Created by: sfraczek

PR types

Bug fixes

PR changes

Others

Describe

Fixed Error when running test_quant2_int8_mobilenetv1_mkldnn with the recieved mobilenetv1_KL_quant model. The error that was fixed was AssertionError: The size of weight scales vector (1000) does not match the number of output channels (1024) in the weights tensor fc7_weights. The reason was that the weights in this mul operator did not require transposition as in previous cases.