PLC가 없어도 시뮬레이션을 통해 작화(drawing) 프로그램과 연동실험을 해볼 수 있다.
'하드웨어 > PLC (LSE)' 카테고리의 다른 글
| plc toggle (1) | 2022.04.28 |
|---|---|
| PLC 변수(XGK) (0) | 2022.04.27 |
| plc 모듈 제거 부팅 (0) | 2022.03.23 |
| QLight ST56LF 사용 (0) | 2022.03.21 |
| lse xgk-cpue rs232/modbus 연결 (0) | 2022.03.21 |
'잡동사니'에 해당되는 글 14093건
- 2022.04.22 LSE PLC XG5000과 XP-Builder 시뮬레이션 연동하기
- 2022.04.22 deepstream NCHW, NHWC
- 2022.04.21 FLIR ETS320 / v4l
- 2022.04.20 보안 전시회
- 2022.04.19 deepstream 구조, gstreamer module 설명 2
- 2022.04.18 go run ./ 2
- 2022.04.18 deepstream nvinfer
- 2022.04.17 신속항원 검사
- 2022.04.16 짧은 주말
- 2022.04.15 deepstream SSD
하드웨어/PLC (LSE)2022. 4. 22. 17:30
embeded/jetson2022. 4. 22. 15:34
deepstream 6.0 부터 NHWC 네트워크 입력을 지원한다고 한다.
그런데 이 NHWC가 먼지 몰라서 헤매는 중...
그러니까.. 이전에는 NHWC는 지원하지 않았으니 NCHW만 지원했던건가?
| Support for NHWC network input DS 6.0 |
nvinfer 모듈에서 NCHW가 언급되는 항목은 아래와 같은데
입력 레이어, 출력 레이어의 순서 그리고 uff 관련 입력 차원/순서에 대한 내용인데..
UFF 안쓰면 network-input-order와 segmentation-output-order만 보면 될 것 같긴하다.
| network-input-order | Order of the network input layer (ignored if input-tensor-meta enabled) | Integer 0:NCHW 1:NHWC | network-input-order=1 | All Both |
| segmentation-output-order | Segmentation network output layer order | Integer 0: NCHW 1: NHWC | segmentation-output-order=1 | Segmentation Both |
| uff-input-dims | DEPRECATED. Use infer-dims and uff-input-order instead. Dimensions of the UFF model |
channel; height; width; input-order All integers, ≥0 | input-dims=3;224;224;0 Possible values for input-order are: 0: NCHW 1: NHWC |
All Both |
| uff-input-order | UFF input layer order | Integer 0: NCHW 1: NHWC 2: NC | uff-input-order=1 | All Both |
[링크 : https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_plugin_gst-nvinfer.html]
conv 연산시 nhwc가 nchw에 비해서 빠르다고 하는데 데이터 순서에 따른 인접성 때문에 그런가?
[링크 : https://moon-walker.medium.com/train-faster-텐서플로우-성능-최적화-기법-d67d3faee959]
약어는 아래와 같다고.
| N: number of images in the batch H: height of the image W: width of the image C: number of channels of the image (ex: 3 for RGB, 1 for grayscale...) |
[링크 : https://stackoverflow.com/questions/37689423/convert-between-nhwc-and-nchw-in-tensorflow]
[링크 : https://code-examples.net/ko/q/23f184f]
일단.. deepstream 에서 받아들이는 텐서는 3x320x320 인데
| INFO: [Implicit Engine Info]: layers num: 4 0 INPUT kFLOAT image_tensor 3x320x320 1 OUTPUT kHALF detected_boxes 256x4 2 OUTPUT kINT32 detected_classes 256 3 OUTPUT kHALF detected_scores 256 |
NCHW를 NHWC로 바꾸니까
1x3x320x320 으로 들어올 것이
1x320x320x3 으로 들어오는지 범위를 벗어났다고 경고를 띄운다.
| WARNING: Backend context bufferIdx(0) request dims:1x320x320x3 is out of range, [min: 1x3x320x320, max: 1x3x320x320] ERROR: [TRT]: 4: [network.cpp::validate::2959] Error Code 4: Internal Error (image_tensor: for dimension number 1 in profile 0 does not match network definition (got min=320, opt=320, max=320), expected min=opt=max=3).) ERROR: Build engine failed from config file ERROR: failed to build trt engine. 0:00:05.708555452 30995 0x2a01fa70 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 0:00:05.713238769 30995 0x2a01fa70 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 0:00:05.713377574 30995 0x2a01fa70 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 ** ERROR: <main:707>: Failed to set pipeline to PAUSED Quitting ERROR from primary_gie: Failed to create NvDsInferContext instance Debug info: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(841): gst_nvinfer_start (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie: Config file path: /opt/nvidia/deepstream/deepstream-6.0/sources/objectDetector_SSD/config_infer_primary_ssd.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED |
'embeded > jetson' 카테고리의 다른 글
| 젯슨 레이서 조립 2 (0) | 2023.01.21 |
|---|---|
| 젯슨 레이서 조립 1 (0) | 2023.01.20 |
| FLIR ETS320 / v4l (0) | 2022.04.21 |
| deepstream 구조, gstreamer module 설명 (2) | 2022.04.19 |
| deepstream nvinfer (0) | 2022.04.18 |
embeded/jetson2022. 4. 21. 11:54
ETS320 장비를 jetson nano에 연결하니 스토리지와 v4l/uvc 장비로 인식이 되는 것 같다.
