在 Tensorflow 中训练时获取 Tensor 形状

Question

如何在训练时获得张量的“实际”形状？例如，

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

换句话说，在训练时，我得到类似 (None, 64) 的形状，其中 None 表示张量的第一维是动态的 w.r.t 输入大小，并且 64 是第二个维度的示例值。我假设在训练时，框架知道该张量的“实际”大小，所以我想知道 how/if 我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，我有兴趣获得 (128, 64) 而不是 (None, 64)，其中 128 是输入的大小。

请考虑以下简化的代码示例。

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 中默认激活急切执行:

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>

在 Tensorflow 中训练时获取 Tensor 形状

Get Tensor shape at train time in Tensorflow

python

machine-learning

deep-learning

keras

tensorflow