Skip to content

DeepDetect v0.9.1 - TensorRT backend
Compare
Choose a tag to compare
@beniz beniz released this 30 Jun 13:26
· 1206 commits to master since this release
v0.9.1
b5d5ff0
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.

This release mainly adds support for TensorRT, including DLA acceleration on NVidia Xavier boards.

For a full report on performances for a variety of image models (classification and object detection) on various embedded boards (Jetson Nano, TX2 & Xavier), see Jolibrain's report here: https://www.jolibrain.com/reports/Jolibrain_DeepDetect_NVidia_Caffe_TensorRT_benchmarks_june_2019_2.pdf

Main changes:

  • Support for TensorRT 5.x with "mllib":"tensorrt" API option (#594)
    • Automated compilation from Caffe models to TensorRT accelerated models
    • Support for DLA on Xavier board
    • Benchmark tool update for tensorRT (#589)
  • Fix to object detection bounding boxes boundaries (#594)
  • Support for residual networks with LSTMs for time-series (#583)
  • Performances fixes for time-series (#583)
Assets 2