Open NannilaJagadees opened 1 month ago
Note: dynamic shape need set calibration profile, and check the batch size, cuda h2d ptr, no -1
shape .
ref https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#int8-calib-dynamic-shapes
Hi @lix19937
I set the calibration profile. Values with batch size 1: Min (1, 3, 640, 640) Opt (1, 3, 640, 640) Max (1, 3, 640, 640).
Note: Model input size is fixed, not dynamic. Only the NMS and following nodes are dynamic.
Description
I am using this calibration script to generate the calib cache file for YoloV5 onnx model using EntropyCalibration2 method. But faced this issue after it starts calibrating for the 1st image.
Yolov5 model has topk and NMS nodes which has dynamic shape. How can we do calibration for such models?
Environment
TensorRT Version: 8.6.2.3
NVIDIA GPU: Orin Nano 8 GB
CUDA Version: 12.2
CUDNN Version: 8.9.4
Operating System: Jetpack 6.0
Python Version: 3.10
PyTorch Version: 2.3.0