How can Keras be used to load weights from checkpoint and re-evaluate the model using Python?

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.

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 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.

Keras means ‘horn’ in Greek. 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.

Keras is already present within the Tensorflow package. It can be accessed using the below line of code.

import tensorflow
from tensorflow import keras

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 −


print("The weights are loaded")

print("The model is being re-evaluated")
loss, acc = model.evaluate(test_images, test_labels, verbose=2)
print("This is the restored model, with accuracy: {:5.3f}%".format(100 * acc))

Code credit −


The Weights are loaded
The model is beign re-evaluated
32/32 - 0 - loss:0.4066 - sparse_categorical_accuracy:0.8740
This is the restored model, with accuracy:87.400%


  • This new model is used to map weights to it.

  • The ‘evaluate’ method is used to check how well the model performs on new data.

  • In addition, the loss when the model is being trained and the accuracy of the model are both determined.

  • The loss and accuracy are printed on the console.