update_state() 和 call() 方法多久被调用一次，tf.keras 中参数的维度是多少？
how often are update_state() and call() method called and what are the dimension of the parameters in tf.keras?
我想知道
(1) tf.keras.losses.Loss的call()方法多久调用一次
tf.keras.metrics.Metric 的 update_state() 方法在训练期间被调用：
- 是否每个实例都调用它们（观察）？
- 或每批调用一次？
(2) y_true 和 y_pred 的维度传递给那些方法：
- 是它们的尺寸 (batch_size x output_dimension)
- 或 (1 x output_dimension)
以下代码片段来自
https://www.tensorflow.org/guide/keras/train_and_evaluate
为了实验，我在 update_state() 中插入了 print(y_true.shape, y_pred.shape) ，我发现它在第一个时期只打印了一次。从印刷品来看，y_true 和 y_pred 的尺寸似乎是
(1 x output_dimension) 在此特定示例中，但情况总是如此吗？
所以，另外
(3)我想知道为什么它只打印一次并且只在第一个epoch中打印。
(4) 我无法打印 y_true 或 y_pred 的值。我怎么可以？
Epoch 1/3
(None, 1) (None, 10)
(None, 1) (None, 10)
782/782 [==============================] - 3s 4ms/step - loss: 0.5666 - categorical_true_positives: 22080.8940
Epoch 2/3
782/782 [==============================] - 3s 4ms/step - loss: 0.1680 - categorical_true_positives: 23877.1162
Epoch 3/3
782/782 [==============================] - 3s 4ms/step - loss: 0.1190 - categorical_true_positives: 24198.2733
<tensorflow.python.keras.callbacks.History at 0x1fb132cde80>
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
# Preprocess the data (these are NumPy arrays)
x_train = x_train.reshape(60000, 784).astype("float32") / 255
x_test = x_test.reshape(10000, 784).astype("float32") / 255
y_train = y_train.astype("float32")
y_test = y_test.astype("float32")
# Reserve 10,000 samples for validation
x_val = x_train[-10000:]
y_val = y_train[-10000:]
x_train = x_train[:-10000]
y_train = y_train[:-10000]
inputs = keras.Input(shape=(784,), name="digits")
x = layers.Dense(64, activation="relu", name="dense_1")(inputs)
x = layers.Dense(64, activation="relu", name="dense_2")(x)
outputs = layers.Dense(10, activation="softmax", name="predictions")(x)
model = keras.Model(inputs=inputs, outputs=outputs)
class CategoricalTruePositives(keras.metrics.Metric):
def __init__(self, name="categorical_true_positives", **kwargs):
super(CategoricalTruePositives, self).__init__(name=name, **kwargs)
self.true_positives = self.add_weight(name="ctp", initializer="zeros")
def update_state(self, y_true, y_pred, sample_weight=None):
print(y_true.shape, y_pred.shape) # For experiment
y_pred = tf.reshape(tf.argmax(y_pred, axis=1), shape=(-1, 1))
values = tf.cast(y_true, "int32") == tf.cast(y_pred, "int32")
values = tf.cast(values, "float32")
if sample_weight is not None:
sample_weight = tf.cast(sample_weight, "float32")
values = tf.multiply(values, sample_weight)
self.true_positives.assign_add(tf.reduce_sum(values))
def result(self):
return self.true_positives
def reset_states(self):
# The state of the metric will be reset at the start of each epoch.
self.true_positives.assign(0.0)
model.compile(
optimizer=keras.optimizers.RMSprop(learning_rate=1e-3),
loss=keras.losses.SparseCategoricalCrossentropy(),
metrics=[CategoricalTruePositives()],
)
model.fit(x_train, y_train, batch_size=64, epochs=3)
(1) how often the call() method of tf.keras.losses.Loss and the update_state() method of tf.keras.metrics.Metric gets called during a training:
tf.keras.losses.Loss和update_state()的调用方法在每批结束时使用。
(2) the dimension of y_true and y_pred passed to those methods:
y_true 的尺寸与您在 y_train 中传递的尺寸相同。唯一的变化是，y_train 的第一个维度将是 no_of 个样本 ，而在 y_true 的情况下，它将是 batch_size。在您的情况下，它是 (64, 1)，其中 64 是 batch_size.
y_pred的维度是模型输出的形状。在你的情况下它是 (64, 10) 因为你在最后一层有 10 个密集单元。
(3) I would like to know why it is printed only once and only in the first epoch.
