node.js나 python 같은 인터프리트 언어가 대세라 그런가..
컴파일 언어를 인터프리트 언어 처럼 쓰게 해주는 환경이라니..
REPL(read-eval-print loop)
[링크 : https://github.com/x-motemen/gore]
[링크 : https://gorepl.com/]
[링크 : https://tkim.info/ko/devnote/d054-gore쓰다가-답답해서-tour-of-go-설치해서-쓴-썰/]
delve는 디버거 패키지.. 아니 툴이라고 해야하나?
| golang 다른 파일 함수 불러오기 (0) | 2022.04.04 |
|---|---|
| liteide (0) | 2022.04.04 |
| go build 옵션 (0) | 2022.03.31 |
| go lang static http server (0) | 2022.03.10 |
| go hello world build static / shared (0) | 2022.02.17 |
gcc와 유사한 옵션들이군..
-o 옵션을 통해 실행파일 이름을 지정할 수 있는데, 지정하지 않을 경우 소스코드의 이름을 출력이름으로 지정한다.
| go build [-o output] [build flags] [packages] |
[링크 : https://pkg.go.dev/cmd/go]
| $ go build -linkshared filename.go |
옵션을 통해 빌드할때
| open /usr/lib/go-1.17/pkg/linux_amd64_dynlink/archive/zip.shlibname: permission denied |
권한이 부족해서 거부되었다는 에러가 발생하는데 대개는 sudo를 주고 하지만
왜 발생하나 궁금해서 찾아보니
dynlink에 파일들이 linkshared 옵션으로 빌드할때 날짜가 변경되는 것으로 보인다.
*.a 나 libstd.so 들 역시 변경되는걸 봐서는 linkshared로 빌드할때 해당 so도 같이 빌드 하는 듯.
[링크 : https://superuser.com/questions/739738/how-to-use-go-get-as-non-root]
dynlink 에서 GOROOT라는 변수가 보이길래 보는데 선언된건 없고..
| $ cd $GOROOT/pkg/linux_amd64_dynlink $ ls libstd.so libstd.so |
[링크 : https://www.codestudyblog.com/cs2112goa/1212131010.html]
도움말 보다보니 env라는 명령어 발견
| $ go --help Go is a tool for managing Go source code. Usage: go <command> [arguments] The commands are: bug start a bug report build compile packages and dependencies clean remove object files and cached files doc show documentation for package or symbol env print Go environment information fix update packages to use new APIs fmt gofmt (reformat) package sources generate generate Go files by processing source get add dependencies to current module and install them install compile and install packages and dependencies list list packages or modules mod module maintenance run compile and run Go program test test packages tool run specified go tool version print Go version vet report likely mistakes in packages Use "go help <command>" for more information about a command. Additional help topics: buildconstraint build constraints buildmode build modes c calling between Go and C cache build and test caching environment environment variables filetype file types go.mod the go.mod file gopath GOPATH environment variable gopath-get legacy GOPATH go get goproxy module proxy protocol importpath import path syntax modules modules, module versions, and more module-get module-aware go get module-auth module authentication using go.sum packages package lists and patterns private configuration for downloading non-public code testflag testing flags testfunc testing functions vcs controlling version control with GOVCS Use "go help <topic>" for more information about that topic. |
| $ go env GO111MODULE="" GOARCH="amd64" GOBIN="" GOCACHE="/home/minimonk/.cache/go-build" GOENV="/home/minimonk/.config/go/env" GOEXE="" GOEXPERIMENT="" GOFLAGS="" GOHOSTARCH="amd64" GOHOSTOS="linux" GOINSECURE="" GOMODCACHE="/home/minimonk/go/pkg/mod" GONOPROXY="" GONOSUMDB="" GOOS="linux" GOPATH="/home/minimonk/go" GOPRIVATE="" GOPROXY="https://proxy.golang.org,direct" GOROOT="/usr/lib/go-1.17" GOSUMDB="sum.golang.org" GOTMPDIR="" GOTOOLDIR="/usr/lib/go-1.17/pkg/tool/linux_amd64" GOVCS="" GOVERSION="go1.17.8" GCCGO="gccgo" AR="ar" CC="gcc" CXX="g++" CGO_ENABLED="1" GOMOD="/dev/null" CGO_CFLAGS="-g -O2" CGO_CPPFLAGS="" CGO_CXXFLAGS="-g -O2" CGO_FFLAGS="-g -O2" CGO_LDFLAGS="-g -O2" PKG_CONFIG="pkg-config" GOGCCFLAGS="-fPIC -m64 -pthread -fmessage-length=0 -fdebug-prefix-map=/tmp/go-build1772520358=/tmp/go-build -gno-record-gcc-switches" |
저 놈의 GOTOOLDIR을 바꾸어 주면 되려나?
GOOS와 GOARCH를 이용해서 크로스컴파일 가능하다고 한다.
| $ env GOOS=windows GOARCH=amd64 go build source.go |
이게 되네..
| $ GOARCH=arm go build hello.go $ file hello hello: ELF 32-bit LSB executable, ARM, EABI5 version 1 (SYSV), statically linked, not stripped $ GOARCH=arm64 go build hello.go $ file hello hello: ELF 64-bit LSB executable, ARM aarch64, version 1 (SYSV), statically linked, not stripped |
| liteide (0) | 2022.04.04 |
|---|---|
| golang gore(repl), delve (0) | 2022.03.31 |
| go lang static http server (0) | 2022.03.10 |
| go hello world build static / shared (0) | 2022.02.17 |
| go lang rest (0) | 2022.02.11 |
gstreamer 에러 로그 보는데 색상이 있으면 좋겠다 싶어서
gst-launch .. > log 2>&1
으로 로그 저장하고 aha로 변환
| codesys (0) | 2022.05.18 |
|---|---|
| debian noroot 와 userland (0) | 2022.05.02 |
| mscgen (0) | 2022.03.17 |
| android userland ubuntu (0) | 2022.03.03 |
| bingwall (for ubuntu) (0) | 2022.01.19 |
이 한줄이 참.. 많은 문제를 낳는구만.. -_-
| $ gst-launch-1.0 nvinferserver ERROR: pipeline could not be constructed: no element "nvinferserver". |
왜 안되나 했는데 native하게 까는건 없는지 멀 하려고 하면 다 막히고, 걍 docker로 ㄱㄱ -_-
| Can Gst-nvinfereserver (DeepSream Triton plugin) run on Nano platform? Yes. But due to Nano’s memory limitation, performance of certain models is slow and even run into OOM (out of memory) issues, specifically on heavy Tensorflow models. There is an option to run CPU instance for certain models on Nano. For more details, see samples/configs/deepstream-app-triton/README |
[링크 : https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_FAQ.html]
[링크 : https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_plugin_gst-nvinferserver.html]
어느쪽 말이 맞는거냐 -_-
[링크 : https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_plugin_gst-nvinferserver.html]
일단 실행은 이렇게 하면 되려나.. ds l4t 인지 ds triton으로 해야할지 모르겠네
| $ sudo docker run --rm -it nvcr.io/nvidia/deepstream-l4t:6.0-samples /bin/bash |
하나가 되면 하나가 안되고 아놔 ㅋㅋㅋ
| $ sudo docker image ls REPOSITORY TAG IMAGE ID CREATED SIZE nvcr.io/nvidia/deepstream 6.0.1-triton ac5f4c456b5b 5 weeks ago 17.5GB nvcr.io/nvidia/deepstream-l4t 6.0.1-triton d3984db2b6b1 6 weeks ago 3.98GB $ sudo docker run --rm -it d3984db2b6b1 /bin/bash root@d30ca855a6ce:/opt/nvidia/deepstream/deepstream-6.0# gst-inspect-1.0 nvinferserver (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.344: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_osd.so': libnvbufsurface.so.1.0.0: cannot open shared object file: No such file or directory (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.378: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_inferaudio.so': libcufft.so.10: cannot open shared object file: No such file or directory (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.454: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_deepstream_bins.so': libnvdsbufferpool.so.1.0.0: cannot open shared object file: No such file or directory (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.456: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libgstnvvideoconvert.so': libnvdsbufferpool.so.1.0.0: cannot open shared object file: No such file or directory (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.477: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_preprocess.so': libnvbufsurface.so.1.0.0: cannot open shared object file: No such file or directory (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.479: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_infer.so': libnvbufsurface.so.1.0.0: cannot open shared object file: No such file or directory (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.490: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_multistream.so': libnvbufsurface.so.1.0.0: cannot open shared object file: No such file or directory (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.499: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_ofvisual.so': libnvdsbufferpool.so.1.0.0: cannot open shared object file: No such