在张量流中获取列车时刻的张量形状

Question

如何获得"实际的"；训练时张量的形状？例如

(None, 64) -> (128, 64)

换句话说，在训练时，我得到了类似(None, 64)的形状，其中None表示张量的第一维度相对于输入大小是动态的，而64是第二维度的示例值。我认为在训练时；实际的"；该张量的大小是框架已知的，所以我想知道如何/是否可以获得张量的实际大小，其中None被评估为train/test/eval数据集大小。因此，我有兴趣得到(128, 64)而不是(None, 64)，其中128是输入的大小。

请考虑以下简化代码示例。

class ALayer(tensorflow.keras.layers.Layer):
def call(self, inputs):
features = tf.matmul(inputs, self.kernel) + self.bias

# These are the different approaches I've tried.
print(features.shape)
# This prints: (None, 64)
print(tf.shape(features)
# This prints: Tensor("ALayer/Shape:0", shape=(2,), dtype=int32)
return features
input_layer = layers.Input(input_dim)
x = ALayer()([input_layer])
x = layers.Dense(1)(x)
model = keras.Model(inputs=[input_layer], outputs=[x])
model.compile()
train_dataset = tf.data.Dataset.from_tensor_slices((X_train, (y_train)))
val_dataset = tf.data.Dataset.from_tensor_slices((X_val, (y_val)))
model.fit(train_dataset, validation_data=val_dataset)

Answer 1

您应该使用tf.print，因为在TF 2.7:中默认情况下会激活热切执行

import tensorflow as tf
class ALayer(tf.keras.layers.Layer):
def __init__(self, units=32):
super(ALayer, self).__init__()
self.units = units
def build(self, input_shape):
self.w = self.add_weight(
shape=(input_shape[-1], self.units),
initializer="random_normal",
trainable=True,
)
self.b = self.add_weight(
shape=(self.units,), initializer="random_normal", trainable=True
)
def call(self, inputs):
features = tf.matmul(inputs, self.w) + self.b

tf.print('Features shape -->', tf.shape(features), 'n')
return features

input_layer = tf.keras.layers.Input(shape=(10,))
x = ALayer(10)(input_layer)
x = tf.keras.layers.Dense(1)(x)
model = tf.keras.Model(inputs=[input_layer], outputs=[x])
model.compile(loss=tf.keras.losses.BinaryCrossentropy())
X_train, y_train = tf.random.normal((64, 10)), tf.random.uniform((64,), maxval=2, dtype=tf.int32)
X_val, y_val = tf.random.normal((64, 10)), tf.random.uniform((64,), maxval=2, dtype=tf.int32)
train_dataset = tf.data.Dataset.from_tensor_slices((X_train, y_train)).batch(32)
val_dataset = tf.data.Dataset.from_tensor_slices((X_val, y_val)).batch(32)
model.fit(train_dataset, validation_data=val_dataset, epochs=1, verbose=0)

Features shape --> [32 10] 
Features shape --> [32 10] 
Features shape --> [32 10] 
Features shape --> [32 10] 
<keras.callbacks.History at 0x7fab3ce15910>