文章目录
Metrics
Metrics测量表,可以对一个epoch的loss或者acc求平均值
新建meter
acc_meter = metrics.Accuracy()
loss_meter = metrics.Mean()
添加数据
loss_meter.update_state(loss)
acc_meter.update(y, pred) # 自动计算acc
获取平均数据
print(epoch, "loss", loss_meter.result().numpy())
....
print(epoch, step, "Evaluate Acc", acc.meter.result().numpy())
获取数据后进行下一次添加数据时, 一般需要清除数据
loss_meter.reset_states()
....
acc_meter.reset_states()
完整代码
import tensorflow as tf
from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics
def preprocess(x, y):
x = tf.cast(x, dtype=tf.float32) / 255.
y = tf.cast(y, dtype=tf.int32)
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())
db = tf.data.Dataset.from_tensor_slices((x,y))
db = db.map(preprocess).shuffle(60000).batch(batchsz).repeat(10)
ds_val = tf.data.Dataset.from_tensor_slices((x_val, y_val))
ds_val = ds_val.map(preprocess).batch(batchsz)
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()
optimizer = optimizers.Adam(lr=0.01)
acc_meter = metrics.Accuracy()
loss_meter = metrics.Mean()
for step, (x,y) in enumerate(db):
with tf.GradientTape() as tape:
# [b, 28, 28] => [b, 784]
x = tf.reshape(x, (-1, 28*28))
# [b, 784] => [b, 10]
out = network(x)
# [b] => [b, 10]
y_onehot = tf.one_hot(y, depth=10)
# [b]
loss = tf.reduce_mean(tf.losses.categorical_crossentropy(y_onehot, out, from_logits=True))
loss_meter.update_state(loss)
grads = tape.gradient(loss, network.trainable_variables)
optimizer.apply_gradients(zip(grads, network.trainable_variables))
if step % 100 == 0:
print(step, 'loss:', loss_meter.result().numpy())
loss_meter.reset_states()
# evaluate
if step % 500 == 0:
total, total_correct = 0., 0
acc_meter.reset_states()
for step, (x, y) in enumerate(ds_val):
# [b, 28, 28] => [b, 784]
x = tf.reshape(x, (-1, 28*28))
# [b, 784] => [b, 10]
out = network(x)
# [b, 10] => [b]
pred = tf.argmax(out, axis=1)
pred = tf.cast(pred, dtype=tf.int32)
# bool type
correct = tf.equal(pred, y)
# bool tensor => int tensor => numpy
total_correct += tf.reduce_sum(tf.cast(correct, dtype=tf.int32)).numpy()
total += x.shape[0]
acc_meter.update_state(y, pred)
print(step, 'Evaluate Acc:', total_correct/total, acc_meter.result().numpy())
Compile&Fit
compile
# (优化器, loss函数, metrics)
network.compile(optimizer=optimizers.Adam(lr=0.01),
loss=tf.losses.CategoricalCrossentropy(from_logits=True),
metrics=['accuracy']
)
fit
# (db_train, epochs, db_test, validation_freq(多少个epoch验证一次测试集))
network.fit(db, epochs=5, validation_data=ds_val, validation_freq=2)
evaluate
network.evaluate(ds_val)
完整代码
import tensorflow as tf
from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics
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())
db = tf.data.Dataset.from_tensor_slices((x,y))
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)
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()
# (优化器, loss函数, metrics)
network.compile(optimizer=optimizers.Adam(lr=0.01),
loss=tf.losses.CategoricalCrossentropy(from_logits=True),
metrics=['accuracy']
)
# (db_train, epochs, db_test, validation_freq(多少个epoch验证一次测试集))
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)
print(y)
自定义层或网络
自定义层
class MyDense(layers.Layer):
# (self, 输入节点数, 输出节点数)
def __init__(self, inp_dim, outp_dim):
# 必须调用父类的构造方法
super(MyDense, self).__init__()
# 指定并创建w和b参数,Variable类型
self.kernel = self.add_variable('w', [inp_dim, outp_dim])
self.bias = self.add_variable('b', [outp_dim])
# 接口由__call__()自动调用
def call(self, inputs, training=None):
# 当调用MyDense的实例对象时,进行运算
# out = x @ w + b
out = inputs @ self.kernel + self.bias
return out
自定义网络
class MyModel(keras.Model):
def __init__(self):
# 必须调用父类的构造方法
super(MyModel, self).__init__()
# 指定网络的每一层
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):
# 进行运算
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
完整代码
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())
db = tf.data.Dataset.from_tensor_slices((x,y))
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)
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()
class MyDense(layers.Layer):
def __init__(self, inp_dim, outp_dim):
super(MyDense, self).__init__()
self.kernel = self.add_variable('w', [inp_dim, outp_dim])
self.bias = self.add_variable('b', [outp_dim])
def call(self, inputs, training=None):
out = inputs @ self.kernel + self.bias
return out
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()
network.compile(optimizer=optimizers.Adam(lr=0.01),
loss=tf.losses.CategoricalCrossentropy(from_logits=True),
metrics=['accuracy']
)
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)
print(y)
