I try to run deepstream’s samples in nano, I feel too slow in starting when to convert the caffe model to trt model, I noticed a trt model writed when runing… so ,how to used it ?
this is test1’s config file:
[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
model-file=../../../../samples/models/Primary_Detector/resnet10.caffemodel
proto-file=../../../../samples/models/Primary_Detector/resnet10.prototxt
labelfile-path=../../../../samples/models/Primary_Detector/labels.txt
int8-calib-file=../../../../samples/models/Primary_Detector/cal_trt.bin
batch-size=1
network-mode=1
num-detected-classes=4
interval=0
gie-unique-id=1
output-blob-names=conv2d_bbox;conv2d_cov/Sigmoid
[class-attrs-all]
threshold=0.2
eps=0.2
group-threshold=1
and this is console log when run test1
deepstream-test1-app /usr/share/visionworks/sources/data/pedestrians.h264
Now playing: /usr/share/visionworks/sources/data/pedestrians.h264
Using winsys: x11
Opening in BLOCKING MODE
Creating LL OSD context new
0:00:01.154296444 7881 0x378ddf20 INFO nvinfer gstnvinfer.cpp:519:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]:initialize(): Trying to create engine from model files
0:00:01.154511303 7881 0x378ddf20 WARN nvinfer gstnvinfer.cpp:515:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]:generateTRTModel(): INT8 not supported by platform. Trying FP16 mode.
0:01:52.210185315 7881 0x378ddf20 INFO nvinfer gstnvinfer.cpp:519:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]:generateTRTModel(): Storing the serialized cuda engine to file at /usr/local/liu/deepstream/samples/models/Primary_Detector/resnet10.caffemodel_b1_fp16.engine
Running...
NvMMLiteOpen : Block : BlockType = 261
NVMEDIA: Reading vendor.tegra.display-size : status: 6
NvMMLiteBlockCreate : Block : BlockType = 261
Creating LL OSD context new
so,how to use the /usr/local/liu/deepstream/samples/models/Primary_Detector/resnet10.caffemodel_b1_fp16.engine file to accelerate the program when starting?