file or directory (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.508: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_dsexample.so': libnvbufsurface.so.1.0.0: cannot open shared object file: No such file or directory (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.511: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_tracker.so': libnvbufsurface.so.1.0.0: cannot open shared object file: No such file or directory (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.543: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_segvisual.so': libnvdsbufferpool.so.1.0.0: cannot open shared object file: No such file or directory (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.619: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_inferserver.so': libnvbufsurface.so.1.0.0: cannot open shared object file: No such file or directory (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.638: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libcustom2d_preprocess.so': libnvbufsurftransform.so.1.0.0: cannot open shared object file: No such file or directory (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.660: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_udp.so': librivermax.so.0: cannot open shared object file: No such file or directory (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.664: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_dewarper.so': libnvdsbufferpool.so.1.0.0: cannot open shared object file: No such file or directory (gst-plugin-scanner:12): GStreamer-WARNING **: 01:40:47.667: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_multistreamtiler.so': libnvbufsurface.so.1.0.0: cannot open shared object file: No such file or directory No such element or plugin 'nvinferserver' |
에라이 -_-
| $ sudo docker image list REPOSITORY TAG IMAGE ID CREATED SIZE nvcr.io/nvidia/deepstream 6.0.1-triton ac5f4c456b5b 5 weeks ago 17.5GB nvcr.io/nvidia/deepstream-l4t 6.0.1-triton d3984db2b6b1 6 weeks ago 3.98GB $ sudo docker run --rm -it ac5f4c456b5b /bin/bash WARNING: The requested image's platform (linux/amd64) does not match the detected host platform (linux/arm64/v8) and no specific platform was requested standard_init_linux.go:228: exec user process caused: exec format error |
| Building Jetson Containers on an x86 workstation (using qemu) |
[링크 : https://github.com/NVIDIA/nvidia-docker/wiki/NVIDIA-Container-Runtime-on-Jetson]
+
[링크 : https://blog.ml6.eu/nvidia-deepstream-quickstart-9147dd49a15d]
+
deb로 깔아도 install을 해주어야 하는것인가!!!
| $ cd /opt/nvidia/deepstream/deepstream-6.0 $ sudo ./install.sh $ sudo ldconfig |
[링크 : https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Quickstart.html#jetson-setup]
| $ gst-inspect-1.0 nvinferserver Factory Details: Rank primary (256) Long-name NvInferServer plugin Klass NvInferServer Plugin Description Nvidia DeepStreamSDK TensorRT plugin Author NVIDIA Corporation. Deepstream for Tesla forum: https://devtalk.nvidia.com/default/board/209 Plugin Details: Name nvdsgst_inferserver Description NVIDIA DeepStreamSDK TensorRT Inference Server plugin Filename /usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_inferserver.so Version 6.0.0 License Proprietary Source module nvinferserver Binary package NVIDIA DeepStreamSDK TensorRT Inference Server plugin Origin URL http://nvidia.com/ GObject +----GInitiallyUnowned +----GstObject +----GstElement +----GstBaseTransform +----GstNvInferServer Pad Templates: SRC template: 'src' Availability: Always Capabilities: video/x-raw(memory:NVMM) format: { (string)NV12, (string)RGBA } width: [ 1, 2147483647 ] height: [ 1, 2147483647 ] framerate: [ 0/1, 2147483647/1 ] SINK template: 'sink' Availability: Always Capabilities: video/x-raw(memory:NVMM) format: { (string)NV12, (string)RGBA } width: [ 1, 2147483647 ] height: [ 1, 2147483647 ] framerate: [ 0/1, 2147483647/1 ] Element has no clocking capabilities. Element has no URI handling capabilities. Pads: SINK: 'sink' Pad Template: 'sink' SRC: 'src' Pad Template: 'src' Element Properties: name : The name of the object flags: readable, writable String. Default: "nvinferserver0" parent : The parent of the object flags: readable, writable Object of type "GstObject" qos : Handle Quality-of-Service events flags: readable, writable Boolean. Default: false unique-id : Unique ID for the element. Can be used to identify output of the element flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 4294967295 Default: 0 process-mode : Inferserver processing mode, (0):None, (1)FullFrame, (2)ClipObject flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 2 Default: 0 config-file-path : Path to the configuration file for this instance of nvinferserver flags: readable, writable, changeable in NULL, READY, PAUSED or PLAYING state String. Default: "" batch-size : Maximum batch size for inference flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 1024 Default: 0 infer-on-gie-id : Infer on metadata generated by GIE with this unique ID. Set to -1 to infer on all metadata. flags: readable, writable, changeable only in NULL or READY state Integer. Range: -1 - 2147483647 Default: -1 infer-on-class-ids : Operate on objects with specified class ids Use string with values of class ids in ClassID (int) to set the property. e.g. 0:2:3 flags: readable, writable, changeable only in NULL or READY state String. Default: "" interval : Specifies number of consecutive batches to be skipped for inference flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 2147483647 Default: 0 raw-output-generated-callback: Pointer to the raw output generated callback funtion (type: gst_nvinfer_server_raw_output_generated_callback in 'gstnvdsinfer.h') flags: readable, writable, changeable only in NULL or READY state Pointer. raw-output-generated-userdata: Pointer to the userdata to be supplied with raw output generated callback flags: readable, writable, changeable only in NULL or READY state Pointer. |
| nvidia jetson partition table (0) | 2022.04.06 |
|---|---|
| jetson nano 부팅이 안됨 (0) | 2022.04.06 |
| deepstream part.3 (0) | 2022.03.29 |
| deepstream onnx part.2 (0) | 2022.03.29 |
| jetson nano python numpy Illegal instruction (core dumped) (0) | 2022.03.29 |
[링크 : https://github.com/NVIDIA-AI-IOT/deepstream_python_apps]
[링크 : https://github.com/NVIDIA-AI-IOT/deepstream_python_apps/tree/master/apps/deepstream-ssd-parser]
----
tritonserver for jetson (build)
[링크 : https://github.com/triton-inference-server/server/blob/main/docs/jetson.md]
+
| [ 50%] Building CXX object CMakeFiles/triton-core.dir/backend_model_instance.cc.o In file included from /home/jetson/work/server/build/_deps/repo-core-src/src/backend_model_instance.cc:37:0: /home/jetson/work/server/build/_deps/repo-core-src/src/metrics.h:40:10: fatal error: dcgm_agent.h: No such file or directory #include <dcgm_agent.h> ^~~~~~~~~~~~~~ compilation terminated. |
[링크 : https://github.com/NVIDIA/gpu-monitoring-tools/tree/master/bindings/go/dcgm]
[링크 : https://github.com/NVIDIA/gpu-monitoring-tools]
pytorch 다운로드 경로
[링크 : https://jstar0525.tistory.com/171]
| Known Issues Triton PIP wheels for ARM SBSA are not available from PyPI and pip will install an incorrect Jetson version of Triton for ARM SBSA. The correct wheel file can be pulled directly from the ARM SBSA SDK image and manually installed. |
[링크 : https://github.com/triton-inference-server/server/releases]
| $ sudo docker pull nvcr.io/nvidia/tritonserver:21.11-py3-sdk |
| jetson nano 부팅이 안됨 (0) | 2022.04.06 |
|---|---|
| deepstream triton server (0) | 2022.03.30 |
| deepstream onnx part.2 (0) | 2022.03.29 |
| jetson nano python numpy Illegal instruction (core dumped) (0) | 2022.03.29 |
| deepstream onnx (0) | 2022.03.28 |
생각해보니 deepstream onnx github프로젝트의 경우
tiny_yolov2를 기반으로 작동하도록 libnvdsinfer_custom_bbox_tiny_yolo.so 를 생성했으니
ssd 와는 구조가 달라 당연히(?) 맞지 않으니 에러가 발생하고 죽는 듯.