| $ dmesg [264102.798221] usb 1-2.3: new high-speed USB device number 5 using tegra-xusb [264102.825756] usb 1-2.3: New USB device found, idVendor=09cb, idProduct=1007 [264102.825770] usb 1-2.3: New USB device strings: Mfr=7, Product=8, SerialNumber=0 [264102.825780] usb 1-2.3: Product: FLIR Ex-Series [264102.825790] usb 1-2.3: Manufacturer: FLIR Systems [264102.852306] uvcvideo: Unknown video format 304d3746-0000-0010-8000-00aa00389b71 [264102.852439] uvcvideo: Found UVC 1.00 device FLIR Ex-Series (09cb:1007) [264108.030765] uvcvideo: UVC non compliance - GET_DEF(PROBE) not supported. Enabling workaround. [264108.034120] uvcvideo 1-2.3:1.0: Entity type for entity Extension 6 was not initialized! [264108.042461] uvcvideo 1-2.3:1.0: Entity type for entity Processing 5 was not initialized! [264108.050726] uvcvideo 1-2.3:1.0: Entity type for entity Selector 4 was not initialized! [264108.058830] uvcvideo 1-2.3:1.0: Entity type for entity Camera 1 was not initialized! [264108.067201] input: FLIR Ex-Series as /devices/70090000.xusb/usb1/1-2/1-2.3/1-2.3:1.0/input/input4 [264108.067689] usb-storage 1-2.3:1.2: USB Mass Storage device detected [264108.067964] scsi host0: usb-storage 1-2.3:1.2 [264109.087991] scsi 0:0:0:0: Direct-Access FLIR Removable 1.00 PQ: 0 ANSI: 0 [264109.100246] sd 0:0:0:0: [sda] 89664 2048-byte logical blocks: (184 MB/175 MiB) [264109.110068] sd 0:0:0:0: [sda] Write Protect is off [264109.115117] sd 0:0:0:0: [sda] Mode Sense: 00 06 00 00 [264109.116447] sd 0:0:0:0: [sda] Asking for cache data failed [264109.122082] sd 0:0:0:0: [sda] Assuming drive cache: write through [264109.151779] sda: [264109.170721] sd 0:0:0:0: [sda] Attached SCSI removable disk |
젯슨 나노 하나 전체를 찍을 만큼의 배율과 촛점 거리는 안되는 듯..
[링크 : https://www.flirkorea.com/products/ets320]
사용자 설명서를 보니 FOV 고정, 촛점거리 7cm 로 고정 -_ㅠ
영상은 초당 9프레임
하지만 UVC 상에서는 15프레임으로 프레임이 변경되는 듯.
| $ v4l2-ctl -d /dev/video1 --list-formats-ext ioctl: VIDIOC_ENUM_FMT Index : 0 Type : Video Capture Pixel Format: 'YUYV' Name : YUYV 4:2:2 Size: Discrete 320x240 Interval: Discrete 0.067s (15.000 fps) Interval: Discrete 0.133s (7.500 fps) Interval: Discrete 0.267s (3.750 fps) Index : 1 Type : Video Capture Pixel Format: '' Name : 304d3746-0000-0010-8000-00aa003 Size: Discrete 320x246 Interval: Discrete 0.067s (15.000 fps) Interval: Discrete 0.133s (7.500 fps) Interval: Discrete 0.267s (3.750 fps) |
와.. 가격 미친.. 예상보다 2배.. ㄷㄷ
'embeded > jetson' 카테고리의 다른 글
| 젯슨 레이서 조립 1 (0) | 2023.01.20 |
|---|---|
| deepstream NCHW, NHWC (0) | 2022.04.22 |
| deepstream 구조, gstreamer module 설명 (2) | 2022.04.19 |
| deepstream nvinfer (0) | 2022.04.18 |
| deepstream SSD (0) | 2022.04.15 |
개소리 왈왈/직딩의 비애2022. 4. 20. 23:26
embeded/jetson2022. 4. 19. 15:22
primary / secondary가 먼가 했더니..
한번 분석한걸 tracker를 거쳐 한번 더 분류하는 식으로 구성이 가능하도록 되어 있었기에 그런식으로 표현한 듯.
nvtracker는 openCV 기반이라 쓸 일은 없을 것 같고..
nvmultistreamtiler 가 nvstreammux 을 통해 받은 영상을 tile 구조로 mux 해서 출력해주고
nvosd가 nvinfer의 결과값을 받아 이름과 박스를 쳐주는 듯.
