CODEWITHSUNDEEP
python-3.xdeep-learningtensorflow2.0tensorflow-addons
zwldwhdk
zwldwhdk

Reputation: 1

TypeError identified in implementing ‘WeightNormalization’ layer within tensorflow-addon

I found the error below when I followed the example code of 'WeightNormalization' wrapper implemented in the tensorflow-addons.

The environment is

I identify the following code doesn't work in the Colab notebook.

The code in trouble is as follows,

import tensorflow as tf
import tensorflow_addons as tfa
import numpy as np
from matplotlib import pyplot as plt

# Hyper Parameters
batch_size = 32
epochs = 10
num_classes=10

# WeightNorm ConvNet
wn_model = tf.keras.Sequential([
    tfa.layers.WeightNormalization(tf.keras.layers.Conv2D(6, 5, activation='relu')),
    tf.keras.layers.MaxPooling2D(2, 2),
    tfa.layers.WeightNormalization(tf.keras.layers.Conv2D(16, 5, activation='relu')),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Flatten(),
    tfa.layers.WeightNormalization(tf.keras.layers.Dense(120, activation='relu')),
    tfa.layers.WeightNormalization(tf.keras.layers.Dense(84, activation='relu')),
    tfa.layers.WeightNormalization(tf.keras.layers.Dense(num_classes, activation='softmax')),
])

TypeError() raised for the tfa.layers.WeightNormalization()

TypeError                                 Traceback (most recent call last)
<ipython-input-5-973cec7abd8b> in <module>
      1 # WeightNorm ConvNet
      2 wn_model = tf.keras.Sequential([
----> 3     tfa.layers.WeightNormalization(tf.keras.layers.Conv2D(6, 5, activation='relu')),
      4     tf.keras.layers.MaxPooling2D(2, 2),
      5     tfa.layers.WeightNormalization(tf.keras.layers.Conv2D(16, 5, activation='relu')),

2 frames
/usr/local/lib/python3.9/dist-packages/tensorflow_addons/layers/wrappers.py in __init__(self, layer, data_init, **kwargs)
     57 
     58     @typechecked
---> 59     def __init__(self, layer: tf.keras.layers, data_init: bool = True, **kwargs):
     60         super().__init__(layer, **kwargs)
     61         self.data_init = data_init

/usr/local/lib/python3.9/dist-packages/typeguard/_functions.py in check_argument_types(memo)
    111             value = memo.arguments[argname]
    112             try:
--> 113                 check_type_internal(value, expected_type, memo=memo)
    114             except TypeCheckError as exc:
    115                 qualname = qualified_name(value, add_class_prefix=True)

/usr/local/lib/python3.9/dist-packages/typeguard/_checkers.py in check_type_internal(value, annotation, memo)
    668             return
    669 
--> 670     if not isinstance(value, origin_type):
    671         raise TypeCheckError(f"is not an instance of {qualified_name(origin_type)}")
    672 

TypeError: isinstance() arg 2 must be a type or tuple of types

I think that 'typeguard' package makes trouble, but I can't address this issue. Can you give me an answer please?

Upvotes: 0

Views: 96

Answers (1)

anonymousJP
anonymousJP

Reputation: 1

You should use a typeguard version below 3.0:

pip install typeguard<3.0

Upvotes: 0

Related Questions