onnx-tensorflow

onnx-tensorflow copied to clipboard

BackendIsNotSupposedToImplementIt: Unique is not implemented.

4

**Describe the bug** When I want to convert the onnx model to the tf model, a unique operator does not support it. Is there anything I can replace this operator?...

chenluuyou

I have converted my darknet model into onnx & then tensorrt. Everything is working fine i used this repo . https://github.com/jkjung-avt/tensorrt_demos. My goal is to use this converted yolov4x-mish.onnx model...

akashAD98

backend.prepare input_tensor_dict argument not useful because of new graph creation

6

It would be nice if the `input_tensor_dict` keyword argument to `backend.prepare()` was actually useful, but right now, because the code [creates a new graph](https://github.com/onnx/onnx-tensorflow/blob/72c81448bb17ca4adcd6c4f55e8e84ee0aef445a/onnx_tf/backend.py#L131), it's not usable. (The caller can't...

anishathalye

**Describe the bug** I have a quantized ONNX model that I want to convert to Tensorflow, but when using onnx-tensorflow to convert, it prints the following error message: ``` ValueError:...

peiwenhuang27

onnx_tf.backend.prepare for protobuf with External Data > 2GB

4

**Describe the bug** onnx_tf.backend.prepare fails for files that are smaller than 2GB that reference external data that cause them to grow beyond 2GB. Due to https://github.com/onnx/onnx-tensorflow/blob/b13a282f6c404df04a2ae5aaa24ea5ec6d2d4e64/onnx_tf/backend.py#L67 and https://github.com/onnx/onnx/blob/c24cd429c4ab47d2b057da8174788c39c60f8760/onnx/backend/base.py#L76 To check...

aron-easics

onnx to pb parse conv(padding=='same') as 2 seperate layer (pad + conv)

3

**Describe the bug** The tools parses conv(padding=='same') as 2 seperate layer (pad + conv) when converting from onnx to pb, this will affect the performance. **Python, ONNX, ONNX-TF, Tensorflow version**...

huangteng

GatherAndScatterMixin: TypeError: slice indices must be integers or None or have an __index__ method

1

**Describe the bug** I am trying to convert an ONNX model exported from [mmdetection](https://github.com/open-mmlab/mmdetection) framework but I am getting this error: ``` 2021-07-24 13:24:50.300861: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library...

mmeendez8

The program fails when there are two RNNs of the same flavor. The reason seems to be that the program registers them as the same layer. This implies that: -...

londumas

In RNN or LSTM, input_size =1 and /or hidden_size = 1 fails

1

Apparently trying to set input_size =1 and /or hidden_size = 1 in RNNs or LSTMs fails. Here is a minimal code and output ``` import numpy as np import torch...

londumas

Train onnx model from another framework

2

Hi everyone, I am now testing the example/train_onnx_model.py on Google Colab with the onnx model generated from MATLAB Deep Learning Tool Box and it shows the error: `==> Train the...

letruongthanh3698