onnx-tensorflow
onnx-tensorflow copied to clipboard
onnx
Tensorflow Backend for ONNX
**Describe the bug** After an export of pytorch pretrained resnet101, and it conversion into savedModel with onnx-tf, it seems that even if SignatureDefs are present, ConcreteFunction are not well converted...
when I use import the backend, like: > from onnx_tf.backend import prepare --------------------------------------------------------------------------- ImportError Traceback (most recent call last) in () ----> 1 from onnx_tf.backend import prepare C:\Users\7000031151\Miniconda3\envs\python36\lib\site-packages\onnx_tf\__init__.py in ()...
**Describe the bug** When using PB model to load locally, it can be predicted normally, but TF serving reports an error，as follow： {'error': 'indices = 1 is not in [0,...
Since I have to use tensorflow 1.14, I would like to ask which version of onnx-tf is suitable for tensorflow 1.14.
When I export onnx model to tensorflow using the following code: ``` import onnx from onnx_tf.backend import prepare onnx_model = onnx.load("PtMaskRCNN-leaves.onnx") tf_rep = prepare(onnx_model) tf_rep.export_graph("model.pb") ``` following run time error...
**I have a quantize onnx model and also I want to export to tf and then export to tflite(tensorflow-lite). But unfortunately I face this error.** Could you please help me...
I tried to convert pytorch [RAFT model](https://github.com/princeton-vl/RAFT) to tensorflow model via onnx. However, I got an error message like below: ``` 2022-05-26 00:46:27.068698: W tensorflow/core/framework/op_kernel.cc:1745] OP_REQUIRES failed at functional_ops.cc:373 :...
**Describe the bug** When `QLinearConv` is used with a 1-D bias, it is expecting the wrong shape. Specifically, given a 1x3x224x224 `x` input (NxCxHxW), a 64x3x7x7 `w` input (MxCxkHxkW) and...
Hello, everyone! I would like to know who is using onnx-tensorflow converter. If you are one of them, please leave a comment. We are currently short of development resources and...
**Describe the bug** Cannot convert ONNX with dynamic input to Tensorflow  **To Reproduce** 1. converting Pytorch model to ONNX model was used **Resnext50_32x4d** with dynamic batch size ``` dummy_input...
