Jiwon Hwang (Jin)

Results 3 comments of Jiwon Hwang (Jin)

thanks! :D

use original model with strict=False

not sure what int8 model means. anyway, i use this method. at model init part, during training self.conv1 = lsqconv(~~) during inferencing self.conv1 = nn.Conv2d(~~) name "self.conv1" does not changed...