Hi, Using maskrcnn from tlt v2, on jetson, following the notebook training in the user guide. — NOT USING DEEPSTREAM — Say I managed to convert (using tlt-converter) the model . How do I parse the results in my c/c++ code ? That is, I enqueue the input to the model, and copy the results (say u…

See https://docs.nvidia.com/metropolis/TLT/tlt-getting-started-guide/text/deploying_to_deepstream.html#generating-an-engine-using-tlt-converter For classification use: predictions/Softmax. For DetectNet_v2: output_bbox/BiasAdd,output_cov/Sigmoid For FasterRCNN: dense_class_td/Softmax,dense_regr…

Maskrcnn (segmentation) using a converted model in c++ without DeepStream

Accelerated Computing Intelligent Video Analytics TAO Toolkit

dannykario December 4, 2020, 5:35am 4

Great, thanks.

Topic		Replies	Views
Parsing Maskrcnn output with TensorRT in python TensorRT	1	370	August 2, 2021
Modify NvDsInferObjectDetectionInfo for get mask from Mask RCNN TensorRT tensorrt	9	554	October 12, 2021
Get TLT Mask-RCNN output masks into python / numpy DeepStream SDK	2	453	October 12, 2021
Deepstream doesn't give expected Mask-RCNN output DeepStream SDK	26	3156	February 8, 2022
Parsing Maskrcnn output with TensorRT in python TAO Toolkit	3	717	October 1, 2021
Error running TLT-retrained maskrcnn on deepstream DeepStream SDK	6	455	October 12, 2021
Modify NvDsInferObjectDetectionInfo for get mask from Mask RCNN DeepStream SDK	3	434	October 12, 2021
Deepstream_mrcnn_test could not output mask DeepStream SDK	8	1718	October 12, 2021
Running inference outside of TLT pipeline / getting predictions TAO Toolkit tensorflow	8	782	October 12, 2021
MaskRCNN on Xavier - UffParser: Validator error Unsupported operation _GenerateDetection_TRT TAO Toolkit jetson-inference	12	1328	October 12, 2021

Maskrcnn (segmentation) using a converted model in c++ without DeepStream

Related topics