# Errors in converting yolov3 to TensorRT **URL:** \ **Category:** Jetson TX2\ **Created:** [July 1, 2019, 6:42am UTC](https://forums.developer.nvidia.com/t/errors-in-converting-yolov3-to-tensorrt/77303 "2019-07-01T06:42:21Z")\ **Posts on this page:** 10\ **Page:** 1
**Author:** ![niuniu\_niu1](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@niuniu\_niu1](https://forums.developer.nvidia.com/u/niuniu_niu1)\ **Post date:** [July 1, 2019, 6:42am UTC](https://forums.developer.nvidia.com/t/errors-in-converting-yolov3-to-tensorrt/77303/1 "2019-07-01T06:42:21Z")
When i test the demo in /usr/src/tensorrt/samples/python/yolov3\_onnx, got errors as follows Reading engine from file yolov3.trt Segmentation fault (core dumped) and i have set up virtual memory,but it doesn’t work. ---
**Author:** ![kayccc](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/kayccc/32/14043_2.png) [@kayccc](https://forums.developer.nvidia.com/u/kayccc)\ **Post date:** [July 1, 2019, 7:38am UTC](https://forums.developer.nvidia.com/t/errors-in-converting-yolov3-to-tensorrt/77303/2 "2019-07-01T07:38:21Z")
Hi niuniu\_niu1, Do you follow the steps shared in our document? [url][https://docs.nvidia.com/deeplearning/sdk/tensorrt-sample-support-guide/index.html#yolov3\_onnx[/url]](https://docs.nvidia.com/deeplearning/sdk/tensorrt-sample-support-guide/index.html#yolov3_onnx%5B/url%5D) Thanks ---
**Author:** ![AastaLLL](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aastalll/32/14043_2.png) [@AastaLLL](https://forums.developer.nvidia.com/u/AastaLLL)\ **Post date:** [July 1, 2019, 7:52am UTC](https://forums.developer.nvidia.com/t/errors-in-converting-yolov3-to-tensorrt/77303/3 "2019-07-01T07:52:11Z")
Hi, This is a know issue. The default workspace size it too big for Jetson platform. Please decrease the number from 1G into 256Mb with the comment here: [url][https://devtalk.nvidia.com/default/topic/1052153/jetson-nano/tensorrt-backend-for-onnx-on-jetson-nano/post/5349962/#5349962[/url]](https://devtalk.nvidia.com/default/topic/1052153/jetson-nano/tensorrt-backend-for-onnx-on-jetson-nano/post/5349962/#5349962%5B/url%5D) Thanks. ---
**Author:** ![niuniu\_niu1](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@niuniu\_niu1](https://forums.developer.nvidia.com/u/niuniu_niu1)\ **Post date:** [July 1, 2019, 9:44am UTC](https://forums.developer.nvidia.com/t/errors-in-converting-yolov3-to-tensorrt/77303/4 "2019-07-01T09:44:29Z")
it doesn’t work on jetson TX2 ---
**Author:** ![AastaLLL](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aastalll/32/14043_2.png) [@AastaLLL](https://forums.developer.nvidia.com/u/AastaLLL)\ **Post date:** [July 2, 2019, 2:03am UTC](https://forums.developer.nvidia.com/t/errors-in-converting-yolov3-to-tensorrt/77303/5 "2019-07-02T02:03:27Z")
Thanks for your feedback. We will check this and update more information with you asap. ---
**Author:** ![AastaLLL](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aastalll/32/14043_2.png) [@AastaLLL](https://forums.developer.nvidia.com/u/AastaLLL)\ **Post date:** [July 2, 2019, 8:02am UTC](https://forums.developer.nvidia.com/t/errors-in-converting-yolov3-to-tensorrt/77303/6 "2019-07-02T08:02:03Z")
Hi, We can run the sample without any issue. Here is some update for your reference: **1.** Make sure your onnx is v1.4.1 ```auto $ pip install onnx==1.4.1 ``` **2.** Update _onnx\_to\_tensorrt.py_ workspace size into 256Mb Please try it again and let us know the result. Thanks. ---
**Author:** ![niuniu\_niu1](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@niuniu\_niu1](https://forums.developer.nvidia.com/u/niuniu_niu1)\ **Post date:** [July 3, 2019, 1:38am UTC](https://forums.developer.nvidia.com/t/errors-in-converting-yolov3-to-tensorrt/77303/7 "2019-07-03T01:38:24Z")
when i use yolov3-416 i get this error ValueError: cannot reshape array of size 43095 into shape (1,255,19,19) also i have modified onnx\_to\_tensorrt.py as follows # Two-dimensional tuple with the target network’s (spatial) input resolution in HW ordered ``` input_resolution_yolov3_HW = (416, 416) ``` so how to modify output\_shapes in onnx\_to\_tensorrt.py # Output shapes expected by the post-processor ``` output_shapes = [(1, 255, 19, 19), (1, 255, 38, 38), (1, 255, 76, 76)] ``` Thanks. ---
**Author:** ![niuniu\_niu1](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@niuniu\_niu1](https://forums.developer.nvidia.com/u/niuniu_niu1)\ **Post date:** [July 3, 2019, 2:46am UTC](https://forums.developer.nvidia.com/t/errors-in-converting-yolov3-to-tensorrt/77303/8 "2019-07-03T02:46:30Z")
it works when i modify output\_shapes = [(1, 255, 13, 13), (1, 255, 26, 26), (1, 255, 52, 52)] Thanks a lot! ---
**Author:** ![niuniu\_niu1](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@niuniu\_niu1](https://forums.developer.nvidia.com/u/niuniu_niu1)\ **Post date:** [July 3, 2019, 6:08am UTC](https://forums.developer.nvidia.com/t/errors-in-converting-yolov3-to-tensorrt/77303/9 "2019-07-03T06:08:22Z")
is there any demo for video? Thanks. ---
**Author:** ![nadeemm](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/nadeemm/32/367020_2.png) [@nadeemm](https://forums.developer.nvidia.com/u/nadeemm)\ **Post date:** [October 18, 2021, 6:33pm UTC](https://forums.developer.nvidia.com/t/errors-in-converting-yolov3-to-tensorrt/77303/10 "2021-10-18T18:33:00Z")
Closed on October 18, 2021, 6:33pm UTC