Abdelrahman Rabah

` while True: # capture the next image img = input.Capture() detections = net.Detect(img, overlay='box,labels,conf') # Convert from Cuda to BGR numpy array img_array = jetson.utils.cudaToNumpy(img) #print('shape of the image',...

> `net.GetNetworkFPS()` returns the FPS for just the DNN network. > > `videoOutput.GetFrameRate()` would return the frame rate that images are rendered to the display. when I replaced ` print("{:.0f}...

@dusty-nv I want to try inception and mobilenet for research purposes also, thats why I was asking about mobilenet v2 or inception compatibility if that's possible

@dusty-nv I'm actually concerned about both I want to test fps using TRT on the jetson nano for few models and pick the one with the optimal performance *Of course...

I've the same issue @kevinch-nv