[링크 : https://github.com/thatbrguy/Deep-Stream-ONNX]
| ERROR: [TRT]: 2: [pluginV2DynamicExtRunner.cpp::execute::115] Error Code 2: Internal Error (Assertion status == kSTATUS_SUCCESS failed.) ERROR: Build engine failed from config file ERROR: failed to build trt engine. 0:08:17.537206102 9070 0x3f617730 ERROR nvinfer gstnvinfer.cpp:632:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1934> [UID = 1]: build engine file failed 0:08:17.545680634 9070 0x3f617730 ERROR nvinfer gstnvinfer.cpp:632:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2020> [UID = 1]: build backend context failed 0:08:17.545766053 9070 0x3f617730 ERROR nvinfer gstnvinfer.cpp:632:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1257> [UID = 1]: generate backend failed, check config file settings 0:08:17.546456543 9070 0x3f617730 WARN nvinfer gstnvinfer.cpp:841:gst_nvinfer_start:<primary_gie> error: Failed to create NvDsInferContext instance 0:08:17.546521285 9070 0x3f617730 WARN nvinfer gstnvinfer.cpp:841:gst_nvinfer_start:<primary_gie> error: Config file path: /home/jetson/work/Deep-Stream-ONNX/config/config_infer_custom_yolo.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED ** ERROR: <main:658>: Failed to set pipeline to PAUSED |
azure의 custom vision 의 README에 기재된 링크를 가보았는데
[링크 : https://github.com/Azure-Samples/customvision-export-samples]
onnx 포맷으로는 python과 c#만 제공하고
해당 사이트에서 python을 받아서 실행해보니 하나의 사진에 대해서 처리가 가능한 예제를 제공한다.
[링크 : https://github.com/Azure-Samples/customvision-export-samples/tree/main/samples/python/onnx]
[링크 : https://github.com/Azure-Samples/customvision-export-samples/tree/main/samples/csharp/onnx]
+
ssd deepstream 예제가 있는데
python 스크립트에 h264 elementary stream을 넣어주어야 한댄다
[링크 : https://github.com/NVIDIA-AI-IOT/deepstream_python_apps/tree/master/apps/deepstream-ssd-parser]
-h h264가 포인트 인 듯.
| $ ffmpeg -f video4linux2 -s 320x240 -i /dev/video0 -vcodec libx264 -f h264 test.264 |
[링크 : https://stackoverflow.com/questions/27090114/what-does-elementary-stream-mean-in-terms-of-h264]
JVT NAL sequence, H.264 라는 타입으로 변경된 듯.
| sample_0.h264: JVT NAL sequence, H.264 video @ L 31 sample_0.mp4: ISO Media, MP4 v2 [ISO 14496-14] |
| Joint Video Team (JVT) NAL: Network Abstraction Layer |
[링크 : http://iphome.hhi.de/suehring/tml/JM%20Reference%20Software%20Manual%20(JVT-AE010).pdf]
+
sample_ssd_relu6.uff 파일은 ssd inception v2 기반 모델인가?
[링크 : https://eva-support.adlinktech.com/docs/ssdnbspinception-v2-nbsp-nbsp-nbsp-nbspnbsp]
| deepstream triton server (0) | 2022.03.30 |
|---|---|
| deepstream part.3 (0) | 2022.03.29 |
| jetson nano python numpy Illegal instruction (core dumped) (0) | 2022.03.29 |
| deepstream onnx (0) | 2022.03.28 |
| azure custom vision - precision, recall (0) | 2022.03.28 |
| $ OPENBLAS_CORETYPE=ARMV8 python3 |
[링크 : https://stackoverflow.com/questions/65631801/illegal-instructioncore-dumped-error-on-jetson-nano]
| deepstream part.3 (0) | 2022.03.29 |
|---|---|
| deepstream onnx part.2 (0) | 2022.03.29 |
| deepstream onnx (0) | 2022.03.28 |
| azure custom vision - precision, recall (0) | 2022.03.28 |
| flud nvidia cuda (0) | 2022.03.28 |
| git clone https://github.com/thatbrguy/Deep-Stream-ONNX.git cd Deep-Stream-ONNX wget https://github.com/onnx/models/blob/main/vision/object_detection_segmentation/tiny-yolov2/model/tinyyolov2-8.tar.gz wget https://github.com/onnx/models/blob/main/vision/object_detection_segmentation/tiny-yolov2/model/tinyyolov2-8.tar.gz # 구글 드라이브 다운로드 tar -xvf sample.tar.gz tar -xvf tinyyolov2-7.tar.gz cp tiny_yolov2/Model.onnx tiny_yolov2.onnx cd custom_bbox_parser/ $ git diff diff --git a/custom_bbox_parser/Makefile b/custom_bbox_parser/Makefile index 5bab5a4..b764725 100644 --- a/custom_bbox_parser/Makefile +++ b/custom_bbox_parser/Makefile @@ -1,7 +1,8 @@ CUDA_VER:=10 SRCFILES:=nvdsparsebbox_tiny_yolo.cpp TARGET_LIB:=libnvdsinfer_custom_bbox_tiny_yolo.so -DEEPSTREAM_PATH:=/home/nano/deepstream_sdk_v4.0_jetson +#DEEPSTREAM_PATH:=/home/nano/deepstream_sdk_v4.0_jetson +DEEPSTREAM_PATH:=/opt/nvidia/deepstream/deepstream-6.0 ifeq ($(CUDA_VER),) $(error "CUDA_VER is not set") diff --git a/custom_bbox_parser/nvdsparsebbox_tiny_yolo.cpp b/custom_bbox_parser/nvdsparsebbox_tiny_yolo.cpp index c6251e5..0825e68 100644 --- a/custom_bbox_parser/nvdsparsebbox_tiny_yolo.cpp +++ b/custom_bbox_parser/nvdsparsebbox_tiny_yolo.cpp @@ -432,7 +432,7 @@ extern "C" bool NvDsInferParseCustomYoloV2Tiny( // Obtaining the output layer. const NvDsInferLayerInfo &layer = outputLayersInfo[0]; - assert (layer.dims.numDims == 3); + assert (layer.inferDims.numDims == 3); // Decoding the output tensor of TinyYOLOv2 to the NvDsInferParseObjectInfo format. std::vector<NvDsInferParseObjectInfo> objects = |
