紀錄關於在Jetson Nano 使用YoloV3 tiny 自製的預訓練檔案
1.預訓練檔案來源
https://github.com/amineHY/YOLOv3-for-custum-objects
2.將以下檔案放置到Jetson Nano上 /opt/nvidia/deepstream/deepstream-5.0//sources/objectDetector_Yolo目錄下
fire/model/yolov3-tiny-obj_final.weights
cfg/yolov3-tiny-obj.cfg
3.切換至 /opt/nvidia/deepstream/deepstream-5.0//sources/objectDetector_Yolo目錄
4.新建檔案 lables-obj.txt
fire
5.編輯檔案 config_infer_primary_yoloV3_tiny.txt
#custom-network-config=yolov3-tiny.cfg
custom-network-config=yolov3-tiny-obj.cfg
#model-file=yolov3-tiny.weights
model-file=yolov3-tiny-obj_final.weights
#labelfile-path=labels.txt
labelfile-path=labels-obj.txt
#network-mode=1
network-mode=2
#num-detected-classes=80
num-detected-classes=1
6.編輯檔案 nvdsinfer_custom_impl_Yolo/nvdsparsebbox_Yolo.cpp
-static const int NUM_CLASSES_YOLO = 80;
+static const int NUM_CLASSES_YOLO = 1;
7.Compile 檔案
export CUDA_VER=10.2
make -C nvdsinfer_custom_impl_Yolo
8.清除暫存檔 rm -rf ~/.cache/gstreamer-1.0/registry.aarch64.bin
9.執行 deepstream-app -c deepstream_app_config_yoloV3_tiny.txt
(deepstream-app:18137): GLib-GObject-WARNING **: 01:42:51.150: g_object_set_is_valid_property: object class 'GstNvArgusCameraSrc' has no property named 'maxperf'
(deepstream-app:18137): GStreamer-CRITICAL **: 01:42:51.152: passed '0' as denominator for `GstFraction'
Unknown or legacy key specified 'is-classifier' for group [property]
Warn: 'threshold' parameter has been deprecated. Use 'pre-cluster-threshold' instead.
Using winsys: x11
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream-5.0/lib/libnvds_mot_klt.so
gstnvtracker: Optional NvMOT_RemoveStreams not implemented
gstnvtracker: Batch processing is OFF
gstnvtracker: Past frame output is OFF
0:00:00.258438073 18137 0x983e930 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1715> [UID = 1]: Trying to create engine from model files
Loading pre-trained weights...
Loading weights of yolov3-tiny complete!
Total Number of weights read : 8676244
Loading pre-trained weights...
Loading weights of yolov3-tiny complete!
Total Number of weights read : 8676244
Building Yolo network...
layer inp_size out_size weightPtr
(0) conv-bn-leaky 3 x 608 x 608 16 x 608 x 608 496
(1) maxpool 16 x 608 x 608 16 x 304 x 304 496
(2) conv-bn-leaky 16 x 304 x 304 32 x 304 x 304 5232
(3) maxpool 32 x 304 x 304 32 x 152 x 152 5232
(4) conv-bn-leaky 32 x 152 x 152 64 x 152 x 152 23920
(5) maxpool 64 x 152 x 152 64 x 76 x 76 23920
(6) conv-bn-leaky 64 x 76 x 76 128 x 76 x 76 98160
(7) maxpool 128 x 76 x 76 128 x 38 x 38 98160
(8) conv-bn-leaky 128 x 38 x 38 256 x 38 x 38 394096
(9) maxpool 256 x 38 x 38 256 x 19 x 19 394096
(10) conv-bn-leaky 256 x 19 x 19 512 x 19 x 19 1575792
(11) maxpool 512 x 19 x 19 512 x 19 x 19 1575792
(12) conv-bn-leaky 512 x 19 x 19 1024 x 19 x 19 6298480
(13) conv-bn-leaky 1024 x 19 x 19 256 x 19 x 19 6561648
(14) conv-bn-leaky 256 x 19 x 19 512 x 19 x 19 7743344
(15) conv-linear 512 x 19 x 19 18 x 19 x 19 7752578
(16) yolo 18 x 19 x 19 18 x 19 x 19 7752578
(17) route - 256 x 19 x 19 7752578
(18) conv-bn-leaky 256 x 19 x 19 128 x 19 x 19 7785858
INFO: [TRT]: mm1_19: broadcasting input0 to make tensors conform, dims(input0)=[1,38,19][NONE] dims(input1)=[128,19,19][NONE].
