tensorflow-onnx icon indicating copy to clipboard operation
tensorflow-onnx copied to clipboard

Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

Results 269 tensorflow-onnx issues
Sort by recently updated
recently updated
newest added

**Describe the bug** I have a model of segmentation, [Bisenet-V2](https://github.com/MaybeShewill-CV/bisenetv2-tensorflow/blob/master/bisenet_model/bisenet_v2.py). Need to convert to FP16 model, first convert a FP32 model successfully, and predict successfully too. Then use `float16_converter` of...

bug

**Describe the bug** A simple tensorflow model with Conv3D and pooling is 3.6x slower on CPU after converting to ONNX. The same model with Conv3D replaced by Conv2D is 10x...

bug
pending on user response

Im trying to convert tensorflow model to onnx. I have attached my python file. Error ``` raise e.with_traceback(filtered_tb) from None ValueError: Exception encountered when calling layer 'max_pooling2d' (type MaxPooling2D). Negative...

bug

tf2onnx>=1.15 pins protobuf~=3.20.2. Tensorflow >=2.13 requires tf2onnx >= 1.15 due to https://github.com/onnx/tensorflow-onnx/pull/2215 In order to use gRPC natively with M1/M2 chips, we need at least grpcio>=1.51.3, which in turn requires...

enhancement
pending on user response

# New Operator ### Describe the operator Basic BeamSearch decoder as described [here](https://www.tensorflow.org/api_docs/python/tf/nn/ctc_beam_search_decoder) ### Do you know this operator be constructed using existing ONNX operators? I think so but I...

pending on user response
unsupported ops

**Describe the bug** I trained the YOLOV8Detector model in Kerala CM, then I converted it to saved_model format and then converted it to ON format. If I convert a model...

bug
pending on user response
unsupported ops

**Describe the bug** When I convert a u-net architecture a Conv operator and a BN operator are not fused together and 2 Reshape operators are added which reshape to the...

bug
pending on user response

**Describe the bug** I converted a frozen TensorFlow model (in the form of a .pb file) to ONNX using the following command: python -m tf2onnx.convert --input rfcn_WIDERFACE.pb --inputs image_tensor:0[1,-1,-1,3] --outputs...

bug
pending on user response

Before submitting your request, please review past submissions to ensure that it is not a duplicate of a known feature request. ### Describe the feature request Add mypy type hints...

enhancement