[링크 : https://github.com/thatbrguy/Deep-Stream-ONNX]
| *** DeepStream: Launched RTSP Streaming at rtsp://localhost:8554/ds-test *** Opening in BLOCKING MODE Opening in BLOCKING MODE Using winsys: x11 WARNING: [TRT]: Detected invalid timing cache, setup a local cache instead INFO: [Implicit Engine Info]: layers num: 2 0 INPUT kFLOAT image 3x416x416 1 OUTPUT kFLOAT grid 125x13x13 Runtime commands: h: Print this help q: Quit p: Pause r: Resume NOTE: To expand a source in the 2D tiled display and view object details, left-click on the source. To go back to the tiled display, right-click anywhere on the window. **PERF: FPS 0 (Avg) FPS 1 (Avg) FPS 2 (Avg) FPS 3 (Avg) **PERF: 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) ** INFO: <bus_callback:194>: Pipeline ready Opening in BLOCKING MODE Opening in BLOCKING MODE Opening in BLOCKING MODE Opening in BLOCKING MODE ** INFO: <bus_callback:180>: Pipeline running ------------------------------- 0:00:00.369440298 8235 0x31571330 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1161> [UID = 1]: Warning, OpenCV has been deprecated. Using NMS for clustering instead of cv::groupRectangles with topK = 20 and NMS Threshold = 0.5 ERROR: Deserialize engine failed because file path: /home/jetson/work/Deep-Stream-ONNX/config/../tiny_yolov2.onnx_b1_fp16.engine open error 0:00:01.781999412 8235 0x31571330 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1889> [UID = 1]: deserialize engine from file :/home/jetson/work/Deep-Stream-ONNX/config/../tiny_yolov2.onnx_b1_fp16.engine failed 0:00:01.782126640 8235 0x31571330 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1996> [UID = 1]: deserialize backend context from engine from file :/home/jetson/work/Deep-Stream-ONNX/config/../tiny_yolov2.onnx_b1_fp16.engine failed, try rebuild 0:00:01.782165021 8235 0x31571330 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 1]: Trying to create engine from model files 0:01:43.015792426 8235 0x31571330 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1947> [UID = 1]: serialize cuda engine to file: /home/jetson/work/Deep-Stream-ONNX/tiny_yolov2.onnx_b1_gpu0_fp16.engine successfully 0:01:43.196589822 8235 0x31571330 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/home/jetson/work/Deep-Stream-ONNX/config/config_infer_custom_yolo.txt sucessfully NvMMLiteOpen : Block : BlockType = 261 NvMMLiteOpen : Block : BlockType = 261 NvMMLiteOpen : Block : BlockType = 261 NvMMLiteOpen : Block : BlockType = 261 NVMEDIA: Reading vendor.tegra.display-size : status: 6 NVMEDIA: Reading vendor.tegra.display-size : status: 6 NVMEDIA: Reading vendor.tegra.display-size : status: 6 NVMEDIA: Reading vendor.tegra.display-size : status: 6 NvMMLiteBlockCreate : Block : BlockType = 261 NvMMLiteBlockCreate : Block : BlockType = 261 NvMMLiteBlockCreate : Block : BlockType = 261 NvMMLiteBlockCreate : Block : BlockType = 261 NvMMLiteOpen : Block : BlockType = 4 NvMMLiteOpen : Block : BlockType = 4 ===== NVMEDIA: NVENC ===== ===== NVMEDIA: NVENC ===== NvMMLiteBlockCreate : Block : BlockType = 4 NvMMLiteBlockCreate : Block : BlockType = 4 H264: Profile = 66, Level = 0 H264: Profile = 66, Level = 0 NVMEDIA_ENC: bBlitMode is set to TRUE NVMEDIA_ENC: bBlitMode is set to TRUE |
| deepstream onnx part.2 (0) | 2022.03.29 |
|---|---|
| jetson nano python numpy Illegal instruction (core dumped) (0) | 2022.03.29 |
| azure custom vision - precision, recall (0) | 2022.03.28 |
| flud nvidia cuda (0) | 2022.03.28 |
| jetson nano deepstream (0) | 2022.02.10 |
ms azure의 custon vision 서비스(?)를 이용해서 학습을 시도하는데
"하나의 태그당 15개 이상의 이미지 필요" 라는 제약조건이 걸려있다.
