Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Unable to deserialise TRT engine #52

Open
Melvin-leo opened this issue Nov 8, 2024 · 0 comments
Open

Unable to deserialise TRT engine #52

Melvin-leo opened this issue Nov 8, 2024 · 0 comments

Comments

@Melvin-leo
Copy link

[info] load engine from file: /root/swarm_ws/src/D2SLAM/models/hitnet_series/hitnet_1x240x320_model_float16_quant_opt.trt
[11/08/2024-08:46:50] [I] [TRT] [MemUsageChange] Init CUDA: CPU +571, GPU +0, now: CPU 801, GPU 369 (MiB)
[11/08/2024-08:46:50] [I] [TRT] Loaded engine size: 6 MiB
[11/08/2024-08:46:50] [E] [TRT] 1: [stdArchiveReader.cpp::StdArchiveReader::40] Error Code 1: Serialization (Serialization assertion stdVersionRead == serializationVersion failed.Version tag does not match. Note: Current Version: 213, Serialized Engine Version: 232)
[11/08/2024-08:46:50] [E] [TRT] 4: [runtime.cpp::deserializeCudaEngine::50] Error Code 4: Internal Error (Engine deserialization failed.)
[2024-11-08 08:46:50.861] [error] deserializeCudaEngine failed
[2024-11-08 08:46:50.861] [error] deserializeEngine failed

Unable to deserialise the TRT of the quadcam depth estimation, using the dockerfile of x86, tensorrt version is 22.08 which might not support serialisation of the engine version 232. Hopefully, someone who got this to work can show me some workarounds, tried reinstalling tensorrt but it didnt work

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant