search

enazoe / yolo-tensorrt

TensorRT8.Support Yolov5n,s,m,l,x .darknet -> tensorrt. Yolov4 Yolov3 use raw darknet *.weights and *.cfg fils. If the wrapper is useful to you,please Star it.
MIT License
1.18k stars 316 forks source link

YOLOV4 INT8 Calibration ERROR #173

Open liuyang9709 opened 2 years ago

liuyang9709 commented 2 years ago

File does not exist : ../configs/yolov4-kINT8-batch2.engine Building the TensorRT Engine... Using cached calibration table to build the engine Using cached calibration table to build the engine WARNING: TensorRT was linked against cuBLAS/cuBLAS LT 11.5.1 but loaded cuBLAS/cuBLAS LT 11.4.2 WARNING: Detected invalid timing cache, setup a local cache instead ERROR: 2: [reformatRunner.cpp::onShapeChangeNONCONST::104] Error Code 2: Internal Error (Assertion mCombinedScalesSize >= channelDst failed.) yolo-trt: /work/app/yolo-tensorrt/modules/yolo.cpp:488: void Yolo::createYOLOEngine(nvinfer1::DataType, Int8EntropyCalibrator*): Assertion `m_Engine != nullptr' failed.

Device: RTX A4000 OS: Ubuntu 20.04 CUDA 11.3, CUDNN 8.2.1, TensorRT 8.0.1.6

wangxudong-cq commented 2 years ago

I had the same issue with xavier on yolov3/4/5. ENV: Xlib: extension "NV-GLX" missing on display "localhost:11.0". Xlib: extension "NV-GLX" missing on display "localhost:11.0". Xlib: extension "NV-GLX" missing on display "localhost:11.0".

wangxudong-cq commented 1 year ago

the same issue, pls make a reply.

Lenan22 commented 1 year ago

File does not exist : ../configs/yolov4-kINT8-batch2.engine Building the TensorRT Engine... Using cached calibration table to build the engine Using cached calibration table to build the engine WARNING: TensorRT was linked against cuBLAS/cuBLAS LT 11.5.1 but loaded cuBLAS/cuBLAS LT 11.4.2 WARNING: Detected invalid timing cache, setup a local cache instead ERROR: 2: [reformatRunner.cpp::onShapeChangeNONCONST::104] Error Code 2: Internal Error (Assertion mCombinedScalesSize >= channelDst failed.) yolo-trt: /work/app/yolo-tensorrt/modules/yolo.cpp:488: void Yolo::createYOLOEngine(nvinfer1::DataType, Int8EntropyCalibrator*): Assertion `m_Engine != nullptr' failed.

Device: RTX A4000 OS: Ubuntu 20.04 CUDA 11.3, CUDNN 8.2.1, TensorRT 8.0.1.6

Please refer to our open source quantization tool ppq, the quantization effect is better than the calibration of tensorrt, if you encounter issues, we can help you solve them. https://github.com/openppl-public/ppq/blob/master/md_doc/deploy_trt_by_OnnxParser.md