大桔骑士的学习笔记

CNN架构卷积层 layers.Conv2Ddata-format: 输入图像的格式,当为"channels_last"时为(batch, height, width, channels);当为"channels_first"时为(batch, channels, height, width)filters: 生成多少个卷积核(要得到的图像的厚度),即变换后的图像通道数kernel_si...

读取数据import kerasfrom keras import layersimport numpy as npfrom matplotlib import pyplot as pltimport pandas as pd%matplotlib inlineUsing TensorFlow backend.data = keras.datasets.imdb# 最多提取1...

读取数据import kerasfrom keras import layersimport numpy as npfrom matplotlib import pyplot as pltimport pandas as pd%matplotlib inlineUsing TensorFlow backend.from keras.datasets import mnist a...

读取数据和预处理import kerasfrom keras import layersimport numpy as npfrom matplotlib import pyplot as pltimport pandas as pd%matplotlib inlineUsing TensorFlow backend.data = pd.read_csv("./data/cre...

读取数据和预处理import kerasfrom keras import layersimport numpy as npfrom matplotlib import pyplot as pltimport pandas as pd%matplotlib inlineUsing TensorFlow backend.# header=None表示数据文件没有表头,第一行就是数...

读取数据和预处理import kerasfrom keras import layersfrom matplotlib import pyplot as pltimport numpy as npimport pandas as pd%matplotlib inlineUsing TensorFlow backend.data = pd.read_csv("./data/tt_...

读入数据和预处理import kerasfrom keras import layersimport numpy as npimport pandas as pdfrom matplotlib import pyplot as plt%matplotlib inlineUsing TensorFlow backend.df = pd.read_csv('./data/Iris....

读入数据和预处理import kerasfrom keras import layersimport numpy as npimport pandas as pdfrom matplotlib import pyplot as plt%matplotlib inlineUsing TensorFlow backend.df = pd.read_csv("./data/Iris....

Logistic回归预测Titanic读取数据import pandas as pdimport kerasfrom keras import layersimport numpy as npUsing TensorFlow backend.data = pd.read_csv("./data/tt_train.csv")data.head() ...

多元线性回归训练模型多元线性回归也就相当于NN的一层，y=wx+b，其中w和x是>1维的同维向量，也就是用输入的特征x1,x2,…去使用参数w和b预测y值。import pandas as pdimport matplotlib as plt%matplotlib inline# Kaggle房价的train数据df = pd.read_csv("./data/hp_trai...

简述Keras是在既有的NN框架之上的封装，可以以TF，CNTK，Theano等作为后端来运行。它的价值在于快速实验，能很方便将实验想法用Keras框架写成代码。开发环境搭建默认情况下Keras使用TF为后端。注意后面两个用pip安装，不然一直无法安装成功。这里为了学习方便直接安装了TF，如果有GPU可以去安装GPU版本的TF。conda create -n krs python=3.6....