import tensorflow as tf
import numpy as np
class MNISTLoader():
def __init__(self):
mnist = tf.keras.datasets.mnist
(self.train_data, self.train_label), (self.test_data, self.test_label) = mnist.load_data()
# MNIST中的图像默认为uint8（0-255的数字）。以下代码将其归一化到0-1之间的浮点数，并在最后增加一维作为颜色通道
self.train_data = np.expand_dims(self.train_data.astype(np.float32) / 255.0, axis=-1) # [60000, 28, 28, 1]
self.test_data = np.expand_dims(self.test_data.astype(np.float32) / 255.0, axis=-1) # [10000, 28, 28, 1]
self.train_label = self.train_label.astype(np.int32) # [60000]
self.test_label = self.test_label.astype(np.int32) # [10000]
self.num_train_data, self.num_test_data = self.train_data.shape[0], self.test_data.shape[0]
def get_batch(self, batch_size):
# 从数据集中随机取出batch_size个元素并返回
index = np.random.randint(0, self.num_train_data, batch_size)
return self.train_data[index, :], self.train_label[index]
class MLP(tf.keras.Model):
def __init__(self):
super().__init__()
self.flatten = tf.keras.layers.Flatten() # Flatten层将除第一维（batch_size）以外的维度展平
self.dense1 = tf.keras.layers.Dense(units=100, activation=tf.nn.relu)
self.dense2 = tf.keras.layers.Dense(units=10)
@tf.function
def call(self, inputs): # [batch_size, 28, 28, 1]
x = self.flatten(inputs) # [batch_size, 784]
x = self.dense1(x) # [batch_size, 100]
x = self.dense2(x) # [batch_size, 10]
output = tf.nn.softmax(x)
return output
num_epochs = 1
batch_size = 50
learning_rate = 0.001
log_dir = 'tensorboard'
# 训练
model = MLP()
data_loader = MNISTLoader()
optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)
# 准备好writer
summary_writer = tf.summary.create_file_writer(log_dir) # 参数为记录文件所保存的目录
# 追踪
tf.summary.trace_on(graph=True, profiler=True)
# 训练
num_batches = int(data_loader.num_train_data // batch_size * num_epochs)
for batch_index in range(num_batches):
X, y = data_loader.get_batch(batch_size)
with tf.GradientTape() as tape:
y_pred = model(X)
loss = tf.keras.losses.sparse_categorical_crossentropy(y_true=y, y_pred=y_pred)
loss = tf.reduce_mean(loss)
print("batch %d: loss %f" % (batch_index, loss.numpy()))
# 记录器记录loss
with summary_writer.as_default():
tf.summary.scalar('loss', loss, step=batch_index)
grads = tape.gradient(loss, model.variables)
optimizer.apply_gradients(grads_and_vars=zip(grads, model.variables))
# 显示追踪
with summary_writer.as_default():
tf.summary.trace_export('model_trace', step=0, profiler_outdir=log_dir)
这是我的代码，麻烦老师帮我看看