使用tensorflow中的keras(自定义model)
使用tensorflow中的keras(自定义model)
import tensorflow as tf
from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics
from tensorflow import keras
def preprocess(x, y):
"""
x is a simple image, not a batch
"""
x = tf.cast(x, dtype=tf.float32) / 255.
x = tf.reshape(x, [28 * 28])
y = tf.cast(y, dtype=tf.int32)
y = tf.one_hot(y, depth=10)
return x, y
batchsz = 128
(x, y), (x_val, y_val) = datasets.mnist.load_data()
print('datasets:', x.shape, y.shape, x.min(), x.max())
#输出datasets: (60000, 28, 28) (60000,) 0 255
db = tf.data.Dataset.from_tensor_slices((x, y))
#它的作用是切分传入Tensor的第一个维度，生成相应的dataset。
db = db.map(preprocess).shuffle(60000).batch(batchsz)
ds_val = tf.data.Dataset.from_tensor_slices((x_val, y_val))
ds_val = ds_val.map(preprocess).batch(batchsz)
sample = next(iter(db))
print(sample[0].shape, sample[1].shape)
#输出(128, 784) (128, 10)
# 通过Sequential容器方便的封装成一个网络模型
network = Sequential([layers.Dense(256, activation='relu'),
layers.Dense(128, activation='relu'),
layers.Dense(64, activation='relu'),
layers.Dense(32, activation='relu'),
layers.Dense(10)])
network.build(input_shape=(None, 28 * 28))
network.summary()
# 输出Model: "sequential"
# _________________________________________________________________
# Layer (type) Output Shape Param #
# =================================================================
# dense (Dense) multiple 200960
# _________________________________________________________________
# dense_1 (Dense) multiple 32896
# _________________________________________________________________
# dense_2 (Dense) multiple 8256
# _________________________________________________________________
# dense_3 (Dense) multiple 2080
# _________________________________________________________________
# dense_4 (Dense) multiple 330
# =================================================================
# Total params: 244,522
# Trainable params: 244,522
# Non-trainable params: 0
class MyDense(layers.Layer):#创建类并且继承自layers
def __init__(self, inp_dim, outp_dim):
super(MyDense, self).__init__()
#创建张量W和b
self.kernel = self.add_weight('w', [inp_dim, outp_dim])
self.bias = self.add_weight('b', [outp_dim])
#进入training=None测试模型
def call(self, inputs, training=None):
out = inputs @ self.kernel + self.bias
return
out
#自定义网络创建类，并且继承自Model基类
class MyModel(keras.Model):
def __init__(self):
super(MyModel, self).__init__()
self.fc1 = MyDense(28 * 28, 256)
self.fc2 = MyDense(256, 128)
self.fc3 = MyDense(128, 64)
self.fc4 = MyDense(64, 32)
self.fc5 = MyDense(32, 10)
def call(self, inputs, training=None):
x = self.fc1(inputs)
x = tf.nn.relu(x)
x = self.fc2(x)
x = tf.nn.relu(x)
x = self.fc3(x)
x = tf.nn.relu(x)
x = self.fc4(x)
x = tf.nn.relu(x)
x = self.fc5(x)
return x
network = MyModel()
#model.compile()方法用于在配置训练方法时，告知训练时用的优化器、损失函数和准确率评测标准
network.compile(optimizer=optimizers.Adam(lr=0.01),
loss=tf.losses.CategoricalCrossentropy(from_logits=True),
metrics=['accuracy']
)
#通过fit函数进行模型训练：送入训练集、测试集、训练5个epochs，每2个epochs验证一次
network.fit(db, epochs=5, validation_data=ds_val,
validation_freq=2)
network.evaluate(ds_val)
sample = next(iter(ds_val))
x = sample[0]
y = sample[1] # one-hot
pred = network.predict(x) # [b, 10]
# convert back to number
y = tf.argmax(y, axis=1)
pred = tf.argmax(pred, axis=1)
print(pred)
#输出tf.Tensor(
# [7 2 1 0 4 1 4 9 6 9 0 6 9 0 1 5 9 7 3 4 9 6 6 5 4 0 7 4 0 1 3 1 3 4 7 2 7
# 1 2 1 1 7 4 2 3 5 1 2 4 4 6 3 5 5 6 0 4 1 9 5 7 8 9 3 7 4 6 4 3 0 7 0 2 9
# 1 7 3 2 9 7 7 6 2 7 8 4 7 3 6 1 3 6 9 3 1 4 1 7 6 9 6 0 5 4 9 9 2 1 9 4 8
# 7 3 9 7 4 4 4 9 2 5 4 7 6 7 9 0 5], shape=(128,), dtype=int64)
print(y)
# tf.Tensor(
# [7 2 1 0 4 1 4 9 5 9 0 6 9 0 1 5 9 7 3 4 9 6 6 5 4 0 7 4 0 1 3 1 3 4 7 2 7
# 1 2 1 1 7 4 2 3 5 1 2 4 4 6 3 5 5 6 0 4 1 9 5 7 8 9 3 7 4 6 4 3 0 7 0 2 9
# 1 7 3 2 9 7 7 6 2 7 8 4 7 3 6 1 3 6 9 3 1 4 1 7 6 9 6 0 5 4 9 9 2 1 9 4 8
# 7 3 9 7 4 4 4 9 2 5 4 7 6 7 9 0 5], shape=(128,), dtype=int64)
训练效果