|
[링크 : https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_ref_app_deepstream.html]
| $ unset DISPLAY $ gst-inspect-1.0 | grep ^nv nvarguscamerasrc: nvarguscamerasrc: NvArgusCameraSrc nvdsgst_deepstream_bins: nvinferbin: NvInfer Bin nvdsgst_deepstream_bins: nvinferserverbin: NvInferServer Bin nvdsgst_deepstream_bins: nvosdbin: NvOsd Bin nvdsgst_deepstream_bins: nvdewarperbin: NvDewarper Bin nvdsgst_deepstream_bins: nvtilerbin: NvTiler Bin nvdsgst_deepstream_bins: nvtrackerbin: NvTracker Bin nvdsgst_deepstream_bins: nvurisrcbin: NvUriSrc Bin nvdsgst_deepstream_bins: nvcamerasrcbin: NvCameraSrc Bin nvdsgst_deepstream_bins: nvanalyticsbin: NvAnalytics Bin nvdsgst_deepstream_bins: nvvideorenderersinkbin: NvVideoRenderer Bin nvdsgst_deepstream_bins: nvvideoencfilesinkbin: NvVideoEncFilesink Bin nvdsgst_deepstream_bins: nvrtspoutsinkbin: NvRtspOut Bin nvdsgst_deepstream_bins: nvmsgbrokersinkbin: NvMsgBroker Bin nvdsgst_deepstream_bins: nvdsbuffersyncbin: NvBufferSync Bin nvdsgst_ofvisual: nvofvisual: nvofvisual nvdsgst_inferaudio: nvinferaudio: NvInfer Audio plugin nvdsgst_videotemplate: nvdsvideotemplate: NvDsVideoTemplate plugin for Transform/In-Place use-cases nvdsgst_msgconv: nvmsgconv: Message Converter nvdsgst_multistream: nvstreammux: Stream multiplexer nvdsgst_multistream: nvstreamdemux: Stream demultiplexer nvdsgst_multistreamtiler: nvmultistreamtiler: Stream Tiler DS nvdsgst_segvisual: nvsegvisual: nvsegvisual nvdsgst_osd: nvdsosd: NvDsOsd plugin nvdsgst_logger: nvdslogger: Nvdslogger nvdsgst_infer: nvinfer: NvInfer plugin nvdsgst_dewarper: nvdewarper: nvdewarper nvdsgst_dsexample: dsexample: DsExample plugin nvdsgst_of: nvof: nvof nvdsgst_dsanalytics: nvdsanalytics: DsAnalytics plugin nvdsgst_audiotemplate: nvdsaudiotemplate: DS AUDIO template Plugin for Transform IP use-cases nvdsgst_msgbroker: nvmsgbroker: Message Broker nvdsgst_tracker: nvtracker: NvTracker plugin nvvideoconvert: nvvideoconvert: NvVidConv Plugin nvdsgst_preprocess: nvdspreprocess: gst-nvdspreprocess plugin nvvideosink: nvvideosink: nVidia Video Sink nvtee: nvtee: NvTee nvegltransform: nvegltransform: NvEGLTransform nveglglessink: nveglglessink: EGL/GLES vout Sink nvvideo4linux2: nvv4l2decoder: NVIDIA v4l2 video decoder nvvideo4linux2: nvv4l2h264enc: V4L2 H.264 Encoder nvvideo4linux2: nvv4l2h265enc: V4L2 H.265 Encoder nvvideo4linux2: nvv4l2vp8enc: V4L2 VP8 Encoder nvvideo4linux2: nvv4l2vp9enc: V4L2 VP9 Encoder nvvideocuda: videocuda: CUDA Post processor nvivafilter: nvivafilter: NvIVAFilter Plugin nvcompositor: nvcompositor: NvCompositor nvvideosinks: nv3dsink: Nvidia 3D sink nveglstreamsrc: nveglstreamsrc: nVidia EGL Stream nvvidconv: nvvidconv: NvVidConv Plugin nvv4l2camerasrc: nvv4l2camerasrc: NvV4l2CameraSrc nvdrmvideosink: nvdrmvideosink: Nvidia Drm Video Sink nvjpeg: nvjpegenc: JPEG image encoder nvjpeg: nvjpegdec: JPEG image decoder |
모듈별 설명
| $ gst-inspect-1.0 nvstreammux Factory Details: Rank primary (256) Long-name Stream multiplexer Klass Generic Description N-to-1 pipe stream multiplexing Author NVIDIA Corporation. Post on Deepstream for Tesla forum for any queries @ https://devtalk.nvidia.com/default/board/209/ Plugin Details: Name nvdsgst_multistream Description NVIDIA Multistream mux/demux plugin Filename /usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_multistream.so Version 6.0.1 License Proprietary Source module nvmultistream Binary package NVIDIA Multistream Plugins Origin URL http://nvidia.com/ GObject +----GInitiallyUnowned +----GstObject +----GstElement +----GstNvStreamMux Pad Templates: SINK template: 'sink_%u' Availability: On request Capabilities: video/x-raw(memory:NVMM) format: { (string)NV12, (string)RGBA, (string)I420 } width: [ 1, 2147483647 ] height: [ 1, 2147483647 ] framerate: [ 0/1, 2147483647/1 ] SRC template: 'src' Availability: Always Capabilities: video/x-raw(memory:NVMM) format: { (string)NV12, (string)RGBA, (string)I420 } width: [ 1, 2147483647 ] height: [ 1, 2147483647 ] framerate: [ 0/1, 2147483647/1 ] Element has no clocking capabilities. Element has no URI handling capabilities. Pads: SRC: 'src' Pad Template: 'src' Element Properties: name : The name of the object flags: readable, writable String. Default: "nvstreammux0" parent : The parent of the object flags: readable, writable Object of type "GstObject" batch-size : Maximum number of buffers in a batch flags: readable, writable Unsigned Integer. Range: 0 - 1024 Default: 0 batched-push-timeout: Timeout in microseconds to wait after the first buffer is available to push the batch even if the complete batch is not formed. Set to -1 to wait infinitely flags: readable, writable Integer. Range: -1 - 2147483647 Default: -1 width : Width of each frame in output batched buffer. This property MUST be set. flags: readable, writable Unsigned Integer. Range: 0 - 4294967295 Default: 0 height : Height of each frame in output batched buffer. This property MUST be set. flags: readable, writable Unsigned Integer. Range: 0 - 4294967295 Default: 0 enable-padding : Maintain input aspect