TypeError: Input 'y' of 'Mul' Op has type float32 that does not match type int64 of argument 'x'

Question

after this code i am getting the error in categoricalfocalloss i m not getting whereint64 error is coming

def categorical_focal_loss(gamma=2., alpha=.25):
    def categorical_focal_loss_fixed(y_true, y_pred):
        y_pred /= K.sum(y_pred, axis=-1, keepdims=True)
        epsilon = K.epsilon()
        y_pred = K.clip(y_pred, epsilon, 1. - epsilon)
        y_pred = tf.cast(y_pred, dtype= tf.float32)
        cross_entropy = -y_true * K.log(y_pred)
        loss = alpha * K.pow(1 - y_pred, gamma) * cross_entropy
        return K.sum(loss, axis=1)
    return categorical_focal_loss_fixed

model description here in this code , in the loss categoricalfocal loss is used

    with strategy.scope():
        ef7 =tf.keras.Sequential()
        ef7.add(enet)
        ef7.add(tf.keras.layers.MaxPooling2D())
        ef7.add(tf.keras.layers.Conv2D(4096,3,padding='same'))
        ef7.add(tf.keras.layers.BatchNormalization())
        ef7.add(tf.keras.layers.ReLU())
        ef7.add(tf.keras.layers.GlobalAveragePooling2D())
        ef7.add(tf.keras.layers.Dropout(0.35))
        ef7.add(tf.keras.layers.Flatten())
    
        ef7.add(tf.keras.layers.Dense(2048,activation='relu'))
        ef7.add(tf.keras.layers.BatchNormalization())
        ef7.add(tf.keras.layers.LeakyReLU())
        ef7.add(tf.keras.layers.Dropout(0.35))
    
        ef7.add(tf.keras.layers.Dense(1024,activation='relu'))
        ef7.add(tf.keras.layers.BatchNormalization())
        ef7.add(tf.keras.layers.LeakyReLU())
        ef7.add(tf.keras.layers.Dropout(0.25))
        ef7.add(tf.keras.layers.Dense(3,activation='softmax'))
        ef7.compile(
                    optimizer=tf.optimizers.Adam(lr=0.0001),
                    loss=categorical_focal_loss(gamma=2., alpha=.25),
                    metrics=['categorical_accuracy',
                            tf.keras.metrics.Recall(),
                            tf.keras.metrics.Precision(),   
                            tf.keras.metrics.AUC(),
                            tfa.metrics.F1Score(num_classes=3, average="macro")
                           ])

here in the model i used categorical focal loss when i run this ,in train dataset i am not getting how tcovert itintointoint64

    h7=ef7.fit(
    train_dataset,
    steps_per_epoch=train_labels.shape[0] // BATCH_SIZE,
    callbacks=[lr_callback],
    epochs=EPOCHS)

error is got is mentioned below

        Epoch 1/20
    
    ```Epoch 00001: LearningRateScheduler reducing learning rate to 1e-05.```
    ---------------------------------------------------------------------------
    >TypeError                                 Traceback (most recent call last)
    <ipython-input-133-d27eee469b2b> in <module>()
          3     steps_per_epoch=train_labels.shape[0] // BATCH_SIZE,
          4     callbacks=[lr_callback],
    ----> 5     epochs=EPOCHS)
    
    9 frames
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
        975           except Exception as e:  # pylint:disable=broad-except
        976             if hasattr(e, "ag_error_metadata"):
    --> 977               raise e.ag_error_metadata.to_exception(e)
        978             else:
        979               raise
    
    TypeError: in user code:
    
        >/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:805 train_function  *
            >return step_function(self, iterator)
        ><ipython-input-68-de42355e464e>:7 categorical_focal_loss_fixed  *
            cross_entropy = -y_true * K.log(y_pred)
        >/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/math_ops.py:1180 binary_op_wrapper
            >raise e
        >/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/math_ops.py:1164 binary_op_wrapper
            >return func(x, y, name=name)
        >/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/math_ops.py:1496 _mul_dispatch
            >return multiply(x, y, name=name)
        >/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
            return target(*args, **kwargs)
        >/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/math_ops.py:518 multiply
            >return gen_math_ops.mul(x, y, name)
        >/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/gen_math_ops.py:6078 mul
         >   "Mul", x=x, y=y, name=name)
        >/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/op_def_library.py:558 _apply_op_helper
         >   inferred_from[input_arg.type_attr]))
    
        >TypeError: Input 'y' of 'Mul' Op has type float32 that does not match type int64 of argument 'x'.```

def categorical_focal_loss(gamma=2., alpha=.25): def categorical_focal_loss_fixed(y_true, y_pred): y_pred /= K.sum(y_pred, axis=-1, keepdims=True) epsilon = K.epsilon() y_pred = K.clip(y_pred, epsilon, 1. - epsilon) y_pred = tf.cast(y_pred, dtype= tf.float32) cross_entropy = -y_true * K.log(y_pred) loss = alpha * K.pow(1 - y_pred, gamma) * cross_entropy return K.sum(loss, axis=1) return categorical_focal_loss_fixed — AkAnKsHa BaLi, Jan 31 '21 at 17:05
Posting long blocks of code is discouraged. Especially when no further info has been provided. Please review [ask] and consider editing your post. We're happy to help you find an error but you have to make an honest attempt to solve it yourself and do your best to explain the problem. — BeanBagTheCat, Jan 31 '21 at 17:57
hello BeanBagTheCat sir and Andrey sir now i updated the code — AkAnKsHa BaLi, Feb 01 '21 at 01:09

BeanBagTheCat · Accepted Answer · 2021-02-01T05:12:30.077

The error points to this line of code:

cross_entropy = -y_true * K.log(y_pred)

and is being thrown from the multiply function in math_ops.py within the tensorflow package. Digging into that file I found this summary for the argument requirements.

 Args:
    x: A Tensor. Must be one of the following types: `bfloat16`,
      `half`, `float32`, `float64`, `uint8`, `int8`, `uint16`,
      `int16`, `int32`, `int64`, `complex64`, `complex128`.
    y: A `Tensor`. Must have the same type as `x`.
    name: A name for the operation (optional).
  Returns:
  A `Tensor`.  Has the same type as `x`.
  Raises:
   * InvalidArgumentError: When `x` and `y` have incompatible shapes or types

Looking back at the error

TypeError: Input 'y' of 'Mul' Op has type float32 that does not match type int64 of argument 'x'.```

This means that -y_true is 'x' and K.log(y_pred) is 'y'. To perform this operations you'll have to cast -y_true to a float32 or cast K.log(y_pred) to an int64 or cast them both into any other type as long as they match. .

Thankyou sir I will do this and let you inform about this ....thankyou somuch BeanBag sir — AkAnKsHa BaLi, Feb 01 '21 at 04:40
>It is Working now by doing ``` y_true = tf.cast(y_true, tf.float32) ``` > THANKYOU SO MUCH BeanBag Sir I am highly obliged to you — AkAnKsHa BaLi, Feb 01 '21 at 05:05
@AkAnKsHaBaLi I'm glad I could help! If you could accept the answer that would be much appreciated :) — BeanBagTheCat, Feb 01 '21 at 05:17

TypeError: Input 'y' of 'Mul' Op has type float32 that does not match type int64 of argument 'x'

1 Answers1