用python写基于人工神经网络的数字识别
时间: 2024-11-25 17:33:35 浏览: 23
在Python中,你可以使用深度学习库如TensorFlow或Keras来创建一个人工神经网络(ANN),用于数字识别任务,比如MNIST手写数字识别项目是一个常见的入门示例。以下是简单的步骤:
1. **导入必要的库**:
```python
import tensorflow as tf
from tensorflow.keras import layers
```
2. **数据预处理**:
使用`tf.keras.datasets.mnist`加载MNIST数据集,并对图像进行归一化:
```python
(train_images, train_labels), (test_images, test_labels) = tf.keras.datasets.mnist.load_data()
train_images, test_images = train_images / 255.0, test_images / 255.0
```
3. **构建模型**:
创建一个基本的卷积神经网络(CNN)结构,包括输入层、几个卷积层+池化层、全连接层和输出层:
```python
model = tf.keras.Sequential([
layers.Flatten(input_shape=(28, 28)),
layers.Dense(128, activation='relu'),
layers.Dropout(0.2),
layers.Dense(10)
])
```
4. **编译模型**:
设置损失函数(如交叉熵)、优化器(如Adam)和评估指标(准确率):
```python
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
```
5. **训练模型**:
```python
model.fit(train_images, train_labels, epochs=10, validation_split=0.1)
```
6. **评估和预测**:
测试模型在测试集上的性能:
```python
test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2)
print('\nTest accuracy:', test_acc)
```
7. **预测新图片**:
对新的图像进行分类:
```python
predictions = model.predict(test_images)
predicted_classes = tf.argmax(predictions, axis=1)
```
阅读全文
相关推荐


















