自定义数据集类

class CustomDataset(tf.data.Dataset):

def init(self, x_data, y_data):

self.x_data = tf.convert_to_tensor(x_data, dtype=tf.float32)

self.y_data = tf.convert_to_tensor(y_data, dtype=tf.float32)

def iter(self):

for i in range(len(self.x_data)):

yield (self.x_data $i$ , self.y_data $i$ )

逻辑回归模型

class LogisticRegressionModel(tf.keras.Model):

def init(self, input_dim):

super(LogisticRegressionModel, self).init()

self.linear = tf.keras.layers.Dense(1, input_shape=(input_dim,), activation='sigmoid')

def call(self, x):

return self.linear(x)

创建数据集

x_data = np.array( $\[1$ , $2$ , $3$ , $4$ , $5$ ], dtype=np.float32)

y_data = np.array( $\[0$ , $0$ , $1$ , $1$ , $1$ ], dtype=np.float32)

dataset = CustomDataset(x_data, y_data)

创建数据加载器

dataloader = dataset.batch(2).shuffle(100).repeat()

创建模型、损失函数和优化器

model = LogisticRegressionModel(input_dim=1)

loss_object = tf.keras.losses.BinaryCrossentropy()

optimizer = tf.keras.optimizers.SGD(learning_rate=0.01)

训练模型

epochs = 100

for epoch in range(epochs):

for x_batch, y_batch in dataloader:

with tf.GradientTape() as tape:

predictions = model(x_batch)

loss = loss_object(y_batch, predictions)

gradients = tape.gradient(loss, model.trainable_variables)

optimizer.apply_gradients(zip(gradients, model.trainable_variables))

if (epoch+1) % 10 == 0:

print(f'Epoch ${epoch+1}/{epochs}$ , Loss: {loss.numpy():.4f}')

保存模型

model.save('logistic_regression_model.h5')

加载模型

model = tf.keras.models.load_model('logistic_regression_model.h5')

进行预测

x_test = np.array( $\[6$ , $7$ , $8$ ], dtype=np.float32)

y_pred = model.predict(x_test)

print('预测值:', y_pred)

七。自定义数据集 使用tensorflow框架实现逻辑回归并保存模型，然后保存模型后再加载模型进行预测