Closed kyflores closed 8 months ago
Did you get the model from here: https://github.com/TexasInstruments/edgeai-modelzoo/blob/main/models/vision/detection/coco/edgeai-mmdet/yolox_s_lite_640x640_20220221_model.onnx.link
I am seeing ONNX v7 in netron.app
I thought so, but I just did a fresh checkout of model zoo and I also have the v7 model now. I must have had a stale file lying around somehow, I remember briefly having a newer onnxruntime package installed while troubleshooting. Sorry for the trouble.
Hi @kyflores, I encountered the same issue as you did. How did you manage to solve it? Thank you.
Problem solved. By default, running setup_pc.sh
installs the latest version of ONNX 1.15.0
, which supports IR 9. To match onnxruntime-tidl==1.14.0
(IR 8), we need to downgrade ONNX version to 1.13.0
. Simpy done by pip install onnx==1.13.0
.
Hi,
I'm trying to adapt the
tutorial_detection
notebook to work a different prebuilt model, specificallyedgeai-mmdet/yolox_s_lite_640x640_20220221_model.onnx
. I'm on an Ubuntu host and set up the environment with the providedsetup_pc.sh
script, and both myedgeai-benchmark
andedgeai-modelzoo
repos are on ther9.1
tag.First I set
session_name = constants.SESSION_NAME_ONNXRT
in cell 6, then changed the pipeline_configs to this, just trying to follow the naming:When I run the cell to compile the model...
It fails with this message.
The onnx runtime version installed by the PC setup script is
onnxruntime-tidl==1.14.0
, but version 1.16.0 is required for IR 9Is there a 1.16.0 version of onnxruntime-tidl, or another pretrained model file that works IR 8?