int8 layers and 8-bit quantization support

Browse Source

...

This commit is contained in:

SamFC10

2021-08-19 09:56:47 +05:30

parent 95919051e0

commit fa90e14b06

36 changed files with 6401 additions and 67 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

modules/dnn/src/int8layers/convolution_layer.cpp

+1136

File diff suppressed because it is too large Load Diff