INT8 Calibration error in YOLOV8 with Tensorrt7.1

[tms2003]

WARNING: [TRT]: Calibration Profile is not defined. Calibrating with Profile 0I use deepstream 7.1 to perform yolov8 fp32 and fp16 reasoning normally, but an error occurs when int8 reasoning:

root@myai:export INT8_CALIB_IMG_PATH=/data/DeepStream-Yolo/calibration.txt
root@myai:/data/DeepStream-Yolo# export INT8_CALIB_BATCH_SIZE=4


root@myai:/data/DeepStream-Yolo# deepstream-app -c deepstream_app_config.txt 

 *** DeepStream: Launched RTSP Streaming at rtsp://localhost:8554/ds-test ***

Failed to query video capabilities: Invalid argument
WARNING: ../nvdsinfer/nvdsinfer_model_builder.cpp:1152 Deserialize engine failed because file path: /data/DeepStream-Yolo/model_b4_gpu0_int8.engine open error
0:00:00.201818454   603 0x593cf8dffe60 WARN                 nvinfer gstnvinfer.cpp:681:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2080> [UID = 1]: deserialize engine from file :/data/DeepStream-Yolo/model_b4_gpu0_int8.engine failed
0:00:00.201856666   603 0x593cf8dffe60 WARN                 nvinfer gstnvinfer.cpp:681:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2185> [UID = 1]: deserialize backend context from engine from file :/data/DeepStream-Yolo/model_b4_gpu0_int8.engine failed, try rebuild
0:00:00.201867746   603 0x593cf8dffe60 INFO                 nvinfer gstnvinfer.cpp:684:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2106> [UID = 1]: Trying to create engine from model files
WARNING: ../nvdsinfer/nvdsinfer_model_builder.cpp:382 INT8 calibration file not specified/accessible. INT8 calibration can be done through setDynamicRange API in 'NvDsInferCreateNetwork' implementation

Building the TensorRT Engine


File does not exist: /data/DeepStream-Yolo/calib.table
WARNING: [TRT]: Calibration Profile is not defined. Calibrating with Profile 0
ERROR: [TRT]: [checkSanity.cpp::checkLinks::218] Error Code 2: Internal Error (Assertion item.second != nullptr failed. region should have been removed from Graph::regions)
Segmentation fault (core dumped)

My configuration code is as follows:

[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
model-color-format=0
onnx-file=/data/weights/yolov8_1280_c11.pt.onnx
model-engine-file=model_b4_gpu0_int8.engine
int8-calib-file=calib.table
labelfile-path=c11.txt
batch-size=4
#0=FP32, 1=INT8, 2=FP16 mode
network-mode=1
num-detected-classes=11
interval=0
gie-unique-id=1
process-mode=1
network-type=0
cluster-mode=2
maintain-aspect-ratio=1
symmetric-padding=1
#workspace-size=2000
parse-bbox-func-name=NvDsInferParseYolo
#parse-bbox-func-name=NvDsInferParseYoloCuda
custom-lib-path=nvdsinfer_custom_impl_Yolo/libnvdsinfer_custom_impl_Yolo.so
engine-create-func-name=NvDsInferYoloCudaEngineGet

[class-attrs-all]
nms-iou-threshold=0.45
pre-cluster-threshold=0.25
topk=300

I use the latest nvidia official docker image.
NVIDIA-SMI 560.35.03 Driver Version: 560.35.03 CUDA Version: 12.6.
The hardware is RTX 4070ti super.

[LJ-Hao]

The same error with Nvidia Jetson Orin Nano.

[jcgassoloncan]

Hi, I think it is related with this #585 (comment)