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 :-

[property]
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

numLandmarks=80
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.

without any code and cfg modification, I can’t reproduce this issue. there are three faces in my test video.
could you highlight your modifications? could you provide your test video by forum private email?

sure, can I DM you?

You can use forum private email. please click forum avatar-> personal messages->new message.

okay wait,let me confirm

There is no update from you for a period, assuming this is not an issue any more. Hence we are closing this topic. If need further support, please open a new one. Thanks.
Sorry for the late reply, Is this still an DeepStream issue to support? Thanks!

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