
- Language: Python
- Homepage:
- Size: 1.74 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# FlyOrBird
`toy project` `resnet` `cifar10` `classification` `pytorch` `torchvision` `onxx` `gradio`
Use cifar10 dataset bird and airplane to train a model, then convert the model to onnx format, and deploy the model with gradio.
### 0. Install Requirements
```shell
conda create -n flyorbird python=3.10
pip install torch torchvision gradio numpy onnxruntime-gpu
```
> Note: maybe is not enough, place by yourself.
### 1. Train Model
```shell
python train.py
```
### 2. Test Model
> pretrained model weights can get for [release](https://github.com/xx025/FlyOrBird/releases)
```shell
python test.py
```
### 3. Convert Model to ONNX
```shell
python convert2onnx.py
```
### 4. Deploy ONNX Model With Gradio
> onxx model can get for [release](https://github.com/xx025/FlyOrBird/releases)
```shell
python deploy.py
```
### 5. Test
