onnx2keras

onnx2keras copied to clipboard

**Pull Request: Small Correction to convert_clip Function** This pull request addresses a small correction in the `convert_clip` function, as suggested in [comment #1129549436](https://github.com/gmalivenko/onnx2keras/issues/79#issuecomment-1129549436) of [issue #79](https://github.com/gmalivenko/onnx2keras/issues/79). ### Why: The convert_clip()...

UncleBen420

Hey, I cannot convert a model which uses BatchNormalization Layers, because of dimension mismatches.. Assume the input tensor for BN is 48x112x112 (CHW) the parameters (e.g. gamma) has a size...

oconnor127

TypeError: unhashable type: 'google._upb._message.RepeatedScalarContainer'

3

I am trying to convert an ONNX model to Keras, but when I call the conversion function I receive the following error message "TypeError: unhashable type: 'google._upb._message.RepeatedScalarContainer'" ``` import onnx...

kurpav00

'/Reshape_output_0/' is not a valid root scope name.

2

Trying to load and use onnx exported from pytorch - (1, 3, 28, 28). onnx_model = onnx.load('data/export-torch.onnx') k_model = onnx_to_keras(onnx_model, ['actual_input']) DEBUG:onnx2keras:... DEBUG:onnx2keras:Check if all inputs are available: DEBUG:onnx2keras:Check input...

kovarole2

Converting a model that has Relu6 operation fails; it seems to be converted into a `clip` where the min and max is not set. I hacked together a temporary fix...

banoffee-pie

I trained my model using yolov5 and with ultralitics/yolov5 github repository converted it to a onnx model. I want to convert it to a h5 keras model but the code...

SaulA01745146

AttributeError: Number of inputs is not equal 1 for unsqueeze layer

1

There are two similar LeNet5 models. But when using onnx2keras, their node information is different. As a result, an error is reported when converting the second model. VGG16 met the...

MT010104

I am trying to convert an onnx model with dynamic input shape : ['p2o.DynamicDimension.0', 3, 'p2o.DynamicDimension.1', 'p2o.DynamicDimension.2'] . > Traceback (most recent call last): > File "/home/dockerpaddle/Desktop/onnx/test.py", line 11, in...

alexg93333

ValueError: `padding` should have 3 elements. Received: [0].

1

_**i was trying to export .onnx file to .h5 file i don't konw how to solve this error**_ DEBUG:onnx2keras:Output TF Layer -> KerasTensor(type_spec=TensorSpec(shape=(None, 128, 42), dtype=tf.float32, name=None), name='input.1/transpose_1:0', description="created by...

Eien9

In the original implementation, when converting Conv1d layers from ONNX to Keras, bias terms of conv1d was ignored. Fixed this issue by adding back bias terms to the output.

BoChenYS