Record .engin

Hello ,

Please I’m looking for how to register the engine yolov3_b1_gpu0.engin generate after doing the inference, so as not to be forced to compile my application each time, my configuration file is as follows:inference.txt (2.0 KB)


We don’t know your model type and features. Is your model exported according to Exporting the Model — Transfer Learning Toolkit 2.0 documentation ( If so, you can refer to Deploying to Deepstream — Transfer Learning Toolkit 2.0 documentation (

From deepstream point of view, deepstream supports caffe model, uff file, onnx and TLT encoded models, for different type of model, the configurations will be different.