PAC | Troubleshooting Python Deep Learning (2019 EN)

Discussion in 'Artificial Intelligence' started by Kanka, Jul 17, 2019.

  1. Kanka

    Kanka Well-Known Member Loyal User

    Messages:
    13,502
    Likes Received:
    359
    Trophy Points:
    83
    [​IMG]

    Company: Packt Publishing
    Author: Jakub Konczyk
    Full Title: Troubleshooting Python Deep Learning
    Year: 2019
    Language: English
    Genre: Educational: Data
    Skill Level: -
    Price: €124.99
    -
    Files: MP4 (+ Code Files)
    Time: 03:02:26
    Video: AVC, 1920 x 1080 (1.778) at 30.000 fps, 200 kbps
    Audio: AAC at 160 Kbps, 2 channels, 48.0 KHz



    Practical solutions to your problems while building Deep Learning models using CNN, LSTM, Scikit-Learn, and NumPy.

    Building Deep Learning models with Python is a strenuous task and there are chances of getting stuck on specific tasks. When that happens, you usually end up searching for solutions and need to manually look for ways to come out of these problems. This wastes both time and effort and may also lead to reduced performance of your Deep Learning system.

    After carefully analyzing the most popular errors or problems that arise while working on Deep Learning models, we have identified the most usable models used for classification in this course and provided practical yet unique solutions to each problem that are easy to understand and implement.
    You can either follow the entire course or directly jump into the section that covers a specific problem you’re facing. Some of the common yet important issues we cover include errors while building and training Deep Learning with neural networks, especially without a specific framework.

    By the end of the course, you will be well-versed to tackle and troubleshoot any errors with your Deep learning models.

    Style and Approach:
    This video tutorial provides practical insights on how to solve issues in your Deep Learning models. You’ll identify and address specific problems faced while working with Deep Learning and tackle them straight away with Python.


    Learn:
    ✓ Go through curated issues that many developers face when building their deep learning models
    ✓ Discover the most efficient techniques to overcome classification problems in CNN
    ✓ Resolve issues that are related to the CNN architecture, accuracy, input, and output
    ✓ Work with LSTM, which is a part of RNN, and deal with the most efficient part of text problems
    ✓ Discover how to solve the most popular problems from architecture to input and output
    ✓ Implement the most usable libraries: Scikit Learn and Numpy, to resolve the major problems arising from your Deep Learning models

    Features:
    ✓ Discover the limitless use of building any application using Deep Learning and ensure its issues aren’t a roadblock for your projects
    ✓ Problems are addressed with practical yet unique solutions that are easy to understand and implement
    ✓ Identify and address specific problems that developers face while working with Deep Learning and show them to tackle it straight away with Python


    Lessons:
    1. Solutions to Convolutional Neural Network Problems - Part One
    01. The Course Overview
    02. Concatenate Two CNNs Correctly
    03. Splitting Trained Model
    04. Resolving fit_generator Errors
    05. Model Object Has No Attribute load_model Keras
    06. High val_acc, But Low Accuracy in Practice
    07. Error in Adding a Dense Layer
    08. Model with Multiple Outputs Errors
    09. Model That Uses Dropout Is Still Overfitting
    2. Solutions to Convolutional Neural Network Problems - Part Two
    10. When the Value Error Input 0 Is Incompatible with Layer conv2d_1
    11. Interpreting kernel_size Notation in CNNs
    12. Choosing Last Layer’s Activation Function in CNN
    13. Using Validation Accuracy
    14. Error When Using CNN to Classify Text
    15. Kernel Weight Initialization in CNN Model
    16. Common Problems When Using Pre-Trained CNN Models
    17. Shape Error When Training CIFAR-10 Dataset on CNN
    3. Solutions to Recurrent Neural Network Problems
    18. Building an RNN Model in Keras
    19. Wrong Input: ValueError – Error When Checking Input
    20. Correct Text Preparation for Machine Translation
    21. Handling Invalid Input Shape Error
    22. Mapping Series of Vectors to a Single Vector
    23. Resolving a Bad Output from RNN While Generating a Simple Sequence
    24. Preparing Data Correctly for Time Series Prediction
    25. How to Enable Stateful RNN?
    4. Solutions to LSTM Recurrent Neural Networks Problems
    26. Stacking Multiple LSTM in Keras TypeError - Call() Got an Unexpected Keyword Argument 'return_sequences'
    27. Working with Different Lengths of Input and Output Sequences
    28. How to Use Stacked LSTMs
    29. Using CNN-LSTM for Time Series Prediction
    30. Solving LSTM Underfitting on Time Series Problem
    31. Using LSTM for Multi-Value Prediction
    32. How To Do Text Classification with LSTM
    33. Data Preparation for Seq2Seq Learning
    5. Troubleshooting Models with scikit-learn
    34. LabelBinarizer Returns Vector When There Are Two Classes
    35. Handling Missing Values
    36. Evaluating Deep Learning Models Using Additional Metrics
    37. Fixing Warning Messages
    38. Generating Test Datasets
    39. Normalizing and Standardizing the Data
    40. Preparing Text for Use with Deep Learning Models
    6. Solving NumPy Problems
    41. Converting a 2D Matrix to a One-Hot Encoded Matrix
    42. Reshaping a 2D NumPy Array to 3D Array
    43. Fix load.npy Error in Python3
    44. Turn ND Matrix Into 1D Vector


    -------------