代码 中的手写字数据是自建的。当然也可以用官方的数据。
BP-手写字识别
#BP手写字识别
import tensorflow as tf
tf.random.set_seed(123)
import matplotlib.pyplot as plt
import os
import PIL
import numpy as np
np.random.seed(123)
from tensorflow import keras
from tensorflow.keras import layers,models
import pathlib
data_dir = r"D:\Python\python_code\tensorflow\data_one"
data_dir = pathlib.Path(data_dir)
image_count = len(list(data_dir.glob('*/*.png')))
print("图片总数",image_count)
batch_size = 32
img_height = 28
img_width = 28
train_datsets = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
color_mode='grayscale',
validation_split=0.2,
subset='training',
seed=123,
image_size=(img_height,img_width),
batch_size=batch_size)
val_datasets = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
color_mode='grayscale',
validation_split=0.2,
subset='validation',
seed=123,
image_size=(img_height,img_width),
batch_size=batch_size)
class_names = train_datsets.class_names
print(class_names)
print(len(class_names))
AUTOTUNE = tf.data.experimental.AUTOTUNE
train_datsets = train_datsets.cache().shuffle(500).prefetch(buffer_size=AUTOTUNE)
val_datasets =val_datasets.cache().prefetch(buffer_size=AUTOTUNE)
model1 = models.Sequential([
layers.experimental.preprocessing.Rescaling(1./255,input_shape=(img_height,img_width,1)),
layers.Flatten(),
layers.Dense(64,activation='relu'),
layers.Dense(64,activation='relu'),
layers.Dense(10)
])
model1.summary()
model1.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.0001),
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
history = model1.fit(train_datsets,validation_data=val_datasets,epochs=100)
import matplotlib.pyplot as plt
plt.figure(figsize=(20,20))
plt.subplot(1,2,1)
plt.plot(history.history['accuracy'],label='training accuracy')
plt.plot(history.history['val_accuracy'],label='val accuracy')
plt.legend(loc='upper right')
plt.title('Training and Validation Accuracy')
plt.subplot(1,2,2)
plt.plot(history.history['loss'],label=' training loss')
plt.plot(history.history['val_loss'],label='val loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()
model1.get_weights() #导入各层权重以及偏置值 很重要!!!
#保存模型
model1.save(model/model1.h5)
#加载模型
model = tf.keras.models.load_model('model/model1.h5')
#预测
自己写吧,很简单滴
结果: