I would like to duplicate the results published in “Jetson AGX Xavier: Deep Learning Inference Benchmarks” seciton MAX-N Mode* (HD) [url]https://developer.nvidia.com/embedded/jetson-agx-xavier-dl-inference-benchmarks[/url]. Where can I find instructions, models, and training weights to duplicate these results?
Hi brad.larson, the example commands to run the inferencing with the trtexec tool are listed at the bottom of the page here:
https://developer.nvidia.com/embedded/jetson-agx-xavier-dl-inference-benchmarks#trtexec
trtexec is open-source and ships with the TensorRT samples (code found in /usr/src/tensorrt/samples)
See these links below to find the models:
- AlexNet.......https://github.com/BVLC/caffe/tree/master/models/bvlc_alexnet
- GoogleNet...https://github.com/BVLC/caffe/tree/master/models/bvlc_googlenet
- ResNet-50...https://github.com/KaimingHe/deep-residual-networks#models
- ResNet-18 FCN...https://drive.google.com/file/d/1HSP7xzj2k-z12r37vEn7mqCamZU8dR9T/view?usp=sharing
- VGG19...https://github.com/BVLC/caffe/wiki/Model-Zoo#neural-activation-constellations-unsupervised-part-model-discovery-with-convolutional-networks