UFF Parser Error when build TRT Engine for SSD_mobilenet_v2

Robotics & Edge Computing Jetson & Embedded Systems Jetson AGX Xavier
1

Env:
Xavier
Jetpack 4.2

reproduce:
git clone GitHub - AastaNV/TRT_object_detection: Python sample for referencing object detection model with TensorRT
Follow README.md and run ssd_mobilenet_v2_coco sample successfully
replace model file(.pb) with my mobilenet_v2（maybe build on another version of tensorflow than sample）, re-run failed

Error Message
[TensorRT] ERROR: UFFParser: Parser error: BoxPredictor_0/Reshape: Reshape: -1 dimension specified more than 1 time

Model:
link: 百度网盘-链接不存在
password: jv0g

2

Hi,

I cannot access your model. Could you check the link.
Thanks.

3

pls try ssd.pb - Google Drive

4

Hi,

Do you update the ssd_mobilenet_v2_coco’s architecture? Your model is much smaller than the default data.

-rw-r--r--  1 nvidia nvidia 69688296  七  24 15:42 frozen_inference_graph.pb
-rw-rw-r--  1 nvidia nvidia  5421103  七  24 15:42 ssd.pb

If you customize the architecture, the config should also be updated.
Thanks.