# Jetson-inference detectnet.py --model=peoplenet , no engine file **URL:** \ **Category:** Jetson Xavier NX\ **Tags:** jetson-inference\ **Created:** [January 21, 2024, 7:20am UTC](https://forums.developer.nvidia.com/t/jetson-inference-detectnet-py-model-peoplenet-no-engine-file/279574 "2024-01-21T07:20:10Z")\ **Posts on this page:** 12\ **Page:** 1
**Author:** ![ztm](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/ztm/32/386588_2.png) [@ztm](https://forums.developer.nvidia.com/u/ztm)\ **Post date:** [January 21, 2024, 7:20am UTC](https://forums.developer.nvidia.com/t/jetson-inference-detectnet-py-model-peoplenet-no-engine-file/279574/1 "2024-01-21T07:20:10Z")
hi， I refer to the link guide to use Using TAO Detection Models. The hardware is Xavier NX, jetpack 5.1.2. > error logs: ![image](https://global.discourse-cdn.com/nvidia/original/4X/c/8/b/c8be6faf4a6c4d9e0c23acb59a4d61aee3e8363d.png) What have under networks folder: ![image](https://global.discourse-cdn.com/nvidia/original/4X/c/5/4/c540412ae19ac1dd191b60a7b3efa4db70751bb1.png) Looks like something wrong with peoplenet model. I can success with SSD-Mobilenet-v2 and SSD-Inception-v2 model. ---
**Author:** ![dusty\_nv](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/dusty_nv/32/14043_2.png) [@dusty\_nv](https://forums.developer.nvidia.com/u/dusty_nv)\ **Post date:** [January 21, 2024, 5:10pm UTC](https://forums.developer.nvidia.com/t/jetson-inference-detectnet-py-model-peoplenet-no-engine-file/279574/2 "2024-01-21T17:10:39Z")
Hi @ztm, can you please provide the command-line that you ran to start detectnet.py, along with the full console log (not a screenshot)? Thanks! ---
**Author:** ![ztm](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/ztm/32/386588_2.png) [@ztm](https://forums.developer.nvidia.com/u/ztm)\ **Post date:** [January 23, 2024, 2:31am UTC](https://forums.developer.nvidia.com/t/jetson-inference-detectnet-py-model-peoplenet-no-engine-file/279574/4 "2024-01-23T02:31:54Z")
Hi, the cmd is: ./detectnet.py --model=peoplenet pedestrians.mp4 pedestrians\_peoplenet.mp4 the full log is attached. The pedestrians.mp4 is under same folder with detectnet.py. [log.txt](https://forums.developer.nvidia.com/uploads/short-url/q6szhES0DN7uvhj1m4oc5OjwB6c.txt) (7.5 KB) ---
**Author:** ![dusty\_nv](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/dusty_nv/32/14043_2.png) [@dusty\_nv](https://forums.developer.nvidia.com/u/dusty_nv)\ **Post date:** [January 23, 2024, 5:17pm UTC](https://forums.developer.nvidia.com/t/jetson-inference-detectnet-py-model-peoplenet-no-engine-file/279574/5 "2024-01-23T17:17:02Z")
Hi @ztm, I just tried this on JetPack 5.1.2 with the same video and model, and was able to run it without issues - twice actually (once for the first time it generates the TRT engine, and again for when it just loads the already serialized TRT engine) I would recommend deleting your `jetson-inference/data/networks/peoplenet_deployable_quantized_v2.6.1` folder and trying again, perhaps there is something corrupted with your model. ---
**Author:** ![ztm](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/ztm/32/386588_2.png) [@ztm](https://forums.developer.nvidia.com/u/ztm)\ **Post date:** [January 24, 2024, 1:34am UTC](https://forums.developer.nvidia.com/t/jetson-inference-detectnet-py-model-peoplenet-no-engine-file/279574/6 "2024-01-24T01:34:19Z")
Hi Dusty\_nv, Thanks for your help. The first time I run detectnet.py --model=perplenet, it will download peoplenet\_deployable\_quantized\_v2.6.1 automatically but not all files can success download. The passed files including resnet34\_peoplenet\_int8.etlt resnet34\_peoplenet\_int8.txt labels.txt, the failed one is colors.txt. Then I download it from [https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/models/peoplenet](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/models/peoplenet). Could you paste the worked peoplenet\_deployable\_quantized\_v2.6.1 folder here? Thanks! ---
**Author:** ![dusty\_nv](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/dusty_nv/32/14043_2.png) [@dusty\_nv](https://forums.developer.nvidia.com/u/dusty_nv)\ **Post date:** [January 24, 2024, 2:55am UTC](https://forums.developer.nvidia.com/t/jetson-inference-detectnet-py-model-peoplenet-no-engine-file/279574/7 "2024-01-24T02:55:13Z")
> [@ztm](#): > > Could you paste the worked peoplenet\_deployable\_quantized\_v2.6.1 folder here? Thanks! Yes, here it is: [https://nvidia.box.com/shared/static/3q6252z11aot2rrdih8pfxervqpat2tz.gz](https://nvidia.box.com/shared/static/3q6252z11aot2rrdih8pfxervqpat2tz.gz) ---
