Home Exception encountered when calling layer and 'KerasTensor' object is not callable

Questions

Exception encountered when calling layer and 'KerasTensor' object is not callable

August 22, 2023

I’m newbie to reinforcement learning.
I’d like to see and understand the code that predicts Kerath’s actor critic value, and then run it with some changes.

Example code: https://github.com/keras-team/keras-io/blob/master/examples/rl/actor_critic_cartpole.py

However, I ran into a problem when running it.

Below is the total error.

예외가 발생했습니다. TypeError
Exception encountered when calling layer "custom_model" "f"(type CustomModel).
'KerasTensor' object is not callable
Call arguments received by layer "custom_model""f"(type CustomModel):
  • inputs=tf.Tensor(shape=(1, 10, 10), dtype=float32)
  File "C:\Users\cglab\Desktop\Match3\Model.py", line 19, in call
    common = self.common(inputs)
TypeError: 'KerasTensor' object is not callable

Here is the code

import tensorflow as tf

from keras import layers

class CustomModel(tf.keras.Model):
    def __init__(self, num_hidden, max_x, max_y, n_tile_type):
        super(CustomModel, self).__init__()
        self.inputs = layers.Input(shape=(max_y, max_x))
        self.common = layers.Dense(num_hidden, activation="relu")(self.inputs)
        tf.debugging.assert_shapes([(self.inputs, (tf.TensorShape([None, 10, 10])))]) #not assert
        self.x_probs = layers.Dense(max_x, activation="softmax")(self.common)
        self.y_probs = layers.Dense(max_y, activation="softmax")(self.common)
        self.tile_prob = layers.Dense(n_tile_type, activation="softmax")(self.common)
        self.critic = layers.Dense(1)(self.common)

    def call(self, inputs):
        tf.debugging.assert_shapes([(inputs, (tf.TensorShape([None, 10, 10])))]) #not assert

        common = self.common(inputs) ##Error
        x_probs = self.x_probs(common)
        y_probs = self.y_probs(common)
        tile_prob = self.tile_prob(common)
        critic = self.critic(common)

    return [x_probs, y_probs, tile_prob, critic]

#Initialize and call

model = CustomModel(256, max_x, max_y, max_tile_type)

state = np.full((self.max_y, self.max_x), -1)
state = tf.convert_to_tensor(state, dtype=tf.float32)
state = tf.expand_dims(state, 0)

x_probs, y_probs, tile_probs, critic_value = model(state)

I need help. thank you

>Solution :

A Layer is callable, and calling it with a Tensor will return another Tensor, which is not callable. More specifically, in __init__() we should just create the layers, and in call() we call them on actual input (that looked OK in the code):

    def __init__(self, num_hidden, max_x, max_y, n_tile_type):
        super(CustomModel, self).__init__()
        self.inputs = layers.Input(shape=(max_y, max_x))
        self.common = layers.Dense(num_hidden, activation="relu")
        tf.debugging.assert_shapes([(self.inputs, (tf.TensorShape([None, 10, 10])))]) #not assert
        self.x_probs = layers.Dense(max_x, activation="softmax")
        self.y_probs = layers.Dense(max_y, activation="softmax")
        self.tile_prob = layers.Dense(n_tile_type, activation="softmax")
        self.critic = layers.Dense(1)

Note how the (self.common) and likes were removed.