由于tensorflow是以图方式执行的，所以print语句只执行了一次。打印仅适用于急切模式。如果你想在 eager 模式下执行 tensorflow 代码，请在 model.compile 步骤中添加 run_eagerly = True。
(4) I can't print the value of y_true or y_pred. How can I?
运行 急切模式下的代码。
代码：
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
# Preprocess the data (these are NumPy arrays)
x_train = x_train.reshape(60000, 784).astype("float32") / 255
x_test = x_test.reshape(10000, 784).astype("float32") / 255
y_train = y_train.astype("float32")
y_test = y_test.astype("float32")
# Reserve 10,000 samples for validation
x_val = x_train[-10000:]
y_val = y_train[-10000:]
x_train = x_train[:-10000]
y_train = y_train[:-10000]
inputs = keras.Input(shape=(784,), name="digits")
x = layers.Dense(64, activation="relu", name="dense_1")(inputs)
x = layers.Dense(64, activation="relu", name="dense_2")(x)
outputs = layers.Dense(10, activation="softmax", name="predictions")(x)
model = keras.Model(inputs=inputs, outputs=outputs)
class CategoricalTruePositives(keras.metrics.Metric):
def __init__(self, name="categorical_true_positives", **kwargs):
super(CategoricalTruePositives, self).__init__(name=name, **kwargs)
self.true_positives = self.add_weight(name="ctp", initializer="zeros")
def update_state(self, y_true, y_pred, sample_weight=None):
print('update_state', y_true.shape, y_pred.shape) # For experiment
y_pred = tf.reshape(tf.argmax(y_pred, axis=1), shape=(-1, 1))
values = tf.cast(y_true, "int32") == tf.cast(y_pred, "int32")
values = tf.cast(values, "float32")
if sample_weight is not None:
sample_weight = tf.cast(sample_weight, "float32")
values = tf.multiply(values, sample_weight)
self.true_positives.assign_add(tf.reduce_sum(values))
def result(self):
return self.true_positives
def reset_states(self):
# The state of the metric will be reset at the start of each epoch.
self.true_positives.assign(0.0)
class CustomCallback(tf.keras.callbacks.Callback):
def on_epoch_begin(self, epoch, logs=None):
print("Start epoch {} of training".format(epoch))
def on_train_batch_begin(self, batch, logs=None):
keys = list(logs.keys())
print("...Training: start of batch {}".format(batch))
def on_train_batch_end(self, batch, logs=None):
print("...Training: end of batch {}".format(batch))
model.compile(
optimizer=keras.optimizers.RMSprop(learning_rate=1e-3),
loss=keras.losses.SparseCategoricalCrossentropy(),
metrics=[CategoricalTruePositives()],
run_eagerly = True,
)
model.fit(x_train, y_train, batch_size=64, epochs=3, verbose = 0, callbacks=[CustomCallback()])
输出：
Start epoch 0 of training
...Training: start of batch 0
update_state (64, 1) (64, 10)
...Training: end of batch 0
...Training: start of batch 1
update_state (64, 1) (64, 10)
...Training: end of batch 1
...Training: start of batch 2
update_state (64, 1) (64, 10)
...Training: end of batch 2
...Training: start of batch 3
update_state (64, 1) (64, 10)
...Training: end of batch 3
...Training: start of batch 4
update_state (64, 1) (64, 10)
...Training: end of batch 4
...Training: start of batch 5
update_state (64, 1) (64, 10)
...Training: end of batch 5
上面的例子会让你一目了然。
我想知道
(1) tf.keras.losses.Loss的call()方法多久调用一次 tf.keras.metrics.Metric 的 update_state() 方法在训练期间被调用：
- 是否每个实例都调用它们（观察）？
- 或每批调用一次？
(2) y_true 和 y_pred 的维度传递给那些方法：
