Open YizhouFan opened 3 years ago
MODEL_NAME = "data/pie/intention/context_loc_pretrained/model" model = load_model(MODEL_NAME + ".h5") onnx_model = keras2onnx.convert_keras(model, model.name, target_opset=14) temp_model_file = MODEL_NAME + ".onnx" onnx.save_model(onnx_model, temp_model_file)
ValueError: Unable to find out a correct type for tensor type = 0 of conv_lst_m2d_1/while/TensorArrayWrite/TensorArrayWriteV3/Enter:0
See the open-source repository here, https://github.com/aras62/PIEPredict/blob/df76b6512dd8afa8e695025e306a9a21f54b1179/pie_intent.py#L451
Keras2onnx: 1.9.0 onnxconverter-common: 1.9.0 tensorflow: 1.14.0 Keras: 2.2.4
Happens to me too. Any updates about this?
My code snippet for conversion:
Error message:
Network definition:
See the open-source repository here, https://github.com/aras62/PIEPredict/blob/df76b6512dd8afa8e695025e306a9a21f54b1179/pie_intent.py#L451
Versions:
Keras2onnx: 1.9.0 onnxconverter-common: 1.9.0 tensorflow: 1.14.0 Keras: 2.2.4