ratio when scaling by padding with black bands. flags: readable, writable Boolean. Default: false gpu-id : Set GPU Device ID flags: readable, writable Unsigned Integer. Range: 0 - 4294967295 Default: 0 live-source : Boolean property to inform muxer that sources are live. flags: readable, writable Boolean. Default: false num-surfaces-per-frame: Max number of surfaces per frame flags: readable, writable Unsigned Integer. Range: 1 - 4 Default: 1 nvbuf-memory-type : Type of NvBufSurface Memory to be allocated for output buffers flags: readable, writable, changeable only in NULL or READY state Enum "GstNvBufMemoryType" Default: 0, "nvbuf-mem-default" (0): nvbuf-mem-default - Default memory allocated, specific to particular platform (1): nvbuf-mem-cuda-pinned - Allocate Pinned/Host cuda memory (2): nvbuf-mem-cuda-device - Allocate Device cuda memory (3): nvbuf-mem-cuda-unified - Allocate Unified cuda memory (4): nvbuf-mem-surface-array - Allocate Surface Array memory, applicable for Jetson compute-hw : Compute Scaling HW flags: readable, writable, controllable Enum "GstNvComputeHWType" Default: 0, "Default" (0): Default - Default, GPU for Tesla, VIC for Jetson (1): GPU - GPU (2): VIC - VIC interpolation-method: Set interpolation methods flags: readable, writable, controllable Enum "GstNvInterpolationMethod" Default: 1, "Bilinear" (0): Nearest - Nearest (1): Bilinear - Bilinear (2): Algo-1 - GPU - Cubic, VIC - 5 Tap (3): Algo-2 - GPU - Super, VIC - 10 Tap (4): Algo-3 - GPU - LanzoS, VIC - Smart (5): Algo-4 - GPU - Ignored, VIC - Nicest (6): Default - GPU - Nearest, VIC - Nearest buffer-pool-size : Maximum number of buffers from muxer's output pool flags: readable, writable Unsigned Integer. Range: 4 - 1024 Default: 4 attach-sys-ts : If set to TRUE, system timestamp will be attached as ntp timestamp. If set to FALSE, ntp timestamp from rtspsrc, if available, will be attached. flags: readable, writable Boolean. Default: true sync-inputs : Boolean property to force sychronization of input frames. flags: readable, writable Boolean. Default: false max-latency : Additional latency in live mode to allow upstream to take longer to produce buffers for the current position (in nanoseconds) flags: readable, writable Unsigned Integer. Range: 0 - 4294967295 Default: 0 frame-num-reset-on-eos: Reset frame numbers to 0 for a source from which EOS is received (For debugging purpose only) flags: readable, writable Boolean. Default: false |
| $ gst-inspect-1.0 nvinfer Factory Details: Rank primary (256) Long-name NvInfer plugin Klass NvInfer Plugin Description Nvidia DeepStreamSDK TensorRT plugin Author NVIDIA Corporation. Deepstream for Tesla forum: https://devtalk.nvidia.com/default/board/209 Plugin Details: Name nvdsgst_infer Description NVIDIA DeepStreamSDK TensorRT plugin Filename /usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_infer.so Version 6.0.1 License Proprietary Source module nvinfer Binary package NVIDIA DeepStreamSDK TensorRT plugin Origin URL http://nvidia.com/ GObject +----GInitiallyUnowned +----GstObject +----GstElement +----GstBaseTransform +----GstNvInfer 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: "nvinfer0" 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: 15 process-mode : Infer processing mode flags: readable, writable, changeable only in NULL or READY state Enum "GstNvInferProcessModeType" Default: 1, "primary" (1): primary - Primary (Full Frame) (2): secondary - Secondary (Objects) config-file-path : Path to the configuration file for this instance of nvinfer flags: readable, writable, changeable in NULL, READY, PAUSED or PLAYING state String. Default: "" 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: "" filter-out-class-ids: Ignore metadata for objects of 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: "" model-engine-file : Absolute path to the pre-generated serialized engine file for the model 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: 1 - 1024 Default: 1 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 gpu-id : Set GPU Device ID flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 4294967295 Default: 0 raw-output-file-write: Write raw inference output to file flags: readable, writable, changeable only in NULL or READY state Boolean. Default: false raw-output-generated-callback: Pointer to the raw output generated callback funtion (type: gst_nvinfer_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. output-tensor-meta : Attach inference tensor outputs as buffer metadata flags: readable, writable, changeable only in NULL or READY state Boolean. Default: false output-instance-mask: Instance mask expected in network output and attach it to metadata flags: readable, writable, changeable only in NULL or READY state Boolean. Default: false input-tensor-meta : Use preprocessed input tensors attached as metadata instead of preprocessing inside the plugin flags: readable, writable, changeable only in NULL or READY state Boolean. Default: false Element Signals: "model-updated" : void user_function (GstElement* object, gint arg0, gchararray arg1, gpointer user_data); |
