I used Nvidia's Transfer Learning Toolkit(TLT) to train and then used the tlt-converter to convert the .etlt model into an .engine file. I want to use this .engine file for inference in python. But since I trained using TLT I dont have any frozen graphs or pb files which is what all the TensorRT inference tutorials need. I would like to know if python inference is possible on .engine files. If not, what are the supported conversions(UFF,ONNX) to make this possible? Continue reading...
