Setup:
• Hardware Platform: GPU
• DeepStream Version: docker deepstream:5.0.1-20.09-triton
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only): 450.51.06
• Issue Type( questions, new requirements, bugs): bugs, trouble
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
Currently, I am using the sample app deepstream-transfer-learning-app to extract frames and crops of a large video (6GB). I am using my own model, which was trained with the transfer learning tool kit. The infer configuration of this file is the following:
[property]
gpu-id=0
gie-unique-id=1
net-scale-factor=0.0039215697906911373
tlt-model-key=placas
tlt-encoded-model=../../../../../samples/tlt_models/1/resnet18_detector.etlt
labelfile-path=../../../../../samples/tlt_models/1/placas_labels.txt
int8-calib-file=../../../../../samples/tlt_models/1/calibration.bin
#input-dims=3;544;960;0
infer-dims=3;544;960
uff-input-blob-name=input_1
output-blob-names=output_bbox/BiasAdd;output_cov/Sigmoid
batch-size=1
process-mode=1
model-color-format=0
## 0=FP32, 1=INT8, 2=FP16 mode
network-mode=1
num-detected-classes=2
is-classifier=0
## 0=Group Rectangles, 1=DBSCAN, 2=NMS, 3= DBSCAN+NMS Hybrid, 4 = None(No clustering)
cluster-mode=1
interval=0
[class-attrs-all]
pre-cluster-threshold=0.2
eps=0.7
minBoxes=1
However, when I used this model with the app the performance rate goes down to 0:00 after some seconds of execution. I don’t understand what is the problem. Therefore, just a few frames and crops are saved.
The file of configuration that I used is the following:
[application]
enable-perf-measurement=1
perf-measurement-interval-sec=5
#gie-kitti-output-dir=streamscl
[tiled-display]
enable=1
rows=1
columns=1
width=1280
height=720
gpu-id=0
#(0): nvbuf-mem-default - Default memory allocated, specific to particular platform
#(1): nvbuf-mem-cuda-pinned - Allocate Pinned/Host cuda memory applicable for Tesla
#(2): nvbuf-mem-cuda-device - Allocate Device cuda memory applicable for Tesla
#(3): nvbuf-mem-cuda-unified - Allocate Unified cuda memory applicable for Tesla
#(4): nvbuf-mem-surface-array - Allocate Surface Array memory, applicable for Jetson
nvbuf-memory-type=0
[source0]
enable=1
#Type - 1=CameraV4L2 2=URI 3=MultiURI 4=RTSP
type=2
uri=file://../../../../../samples/streams/placas23largo.mp4
num-sources=1
#drop-frame-interval=2
gpu-id=0
# (0): memtype_device - Memory type Device
# (1): memtype_pinned - Memory type Host Pinned
# (2): memtype_unified - Memory type Unified
cudadec-memtype=0
[sink0]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File
type=1
sync=1
source-id=0
gpu-id=0
nvbuf-memory-type=0
[osd]
enable=1
gpu-id=0
border-width=1
text-size=15
text-color=1;1;1;1;
text-bg-color=0.3;0.3;0.3;1
font=Serif
show-clock=0
clock-x-offset=800
clock-y-offset=820
clock-text-size=12
clock-color=1;0;0;0
nvbuf-memory-type=0
[streammux]
gpu-id=0
##Boolean property to inform muxer that sources are live
live-source=0
batch-size=1
##time out in usec, to wait after the first buffer is available
##to push the batch even if the complete batch is not formed
batched-push-timeout=40000
## Set muxer output width and height
width=1920
height=1080
##Enable to maintain aspect ratio wrt source, and allow black borders, works
##along with width, height properties
enable-padding=0
nvbuf-memory-type=0
## 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
# attach-sys-ts-as-ntp=1
# config-file property is mandatory for any gie section.
# Other properties are optional and if set will override the properties set in
# the infer config file.
[primary-gie]
enable=1
gpu-id=0
#model-engine-file=../../../../../samples/models/Primary_Detector/resnet10.caffemodel_b4_gpu0_int8.engine
batch-size=1
#Required by the app for OSD, not a plugin property
bbox-border-color0=1;0;0;1
bbox-border-color1=0;1;1;1
bbox-border-color2=0;0;1;1
bbox-border-color3=0;1;0;1
interval=0
gie-unique-id=1
nvbuf-memory-type=0
config-file=config_infer_primary_ds_transfer_learning.txt
#config-file=config_infer.txt
[tracker]
enable=0
# For the case of NvDCF tracker, tracker-width and tracker-height must be a multiple of 32, respectively
tracker-width=640
tracker-height=384
#ll-lib-file=/opt/nvidia/deepstream/deepstream-5.0/lib/libnvds_mot_iou.so
#ll-lib-file=/opt/nvidia/deepstream/deepstream-5.0/lib/libnvds_nvdcf.so
ll-lib-file=/opt/nvidia/deepstream/deepstream-5.0/lib/libnvds_mot_klt.so
#ll-config-file required for DCF/IOU only
#ll-config-file=tracker_config.yml
#ll-config-file=iou_config.txt
gpu-id=0
#enable-batch-process and enable-past-frame applicable to DCF only
enable-batch-process=1
enable-past-frame=0
display-tracking-id=1
[tests]
file-loop=0
[img-save]
enable=1
output-folder-path=./output
save-img-cropped-obj=0
save-img-full-frame=1
frame-to-skip-rules-path=capture_time_rules.csv
second-to-skip-interval=10
min-confidence=0.3
max-confidence=1.0
min-box-width=5
min-box-height=5