Get Tensor shape at train time in Tensorflow-CodePudding

How do you get the "actual" shape of a tensor at training time? In other words, at training time, I get a shape like (None, 64) where None means the first dimension of the tensor is dynamic w.r.t to the input size, and 64 is an example value for the second dimension. I assume at training time, the "actual" size of that tensor is known to the framework, so I am wondering how/if I can get the actual size of the tensor, where None is evaluated to the train/test/eval dataset size. Hence, I am interested to get (128, 64) instead of (None, 64) where 128 is the size of the input.

Please consider the following simplified code example.

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)

CodePudding user response：

You should use tf.print since eager execution is activated by default in TF 2.7:

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>