about train() and eval()

[leonzgtee]

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

[Eric-mingjie]

This is to ensure that the batch norm layer are set accordingly. These two lines should be kept.

[leonzgtee]

thanks for your reply.

[abhigoku10]

@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

[leonzgtee]

@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