我想使用tf.keras
的方法clone_model
,并更改功能API创建的tensorflow/keras模型的输入形状。因此,我尝试使用参数input_tensor
来更改形状。然而,它似乎没有使用提供的input_tensors
,名称和形状与原始模型保持不变。论点input_tensors
的目的是什么?
代码:
import tensorflow as tf
from tensorflow.keras import layers
inputs_small = layers.Input((64, 64, 3), name="small")
outputs = layers.Conv2D(32, 1)(inputs_small)
model_small = tf.keras.models.Model(inputs=inputs_small, outputs=outputs)
inputs_large = layers.Input((128, 128, 3), name="large")
model_large = tf.keras.models.clone_model(model_small, input_tensors=inputs_large)
model_large.summary()
结果在:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
small (InputLayer) [(None, 64, 64, 3)] 0
_________________________________________________________________
conv2d (Conv2D) (None, 64, 64, 32) 128
=================================================================
但我喜欢
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
large (InputLayer) [(None, 128, 128, 3)] 0
_________________________________________________________________
conv2d (Conv2D) (None, 128, 128, 32) 128
=================================================================
我使用TensorFlow 2.4.1。我简化了我的问题。在我的代码中,我还使用clone_model
的参数clone_function
来替换层。
我进行了进一步调查,发现了一个Keras错误:https://github.com/keras-team/keras/issues/14937