onnx-tensorflow
onnx-tensorflow copied to clipboard
onnx
Tensorflow Backend for ONNX
The converted model can not be finetuned, the following snippet will produce error: `net=tf.saved_model.load('./tf_model') for v in net.trainable_variables: print(v.name)` AttributeError: '_UserObject' object has no attribute 'trainable_variables'
**Describe the bug** 1. Why does `onnx-tensorflow` add **Transpose** layers for each Conv2D layer? 2. Why does `onnx-tensorflow` use multiple Conv2D layers instead of one GroupedConv2D layer? It increases inference...
**Describe the bug** Hi, I'm facing the following issue and I really need some help please: - Can convert to pytorch to Onnx - Can run inference using ONNX runtime...
**Describe the bug** depthwise and pointwise convolution convert ONNX to tensorflow failed `Traceback (most recent call last): File "trutorch_convert_onnx.py", line 108, in tf_rep.export_graph(tf_model_path) File "onnx-tensorflow/onnx_tf/backend_rep.py", line 132, in export_graph signatures=self.tf_module.__call__.get_concrete_function(...
**Describe the bug** Traceback (most recent call last): File "/usr/local/lib/python3.7/dist-packages/tensorflow_core/python/framework/ops.py", line 1607, in _create_c_op c_op = c_api.TF_FinishOperation(op_desc) tensorflow.python.framework.errors_impl.InvalidArgumentError: Shapes must be equal rank, but are 0 and 3 for 'onnx_tf_prefix_Where_1751'...
hi, i'm trying to covert a ONNX model to TF model, but it reported "RuntimeError: Node name is not unique in your model. Please recreate your model with unique node...
