peopleSegNetV2 output is black

[Edu4444]

Hello. I have tested peopleSegNetV2 and peopleSegNet on a jetson Nano and on a jetson TX2.
I used a .jpg and a .h264 files from deepstream samples and as output I got black images and black videos without any detection.

I have TensorRT OSS plugin installed, deepstream 5.1, TensorRT 7.1.3, jetpack 4.5.1.
Using updated github files.
Deepstream sample apps works properly on the devices.

mero@Jetson-HC02:~/deepstream_tlt_apps$ export SHOW_MASK=1
mero@Jetson-HC02:~/deepstream_tlt_apps$ ./apps/tlt_segmentation/ds-tlt-segmentation -c configs/peopleSegNet_tlt/pgie_peopleSegNetv2_tlt_config.txt -i /opt/nvidia/deepstream/deepstream-5.1/samples/streams/sample_720p.jpg
Now playing: configs/peopleSegNet_tlt/pgie_peopleSegNetv2_tlt_config.txt
Opening in BLOCKING MODE
Opening in BLOCKING MODE 
0:00:24.214130103 10905   0x557a39d640 INFO                 nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1702> [UID = 1]: deserialized trt engine from :/home/mero/deepstream_tlt_apps/models/peopleSegNet/peopleSegNetV2_resnet50.etlt_b1_gpu0_fp16.engine
INFO: [Implicit Engine Info]: layers num: 3
0   INPUT  kFLOAT Input           3x576x960       
1   OUTPUT kFLOAT generate_detections 100x6           
2   OUTPUT kFLOAT mask_fcn_logits/BiasAdd 100x2x28x28     

0:00:24.214316410 10905   0x557a39d640 INFO                 nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1806> [UID = 1]: Use deserialized engine model: /home/mero/deepstream_tlt_apps/models/peopleSegNet/peopleSegNetV2_resnet50.etlt_b1_gpu0_fp16.engine
0:00:24.334049448 10905   0x557a39d640 INFO                 nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<primary-nvinference-engine> [UID 1]: Load new model:configs/peopleSegNet_tlt/pgie_peopleSegNetv2_tlt_config.txt sucessfully
Running...
NvMMLiteBlockCreate : Block : BlockType = 256 
[JPEG Decode] BeginSequence Display WidthxHeight 1280x720
in videoconvert caps = video/x-raw(memory:NVMM), format=(string)RGBA, framerate=(fraction)1/1, width=(int)1280, height=(int)720
End of stream
Returned, stopping playback
[JPEG Decode] NvMMLiteJPEGDecBlockPrivateClose done
[JPEG Decode] NvMMLiteJPEGDecBlockClose done
Deleting pipeline

[ALittleBug]

PeopleSegNet is a instance segmentation model, so you need to run the model via ./apps/tlt_detection/ds-tlt-detection, refer following command to see if issue persist?
[SHOW_MASK=1] ./apps/tlt_detection/ds-tlt-detection -c configs/frcnn_tlt/pgie_frcnn_tlt_config.txt -i $DS_SRC_PATH/samples/streams/sample_720p.h264

[Edu4444]

PeopleSegNet is a instance segmentation model, so you need to run the model via ./apps/tlt_detection/ds-tlt-detection, refer following command to see if issue persist?
[SHOW_MASK=1] ./apps/tlt_detection/ds-tlt-detection -c configs/frcnn_tlt/pgie_frcnn_tlt_config.txt -i $DS_SRC_PATH/samples/streams/sample_720p.h264

Thank you.
Now it's working as expected.

[pra-dan]

Can you both kindly update the solution for the newly added TAO examples. I am trying to infer Mask-RCNN uff model & engine and infer using the tao-deepstream-segmentation sample. All I get it dark masks. I even tried the sample on the detection sample and got the input image as output but with a changed size, nothing else.