Giter VIP home page Giter VIP logo

deep-learning-coursera's Introduction

Deep Learning Specialization on Coursera

This is my personal projects for the course. The course covers deep learning from begginer level to advanced. Highly recommend anyone wanting to break into AI.

Instructor: Andrew Ng, DeepLearning.ai

  1. Week1 - Introduction to deep learning
  2. Week2 - Neural Networks Basics
  3. Week3 - Shallow neural networks
  4. Week4 - Deep Neural Networks
  1. Week1 - Practical aspects of Deep Learning - Setting up your Machine Learning Application - Regularizing your neural network - Setting up your optimization problem
  2. Week2 - Optimization algorithms
  3. Week3 - Hyperparameter tuning, Batch Normalization and Programming Frameworks
  1. Week1 - Introduction to ML Strategy - Setting up your goal - Comparing to human-level performance
  2. Week2 - ML Strategy (2) - Error Analysis - Mismatched training and dev/test set - Learning from multiple tasks - End-to-end deep learning
  1. Week1 - Foundations of Convolutional Neural Networks
  2. Week2 - Deep convolutional models: case studies - Papers for read: ImageNet Classification with Deep Convolutional Neural Networks, Very Deep Convolutional Networks For Large-Scale Image Recognition
  3. Week3 - Object detection - Papers for read: You Only Look Once: Unified, Real-Time Object Detection, YOLO
  4. Week4 - Special applications: Face recognition & Neural style transfer - Papers for read: DeepFace, FaceNet

Course 5. Sequence Models

  1. Week1 - Recurrent Neural Networks
  2. Week2 - Natural Language Processing & Word Embeddings
  3. Week3 - Sequence models & Attention mechanism

*************************************************************************************************************************************

deep-learning-coursera's People

Contributors

enggen avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

deep-learning-coursera's Issues

Week 4 Programming Exercise: ValueError: shapes (4,5) and (4,4) not aligned: 5 (dim 1) != 4 (dim 0)

# GRADED FUNCTION: L_model_forward

def L_model_forward(X, parameters):
    """
    Implement forward propagation for the [LINEAR->RELU]*(L-1)->LINEAR->SIGMOID computation
    
    Arguments:
    X -- data, numpy array of shape (input size, number of examples)
    parameters -- output of initialize_parameters_deep()
    
    Returns:
    AL -- last post-activation value
    caches -- list of caches containing:
                every cache of linear_activation_forward() (there are L-1 of them, indexed from 0 to L-1)
    """

    caches = []
    A = X
    L = len(parameters) // 2                  # number of layers in the neural network
    #print(parameters)
    # Implement [LINEAR -> RELU]*(L-1). Add "cache" to the "caches" list.
    for l in range(1, L):
        A_prev = A 
        ### START CODE HERE ### (≈ 2 lines of code)
        A, cache = linear_activation_forward(A_prev, parameters['W'+str(1)], parameters['b'+str(1)], activation='relu')
        caches.append(cache)
        ### END CODE HERE ###
    
    # Implement LINEAR -> SIGMOID. Add "cache" to the "caches" list.
    ### START CODE HERE ### (≈ 2 lines of code)
    AL, cache = linear_activation_forward(A, parameters['W'+str(L)], parameters['b'+str(L)], activation='sigmoid')
    caches.append(cache)
    ### END CODE HERE ###
    
    assert(AL.shape == (1,X.shape[1]))
            
    return AL, caches

And then:

X, parameters = L_model_forward_test_case_2hidden()
AL, caches = L_model_forward(X, parameters)
print("AL = " + str(AL))
print("Length of caches list = " + str(len(caches)))

Error:
ValueError: shapes (4,5) and (4,4) not aligned: 5 (dim 1) != 4 (dim 0)

Any dea how to fix this?

auxiliary python files missing

Hi enggen,
quite good that you've downloaded all the coursework materials but I've noticed you didn't download the auxiliary python files. that would be a nice addition.

Where can I find yolo_anchors.txt?

Hello, thank you for sharing you work :)
I am confused by how to get to file with the values of the anchors, which you call yolo_anchors.txt. Can you tell me how to get it?
Thank you in advance :)

Breaking Coursera Honor Code

Hello @enggen, thank you for your willingness to share about the DL Specialization. I just wanted to remind you that every student who has enrolled in a course in Coursera (you, me, and many more) agreed to follow Coursera's Honor Code. Which literally says:

I will not make solutions to homework, quizzes, exams, projects, and other assignments available to anyone else (except to the extent an assignment explicitly permits sharing solutions). This includes both solutions written by me, as well as any solutions provided by the course staff or others.

Same as you, I completed the DL Specialization, and I personally do not like the idea of anyone having access to solved assignments because it means unethical users could go on and "complete" the Specialization without any effort other than copying your code. Opening this "shortcut" diminishes the value of this great Specialization.

I understand you have > 900 stars in this repository and it gets traction to your GitHub profile, but it's better to play a fair game and avoid breaking Coursera's Honor Code.

Just my humble opinion, thank you.

copyright infringement?

the five course of deeplearning.ai costs 49$ per course, is there copyright infringement.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.