# How can Tensorflow be used to construct an object for customized layers?

TensorflowServer Side ProgrammingProgramming

Tensorflow can be used to construct an object for customized layers by first creating the required layers, and then using this layer on tf.zeros method.

A neural network that contains at least one layer is known as a convolutional layer. We can use the Convolutional Neural Network to build learning model.

The intuition behind transfer learning for image classification is, if a model is trained on a large and general dataset, this model can be used to effectively serve as a generic model for the visual world. It would have learned the feature maps, which means the user won’t have to start from scratch by training a large model on a large dataset.

TensorFlow Hub is a repository that contains pre-trained TensorFlow models. TensorFlow can be used to fine-tune learning models. We will understand how to use models from TensorFlow Hub with tf.keras, use an image classification model from TensorFlow Hub.  Once this is done, transfer learning can be performed to fine-tune a model for customized image classes. This is done by using a pretrained classifier model to take an image and predict what it is. This can be done without needing any training.

We are using the Google Colaboratory to run the below code. Google Colab or Colaboratory helps run Python code over the browser and requires zero configuration and free access to GPUs (Graphical Processing Units). Colaboratory has been built on top of Jupyter Notebook.

## Example

import tensorflow as tf
print(tf.test.is_gpu_available())
layer = tf.keras.layers.Dense(100)
print("A dense layer is created")
layer = tf.keras.layers.Dense(10, input_shape=(None, 5))
print("To use the layer, it is called")
layer(tf.zeros([10, 5]))

## Output

WARNING:tensorflow:From <ipython-input-72-7364732a3855>:2: is_gpu_available (from tensorflow.python.framework.test_util) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.config.list_physical_devices('GPU') instead.
WARNING:tensorflow:From <ipython-input-72-7364732a3855>:2: is_gpu_available (from tensorflow.python.framework.test_util) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.config.list_physical_devices('GPU') instead.
False
A dense layer is created
To use the layer, it is called
<tf.Tensor: shape=(10, 10), dtype=float32, numpy=
array([[0., 0., 0., 0., 0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0., 0., 0., 0., 0.]], dtype=float32)>

## Explanation

• The tf.keras.layers package contains layers that are objects. To construct a layer, an object can be constructed.

• Many layers take the number of output dimensions or channels as a first argument.

• The tf.keras can be used as a high-level API to build neural networks.

• Most of the TensorFlow APIs can be used with eager execution.

• The number of input dimensions is not required, but can be inferred rom the first time the layer is used.

Published on 13-Feb-2021 08:59:27