Update README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ This version was exported using the old torch to ONNX converter (`torch.onnx.exp
|
|
| 17 |
1. **Custom FourierUnitJIT**: A custom [FourierUnitJIT](https://github.com/Carve-Photos/lama/blob/main/saicinpainting/training/modules/ffc.py) implementation is used since the original cannot be directly ported to ONNX without overhead. The result is identical to the original model.
|
| 18 |
2. **Fixed Input Shape**: The input shape is fixed at 512x512 pixels. Although dynamic input shapes are possible, they would require resolving issues with dynamic padding in the `irfft` and `rfftn` functions in `ffc.py`.
|
| 19 |
3. **Opset Version 17**: This model uses opset version 17.
|
| 20 |
-
|
| 21 |
> if you need other resolution - export it using our [jupyter notebook](https://colab.research.google.com/github/Carve-Photos/lama/blob/main/export_LaMa_to_onnx.ipynb)
|
| 22 |
|
| 23 |
### 2. `lama.onnx` (NOT RECOMMENDED)
|
|
|
|
| 17 |
1. **Custom FourierUnitJIT**: A custom [FourierUnitJIT](https://github.com/Carve-Photos/lama/blob/main/saicinpainting/training/modules/ffc.py) implementation is used since the original cannot be directly ported to ONNX without overhead. The result is identical to the original model.
|
| 18 |
2. **Fixed Input Shape**: The input shape is fixed at 512x512 pixels. Although dynamic input shapes are possible, they would require resolving issues with dynamic padding in the `irfft` and `rfftn` functions in `ffc.py`.
|
| 19 |
3. **Opset Version 17**: This model uses opset version 17.
|
| 20 |
+
4. **Exportable to TensorRT**: The model can be successfully used in TensorRT, etc.
|
| 21 |
> if you need other resolution - export it using our [jupyter notebook](https://colab.research.google.com/github/Carve-Photos/lama/blob/main/export_LaMa_to_onnx.ipynb)
|
| 22 |
|
| 23 |
### 2. `lama.onnx` (NOT RECOMMENDED)
|