학습 시간에 따라서도 다르게 나오긴 한데
4시간 학습 걸어놨는데 1시간 조금 넘어서 멈춘걸 보면
학습치가 수렴하면 자동 종료하게 해둔 듯 한다.
precision이야 정확도일 것 같고, recall 번역이 안되네 -_ㅠ
"옳을 것으로 예상되어진 모든 태그들 중에 올바르게 찾은 퍼센트"
precision은 결과값에 대한 true가 true 인 조건
recall은 원본 데이터의 true에 대한 결과의 true가 true인 조건
+
Recall이 낮아졌다가 다시 높아졌는데 어느게 좋은건가 찾아보니 Precision과 Recall도 둘다 높은게 좋은거라고
[링크 : https://sumniya.tistory.com/26]
다운로드 받으면 metadata_properties.json 파일이 존재하는데 (tflite, onnx, onnx float16 확인)
학습시 별다른 옵션이 없던걸 봐서는 azure custom vision은 SSD 알고리즘만 지원하는 듯.
| { "CustomVision.Metadata.AdditionalModelInfo": "", "CustomVision.Metadata.Version": "1.2", "CustomVision.Postprocess.Method": "SSD", "CustomVision.Postprocess.Yolo.Biases": "[]", "CustomVision.Postprocess.Yolo.NmsThreshold": "0.0", "CustomVision.Preprocess.CropHeight": "0", "CustomVision.Preprocess.CropMethod": "NoCrop", "CustomVision.Preprocess.CropWidth": "0", "CustomVision.Preprocess.MaxDimension": "0", "CustomVision.Preprocess.MaxScale": "0.0", "CustomVision.Preprocess.MinDimension": "0", "CustomVision.Preprocess.MinScale": "0.0", "CustomVision.Preprocess.NormalizeMean": "[0.0, 0.0, 0.0]", "CustomVision.Preprocess.NormalizeStd": "[1.0, 1.0, 1.0]", "CustomVision.Preprocess.ResizeMethod": "Stretch", "CustomVision.Preprocess.TargetHeight": "320", "CustomVision.Preprocess.TargetWidth": "320", "Image.BitmapPixelFormat": "Rgb8", "Image.ColorSpaceGamma": "SRGB", "Image.NominalPixelRange": "Normalized_0_1" } |
| jetson nano python numpy Illegal instruction (core dumped) (0) | 2022.03.29 |
|---|---|
| deepstream onnx (0) | 2022.03.28 |
| flud nvidia cuda (0) | 2022.03.28 |
| jetson nano deepstream (0) | 2022.02.10 |
| jetson nano developer board(구형) 부팅 문제 (0) | 2022.02.09 |
nvidia jetson nano 4GB
--- 과거 아키이빙 이미지 끌어옴
nvidia ion
[링크 : https://minimonk.tistory.com/4579]
8800GT 혹은 8600GT 추정
| deepstream onnx (0) | 2022.03.28 |
|---|---|
| azure custom vision - precision, recall (0) | 2022.03.28 |
| jetson nano deepstream (0) | 2022.02.10 |
| jetson nano developer board(구형) 부팅 문제 (0) | 2022.02.09 |
| nvidia jetson nano 2gb / csi (0) | 2022.01.21 |
|
