Open leonzgtee opened 5 years ago
This is to ensure that the batch norm layer are set accordingly. These two lines should be kept.
thanks for your reply.
@leonzgtee did u perform the network slimming, on which architecture how mucha was the performance gain from the main model . did ur accuracy drop ? by how much
@abhigoku10 yes i did the network slimming, in our own training architecture with our own data, map drops about 0.01 from 0.38 to 0.37
anyone konws what the line128 model.tarin() and line 154 model.eval() in network-slimming/main.py are meant for. i did not find the defination of these two function,can i just delete them,thanks