I have just started learning about DeepStream. I am interested to run a resnet50 classifier on a video, just to see how the whole flow works

• Jetson
• DeepStream Version - 6.0
• JetPack Version (valid for Jetson only) - R32 (release), REVISION: 6.1, GCID: 27863751, BOARD: t186ref, EABI: aarch64
• TensorRT Version - 8.0.1.6
• Issue Type( questions, new requirements, bugs)
How do I go about creating a classifier that runs inference on each frame of a video and simply prints the class on the console (just to get started)?

[property]
process-mode=1 # Process full frames
network-type=1 # Classifier

gpu-id=0
net-scale-factor=0.003921568627451
model-color-format=0
onnx-file=resnet50.onnx
model-engine-file=resnet50.onnx_b1_gpu0_fp16.engine
batch-size=1
network-mode=0
labelfile-path=imagenet_classes.txt
output-blob-names=output
classifier-threshold=0.51
gie-unique-id=1
What should I do here?
def osd_sink_pad_buffer_probe(pad,info,u_data)

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

Please refer to this: it is for a single but you can adapt the pipeline to a video.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.