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. It has optimization techniques that help in performing complicated mathematical operations quickly. This is because it uses NumPy and multi-dimensional arrays. These multi-dimensional arrays are also known as ‘tensors’.
The framework supports working with a deep neural networks. It is highly scalable and comes with many popular datasets. It uses GPU computation and automates the management of resources. It comes with multitude of machine learning libraries, and is well-supported and documented. The framework has the ability to run deep neural network models, train them, and create applications that predict relevant characteristics of the respective datasets.
The ‘tensorflow’ package can be installed on Windows using the below line of code −
pip install tensorflow
Tensor is a data structure used in TensorFlow. It helps connect edges in a flow diagram. This flow diagram is known as the ‘Data flow graph’. Tensors are nothing but a multidimensional array or a list. They can be identified using three main attributes −
Rank − It tells about the dimensionality of the tensor. It can be understood as the order of the tensor or the number of dimensions in the tensor that has been defined.
Type − It tells about the data type associated with the elements of the Tensor. It can be a one dimensional, two dimensional or n-dimensional tensor.
Shape − It is the number of rows and columns together.
We are using 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 −
AUTOTUNE = tf.data.experimental.AUTOTUNE print("The configure_dataset method is defined") def configure_dataset(dataset): return dataset.cache().prefetch(buffer_size=AUTOTUNE) print("The function is called on training dataset") binary_train_ds = configure_dataset(binary_train_ds) print("The function is called on validation dataset") binary_val_ds = configure_dataset(binary_val_ds) print("The function is called on test dataset") binary_test_ds = configure_dataset(binary_test_ds) int_train_ds = configure_dataset(int_train_ds) int_val_ds = configure_dataset(int_val_ds) int_test_ds = configure_dataset(int_test_ds)
Code credit − https://www.tensorflow.org/tutorials/load_data/text
The configure_dataset method is defined The function is called on training dataset The function is called on validation dataset The function is called on test dataset
It is important to define two methods to ensure that input or output doesn’t block while loading data.
The ‘cache’ method keeps data in the memory even after it has been loaded off the disk.
This ensures that data doesn’t become a hindrance during training.
The ‘prefetch’ method overloads the data pre-processing and model execution during the training process.