Skip to content

Caffe Framework for DesignWare EV Processors, S-2021.09

Choose a tag to compare

View all tags
@vera121 vera121 released this 31 Aug 07:11
· 129 commits to master since this release
S-2021.09
4601cef
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Verified
Learn about vigilant mode.

This is release S-2021.09 of Synopsys-caffe, a modified version of the popular Caffe Deep Learning framework adapted for use with DesignWare EV Family of Processors.

Synopsys-caffe is meant to be used together with synopsys-caffe-models and the MetaWare EV Development Toolkit S-2021.09, from Synopsys.

New Features in this Release:

  • evconvert enhancement: Added 2 new layers spatial_batching_pooling_layer and tensor2box_layer, and refined existing layers to better support TensorFlow/Keras/ONNX/Pytorch/Caffe2 models conversion
  • Custom Quantized model support: Introduced EV style quantization and rounding mechanism for key layers
  • Updated python dependencies and scripts with newer packages

Full details see: FEATURES.md

Assets 2
Loading