Tensorflow_keras实战（六）：自定义求导（tf.GradientTape）

最新推荐文章于 2025-10-12 12:11:01 发布

原创最新推荐文章于 2025-10-12 12:11:01 发布 · 1.5k 阅读

3 ·

CC 4.0 BY-SA版权

文章标签：

#tensorflow2.0 #tf-keras #gradienttape

深度学习专栏收录该内容

17 篇文章

订阅专栏

本文探讨了TensorFlow中tf.GradientTape与tf.keras的结合使用，实现自定义求导流程，并通过MeanSquaredError指标监测模型训练效果。在加州房价预测任务中，采用SGD优化器和MSE损失函数，展示了从数据预处理到模型训练的全过程。

import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import pandas as pd
import os
import sklearn
import sys
import time
import tensorflow as tf

from tensorflow import keras

print(tf.__version__)
print(sys.version_info)
for module in mpl,np,pd,sklearn,tf,keras:
    print(module.__name__, module.__version__)


from sklearn.datasets import fetch_california_housing

housing = fetch_california_housing()

print(housing.DESCR)
print(housing.data.shape)
print(housing.target.shape)


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_valid.shape, y_valid.shape)
print(x_train.shape, y_train.shape)
print(x_test.shape, y_test.shape)


from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
x_train_scaled = scaler.fit_transform(x_train)
x_valid_scaled = scaler.fit_transform(x_valid)
x_test_scaled = scaler.fit_transform(x_test)


#1. batch 遍历训练集 metric
#    1.1 自动求导
#2. epoch 验证集 metric

epochs = 100
batch_size = 32
steps_per_epoch = len(x_train_scaled) // batch_size
optimizer = keras.optimizers.SGD()
metric = keras.metrics.MeanSquaredError()

def random_batch(x,y,batch_size = 32):
    idx = np.random.ranint(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)
            loss = tf.reduce_mean(
                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)
    valid_loss = tf.reduce_mean(
        keras.losses.mean_squared_error(y_valid_pred,y_valid))
    print("\t","valid mse: ",valid_loss.nump())
    # 效果并不太好