onnx-tensorflow

onnx-tensorflow copied to clipboard

TypeError: __int__ returned non-int (type NoneType)

1

**Describe the bug** A clear and concise description of what the bug is. Due to my preference, I used tensorflow 1.x and the only compatible onnx_tf==1.5.0. I tried to convert...

mohamadHN93

onnx model info: `model.graph.input: [name: "input_ids" type { tensor_type { elem_type: 6 shape { dim { dim_param: "batch_size" } dim { dim_value: 500 } } } } ]` `model.graph.output: [name:...

linchpinlin

Pytorch->ONNX->TF-> SNPE Error for batchnorm variance

3

I converted Mobilenet V1 SSD Pytorch model to ONNX format(https://github.com/qfgaohao/pytorch-ssd) and from there to protobuf format using ONNX TF (TF==1.15). ONNX version == 1.3 and SNPE == 1.36 Now when...

Ashutosh1995

Error when export .pb to onnx which came from kras.application

3

**Describe the bug** Error when export .pb to onnx which came from kras.application.* tf_rep.tensor_dict is empty and onnx too **To Reproduce** ``` Python3 import onnx import os from onnx_tf.backend import...

jangmin-deepx

'_UserObject' object has no attribute 'summary'

8

Hello, I‌ converted my onnx model to a tensorflow model(`'saved_model'` in the code) using you library. It's successfully done. But in the following piece of code when I used the...

sahooora

Error when converting onnx to pb

3

**Describe the bug** When I use an onnx model to convert to pb, the following error appears:  **To Reproduce** This is the code I used when converting:  The...

luxianlebron

**Describe the bug** Hi, I'm looking to retain some TF1 compatibility with a TF2 image classifier model by running in graph mode (eager mode disabled) in order to use Alibi's...

InterferencePattern

ONNX->"TensorFlow Lite micro" fundamentally broken because of transpose operations

8

**Problem** In my usecase, I need to port a model (only containing conv, relu and maxpool layers) from PyTorch to TensorFlow Lite micro, using the following conversions: PyTorch->ONNX->TensorFLow->Tensorflow Lite micro....

maartenvds

onnx->TensorFlow BatchNormalization@0' is not a valid scope name

5

import onnx from onnx_tf.backend import prepare onnx_model = onnx.load("ch_mobile_infer_clipChanged.onnx") tf_rep = prepare(onnx_model) Traceback (most recent call last): File "", line 1, in File "/zhr/onnx-tensorflow/onnx_tf/backend.py", line 66, in prepare return cls.onnx_model_to_tensorflow_rep(model,...

ZHR1997

When indices_shape is a tensor, cannot index it

2

https://github.com/onnx/onnx-tensorflow/blob/0874ca1378a8fe2d06e66f23323c3f828652e900/onnx_tf/handlers/backend/gather_and_scatter_mixin.py#L69 if tf_shape returns a tensor, indexing with indices_shape gives an error: https://github.com/onnx/onnx-tensorflow/blob/0874ca1378a8fe2d06e66f23323c3f828652e900/onnx_tf/handlers/backend/gather_and_scatter_mixin.py#L74 TypeError: slice indices must be integers or None or have an __index__ method

jinluyang