zlpson

Results 11 comments of zlpson

hi,I use keras2onnx to transfer keras_based network,then transfer onnx to tensorrt.when parsing with tensorrt,error shows like:netwokr layers=0!do you know why is it?

code like this: from keras.models import load_model model = load_model('logs/multiBands/testKeras/last1.hdf5' ) onnx_model = keras2onnx.convert_keras(model, model.name) temp_model_file = 'conv_hdf5.onnx' onnx.save_model(onnx_model, temp_model_file)

hi,I use keras2onnx to transfer keras_based network,then transfer onnx to tensorrt.when parsing with tensorrt,error shows like:netwokr layers=0!do you know why is it?

can you show me how to prove the onnx model itself is working?

hi,I use keras2onnx to transfer keras_based network,then transfer onnx to tensorrt.when parsing with tensorrt,error shows like:netwokr layers=0!do you know why is it?

> Is the onnx model itself working? If it does, then it should not be keras2onnx issue. can you show me how to prove the onnx model itself is working?

hi,I use keras2onnx to transfer keras_based network,then transfer onnx to tensorrt.when parsing with tensorrt,error shows like:netwokr layers=0!do you know why is it?

> We have many examples in our tests, does the onnx model run successfully using onnxruntime? I put a png named 00003.png and run run_image in test_utils.py like this,but the...

hi,I use keras2onnx to transfer keras_based network,then transfer onnx to tensorrt.when parsing with tensorrt,error shows like:netwokr layers=0!do you know why is it?

> We have many examples in our tests, does the onnx model run successfully using onnxruntime? or can you show me the details for running the examples in tests?

hi,I use keras2onnx to transfer keras_based network,then transfer onnx to tensorrt.when parsing with tensorrt,error shows like:netwokr layers=0!do you know why is it?

> `test_utils` is the utility file. In `applications/nightly_build`, there are many examples there. Many are computer vision related models. I run test_deeplab_v3.py in applications/nightly_build，the output is like this: Ran 1...

hi,I use keras2onnx to transfer keras_based network,then transfer onnx to tensorrt.when parsing with tensorrt,error shows like:netwokr layers=0!do you know why is it?

> This is probably because you are using old onnx package. Try `onnx==1.7.0`. You can also set `target_opset=12` in `convert_keras` function. > > [Here](https://github.com/onnx/keras-onnx/blob/b49d9a9af8dc27c903a37d575775202d68f23fac/applications/nightly_build/test_keras_applications_v2.py#L66) is an example for ResNet50. I...

hi,I use keras2onnx to transfer keras_based network,then transfer onnx to tensorrt.when parsing with tensorrt,error shows like:netwokr layers=0!do you know why is it?

> This is probably because you are using old onnx package. Try `onnx==1.7.0`. You can also set `target_opset=12` in `convert_keras` function. > > [Here](https://github.com/onnx/keras-onnx/blob/b49d9a9af8dc27c903a37d575775202d68f23fac/applications/nightly_build/test_keras_applications_v2.py#L66) is an example for ResNet50. use...

hi,I use keras2onnx to transfer keras_based network,then transfer onnx to tensorrt.when parsing with tensorrt,error shows like:netwokr layers=0!do you know why is it?

> From the log, the onnx model looks good. Do you transfer to tensorrt through https://github.com/onnx/onnx-tensorrt ? If so, you can raise an issue there. ok,I will try to raise...

hi,I use keras2onnx to transfer keras_based network,then transfer onnx to tensorrt.when parsing with tensorrt,error shows like:netwokr layers=0!do you know why is it?

> Yes, it adds Transpose layer as you said. Will it affect the parse process using tensorrt?The worst situation，I mean，lead to parsing failed?