https://github.com/icgy96/model-pivot
Model-Pivot is a model conversion and visualization tool to help users inter-operate among different deep learning frameworks. Convert models between PyTorch and Tensorflow.
https://github.com/icgy96/model-pivot
intermediate-representation open-exchange pytorch tensorflow
Last synced: about 1 year ago
JSON representation
Model-Pivot is a model conversion and visualization tool to help users inter-operate among different deep learning frameworks. Convert models between PyTorch and Tensorflow.
- Host: GitHub
- URL: https://github.com/icgy96/model-pivot
- Owner: iCGY96
- License: mit
- Created: 2018-12-06T14:14:58.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2021-12-11T09:13:54.000Z (over 4 years ago)
- Last Synced: 2025-03-20T17:22:32.062Z (about 1 year ago)
- Topics: intermediate-representation, open-exchange, pytorch, tensorflow
- Language: Python
- Homepage: https://model-pivot.readthedocs.io
- Size: 1.91 MB
- Stars: 19
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Model-Pivot
Model-Pivot is a model conversion and visualization tool to help users inter-operate among different deep learning frameworks. Convert models between PyTorch and Tensorflow.
IR is based on the National Information Technology Standardization ```Neural Network Representation and Model Compression Part 1: Convolution Neural Network``.
## Requirments
- tensorflow==1.8.0
- pytorch==0.4.0
- torchvision==0.2.0
- protobuf>=3.6.1
- python>=3.6
- flask
## How to deploy visualization on Web
If you want to access the deployed web page from an external network, you should first modify the *host* and *port* for the *./visualization/app.py* file.
You can deploy it on Web by running:
```shell
python app.py
```
## Model
Framework | ResNet50 | Inception V3 | ShuffleNet | FCN | LSTM |
:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|
TensorFlow | √ | √ | √ | √ | √ |
PyTorch | √ | √ | √ | √ | √ |
## Test for Tensorflow and PyTorch
```shell
CUDA_VSIBLE_DEVICES=0 python test.py
```