NVIDIA / object-detection-tensorrt-example

Running object detection on a webcam feed using TensorRT on NVIDIA GPUs in Python.
211 stars 61 forks source link

SSD output #18

Open lchunleo opened 4 years ago

lchunleo commented 4 years ago

Hi

i noted that the SSD output is layout with field such as "image id", "labels" in the TRT_PREDICTION_LAYOUT etc. Can you help to point out how to find out this information from the SSD to know what is the output format for you to able to know the layout? Reason being i am using a custom SSD and i am unable to get the correct information out to do the tensorrt inference. thank you