every blog every motto:

0. 前言

计算图的构建

1. 代码部分

1. 导入模块

import matplotlib as mplimport matplotlib.pyplot as plt%matplotlib inlineimport numpy as npimport sklearnimport pandas as pdimport osimport sysimport timeimport tensorflow as tffrom tensorflow import kerasprint(tf.__version__)print(sys.version_info)for module in mpl,np,pd,sklearn,tf,keras:print(module.__name__,module.__version__)

2. 读取数据

fashion_mnist = keras.datasets.fashion_mnist# print(fashion_mnist)(x_train_all,y_train_all),(x_test,y_test) = fashion_mnist.load_data()x_valid,x_train = x_train_all[:5000],x_train_all[5000:]y_valid,y_train = y_train_all[:5000],y_train_all[5000:]# 打印格式print(x_valid.shape,y_valid.shape)print(x_train.shape,y_train.shape)print(x_test.shape,y_test.shape)

3. 数据归一化

print(np.max(x_train),np.min(x_train))

# 数据归一化from sklearn.preprocessing import StandardScalerscaler = StandardScaler()# x_train:[None,28,28] -> [None,784]x_train_scaled = scaler.fit_transform(x_train.astype(np.float32).reshape(-1,1)).reshape(-1,28,28)x_valid_scaled = scaler.transform(x_valid.astype(np.float32).reshape(-1,1)).reshape(-1,28,28)x_test_scaled = scaler.transform(x_test.astype(np.float32).reshape(-1,1)).reshape(-1,28,28)

print(np.max(x_train_scaled),np.min(x_train_scaled))

4. 计算图构建

hidden_units = [100,100]class_num = 10x = tf.placeholder(tf.float32,[None,28*28])y = tf.placeholder(tf.int64,[None])# 隐藏层input_for_next_layer = xfor hidden_unit in hidden_units:input_for_next_layer = tf.layers.dense(input_for_next_layer,hidden_unit,activation=tf.nn.relu)# 输出层logits = tf.layers.dense(input_for_next_layer,class_num)# last_hidden_output * w(logits) -> softmax -> pro# 1. logit -> softmax -> prob# 2. labels -> ont_hot# 3. calculate cross entropyloss = tf.losses.sparse_softmax_cross_entropy(labels=y,logits=logits)# get accuracyprediction = tf.argmax(logits,1)correct_prediction = tf.equal(prediction,y)accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float64))# train_op = tf.train.AdamOptimizer(1e-3).minimize(loss)

print(x)print(logits)

如果觉得《从零基础入门Tensorflow2.0 ----五 22TF1.0计算图构建》对你有帮助，请点赞、收藏，并留下你的观点哦！