INFO: [TRT]: mm2_19: broadcasting input1 to make tensors conform, dims(input0)=[128,38,19][NONE] dims(input1)=[1,19,38][NONE].
(19) upsample 128 x 19 x 19 128 x 38 x 38 -
(20) route - 384 x 38 x 38 7785858
(21) conv-bn-leaky 384 x 38 x 38 256 x 38 x 38 8671618
(22) conv-linear 256 x 38 x 38 18 x 38 x 38 8676244
(23) yolo 18 x 38 x 38 18 x 38 x 38 8676244
Output yolo blob names :
yolo_17
yolo_24
Total number of yolo layers: 49
Building yolo network complete!
Building the TensorRT Engine...
INFO: [TRT]: mm1_19: broadcasting input0 to make tensors conform, dims(input0)=[1,38,19][NONE] dims(input1)=[128,19,19][NONE].
INFO: [TRT]: mm2_19: broadcasting input1 to make tensors conform, dims(input0)=[128,38,19][NONE] dims(input1)=[1,19,38][NONE].
INFO: [TRT]: Some tactics do not have sufficient workspace memory to run. Increasing workspace size may increase performance, please check verbose output.
INFO: [TRT]: Detected 1 inputs and 2 output network tensors.
Building complete!
0:02:35.752148292 18137 0x983e930 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1748> [UID = 1]: serialize cuda engine to file: /opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_Yolo/model_b1_gpu0_fp16.engine successfully
INFO: [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT data 3x608x608
1 OUTPUT kFLOAT yolo_17 18x19x19
2 OUTPUT kFLOAT yolo_24 18x38x38
0:02:35.795951757 18137 0x983e930 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_Yolo/config_infer_primary_yoloV3_tiny.txt sucessfully
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)
**PERF: 0.00 (0.00)
** INFO: <bus_callback:181>: Pipeline ready
** INFO: <bus_callback:167>: Pipeline running
GST_ARGUS: Creating output stream
CONSUMER: Waiting until producer is connected...
GST_ARGUS: Available Sensor modes :
GST_ARGUS: 3264 x 2464 FR = 21.000000 fps Duration = 47619048 ; Analog Gain range min 1.000000, max 10.625000; Exposure Range min 13000, max 683709000;
GST_ARGUS: 3264 x 1848 FR = 28.000001 fps Duration = 35714284 ; Analog Gain range min 1.000000, max 10.625000; Exposure Range min 13000, max 683709000;
GST_ARGUS: 1920 x 1080 FR = 29.999999 fps Duration = 33333334 ; Analog Gain range min 1.000000, max 10.625000; Exposure Range min 13000, max 683709000;
GST_ARGUS: 1280 x 720 FR = 59.999999 fps Duration = 16666667 ; Analog Gain range min 1.000000, max 10.625000; Exposure Range min 13000, max 683709000;
GST_ARGUS: 1280 x 720 FR = 120.000005 fps Duration = 8333333 ; Analog Gain range min 1.000000, max 10.625000; Exposure Range min 13000, max 683709000;
GST_ARGUS: Running with following settings:
Camera index = 0
Camera mode = 4
Output Stream W = 1280 H = 720
seconds to Run = 0
Frame Rate = 120.000005
GST_ARGUS: Setup Complete, Starting captures for 0 seconds
GST_ARGUS: Starting repeat capture requests.
CONSUMER: Producer has connected; continuing.
KLT Tracker Init
**PERF: 29.67 (29.46)
**PERF: 29.04 (29.10)
**PERF: 29.10 (29.20)
**PERF: 29.04 (29.10)
**PERF: 29.10 (29.16)
**PERF: 29.04 (29.10)
**PERF: 28.87 (29.11)
**PERF: 29.24 (29.10)
10.使用Overlay sink直接輸出結果至HDMI Screen.
編輯檔案 deepstream_app_config_yoloV3_tiny.txt
[sink0]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File 5=overlaysink
type=5
width=1280
height=720
編輯 /etc/ssh/sshd_config
+ #X11Forwarding no
- X11Forwarding yes
設定環境參數
unset DISPLAY
11.使用 CSI camera作為輸入來源
編輯檔案 deepstream_app_config_yoloV3_tiny.txt
[source0]
enable=1
#Type - 1=CameraV4L2 2=URI 3=MultiURI 5=CsiCamera
type=5
camera-width=1280
camera-height=720
12. Reference
