search

NVIDIA-AI-IOT / deepstream_tao_apps

Sample apps to demonstrate how to deploy models trained with TAO on DeepStream
MIT License
380 stars 97 forks source link

No detections with peopleSegNetv2 on Jetson TX2 #40

Closed Edu4444 closed 3 years ago

Edu4444 commented 3 years ago

Hello. I have tested peopleSegNetv2 con a jetson nano and it's working as expected, but on a jetson TX2 the network is not generating any detection over the input image. Threre are no output labels using SHOW_MASK=1 or SHOW_MASK=0. Other models are working fine, I have tested SSD succesfully.

Jetpack 4.5.1,Deepstream 5.1, TensorRT 7.1.3, TRT OSS plugin built with -DGPU_ARCHS="62". Using latest github files.

mero-jetson@Jetson-TX2:~/deepstream_tlt_apps$ export SHOW_MASK=1
mero-jetson@Jetson-TX2:~/deepstream_tlt_apps$ ./apps/tlt_detection/ds-tlt-detection -c configs/peopleSegNet_tlt/pgie_peopleSegNetv2_tlt_config.txt -i /opt/nvidia/deepstream/deepstream-5.1/samples/streams/sample_720p.jpg

Output image: out

younglalala commented 3 years ago

Hello,Has this problem been solved？

Edu4444 commented 3 years ago

Hello,Has this problem been solved？

Hello. Unfortunately it has not been solved yet. I will try recent Jetpack release 4.6.

younglalala commented 3 years ago

Hello,I have solved the problem.Do not convert the model to INT8, conversion to FP16 will work