摘要:
data augmentation 几种方法总结 在深度学习中,有的时候训练集不够多,或者某一类数据较少,或者为了防止过拟合,让模型更加鲁棒性,data augmentation是一个不错的选择。 常见方法 Color Jittering:对颜色的数据增强:图像亮度、饱和度、对比度变化(此处对色彩抖 阅读全文
摘要:
论文《A Deep Neural Network Compression Pipeline: Pruning, Quantization, Huffman Encoding》 Pruning by learning only the important connections. 1. all con 阅读全文
摘要:
Question Given a string s and a dictionary of words dict, determine if s can be segmented into a space separated sequence of one or more dictionary wo 阅读全文