一小时学会TensorFlow2之Fashion Mnist

描述

Fashion Mnist 是一个类似于 Mnist 的图像数据集. 涵盖 10 种类别的 7 万 (6 万训练集 + 1 万测试集) 个不同商品的图片.

Tensorboard

Tensorboard 是 tensorflow 的一个可视化工具.

创建 summary

我们可以通过tf.summary.create_file_writer(file_path)来创建一个新的 summary 实例.

例子:

# 将当前时间作为子文件名current_time = datetime.datetime.now().strftime(\"%Y%m%d-%H%M%S\")# 监听的文件的路径log_dir = \'logs/\' + current_time# 创建writersummary_writer = tf.summary.create_file_writer(log_dir)

存入数据

通过tf.summary.scalar我们可以向 summary 对象存入数据.

格式:

tf.summary.scalar(name, data, step=None, description=None)

例子:

with summary_writer.as_default():tf.summary.scalar(\"train-loss\", float(Cross_Entropy), step=step)

metrics

metrics.Mean()

metrics.Mean()可以帮助我们计算平均数.

格式:

tf.keras.metrics.Mean(name=\'mean\', dtype=None)

例子:

# 准确率表loss_meter = tf.keras.metrics.Mean()

metrics.Accuracy()

格式:

tf.keras.metrics.Accuracy(name=\'accuracy\', dtype=None)

例子:

# 损失表acc_meter = tf.keras.metrics.Accuracy()

变量更新 &重置

我们可以通过update_state来实现变量更新, 通过rest_state来实现变量重置.

例如:

# 跟新损失loss_meter.update_state(Cross_Entropy)# 重置loss_meter.reset_state()

案例

pre_process 函数

def pre_process(x, y):\"\"\"数据预处理:param x: 特征值:param y: 目标值:return: 返回处理好的x, y\"\"\"# 转换xx = tf.cast(x, tf.float32) / 255x = tf.reshape(x, [-1, 784])# 转换yy = tf.cast(y, dtype=tf.int32)y = tf.one_hot(y, depth=10)return x, y

get_data 函数

def get_data():\"\"\"获取数据:return: 返回分批完的训练集和测试集\"\"\"# 获取数据(X_train, y_train), (X_test, y_test) = tf.keras.datasets.fashion_mnist.load_data()# 分割训练集train_db = tf.data.Dataset.from_tensor_slices((X_train, y_train)).shuffle(60000, seed=0)train_db = train_db.batch(batch_size).map(pre_process)# 分割测试集test_db = tf.data.Dataset.from_tensor_slices((X_test, y_test)).shuffle(10000, seed=0)test_db = test_db.batch(batch_size).map(pre_process)# 返回return train_db, test_db

train 函数

def train(epoch, train_db):\"\"\"训练数据:param train_db: 分批的数据集:return: 无返回值\"\"\"for step, (x, y) in enumerate(train_db):with tf.GradientTape() as tape:# 获取模型输出结果logits = model(x)# 计算交叉熵Cross_Entropy = tf.losses.categorical_crossentropy(y, logits, from_logits=True)Cross_Entropy = tf.reduce_sum(Cross_Entropy)# 跟新损失loss_meter.update_state(Cross_Entropy)# 计算梯度grads = tape.gradient(Cross_Entropy, model.trainable_variables)# 跟新参数optimizer.apply_gradients(zip(grads, model.trainable_variables))# 每100批调试输出一下误差if step % 100 == 0:print(\"step:\", step, \"Cross_Entropy:\", loss_meter.result().numpy())# 重置loss_meter.reset_state()# 可视化with summary_writer.as_default():tf.summary.scalar(\"train-loss\", float(Cross_Entropy), step= epoch * 235 + step)

test 函数

def test(epoch, test_db):\"\"\"测试模型:param epoch: 轮数:param test_db: 分批的测试集:return: 无返回值\"\"\"# 重置acc_meter.reset_state()for x, y in test_db:# 获取模型输出结果logits = model(x)# 预测结果pred = tf.argmax(logits, axis=1)# 从one_hot编码变回来y = tf.argmax(y, axis=1)# 计算准确率acc_meter.update_state(y, pred)# 调试输出print(\"epoch:\", epoch + 1, \"Accuracy:\", acc_meter.result().numpy() * 100, \"%\", )# 可视化with summary_writer.as_default():tf.summary.scalar(\"val-acc\", acc_meter.result().numpy(), step=epoch * 235)

main 函数

def main():\"\"\"主函数:return: 无返回值\"\"\"# 获取数据train_db, test_db = get_data()# 轮期for epoch in range(iteration_num):train(epoch, train_db)test(epoch, test_db)

