onnx-tensorflow
onnx-tensorflow copied to clipboard
Tensorflow Backend for ONNX
when the inputs of nn.Linear is three-dimension (batchxseq_lenxdim_size)like the "FeedForward" of Transformer,it occurs ValueError: Shape must be rank 2 but is rank 3 for 'MatMul_2' (op: 'MatMul') with input shapes:...
**Describe the bug** I cannot convert a simple dense network from PyTorch to Tensorflow through ONNX. >ValueError: Dimensions must be equal, but are 1 and 7 for '{{node onnx_tf_prefix_If_4/MatMul}} =...
**Describe the bug** `ValueError: Cannot take the length of shape with unknown rank.` exception is raised from convolution implementation during ONNX evaluation. **ONNX model file** [`stt_fr_quartznet15x5.onnx`](https://drive.google.com/file/d/11CrXHlHreKPT8oQnLmjlqqIktkjMYb8h/view) **To Reproduce** ```python import...
**Describe the bug** iterating over `tf.Tensor` is not allowed: AutoGraph did convert this function. This might indicate you are trying to use an unsupported feature. A clear and concise description...
I was reading about the conversion of pytorch to onnx, the conversion happens because of a parser which takes the dummy input into the pytorch model and looks for the...
Dear all, i'm trying to convert a .onnx model opset 12 to tensorflow. Using the onnx runtime the model works correctly, but if I try to convert it using the...
**Describe the bug** Error "No schema registered for 'Celu'!" happens when I'm trying to run "onnx_tf.backend.prepare(my_model)". Is there a way to solve this problem? **To Reproduce** My code is just:...
I've created new environment, windows OS, conda installed tensorflow==2.3.1 and onnx-tf via pip I have onnx model exported from pytorch. and the code ``` onnx_model = onnx.load(input_path) # load onnx...
It's been more than 10 mins and I'm stuck after: ``` 2021-03-19 12:10:06,839 - onnx-tf - WARNING - Do not fully support sampling_ratio
**Describe the bug** I need export a torch model which consists of vgg and rnn into tensorflow. For this purpose I use PyTorch —> ONNX —> Tensorflow approach. However, I...