Discover fundamental deep learning concepts, master coding models using NumPy and Keras, and test your knowledge with quizzes and coding challenges. Gain insights into effective deep learning techniques.

Dockerfile.tar.gz

keras python

keras python - using models

This beginner level and highly comprehensive course is intended for learners who are familiar with Python programming. You will become familiar with the fundamental concepts and terminologies used in deep learning. In addition, this course will help you understand the importance of deep learning techniques. You will examine simple models like perceptron before learning more complex yet powerful deep learning models. The course will provide hands-on practical knowledge of how to code simple and complex deep learning models in NumPy, a powerful Python library and Keras, a cutting-edge library for deep learning in Python. You can test your knowledge with the quizzes that are provided at the end of every lesson and coding challenges that will help you gain a higher understanding. By the end of the course, you should have a general understanding of the basics in deep learning and you will be equipped with the right tools to learn more advanced concepts.

A Beginner's Guide to Deep Learning

# The `predict` function

Make predictions on the trained model.

import numpy as np 
import matplotlib.pyplot as plt

A = x[0] # pixel values for letter A
B = x[1] # pixel values for letter B
C = x[2] # pixel values for letter C

def predict(letter, x):
    """Computes predictions on the trained weights and bias"""
    out_h1, out_h2, out_y = forward_propagation(letter, w1, w2, w3, b1, b2, b3)
    print("softmax output:", out_y)
    prediction = np.where(out_y == np.amax(out_y)) # returns the maximum value of array
    print("Highest value of index:", prediction[1][0]) 
    # plot the predicted label
    plt.xlabel("Predicted label") 
    plt.imshow(x[prediction[1][0]].reshape(5, 6)) 
    plt.show()
    plt.savefig('output/predicted.png')

letter = A
# printing the target label
plt.imshow(letter.reshape(5, 6)) 
plt.xlabel("Target label") 
plt.show() 
plt.savefig('output/target.png')
predict(letter, x)   

# Explanation
> [Recall](https://www.educative.io/courses/beginners-guide-to-deep-learning/introduction-to-the-letter-classification-data-set) that x[0] has the letter A pixel values, x[1] has letter B pixel values, x[2] has letter C pixel values. We assign these to variables `A`, `B`, `C`. Then we call the `predict` function.  

**`predict` function:**

The function takes in the pixel value of a  `letter` and training data `x`:

- It calls the `forward_propagation` function which returns the output at the hidden layers `out_h1`, and `out_h2` respectively and the output layer `out_y`. 
  >📝 The output value shows the probability of a letter belonging to class A, B, or C.

- It finds the index of the maximum value of array `out_y` (to get the predicted class). This index is searched in training data `x` to look for the corresponding label.

- The predicted label is reshaped in 5 rows and 6 columns to print the letter.

>  🔨 Changing the `letter` to B or C to observe the output.
>
> 🎉 You will notice that all three letters **A, B, and C** are perfectly predicted.

----

✨Before We Begin

✨Introduction to Deep Learning

✨Simple Perceptron Models in NumPY

✨Towards Deep Neural Networks in NumPY

🖥️ Project: Build a Letter Classification Model

Deep Learning in NumPy Exam

✨Building Deep Learning Models with Keras

✨Fine-tune Keras Model

🖥️ Project: Build a Digit Recognition Model

✨Conclusion

Deep Learning in Keras Exam

Making Predictions

The `predict` function

Explanation

Deep Learning in NumPy Exam

Deep Learning in Keras Exam

Making Predictions

The predict function

Explanation

The `predict` function