- 是它们的尺寸 (batch_size x output_dimension)
- 或 (1 x output_dimension)
以下代码片段来自 https://www.tensorflow.org/guide/keras/train_and_evaluate
为了实验，我在 update_state() 中插入了 print(y_true.shape, y_pred.shape) ，我发现它在第一个时期只打印了一次。从印刷品来看，y_true 和 y_pred 的尺寸似乎是 (1 x output_dimension) 在此特定示例中，但情况总是如此吗？
所以，另外
(3)我想知道为什么它只打印一次并且只在第一个epoch中打印。
(4) 我无法打印 y_true 或 y_pred 的值。我怎么可以？
Epoch 1/3
(None, 1) (None, 10)
(None, 1) (None, 10)
782/782 [==============================] - 3s 4ms/step - loss: 0.5666 - categorical_true_positives: 22080.8940
Epoch 2/3
782/782 [==============================] - 3s 4ms/step - loss: 0.1680 - categorical_true_positives: 23877.1162
Epoch 3/3
782/782 [==============================] - 3s 4ms/step - loss: 0.1190 - categorical_true_positives: 24198.2733
<tensorflow.python.keras.callbacks.History at 0x1fb132cde80>
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
# Preprocess the data (these are NumPy arrays)
x_train = x_train.reshape(60000, 784).astype("float32") / 255
x_test = x_test.reshape(10000, 784).astype("float32") / 255
y_train = y_train.astype("float32")
y_test = y_test.astype("float32")
# Reserve 10,000 samples for validation
x_val = x_train[-10000:]
y_val = y_train[-10000:]
x_train = x_train[:-10000]
y_train = y_train[:-10000]
inputs = keras.Input(shape=(784,), name="digits")
x = layers.Dense(64, activation="relu", name="dense_1")(inputs)
x = layers.Dense(64, activation="relu", name="dense_2")(x)
outputs = layers.Dense(10, activation="softmax", name="predictions")(x)
model = keras.Model(inputs=inputs, outputs=outputs)
class CategoricalTruePositives(keras.metrics.Metric):
def __init__(self, name="categorical_true_positives", **kwargs):
super(CategoricalTruePositives, self).__init__(name=name, **kwargs)
self.true_positives = self.add_weight(name="ctp", initializer="zeros")
def update_state(self, y_true, y_pred, sample_weight=None):
print(y_true.shape, y_pred.shape) # For experiment
y_pred = tf.reshape(tf.argmax(y_pred, axis=1), shape=(-1, 1))
values = tf.cast(y_true, "int32") == tf.cast(y_pred, "int32")
values = tf.cast(values, "float32")
if sample_weight is not None:
sample_weight = tf.cast(sample_weight, "float32")
values = tf.multiply(values, sample_weight)
self.true_positives.assign_add(tf.reduce_sum(values))
def result(self):
return self.true_positives
def reset_states(self):
# The state of the metric will be reset at the start of each epoch.
self.true_positives.assign(0.0)
model.compile(
optimizer=keras.optimizers.RMSprop(learning_rate=1e-3),
loss=keras.losses.SparseCategoricalCrossentropy(),
metrics=[CategoricalTruePositives()],
)
model.fit(x_train, y_train, batch_size=64, epochs=3)
(1) how often the call() method of tf.keras.losses.Loss and the update_state() method of tf.keras.metrics.Metric gets called during a training:
tf.keras.losses.Loss和update_state()的调用方法在每批结束时使用。
(2) the dimension of y_true and y_pred passed to those methods:
y_true 的尺寸与您在 y_train 中传递的尺寸相同。唯一的变化是，y_train 的第一个维度将是 no_of 个样本 ，而在 y_true 的情况下，它将是 batch_size。在您的情况下，它是 (64, 1)，其中 64 是 batch_size.
y_pred的维度是模型输出的形状。在你的情况下它是 (64, 10) 因为你在最后一层有 10 个密集单元。
(3) I would like to know why it is printed only once and only in the first epoch.
