Convert pb to uff

spolisetty · May 18, 2021, 3:19pm

Looks like this is known issue. Natively TensorRT doesn’t support UINT8 data type. When we generate ONNX model, observed data type is UINT8, modifying ONNX model may be error prone.

Please refer following, you may find useful.

github.com/onnx/onnx-tensorrt

Unsupported ONNX data type: UINT8 (2)

opened 02:57PM - 21 Feb 20 UTC

bnascimento

bug triaged

Folowing the tutorial from the notebook https://github.com/onnx/tensorflow-onnx/…blob/master/tutorials/ConvertingSSDMobilenetToONNX.ipynb I am trying to work with a mobilenetv2 and v3 frozen models from tensorflow frozen_inference_graph.pb or a saved_model.pb to convert to ONNX and to TensorRT files. Under NGC dockers 20.01-tf1-py3 and 19.05-py3 I am using both this and tensorflow-onnx projects. I alwaysget different issues, the furthest I got was under 20.01-tf1-py3 with both onnx-tensorrt and tensorflow-onnx on master branchs and install the projects from source. I was able to create the .onnx file, but when I try to create the .trt file I get the following. ``` onnx2trt /media/bnascimento/project/frozen_inference_graph.onnx -o /media/bnascimento/project/frozen_inference_graph.trt ---------------------------------------------------------------- Input filename: /media/bnascimento/project/frozen_inference_graph.onnx ONNX IR version: 0.0.6 Opset version: 10 Producer name: tf2onnx Producer version: 1.6.0 Domain: Model version: 0 Doc string: ---------------------------------------------------------------- Parsing model Unsupported ONNX data type: UINT8 (2) ERROR: image_tensor:0:190 In function importInput: [8] Assertion failed: convertDtype(onnxDtype.elem_type(), &trtDtype) ``` I suspect this has to do with the input tensor for the image, but I dont know how to avoid this issue. Anyone with similar issues before? Cheers Bruno

If you still need further assistance we recommend you to post your query on Jetson forum to get better help.

Thank you.

Topic		Replies	Views
Problem converting ONNX model to TensorRT Engine for SSD Mobilenet V2 Jetson Nano tensorrt , nvbugs , ssd , onnx	38	9031	October 18, 2021
Unsupported ONNX data type: UINT8 (2) TensorRT	24	9216	May 6, 2021
Convert Tensoflow V2 model ( pb format) to UFF Jetson Nano tensorflow	7	1393	October 18, 2021
mobilenet onnx problem TensorRT	10	1955	October 12, 2021
TensorRT and Tensorflow: convert to uff failed Jetson TX2	43	14773	October 18, 2021
Uff to trt8 TensorRT tensorrt	6	928	January 19, 2022
Retraining Custom MobilenetV2-fn and use on TensorRT TensorRT	10	690	November 29, 2020
Convert frozen_inference_graph.pb to .uff failed! TensorRT tensorrt , tensorflow	1	640	September 8, 2020
Jetson nano frozen_grap.pb convert to uff TensorRT jetson-inference	1	870	September 23, 2020
Convert the pb files into UFF, some issues to solve Jetson Nano tensorrt	2	390	October 18, 2021

Convert pb to uff

Related topics