search

NVIDIA-AI-IOT / deepstream-occupancy-analytics

This is a sample application for counting people entering/leaving in a building using NVIDIA Deepstream SDK, Transfer Learning Toolkit (TLT), and pre-trained models. This application can be used to build real-time occupancy analytics applications for smart buildings, hospitals, retail, etc. The application is based on deepstream-test5 sample application.
MIT License
221 stars 73 forks source link

NvDsInferCudaEngineGetFromTltModel: TLT encoded model file path not provided #6

Open thunder95 opened 3 years ago

thunder95 commented 3 years ago

In the config file, I do have set: tlt-encoded-model=peoplenet/resnet18_peoplenet_pruned.etlt

config_infer_primary_peoplenet.txt:

[property] gpu-id=0 net-scale-factor=0.0039215697906911373 tlt-model-key=tlt_encode tlt-encoded-model=peoplenet/resnet18_peoplenet_pruned.etlt labelfile-path=peoplenet/labels.txt

model-engine-file=../models/resnet18_peoplenet_pruned.etlt_b4_gpu0_fp16.engine

int8-calib-file=peoplenet/resnet18_peoplenet_int8.txt input-dims=3;544;960;0 uff-input-blob-name=input_1 batch-size=4 process-mode=2 model-color-format=0

0=FP32, 1=INT8, 2=FP16 mode

network-mode=1 num-detected-classes=3 cluster-mode=1 interval=0 gie-unique-id=1 output-blob-names=output_bbox/BiasAdd;output_cov/Sigmoid

[class-attrs-all] pre-cluster-threshold=0.4

Set eps=0.7 and minBoxes for cluster-mode=1(DBSCAN)

eps=0.7 minBoxes=1

[class-attrs-1] pre-cluster-threshold=1.4

Set eps=0.7 and minBoxes for cluster-mode=1(DBSCAN)

eps=0.7 minBoxes=1 [class-attrs-2] pre-cluster-threshold=1.4

Set eps=0.7 and minBoxes for cluster-mode=1(DBSCAN)

eps=0.7 minBoxes=1

monjha commented 3 years ago

Hi Thunder95,

Could you please provide the log and the steps you used?

thunder95 commented 3 years ago

Hi Thunder95,

Could you please provide the log and the steps you used?

Hello, monjha, thanks for you reply firstly. I have figured out it was my mistake. Another question, when I received kafa message from this project, and still not clear which data field indicates the entry or exit, because I need to save the people amount inside timely. Could you help me further?

{'messageid': '3d83fc8b-71c4-4f1f-b70c-d2d51e70d0c2', 'mdsversion': '1.0', '@timestamp': '2021-01-16T03:58:37.007Z', 'place': {'id': '0', 'name': 'HWY_20_AND_LOCUST__EBA', 'type': 'intersection/road', 'location': {'lat': 30.32, 'lon': -40.55, 'alt': 100.0}, 'entrance': {'name': 'C_127_158', 'lane': 'Lane 1', 'level': 'P1', 'coordinate': {'x': 1.0, 'y': 2.0, 'z': 3.0}}}, 'sensor': {'id': 'HWY_20_AND_LOCUSTEBA4_11_2018_4_59_59_508_AM_UTC-07_00', 'type': 'Camera', 'description': 'Aisle Camera', 'location': {'lat': 45.293701447, 'lon': -75.8303914499, 'alt': 48.1557479338}, 'coordinate': {'x': 5.2, 'y': 10.1, 'z': 11.2}}, 'analyticsModule': {'id': 'XYZ', 'description': '', 'source': 'OpenALR', 'version': '1.0', 'confidence': 0.0}, 'object': {'id': '0', 'speed': 0.0, 'direction': 0.0, 'orientation': 0.0, 'person': {'age': 0, 'gender': '', 'hair': '', 'cap': '', 'apparel': '', 'confidence': 1.0}, 'bbox': {'topleftx': 0, 'toplefty': 0, 'bottomrightx': 0, 'bottomrighty': 0}, 'location': {'lat': 0.0, 'lon': 0.0, 'alt': 0.0}, 'coordinate': {'x': 0.0, 'y': 0.0, 'z': 0.0}}, 'event': {'id': '32434d98-4929-45bb-bb8e-a84959595475', 'type': 'entry'}, 'videoPath': ''}