由于tensorflow是以图方式执行的，所以print语句只执行了一次。打印仅适用于急切模式。如果你想在 eager 模式下执行 tensorflow 代码，请在 model.compile 步骤中添加 run_eagerly = True。
(4) I can't print the value of y_true or y_pred. How can I?
运行 急切模式下的代码。
代码：
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
# Preprocess the data (these are NumPy arrays)
x_train = x_train.reshape(60000, 784).astype("float32") / 255
x_test = x_test.reshape(10000, 784).astype("float32") / 255
y_train = y_train.astype("float32")
y_test = y_test.astype("float32")
# Reserve 10,000 samples for validation
x_val = x_train[-10000:]
y_val = y_train[-10000:]
x_train = x_train[:-10000]
y_train = y_train[:-10000]
inputs = keras.Input(shape=(784,), name="digits")
x = layers.Dense(64, activation="relu", name="dense_1")(inputs)
x = layers.Dense(64, activation="relu", name="dense_2")(x)
outputs = layers.Dense(10, activation="softmax", name="predictions")(x)
model = keras.Model(inputs=inputs, outputs=outputs)
class CategoricalTruePositives(keras.metrics.Metric):
def __init__(self, name="categorical_true_positives", **kwargs):
super(CategoricalTruePositives, self).__init__(name=name, **kwargs)
self.true_positives = self.add_weight(name="ctp", initializer="zeros")
def update_state(self, y_true, y_pred, sample_weight=None):
print('update_state', y_true.shape, y_pred.shape) # For experiment
y_pred = tf.reshape(tf.argmax(y_pred, axis=1), shape=(-1, 1))
values = tf.cast(y_true, "int32") == tf.cast(y_pred, "int32")
values = tf.cast(values, "float32")
if sample_weight is not None:
sample_weight = tf.cast(sample_weight, "float32")
values = tf.multiply(values, sample_weight)
self.true_positives.assign_add(tf.reduce_sum(values))
def result(self):
return self.true_positives
def reset_states(self):
# The state of the metric will be reset at the start of each epoch.
self.true_positives.assign(0.0)
class CustomCallback(tf.keras.callbacks.Callback):
def on_epoch_begin(self, epoch, logs=None):
print("Start epoch {} of training".format(epoch))
def on_train_batch_begin(self, batch, logs=None):
keys = list(logs.keys())
print("...Training: start of batch {}".format(batch))
def on_train_batch_end(self, batch, logs=None):
print("...Training: end of batch {}".format(batch))
model.compile(
optimizer=keras.optimizers.RMSprop(learning_rate=1e-3),
loss=keras.losses.SparseCategoricalCrossentropy(),
metrics=[CategoricalTruePositives()],
run_eagerly = True,
)
model.fit(x_train, y_train, batch_size=64, epochs=3, verbose = 0, callbacks=[CustomCallback()])
输出：
Start epoch 0 of training
...Training: start of batch 0
update_state (64, 1) (64, 10)
...Training: end of batch 0
...Training: start of batch 1
update_state (64, 1) (64, 10)
...Training: end of batch 1
...Training: start of batch 2
update_state (64, 1) (64, 10)
...Training: end of batch 2
...Training: start of batch 3
update_state (64, 1) (64, 10)
...Training: end of batch 3
...Training: start of batch 4
update_state (64, 1) (64, 10)
...Training: end of batch 4
...Training: start of batch 5
update_state (64, 1) (64, 10)
...Training: end of batch 5
上面的例子会让你一目了然。