deepstream_app_config.txt의 [primary-gie], [secondary-gie] 섹션
| $ gst-inspect-1.0 nvtracker Factory Details: Rank primary (256) Long-name NvTracker plugin Klass NvTracker functionality Description Gstreamer object tracking element Author NVIDIA Corporation. Post on Deepstream SDK forum for any queries @ https://devtalk.nvidia.com/default/board/209/ Plugin Details: Name nvdsgst_tracker Description Gstreamer plugin to track the objects Filename /usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_tracker.so Version 6.0.1 License Proprietary Source module nvtracker Binary package GStreamer nvtracker Plugin Origin URL http://nvidia.com/ GObject +----GInitiallyUnowned +----GstObject +----GstElement +----GstBaseTransform +----GstNvTracker Pad Templates: SRC template: 'src' Availability: Always Capabilities: video/x-raw(memory:NVMM) format: { (string)I420, (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)I420, (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: "nvtracker0" 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 tracker-width : Frame width at which the tracker should operate, in pixels flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 4294967295 Default: 640 tracker-height : Frame height at which the tracker should operate, in pixels flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 4294967295 Default: 384 gpu-id : Set GPU Device ID flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 4294967295 Default: 0 ll-config-file : Low-level library config file path flags: readable, writable String. Default: null ll-lib-file : Low-level library file path flags: readable, writable String. Default: null enable-batch-process: Enable batch processing across multiple streams ? flags: readable, writable Boolean. Default: true enable-past-frame : Enable adding past frame track into user meta ? flags: readable, writable Boolean. Default: false tracking-surface-type: Set Tracking Surface Type, default is ALL, (1) => SPOT Surface, (2) => AISLE Surface flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 4294967295 Default: 0 compute-hw : Compute Scaling HW flags: readable, writable, controllable Enum "GstNvComputeHWType" Default: 0, "Default" (0): Default - Default, GPU for Tesla, VIC for Jetson (1): GPU - GPU (2): VIC - VIC display-tracking-id : Display tracking id in object text flags: readable, writable Boolean. Default: true tracking-id-reset-mode: Tracking ID reset mode when stream reset or EOS happens flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 3 Default: 1 |
deepstream_app_config.txt의 [tiled-display] 섹션
| $ gst-inspect-1.0 nvmultistreamtiler Factory Details: Rank primary (256) Long-name Stream Tiler DS Klass Generic Description Tile input multistream buffer into a 2D array Author NVIDIA Corporation. Post on Deepstream for Tesla forum for any queries @ https://devtalk.nvidia.com/default/board/209/ Plugin Details: Name nvdsgst_multistreamtiler Description NVIDIA Multistream Tiler plugin Filename /usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_multistreamtiler.so Version 6.0.1 License Proprietary Source module nvmultistreamTiler Binary package NVIDIA Multistream Plugins Origin URL http://nvidia.com/ GObject +----GInitiallyUnowned +----GstObject +----GstElement +----GstBaseTransform +----GstNvMultiStreamTiler Pad Templates: SINK template: 'sink' Availability: Always Capabilities: video/x-raw(memory:NVMM) format: { (string)NV12, (string)RGBA, (string)I420 } width: [ 1, 2147483647 ] height: [ 1, 2147483647 ] framerate: [ 0/1, 2147483647/1 ] SRC template: 'src' Availability: Always Capabilities: video/x-raw(memory:NVMM) format: { (string)NV12, (string)RGBA, (string)I420 } 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: "nvmultistreamtiler0" 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 columns : Number of columns in the Tiled 2D output flags: readable, writable Unsigned Integer. Range: 1 - 4294967295 Default: 1 rows : Number of rows in the Tiled 2D output flags: readable, writable Unsigned Integer. Range: 1 - 4294967295 Default: 1 width : Width of the tiled output in pixels flags: readable, writable Unsigned Integer. Range: 16 - 4294967295 Default: 1920 height : Height of the tiled output in pixels flags: readable, writable Unsigned Integer. Range: 16 - 4294967295 Default: 1080 gpu-id : Set GPU Device ID flags: readable, writable Unsigned Integer. Range: 0 - 4294967295 Default: 0 show-source : ID of the source to be shown. If -1 all the sources will be tiled else only a single source will be scaled into the output buffer. flags: readable, writable Integer. Range: -1 - 2147483647 Default: -1 nvbuf-memory-type : Type of NvBufSurface Memory to be allocated for output buffers flags: readable, writable, changeable only in NULL or READY state Enum "GstNvBufMemoryType" Default: 0, "nvbuf-mem-default" (0): nvbuf-mem-default - Default memory allocated, specific to particular platform (1): nvbuf-mem-cuda-pinned - Allocate Pinned/Host cuda