I am encountering issues when trying to deploy and run the YOLOv5m6 ONNX model on the Metis M.2. Below are the details of the steps I followed and the issues that arose:

1. Deployment Process:

I used the following command to deploy the model:

./deploy.py customers/mymodels/yolov5m6-object-detection.yaml

The deployment was successful, but I encountered warnings about memory overflow during the buffer fitting process:

LowerTIR failed to fit buffers into memory after iteration 0/4.
  Pool usage: {L1: alloc:4,195,840B avail:4,194,304B over:1,536B util:100.04%, L2: alloc:6,864,384B avail:8,077,312B over:0B util:84.98%, DDR: alloc:54,275,328B avail:260,046,848B over:0B util:20.87%}

2. Inference Process:

I then attempted to run inference with the following command:

./inference.py c-yolov5m6-object-detection chinmay/Vehicle-CV-ADAS/assets/VID-20250208-WA0008.mp4 --save-output ~/Desktop/voyager-sdk/chinmay/saved_videos/output.mp4

The model failed to run due to a ShapeInferenceError related to incompatible dimensions during the ONNX model loading:

terminate called after throwing an instance of 'std::runtime_error'
  what():  Failed to create ONNX Runtime session: Load model from /home/aravind/Desktop/voyager-sdk/build/yolov5m6-object-detection/yolov5m6-object-detection/1/postprocess_graph.onnx failed:Node (Mul_526) Op (Mul) [ShapeInferenceError] Incompatible dimensions
Aborted (core dumped)

3. Model Inputs and Outputs:

• The input shape for the model is [1, 3, 512, 640] (batch size 1, 3 channels, 512x640 image size).

• The output shape from the model is [1, 20400, 85], which corresponds to 20400 possible bounding boxes with 85 values per box (4 coordinates, 1 objectness score, 80 class scores).

4. Steps Taken So Far:

• I have validated the model using ONNX runtime and confirmed that the model is correct and the input shape is consistent.
• I also tried adjusting the YAML file to match the model's input/output requirements.

5. Links:

• YAML file: Download YAML file

• ONNX model: Download YOLOv5m6 ONNX model

Looking forward to your guidance on resolving this issue.