随笔分类 - 深度学习
摘要:""" Created on 2021/1/4 20:25. @Author: anne """ # https://blog.csdn.net/Hanghang_/article/details/108592828 详解bisenet网络结构 # https://blog.csdn.net/TTL
阅读全文
摘要:""" Created on 2020/11/29 19:59. @Author: yubaby@anne @Email: yhaif@foxmail.com """ from tensorflow.keras.layers import Input, Conv2D, BatchNormalizat
阅读全文
摘要:""" Created on 2020/11/29 19:51. @Author: yubaby@anne @Email: yhaif@foxmail.com """ import numpy as np import tensorflow as tf from tensorflow.keras.l
阅读全文
摘要:""" Created on 2021/3/15 9:58. @Author: haifei """ # https://zhuanlan.zhihu.com/p/136657292 # https://blog.csdn.net/weixin_44791964/article/details/10
阅读全文
摘要:""" Created on 2020/11/29 19:45. @Author: yubaby@anne @Email: yhaif@foxmail.com """ from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, B
阅读全文
摘要:""" Created on 2020/11/29 19:36. @Author: yubaby@anne @Email: yhaif@foxmail.com """ from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, B
阅读全文
摘要:""" Created on 2020/11/29 19:42. @Author: yubaby@anne @Email: yhaif@foxmail.com """ from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, D
阅读全文
摘要:""" Created on 2021/1/26 22:01. @Author: anne """ from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, Dropout from tensorflow.keras.layer
阅读全文
摘要:""" Created on 2020/11/17 20:02. @Author: yubaby@anne @Email: yhaif@foxmail.com """ import tensorflow as tf from tensorflow.keras.layers import Input,
阅读全文
摘要:""" Created on 2020/11/29 19:49. @Author: yubaby@anne @Email: yhaif@foxmail.com """ from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, D
阅读全文
摘要:""" Created on 2020/11/29 18:57. @Author: yubaby@anne @Email: yhaif@foxmail.com """ from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, D
阅读全文
摘要:MobileNetV1引入深度可分离卷积作为传统卷积层的有效替代,深度可分卷积通过将空间滤波与特征生成机制分离,有效地分解传统卷积。深度可分卷积由两个独立的层定义:用于空间滤波的轻量级深度卷积和用于特征生成的1x1点卷积。具体来说就是深度卷积中一个卷积核通道上只有一维,负责特征图的一个通道,一个通道
阅读全文
摘要:参考:https://blog.csdn.net/fantianning/article/details/115880363
阅读全文