完整代码

import datetimeimport tensorflow as tf# 定义超参数batch_size = 256  # 一次训练的样本数目learning_rate = 0.001  # 学习率iteration_num = 20  # 迭代次数# 优化器optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)# 准确率表loss_meter = tf.keras.metrics.Mean()# 损失表acc_meter = tf.keras.metrics.Accuracy()# 可视化current_time = datetime.datetime.now().strftime(\"%Y%m%d-%H%M%S\")log_dir = \'logs/\' + current_timesummary_writer = tf.summary.create_file_writer(log_dir)  # 创建writer# 模型model = tf.keras.Sequential([tf.keras.layers.Dense(256, activation=tf.nn.relu),tf.keras.layers.Dense(128, activation=tf.nn.relu),tf.keras.layers.Dense(64, activation=tf.nn.relu),tf.keras.layers.Dense(32, activation=tf.nn.relu),tf.keras.layers.Dense(10)])# 调试输出summarymodel.build(input_shape=[None, 28 * 28])print(model.summary())def pre_process(x, y):\"\"\"数据预处理:param x: 特征值:param y: 目标值:return: 返回处理好的x, y\"\"\"# 转换xx = tf.cast(x, tf.float32) / 255x = tf.reshape(x, [-1, 784])# 转换yy = tf.cast(y, dtype=tf.int32)y = tf.one_hot(y, depth=10)return x, ydef get_data():\"\"\"获取数据:return: 返回分批完的训练集和测试集\"\"\"# 获取数据(X_train, y_train), (X_test, y_test) = tf.keras.datasets.fashion_mnist.load_data()# 分割训练集train_db = tf.data.Dataset.from_tensor_slices((X_train, y_train)).shuffle(60000, seed=0)train_db = train_db.batch(batch_size).map(pre_process)# 分割测试集test_db = tf.data.Dataset.from_tensor_slices((X_test, y_test)).shuffle(10000, seed=0)test_db = test_db.batch(batch_size).map(pre_process)# 返回return train_db, test_dbdef train(epoch, train_db):\"\"\"训练数据:param train_db: 分批的数据集:return: 无返回值\"\"\"for step, (x, y) in enumerate(train_db):with tf.GradientTape() as tape:# 获取模型输出结果logits = model(x)# 计算交叉熵Cross_Entropy = tf.losses.categorical_crossentropy(y, logits, from_logits=True)Cross_Entropy = tf.reduce_sum(Cross_Entropy)# 跟新损失loss_meter.update_state(Cross_Entropy)# 计算梯度grads = tape.gradient(Cross_Entropy, model.trainable_variables)# 跟新参数optimizer.apply_gradients(zip(grads, model.trainable_variables))# 每100批调试输出一下误差if step % 100 == 0:print(\"step:\", step, \"Cross_Entropy:\", loss_meter.result().numpy())# 重置loss_meter.reset_state()# 可视化with summary_writer.as_default():tf.summary.scalar(\"train-loss\", float(Cross_Entropy), step=epoch * 235 + step)def test(epoch, test_db):\"\"\"测试模型:param epoch: 轮数:param test_db: 分批的测试集:return: 无返回值\"\"\"# 重置acc_meter.reset_state()for x, y in test_db:# 获取模型输出结果logits = model(x)# 预测结果pred = tf.argmax(logits, axis=1)# 从one_hot编码变回来y = tf.argmax(y, axis=1)# 计算准确率acc_meter.update_state(y, pred)# 调试输出print(\"epoch:\", epoch + 1, \"Accuracy:\", acc_meter.result().numpy() * 100, \"%\", )# 可视化with summary_writer.as_default():tf.summary.scalar(\"val-acc\", acc_meter.result().numpy(), step=epoch * 235)def main():\"\"\"主函数:return: 无返回值\"\"\"# 获取数据train_db, test_db = get_data()# 轮期for epoch in range(iteration_num):train(epoch, train_db)test(epoch, test_db)if __name__ == \"__main__\":main()

输出结果:

