tensorflow-onnx

tensorflow-onnx copied to clipboard

the examples are awesome but file have to named correctly

vishwas1234567

ValueError: tensorflow op ExtractImagePatches is not supported

30

I am trying to convert yolov2-voc generated by DarkFlow in to ONNX, and running in to this error "ValueError: tensorflow op ExtractImagePatches is not supported" I am using tensorflow=1.9.0, onnx=1.4.1,...

ayermolo

Hardcoded UInt8 idtype in FakeQuantWithMinMaxArgs, unsupported in TensorRT

4

These two lines look odd to me... Why hard code the input dtype to uint8? Such type is **unsupported in TensorRT**. How can I avoid such problems when I convert...

doomooo

Turning off back-to-back optimizer does not disable fusing batch normalization layers into convolutional layers

6

**Describe the bug** Hi, I was converting CenterNet([CenterNet HourGlass104 512x512](centernet_hg104_512x512_coco17_tpu-8) from Tensorflow Object Detection API(https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md) with the Back-to-back optimizer turned off to disable the batchnorm fusion into conv layers following...

Mypathissional

[E:onnxruntime:, sequential_executor.cc:346 Execute] Non-zero status code returned while running Add node. Name:'Add_1363' Status Message: /onnxruntime_src/onnxruntime/core/providers/cpu/math/element_wise_ops.h:505 void onnxruntime::BroadcastIterator::Append(ptrdiff_t, ptrdiff_t) axis == 1 || axis == largest was false. Attempting to broadcast an axis by a dimension other than 1. 9 by 505

2

**Error Message ** 2022-02-22 09:30:14.294491544 [E:onnxruntime:, sequential_executor.cc:346 Execute] Non-zero status code returned while running Add node. Name:'Add_1363' Status Message: /onnxruntime_src/onnxruntime/core/providers/cpu/math/element_wise_ops.h:505 void onnxruntime::BroadcastIterator::Append(ptrdiff_t, ptrdiff_t) axis == 1 || axis == largest...

wdYangX

tf2onnx creating empty and unuseable onnx model from SSD Mobilenet

1

**Describe the bug** When attempting to convert a TF SSD Mobilenet FPN model that has been trained via transfer learning from SavedModel to Onnx using tf2onnx the optimizer outputs an...

ingenuityiot

tf.unstack / tf.split on input loses dynamic batch size

3

**Describe the bug** When `tf.unstack` or `tf.split` is used on an input, dynamic batch dimension is lost. This was found while trying to export [NodLabs's DLRM](https://github.com/NodLabs/tensorflow-dlrm). An example script is...

cchan-lm

Convert NHWC/NCHW transpose as ONNX Local Function during export.

6

The original model is in TFLite, with NHWC format. When export to ONNX, because there is no NCHW format in ONNX, exporter spend quite big efforts to convert it to...

fatcat-z

Fixed Conv3DTranspose with strides for data format channels_first (fixes #1714)

1

While shape calculations for the input correctly distinguished between channels_first and channels_last, shape calculations for the inputs of the final Slice and Pad nodes always assumed channels_last format.

fthielke

Added support for int64 -> string CategoryMapper.

1

rmarrugat