Tensorflow is a machine learning framework that is provided by Google. It is an open-source framework used in conjunction with Python to implement algorithms, deep learning applications and much more. It is used in research and for production purposes.
Keras was developed as a part of research for the project ONEIROS (Open ended Neuro-Electronic Intelligent Robot Operating System). Keras is a deep learning API, which is written in Python. It is a high-level API that has a productive interface that helps solve machine learning problems. It runs on top of Tensorflow framework. It was built to help experiment in a quick manner. It provides essential abstractions and building blocks that are essential in developing and encapsulating machine learning solutions.
It is highly scalable, and comes with cross platform abilities. This means Keras can be run on TPU or clusters of GPUs. Keras models can also be exported to run in a web browser or a mobile phone as well.
Keras is already present within the Tensorflow package. It can be accessed using the below line of code.
import tensorflow from tensorflow import keras
Yes, a Keras model be treated as just a layer and invoked using Python. The Keras functional API helps create models that are more flexible in comparison to models created using sequential API. The functional API can work with models that have non-linear topology, can share layers and work with multiple inputs and outputs. A deep learning model is usually a directed acyclic graph (DAG) that contains multiple layers. The functional API helps build the graph of layers.
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. Following is the code snippet to treat Keras model as a layer and invoked using Python −
Example
Encoder_input = keras.Input(shape=(28, 28, 1), name=”original_img”)
print("Adding layers to the model")
x = layers.Conv2D(16, 3, activation="relu")(encoder_input)
x = layers.Conv2D(32, 3, activation="relu")(x)
x = layers.MaxPooling2D(3)(x)
x = layers.Conv2D(32, 3, activation="relu")(x)
x = layers.Conv2D(16, 3, activation="relu")(x)
print("Performing golbal max pooling")
encoder_output = layers.GlobalMaxPooling2D()(x)
print("Creating a model using the layers")
encoder = keras.Model(encoder_input, encoder_output, name="encoder")
print("More information about the model")
encoder.summary()
decoder_input = keras.Input(shape=(16,), name="encoded_img")
print("Reshaping the layers in the model")
x = layers.Reshape((4, 4, 1))(decoder_input)
x = layers.Conv2DTranspose(16, 3, activation="relu")(x)
x = layers.Conv2DTranspose(32, 3, activation="relu")(x)
x = layers.UpSampling2D(3)(x)
x = layers.Conv2DTranspose(16, 3, activation="relu")(x)
decoder_output = layers.Conv2DTranspose(1, 3, activation="relu")(x)
print("Creating a model using the layers")
decoder = keras.Model(decoder_input, decoder_output, name="decoder")
print("More information about the model")
decoder.summary()
autoencoder_input = keras.Input(shape=(28, 28, 1), name="img")
encoded_img = encoder(autoencoder_input)
decoded_img = decoder(encoded_img)
autoencoder = keras.Model(autoencoder_input, decoded_img, name="autoencoder")
print("More information about the model")
autoencoder.summary()Code credit − https://www.tensorflow.org/guide/keras/functional
Output
original_img (InputLayer) [(None, 28, 28, 1)] 0 _________________________________________________________________ conv2d_28 (Conv2D) (None, 26, 26, 16) 160 _________________________________________________________________ conv2d_29 (Conv2D) (None, 24, 24, 32) 4640 _________________________________________________________________ max_pooling2d_7 (MaxPooling2 (None, 8, 8, 32) 0 _________________________________________________________________ conv2d_30 (Conv2D) (None, 6, 6, 32) 9248 _________________________________________________________________ conv2d_31 (Conv2D) (None, 4, 4, 16) 4624 _________________________________________________________________ global_max_pooling2d_3 (Glob (None, 16) 0 ================================================================= Total params: 18,672 Trainable params: 18,672 Non-trainable params: 0 _________________________________________________________________ Reshaping the layers in the model Creating a model using the layers More information about the model Model: "decoder" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= encoded_img (InputLayer) [(None, 16)] 0 _________________________________________________________________ reshape_1 (Reshape) (None, 4, 4, 1) 0 _________________________________________________________________ conv2d_transpose_4 (Conv2DTr (None, 6, 6, 16) 160 _________________________________________________________________ conv2d_transpose_5 (Conv2DTr (None, 8, 8, 32) 4640 _________________________________________________________________ up_sampling2d_1 (UpSampling2 (None, 24, 24, 32) 0 _________________________________________________________________ conv2d_transpose_6 (Conv2DTr (None, 26, 26, 16) 4624 _________________________________________________________________ conv2d_transpose_7 (Conv2DTr (None, 28, 28, 1) 145 ================================================================= Total params: 9,569 Trainable params: 9,569 Non-trainable params: 0 _________________________________________________________________ More information about the model Model: "autoencoder" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= img (InputLayer) [(None, 28, 28, 1)] 0 _________________________________________________________________ encoder (Functional) (None, 16) 18672 _________________________________________________________________ decoder (Functional) (None, 28, 28, 1) 9569 ================================================================= Total params: 28,241 Trainable params: 28,241 Non-trainable params: 0 _________________________________________________________________
Explanation
Any model can be treated as a layer by invoking it on an ‘input’ or output of another layer.
When the model is called, the architecture is being reused.
In addition, the weights are also being reused.
The autoencoder model can be created using the encoder model, a decoder model.
These two models are chained together into two calls to get the autoencoder model.