Skip to content
This repository has been archived by the owner on Aug 5, 2022. It is now read-only.

Caffe_v1.1.2
Compare
Choose a tag to compare
@hshen14 hshen14 released this 29 Sep 03:26
· 81 commits to master since this release
1.1.2
dcc03cb
  • Features

  1. INT8 inference
    Inference speed improved with upgraded MKL-DNN library.
    In-place concat for latency improvement with batch size 1. Scale unify for concat for better performance. Support added in calibration tool as well

  2. FP32 inference
    Performance improved on detectionOutput layer with ~3X
    Add MKL-DNN 3D convolution support

  3. Multi-node training
    SSD-VGG16 multi-node training is supported

  4. New models
    Support training of R-FCN object detection model
    Support training of Yolo-V2 object detection model
    Support inference of SSD-MobileNet object detection model
    Added the SSD-VGG16 multi-node model that converges to SOTA

  5. Build improvement
    Fixed compiler warnings using GCC7+ version

  6. Misc
    MKLML upgraded to mklml_lnx_2019.0.20180710
    MKL-DNN upgraded to v0.16+ (4e333787e0d66a1dca1218e99a891d493dbc8ef1)

  • Known issues
  1. INT8 inference accuracy drop for convolutions with output channel 16-individable
  2. FP32 training cannot reach SOTA accuracy with Winograd convolution
Assets 2