Model: \”sequential\”
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense (Dense) (None, 256) 200960
_________________________________________________________________
dense_1 (Dense) (None, 128) 32896
_________________________________________________________________
dense_2 (Dense) (None, 64) 8256
_________________________________________________________________
dense_3 (Dense) (None, 32) 2080
_________________________________________________________________
dense_4 (Dense) (None, 10) 330
=================================================================
Total params: 244,522
Trainable params: 244,522
Non-trainable params: 0
_________________________________________________________________
None
2021-06-14 18:01:27.399812: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:176] None of the MLIR Optimization Passes are enabled (registered 2)
step: 0 Cross_Entropy: 591.5974
step: 100 Cross_Entropy: 196.49309
step: 200 Cross_Entropy: 125.2562
epoch: 1 Accuracy: 84.72999930381775 %
step: 0 Cross_Entropy: 107.64579
step: 100 Cross_Entropy: 105.854385
step: 200 Cross_Entropy: 99.545975
epoch: 2 Accuracy: 85.83999872207642 %
step: 0 Cross_Entropy: 95.42945
step: 100 Cross_Entropy: 91.366234
step: 200 Cross_Entropy: 90.84072
epoch: 3 Accuracy: 86.69999837875366 %
step: 0 Cross_Entropy: 82.03317
step: 100 Cross_Entropy: 83.20552
step: 200 Cross_Entropy: 81.57012
epoch: 4 Accuracy: 86.11000180244446 %
step: 0 Cross_Entropy: 82.94046
step: 100 Cross_Entropy: 77.56677
step: 200 Cross_Entropy: 76.996346
epoch: 5 Accuracy: 87.27999925613403 %
step: 0 Cross_Entropy: 75.59219
step: 100 Cross_Entropy: 71.70899
step: 200 Cross_Entropy: 74.15144
epoch: 6 Accuracy: 87.29000091552734 %
step: 0 Cross_Entropy: 76.65844
step: 100 Cross_Entropy: 70.09151
step: 200 Cross_Entropy: 70.84446
epoch: 7 Accuracy: 88.27999830245972 %
step: 0 Cross_Entropy: 67.50707
step: 100 Cross_Entropy: 64.85907
step: 200 Cross_Entropy: 68.63099
epoch: 8 Accuracy: 88.41999769210815 %
step: 0 Cross_Entropy: 65.50318
step: 100 Cross_Entropy: 62.2706
step: 200 Cross_Entropy: 63.80803
epoch: 9 Accuracy: 86.21000051498413 %
step: 0 Cross_Entropy: 66.95486
step: 100 Cross_Entropy: 61.84385
step: 200 Cross_Entropy: 62.18851
epoch: 10 Accuracy: 88.45999836921692 %
step: 0 Cross_Entropy: 59.779297
step: 100 Cross_Entropy: 58.602314
step: 200 Cross_Entropy: 59.837025
epoch: 11 Accuracy: 88.66000175476074 %
step: 0 Cross_Entropy: 58.10068
step: 100 Cross_Entropy: 55.097878
step: 200 Cross_Entropy: 59.906315
epoch: 12 Accuracy: 88.70999813079834 %
step: 0 Cross_Entropy: 57.584858
step: 100 Cross_Entropy: 54.95376
step: 200 Cross_Entropy: 55.797752
epoch: 13 Accuracy: 88.44000101089478 %
step: 0 Cross_Entropy: 53.54782
step: 100 Cross_Entropy: 53.62939
step: 200 Cross_Entropy: 54.632828
epoch: 14 Accuracy: 87.02999949455261 %
step: 0 Cross_Entropy: 54.387398
step: 100 Cross_Entropy: 52.323734
step: 200 Cross_Entropy: 53.968185
epoch: 15 Accuracy: 88.98000121116638 %
step: 0 Cross_Entropy: 50.468914
step: 100 Cross_Entropy: 50.79311
step: 200 Cross_Entropy: 51.296227
epoch: 16 Accuracy: 88.67999911308289 %
step: 0 Cross_Entropy: 48.753258
step: 100 Cross_Entropy: 46.809692
step: 200 Cross_Entropy: 48.08208
epoch: 17 Accuracy: 89.10999894142151 %
step: 0 Cross_Entropy: 46.830627
step: 100 Cross_Entropy: 47.208813
step: 200 Cross_Entropy: 48.671318
epoch: 18 Accuracy: 88.77999782562256 %
step: 0 Cross_Entropy: 46.15514
step: 100 Cross_Entropy: 45.026627
step: 200 Cross_Entropy: 45.371685
epoch: 19 Accuracy: 88.7399971485138 %
step: 0 Cross_Entropy: 47.696465
step: 100 Cross_Entropy: 41.52749
step: 200 Cross_Entropy: 46.71362
epoch: 20 Accuracy: 89.56000208854675 %

可视化

到此这篇关于一小时学会TensorFlow2之Fashion Mnist的文章就介绍到这了,更多相关TensorFlow2 Fashion Mnist内容请搜索脚本之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持脚本之家！

您可能感兴趣的文章:

深度学习tensorflow基础mnist
由浅入深学习TensorFlow MNIST 数据集

目录

描述