Logistic Regression Example

最新推荐文章于 2024-05-12 18:41:45 发布

gz153016

最新推荐文章于 2024-05-12 18:41:45 发布

阅读量468

点赞数

CC 4.0 BY-SA版权

分类专栏： TensorFlow学习笔记

本文链接：https://blog.youkuaiyun.com/gz153016/article/details/91490300

TensorFlow学习笔记专栏收录该内容

29 篇文章

订阅专栏

本文介绍了一个使用Logistic回归模型在MNIST数据集上进行手写数字识别的例子。MNIST数据集包含60,000个训练样本和10,000个测试样本，每个样本是一个28x28像素的手写数字图像。通过将图像转换为一维numpy数组，并应用Softmax函数和交叉熵损失函数，我们实现了模型的训练和评估。实验结果显示，在3000个测试样本上的准确率达到较高水平。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >


"""
Logistic Regression Example

This example is using MNIST handwritten digits.
The dataset contains 60,000 examples for training and 10,000 examples for testing.
The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1.
For simplicity, each image has been flattened and converted to a 1-D numpy array of 784 features (28*28).
"""


import tensorflow as tf

# Import MINST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("./data/", one_hot=True)
print("mnist:", mnist)

# Parameters
learning_rate = 0.01
training_epochs = 100
batch_size = 100
display_step = 1
# tf Graph Input
x = tf.placeholder(tf.float32, [None, 784]) # mnist data image of shape 28 * 28 = 784
y = tf.placeholder(tf.float32, [None, 10])  # 0-9 digits recognition => 10 classes

# Set model weights
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

print("W:", W)
print("b:", b)
# Construct model
pred = tf.nn.softmax(tf.matmul(x, W) + b) # Softmax

print("tf.matmul(x, W) + b:", tf.matmul(x, W) + b)
# tf.matmul(x, W) + b: Tensor("add_1:0", shape=(?, 10), dtype=float32)

# tf.matmul(x, W): Tensor("MatMul_1:0", shape=(?, 10), dtype=float32)

# Minimize error using cross entropy
cost = tf.reduce_mean(-tf.reduce_sum(y * tf.log(pred), reduction_indices=1))
# Gradient Descent
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

# Initialize the variables(i,e assign their default value)
init = tf.global_variables_initializer()

# Start training
with tf.Session() as sess:
    sess.run(init)

    # Training cycle
    for epoch in range(training_epochs):
        avg_cost = 0.
        total_batch = int(mnist.train.num_examples/batch_size)
        # Loop over all batches
        for i in range(total_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            # Fit training using batch data
            _, c = sess.run([optimizer, cost], feed_dict={x: batch_xs,
                                                          y: batch_ys})
            # Compute average loss
            avg_cost += c / total_batch
        # Display logs per epoch step
        if (epoch+1) % display_step == 0:
            print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost))

    print("Optimization Finished!")

    # Test model
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
    # Calculate accuracy for 3000 examples
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    print ("Accuracy:", accuracy.eval({x: mnist.test.images[:3000], y: mnist.test.labels[:3000]}))





if __name__ == "__main__":
    pass