memory (2): nvbuf-mem-cuda-device - Allocate Device cuda memory (3): nvbuf-mem-cuda-unified - Allocate Unified cuda memory (4): nvbuf-mem-surface-array - Allocate Surface Array memory, applicable for Jetson compute-hw : Compute Scaling HW flags: readable, writable, controllable Enum "GstNvComputeHWType" Default: 0, "Default" (0): Default - Default, GPU for Tesla, VIC for Jetson (1): GPU - GPU (2): VIC - VIC interpolation-method: Set interpolation methods flags: readable, writable, controllable Enum "GstNvInterpolationMethod" Default: 6, "Default" (0): Nearest - Nearest (1): Bilinear - Bilinear (2): Algo-1 - GPU - Cubic, VIC - 5 Tap (3): Algo-2 - GPU - Super, VIC - 10 Tap (4): Algo-3 - GPU - LanzoS, VIC - Smart (5): Algo-4 - GPU - Ignored, VIC - Nicest (6): Default - GPU - Nearest, VIC - Nearest custom-tile-config : Specifies individual tile resolution for all involved sources flags: writable Pointer. Write only |
deepstream_app_config.txt의 [osd] 섹션
| $ gst-inspect-1.0 nvdsosd Factory Details: Rank primary (256) Long-name NvDsOsd plugin Klass NvDsOsd functionality Description Gstreamer bounding box draw element Author NVIDIA Corporation. Post on Deepstream for Tesla forum for any queries @ https://devtalk.nvidia.com/default/board/209/ Plugin Details: Name nvdsgst_osd Description Gstreamer plugin to draw rectangles and text Filename /usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_osd.so Version 6.0.1 License Proprietary Source module nvdsosd Binary package GStreamer nvosd Plugin Origin URL http://nvidia.com/ GObject +----GInitiallyUnowned +----GstObject +----GstElement +----GstBaseTransform +----GstNvDsOsd Pad Templates: SRC template: 'src' Availability: Always Capabilities: video/x-raw(memory:NVMM) format: { (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)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: "nvdsosd0" 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 display-clock : Whether to display clock flags: readable, writable Boolean. Default: false display-text : Whether to display text flags: readable, writable Boolean. Default: true clock-font : Clock Font to be set flags: readable, writable String. Default: null clock-font-size : font size of the clock flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 60 Default: 0 x-clock-offset : x-clock-offset flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 4294967295 Default: 0 y-clock-offset : y-clock-offset flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 4294967295 Default: 0 clock-color : clock-color flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 4294967295 Default: 0 process-mode : Rect and text draw process mode flags: readable, writable, changeable only in NULL or READY state Enum "GstNvDsOsdMode" Default: 2, "HW_MODE" (0): CPU_MODE - CPU_MODE (1): GPU_MODE - GPU_MODE, yet to be implemented for Tegra (2): HW_MODE - HW_MODE. Only for Tegra. For rectdraw only. hw-blend-color-attr : color attributes for all classes, Use string with values of color class atrributes in ClassID (int), r(float), g(float), b(float), a(float) in order to set the property. Applicable only for HW mode on Jetson. e.g. 0,0.0,1.0,0.0,0.3:1,1.0,0.0,0.3,0.3 flags: readable, writable String. Default: "0,0.000000,0.000000,0.000000,0.000000:" gpu-id : Set GPU Device ID flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 4294967295 Default: 0 display-bbox : Whether to display bounding boxes flags: readable, writable Boolean. Default: true display-mask : Whether to display instance mask flags: readable, writable Boolean. Default: false |
| $ gst-inspect-1.0 nveglglessink Factory Details: Rank secondary (128) Long-name EGL/GLES vout Sink Klass Sink/Video Description An EGL/GLES Video Output Sink Implementing the VideoOverlay interface Author Reynaldo H. Verdejo Pinochet <reynaldo@collabora.com>, Sebastian Dröge <sebastian.droege@collabora.co.uk> Plugin Details: Name nveglglessink Description EGL/GLES sink Filename /usr/lib/aarch64-linux-gnu/gstreamer-1.0/libgstnveglglessink.so Version 1.2.3 License LGPL Source module gst-plugins-bad Source release date 2014-02-08 Binary package GStreamer Nvidia Bad Plug-ins source release Origin URL Unknown package origin GObject +----GInitiallyUnowned +----GstObject +----GstElement +----GstBaseSink +----GstVideoSink +----GstEglGlesSink Implemented Interfaces: GstVideoOverlay Pad Templates: SINK template: 'sink' Availability: Always Capabilities: video/x-raw(memory:EGLImage) format: { (string)RGBA, (string)BGRA, (string)ARGB, (string)ABGR, (string)RGBx, (string)BGRx, (string)xRGB, (string)xBGR, (string)AYUV, (string)Y444, (string)I420, (string)YV12, (string)NV12, (string)NV21, (string)Y42B, (string)Y41B, (string)RGB, (string)BGR, (string)RGB16 } width: [ 1, 2147483647 ] height: [ 1, 2147483647 ] framerate: [ 0/1, 2147483647/1 ] video/x-raw(meta:GstVideoGLTextureUploadMeta) format: { (string)RGBA, (string)BGRA, (string)ARGB, (string)ABGR, (string)RGBx, (string)BGRx, (string)xRGB, (string)xBGR, (string)AYUV, (string)Y444, (string)I420, (string)YV12, (string)NV12, (string)NV21, (string)Y42B, (string)Y41B, (string)RGB, (string)BGR, (string)RGB16 } width: [ 1, 2147483647 ] height: [ 1, 2147483647 ] framerate: [ 0/1, 2147483647/1 ] video/x-raw format: { (string)RGBA, (string)BGRA, (string)ARGB, (string)ABGR, (string)RGBx, (string)BGRx, (string)xRGB, (string)xBGR, (string)AYUV, (string)Y444, (string)I420, (string)YV12, (string)NV12, (string)NV21, (string)Y42B, (string)Y41B, (string)RGB, (string)BGR, (string)RGB16 } width: [ 1, 2147483647 ] height: [ 1, 2147483647 ] framerate: [ 0/1, 2147483647/1 ] video/x-raw(memory:NVMM) format: { (string)BGRx, (string)RGBA, (string)I420, (string)NV12, (string)BGR, (string)RGB } 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' Element Properties: name : The name of the object flags: readable, writable String. Default: "eglglessink0" parent : The parent of the object flags: readable, writable Object of type "GstObject" sync : Sync on the clock flags: readable, writable Boolean. Default: true max-lateness : Maximum number of nanoseconds that a buffer can be late before it is dropped (-1 unlimited) flags: readable, writable Integer64. Range: -1 - 9223372036854775807 Default: 20000000 qos : Generate Quality-of-Service events upstream flags: readable, writable Boolean. Default: true async : Go asynchronously to PAUSED flags: readable, writable Boolean. Default: true ts-offset : Timestamp offset in nanoseconds flags: readable, writable Integer64. Range: -9223372036854775808 - 9223372036854775807 Default: 0 enable-last-sample : Enable the last-sample property flags: readable, writable Boolean. Default: true last-sample : The last sample received in the sink flags: readable Boxed pointer of type "GstSample" blocksize : Size in bytes to pull per buffer (0 = default) flags: readable, writable Unsigned Integer. Range: 0 - 4294967295 Default: 4096 render-delay : Additional render delay of the sink in nanoseconds flags: readable, writable Unsigned Integer64. Range: 0 - 18446744073709551615 Default: 0 throttle-time : The time to keep between rendered buffers (0 = disabled) flags: readable, writable Unsigned Integer64. Range: 0 - 18446744073709551615 Default: 0 max-bitrate : The maximum bits per second to render (0 = disabled) flags: readable, writable Unsigned Integer64. Range: 0 - 18446744073709551615 Default: 0 show-preroll-frame : Whether to render video frames during preroll flags: readable, writable Boolean. Default: true create-window : If set to true, the sink will attempt to create it's own window to render to if none is provided. This is currently only supported when the sink is used under X11 flags: readable, writable Boolean. Default: true force-aspect-ratio : If set to true, the sink will attempt to preserve the incoming frame's geometry while scaling, taking both the storage's and display's pixel aspect ratio into account flags: readable, writable Boolean. Default: true display : If set, the sink will use the passed X Display for rendering flags: readable, writable Pointer. window-x : X coordinate of window flags: readable, writable Unsigned Integer. Range: 0 - 2147483647 Default: 10 window-y : Y coordinate of window flags: readable, writable Unsigned Integer. Range: 0 - 2147483647 Default: 10 window-width : Width of window flags: readable, writable Unsigned Integer. Range: 0 - 2147483647 Default: 0 window-height : Height of window flags: readable, writable Unsigned Integer. Range: 0 - 2147483647 Default: 0 rows : Rows of Display flags: readable, writable Unsigned Integer. Range: 1 - 2147483647 Default: 1 columns : Columns of display flags: readable, writable Unsigned Integer. Range: 1 - 2147483647 Default: 1 profile : gsteglglessink jitter information flags: readable, writable Unsigned Integer. Range: 0 - 4294967295 Default: 0 winsys : Takes in strings "x11" or "wayland" to specify the windowing system to be used flags: readable, writable String. Default: "x11" bufapi-version : Set to use new buf API flags: readable, writable Boolean. Default: false |
'embeded > jetson' 카테고리의 다른 글
| deepstream NCHW, NHWC (0) | 2022.04.22 |
|---|---|
| FLIR ETS320 / v4l (0) | 2022.04.21 |
| deepstream nvinfer (0) | 2022.04.18 |
| deepstream SSD (0) | 2022.04.15 |
| deepstream (0) | 2022.04.15 |
Programming/golang2022. 4. 18. 19:15
| $ cat hello.go package main import "fmt" func main() { fmt.Println("Hello world") hello() } $ cat func.go package main import "fmt" func hello() { fmt.Println("Hello world 2") } $ go run . go: go.mod file not found in current directory or any parent directory; see 'go help modules' $ go mod init go: creating new go.mod: module go2 go: to add module requirements and sums: go mod tidy $ go run . Hello world Hello world 2 |
'Programming > golang' 카테고리의 다른 글
| golang unused import (0) | 2022.07.20 |
|---|---|
| golang websocket package (0) | 2022.07.15 |
| golang module (0) | 2022.04.13 |
| golang 구조체 (0) | 2022.04.11 |
| golang defer와 if (0) | 2022.04.11 |
embeded/jetson2022. 4. 18. 15:12
소스를 분석해보니
objectList에는 x,y,w,h 로 infercence 할 크기 기준으로 결과를 넣어주면 된다.
