Faciallandmark model only works when there is only one face in the image.d

Deepstream 6.4 dGPU

I have a pipeline wherein I’m using FacialLandmarks Estimation model from Tao and I referred to this sample.
My config files are :-

gpu-id=0
model-engine-file=model.etlt_b32_gpu0_int8.engine
tlt-model-key=nvidia_tlt
tlt-encoded-model=model.etlt
int8-calib-file=int8_calibration.txt
#dynamic batch size
batch-size=32
## 0=FP32, 1=INT8, 2=FP16 mode
network-mode=1
num-detected-classes=1
output-blob-names=softargmax;softargmax:1;conv_keypoints_m80
#0=Detection 1=Classifier 2=Segmentation 100=other
network-type=100
# Enable tensor metadata output
output-tensor-meta=1
#1-Primary  2-Secondary
process-mode=2
operate-on-gie-id=1 
net-scale-factor=1.0
offsets=0.0
classifier-async-mode=0
input-object-min-width=5
input-object-min-height=5
#0=RGB 1=BGR 2=GRAY
model-color-format=2
gie-unique-id=2

[class-attrs-all]
threshold=0.0

and

maxBatchSize=32
inputLayerWidth=80
inputLayerHeight=80

The problem that I am facing is that, the landmark estimation is working properly only when there is one face in the image.
if there are multiple faces, them landmarks estimation is random for all except one face.

I have copied this entire post from one of my earlier post which got closed due to inactivity.
like to previous post :- link to previous post

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• 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)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

We did not reproduce the issue you reported. What can we do for you?

Hardware Platform (Jetson / GPU) :- dGPU
DeepStream Version :- 6.4
TensorRT Version :- probably 8.6
NVIDIA GPU Driver Version :- 535
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) :- run the faciallandmarks sample app on a video that has more than one person. or maybe try it out on the video that I provide you, if the issues is not getting reproduced on the video that you use.

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

Please provide the video you used.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.