Pytorch > ONNX > TensorRT

vision
1

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 this issue. Thanks in advance.

2

Hi, I see your problem is on another level but I wanted to ask you how you done the onnx -> tensorrt conversion. Because I could convert my sample neural network code written in pytorch to onnx but I can’t go through with the next step. Thanks!

3

this website have a lot of examples showing on tensorrt examples.

all include training codes of pytorch:

http://manaai.cn

2 Likes
4

Hi @Jinfagang, i am new with manaai.com, and i want to join, would you verify me via wechat security barcode.

Thanks!

Screenshot_20191223-161252_WeChat
Screenshot_20191223-161252_WeChat1440×2960 530 KB

5

@Joe_Smith Pls add me wechat via: jintianiloveu

(If you can not loggin wechat, pls contact via this forum: t.manaai.cn