摘要:
在Improving neural networks by preventing co-adaptation of feature detectors论文中,Hinton提出 Random “dropout” gives big improvements on many benchmark task 阅读全文
摘要:
This dataset is just like the CIFAR-10, except it has 100 classes containing 600 images each. There are 500 training images and 100 testing images per 阅读全文
摘要:
如果项目TestApp中同时存在.c和.cpp文件,可以使用两种方式指定编译器: 1: project(TestApp LANGUAGES C CXX) 2: project(TestApp LANGUAGES C ) project(TestApp LANGUAGES CXX ) 这样可以解决编译 阅读全文