**Author:** ![ztm](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/ztm/32/386588_2.png) [@ztm](https://forums.developer.nvidia.com/u/ztm)\ **Post date:** [January 24, 2024, 3:32am UTC](https://forums.developer.nvidia.com/t/jetson-inference-detectnet-py-model-peoplenet-no-engine-file/279574/8 "2024-01-24T03:32:39Z")
HI Dusty\_nv, I just extract the file tar -zxvf peoplenet\_deployable\_quantized\_v2.6.1.tar.gz ![image](https://global.discourse-cdn.com/nvidia/original/4X/2/d/c/2dc1d23362e901650129dbc46dc36c8c38542d62.png) Then ran ./detectnet.py --model=peoplenet pedestrians.mp4 pedestrians\_peoplenet.mp4 The error still exist as below: [TRT] completed loading NVIDIA plugins. [TRT] detected model format - engine (extension ‘.engine’) [TRT] loading network plan from engine cache… [TRT] failed to load engine cache from [TRT] failed to load [TRT] detectNet – failed to initialize. Traceback (most recent call last): File “./detectnet.py”, line 53, in net = detectNet(args.network, sys.argv, args.threshold) Exception: jetson.inference – detectNet failed to load network I still can success with default model. ./detectnet.py pedestrians.mp4 pedestrians\_peoplenet.mp4 ---
**Author:** ![dusty\_nv](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/dusty_nv/32/14043_2.png) [@dusty\_nv](https://forums.developer.nvidia.com/u/dusty_nv)\ **Post date:** [January 24, 2024, 2:53pm UTC](https://forums.developer.nvidia.com/t/jetson-inference-detectnet-py-model-peoplenet-no-engine-file/279574/9 "2024-01-24T14:53:51Z")
Hmm that is curious, because I can run the exact same thing here without issue. What happens if you run it using detectnet (C++ version) instead of detectnet.py? ---
**Author:** ![ztm](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/ztm/32/386588_2.png) [@ztm](https://forums.developer.nvidia.com/u/ztm)\ **Post date:** [January 27, 2024, 3:18am UTC](https://forums.developer.nvidia.com/t/jetson-inference-detectnet-py-model-peoplenet-no-engine-file/279574/10 "2024-01-27T03:18:29Z")
Hi dusty\_nv, the C++ detectnet has the similar error as attached. [note.txt](https://forums.developer.nvidia.com/uploads/short-url/wQO4e3S7rZRuW6569hHBq5c9GfL.txt) (7.4 KB) The log has a Tensor error: [TRT] Could not register plugin creator - ::FlattenConcat\_TRT version 1 is it the reason? ---
**Author:** ![ztm](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/ztm/32/386588_2.png) [@ztm](https://forums.developer.nvidia.com/u/ztm)\ **Post date:** [January 27, 2024, 3:25am UTC](https://forums.developer.nvidia.com/t/jetson-inference-detectnet-py-model-peoplenet-no-engine-file/279574/11 "2024-01-27T03:25:05Z")
adding the correct logs with default model. [note2.txt](https://forums.developer.nvidia.com/uploads/short-url/aDP1XSdQ4VMyCcblXFkd6zcwMXt.txt) (23.0 KB) After enter CMD, the mp4 video detection will show up after serveral seconds. ---
**Author:** ![dusty\_nv](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/dusty_nv/32/14043_2.png) [@dusty\_nv](https://forums.developer.nvidia.com/u/dusty_nv)\ **Post date:** [January 29, 2024, 3:11pm UTC](https://forums.developer.nvidia.com/t/jetson-inference-detectnet-py-model-peoplenet-no-engine-file/279574/12 "2024-01-29T15:11:56Z")
Hi @ztm, I’m sorry, unfortunately I’m unable to determine the cause of your issue, even after running the same commands on the same version of JetPack (which strangely both run fine here). I’m wondering if perhaps the version of jetson-inference code you are running is older, are you able to update it to the latest and recompile? Or perhaps use the jetson-inference docker container to check it. Sorry again about that! ---
**Author:** ![ztm](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/ztm/32/386588_2.png) [@ztm](https://forums.developer.nvidia.com/u/ztm)\ **Post date:** [February 13, 2024, 1:50am UTC](https://forums.developer.nvidia.com/t/jetson-inference-detectnet-py-model-peoplenet-no-engine-file/279574/13 "2024-02-13T01:50:33Z")
Hi dusty\_nv, Thanks for your experiments and sorry for the late response. I used a new Orin NX module to test. But the result is same. I also tried it with docker, also meet the same error. Attaching the log. [log\_docker.txt](https://forums.developer.nvidia.com/uploads/short-url/7DOKDzwHXmforPsJVRYekmfKbBr.txt) (13.9 KB)