MTCNN conversion to ONNX

[silviuspac]

Is it possible to convert MTCNN to ONNX?

[mboling6]

I am also wondering how to convert this model to ONNX format. Have you figured this out?

[Chappie74]

import onnx
import torch

from resnet import InceptionResnetV1

torch_model = InceptionResnetV1('vggface2')
torch_model.eval()
torch_input = torch.randn(1, 3, 160, 160)
torch.onnx.export(torch_model, torch_input,
                  'facenet.onnx',
                  opset_version=18,  # The ONNX version to export the model to
                  do_constant_folding=True,  # Whether to execute constant folding for optimization
                  input_names=['input0'],  # The model's input names
                  output_names=['output0']  # The model's output names
                  )

# Load the ONNX model
onnx_model = onnx.load('facenet.onnx')

# Check that the model is well-formed
onnx.checker.check_model(onnx_model)

print("ONNX model is well-formed and saved successfully.")

Try modifying this.

https://pytorch.org/tutorials//beginner/onnx/export_simple_model_to_onnx_tutorial.html