ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange
Ask Your Question

Siva's profile - activity

2020-12-18 13:29:07 -0500 marked best answer I am able to convert pre-trained models(pfe.onnx and rpn.onnx) into tensorrt. But I am not able to convert our models into tensorrt.

ONNX IR version: 0.0.4 Opset version: 9 Producer name: pytorch Producer version: 1.1 Domain: Model version: 0 Doc string: While parsing node number 16 [Squeeze -> “175”]: ERROR: /home/erisuser/p4sw/sw/gpgpu/MachineLearning/DIT/release/5.0/parsers/onnxOpenSource/builtin_op_importers.cpp:1570 In function importSqueeze: [8] Assertion failed: axis != BATCH_DIM ERROR: failed to parse onnx file Please address the issue. Thanks in advance

2019-10-21 00:43:36 -0500 received badge  Famous Question (source)
2019-10-21 00:43:36 -0500 received badge  Notable Question (source)
2019-10-21 00:43:36 -0500 received badge  Popular Question (source)
2019-07-23 04:48:53 -0500 received badge  Enthusiast
2019-07-16 07:09:01 -0500 commented answer I am able to convert pre-trained models(pfe.onnx and rpn.onnx) into tensorrt. But I am not able to convert our models into tensorrt.

Got it, I am using Pytorch 1.1,tensorrt 5.0(as you mentioned in readme), ONNX IR version:0.0.4, Opset version:9 and con

2019-07-16 02:45:54 -0500 commented answer I am able to convert pre-trained models(pfe.onnx and rpn.onnx) into tensorrt. But I am not able to convert our models into tensorrt.

Thanks for the reply. May I know which version of Pytorch you used to convert to onnx models and tensorrt version?

2019-07-16 00:52:39 -0500 asked a question I am able to convert pre-trained models(pfe.onnx and rpn.onnx) into tensorrt. But I am not able to convert our models into tensorrt.

I am able to convert pre-trained models(pfe.onnx and rpn.onnx) into tensorrt. But I am not able to convert our models in