즉, x = output * width 식으로 계산해야 한다.
cat config_infer_primary_ssd.txt
num-detected-classes=91
위의 설정은 deepstream plugin의 아래 값으로 넘어옴
detectionParams.numClassesConfigured
| $ gst-inspect-1.0 nvinfer Factory Details: Rank primary (256) Long-name NvInfer plugin Klass NvInfer Plugin Description Nvidia DeepStreamSDK TensorRT plugin Author NVIDIA Corporation. Deepstream for Tesla forum: https://devtalk.nvidia.com/default/board/209 Plugin Details: Name nvdsgst_infer Description NVIDIA DeepStreamSDK TensorRT plugin Filename /usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_infer.so Version 6.0.1 License Proprietary Source module nvinfer Binary package NVIDIA DeepStreamSDK TensorRT plugin Origin URL http://nvidia.com/ GObject +----GInitiallyUnowned +----GstObject +----GstElement +----GstBaseTransform +----GstNvInfer Pad Templates: 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 ] 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 ] 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: "nvinfer0" 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: 15 process-mode : Infer processing mode flags: readable, writable, changeable only in NULL or READY state Enum "GstNvInferProcessModeType" Default: 1, "primary" (1): primary - Primary (Full Frame) (2): secondary - Secondary (Objects) config-file-path : Path to the configuration file for this instance of nvinfer flags: readable, writable, changeable in NULL, READY, PAUSED or PLAYING state String. Default: "" 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: "" filter-out-class-ids: Ignore metadata for objects of 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: "" model-engine-file : Absolute path to the pre-generated serialized engine file for the model 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: 1 - 1024 Default: 1 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 gpu-id : Set GPU Device ID flags: readable, writable, changeable only in NULL or READY state Unsigned Integer. Range: 0 - 4294967295 Default: 0 raw-output-file-write: Write raw inference output to file flags: readable, writable, changeable only in NULL or READY state Boolean. Default: false raw-output-generated-callback: Pointer to the raw output generated callback funtion (type: gst_nvinfer_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. output-tensor-meta : Attach inference tensor outputs as buffer metadata flags: readable, writable, changeable only in NULL or READY state Boolean. Default: false output-instance-mask: Instance mask expected in network output and attach it to metadata flags: readable, writable, changeable only in NULL or READY state Boolean. Default: false input-tensor-meta : Use preprocessed input tensors attached as metadata instead of preprocessing inside the plugin flags: readable, writable, changeable only in NULL or READY state Boolean. Default: false Element Signals: "model-updated" : void user_function (GstElement* object, gint arg0, gchararray arg1, gpointer user_data); |
[링크 : https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_plugin_gst-nvinfer.html]
| model-file (Caffe model) proto-file (Caffe model) uff-file (UFF models) onnx-file (ONNX models) model-engine-file, if already generated int8-calib-file for INT8 mode mean-file, if required offsets, if required maintain-aspect-ratio, if required parse-bbox-func-name (detectors only) parse-classifier-func-name (classifiers only) custom-lib-path output-blob-names (Caffe and UFF models) network-type model-color-format process-mode engine-create-func-name infer-dims (UFF models) uff-input-order (UFF models) |
[링크 : https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_using_custom_model.html]
'embeded > jetson' 카테고리의 다른 글
| FLIR ETS320 / v4l (0) | 2022.04.21 |
|---|---|
| deepstream 구조, gstreamer module 설명 (2) | 2022.04.19 |
| deepstream SSD (0) | 2022.04.15 |
| deepstream (0) | 2022.04.15 |
| ssd_inception_v2_coco_2017_11_17.tar.gz (0) | 2022.04.13 |
개소리 왈왈/육아관련 주저리2022. 4. 17. 23:20
개소리 왈왈/육아관련 주저리2022. 4. 16. 23:35
embeded/jetson2022. 4. 15. 18:04
| Pre-requisites: - Copy the model's label file "ssd_coco_labels.txt" from the data/ssd directory in TensorRT samples to this directory. - Steps to generate the UFF model from ssd_inception_v2_coco TensorFlow frozen graph. These steps have been referred from TensorRT sampleUffSSD README: 1. Make sure TensorRT's uff-converter-tf package is installed. 2. Install tensorflow-gpu package for python: For dGPU: $ pip install tensorflow-gpu For Jetson, refer to https://elinux.org/Jetson_Zoo#TensorFlow 3. Download and untar the ssd_inception_v2_coco TensorFlow trained model from http://download.tensorflow.org/models/object_detection/ssd_inception_v2_coco_2017_11_17.tar.gz 4. Navigate to the extracted directory and convert the frozen graph to uff: $ cd ssd_inception_v2_coco_2017_11_17 $ python /usr/lib/python2.7/dist-packages/uff/bin/convert_to_uff.py \ frozen_inference_graph.pb -O NMS \ -p /usr/src/tensorrt/samples/sampleUffSSD/config.py \ -o sample_ssd_relu6.uff 5. Copy sample_ssd_relu6.uff to this directory. |
| $ python3 /usr/lib/python3.6/dist-packages/uff/bin/convert_to_uff.py |
[링크 : https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_FAQ.html]
변환해서 netron.app 에서 보니 읭... output 이름이 NMS
타입과 텐서 차원이 안보인다?
'embeded > jetson' 카테고리의 다른 글
| deepstream 구조, gstreamer module 설명 (2) | 2022.04.19 |
|---|---|
| deepstream nvinfer (0) | 2022.04.18 |
| deepstream (0) | 2022.04.15 |
| ssd_inception_v2_coco_2017_11_17.tar.gz (0) | 2022.04.13 |
| nvidia jetson deepstream objectDetector_SSD 플러그인 분석 (0) | 2022.04.13 |
