tensorflow2.0，神经网络fit函数及梯度下降代码实现
import matplotlib.pyplot as plt
from tensorflow import keras
import tensorflow as tf
import matplotlib as mpl
import pandas as pd
import numpy as np
import sklearn
import time
import sys
import os
# 加载数据
from sklearn.datasets import fetch_california_housing
housing = fetch_california_housing()
print(housing.data.shape) # (20640, 8)
print(housing.target.shape) # (20640, )
# 切分数据集
from sklearn.model_selection import train_test_split
x_train_all, x_test, y_train_all, y_test = train_test_split(housing.data, housing.target, random_state = 7)
x_train, x_valid, y_train, y_valid = train_test_split(x_train_all, y_train_all, random_state = 11)
print(x_train.shape, y_train.shape) # (11610, 8) (11610,)
print(x_valid.shape, y_valid.shape) # (3870, 8) (3870,)
print(x_test.shape, y_test.shape) # (5160, 8) (5160,)
# 数据归一化 x = (x - u) / d
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
x_train_scaled = scaler.fit_transform(x_train)
x_valid_scaled = scaler.transform(x_valid)
x_test_scaled = scaler.transform(x_test)
# metric使用
metric = keras.metrics.MeanSquaredError()
# metric 会自动将结果累加再求平均
print(metric([5.], [2.])) # tf.Tensor(9.0, shape=(), dtype=float32)
print(metric([0.], [1.])) # 等于5 已经自动将上面的结果加上再平均了
print(metric.result()) # 打印最后的结果
metric.reset_states() # 消除之前的记录
# 这一句结果和上面一样
print(metric([5., 0.], [2., 1.])) # [(5-2)^2+(0-1)^2] / 2
metric.reset_states()
metric([1.], [3.]) # tf.Tensor(4.0, shape=(), dtype=float32)
print(metric.result())
# 建模
# fit函数的作用如下
# 1. batch 遍历训练集 metric
# 1.1 自动求导
# 2. epoch结束 验证集 metric
epochs = 100
batch_size = 32
# 每个epoch训练多少个batch
steps_per_epoch = len(x_train_scaled) // batch_size
optimizer = keras.optimizers.SGD()
metric = keras.metrics.MeanSquaredError()
# 从样本中随机取数据
def random_batch(x, y, batch_size=32):
idx = np.random.randint(0, len(x), size=batch_size)
return x[idx], y[idx]
model = keras.models.Sequential([
keras.layers.Dense(30, activation='relu', input_shape=x_train.shape[1:]),
keras.layers.Dense(1),])
for epoch in range(epochs):
metric.reset_states()
for step in range(steps_per_epoch):
x_batch, y_batch = random_batch(x_train_scaled, y_train,batch_size)
with tf.GradientTape() as tape:
y_pred = model(x_batch)
# y_pred = tf.squeeze(y_pred, 1)
loss = keras.losses.mean_squared_error(y_batch, y_pred)
metric(y_batch, y_pred)
grads = tape.gradient(loss, model.variables)
grads_and_vars = zip(grads, model.variables)
optimizer.apply_gradients(grads_and_vars)
print("\rEpoch", epoch, " train mse:", metric.result().numpy(), end="")
y_valid_pred = model(x_valid_scaled)
# y_valid_pred = tf.squeeze(y_valid_pred, 1)
valid_loss = keras.losses.mean_squared_error(y_valid_pred, y_valid)
print("\t", "valid mse: ", valid_loss.numpy())
作者：WANGBINLONG-
