Your Fast Track To Become A Tensorflow Developer (Certified)

Watch my learning path to become a proficient TensorFlow developer quickly.

What you'll learn

Discover what I learned to become a TensorFlow Certified Developer.

Get my customized training plan to get fluent as a TF Devloper.

Learn the most important concepts of TensorFlow to become a TF Developer.

Get detailed explanations of the functioning and application of TF models, such as CNN, RNN etc.

Learn how to analyze a given task, select the right TF model, and solve the task.

Requirements

Basic python knowledge OR experience in another programming language required.

Some basic knowledge about neural networks.

Description

Hi, I am Florian.I am a computer scientist and just recently passed my TF Developer certification.In this course I want to show you my exact learning path to become a proficient TF developer.When I started with the training, I had good knowledge of AI in general, but no knowledge of TensorFlow and minimal experience with Python (I used to develop in C, C++). Fortunately I created some sort of "battle plan" to get me up and running in Python and TF in only 4 weeks! (I even passed the 5h exam on the first attempt).Now I want to give you a way to "look me over the shoulder" while I go through ALL of my trainings once more.Unfortunately I had nobody to explain anything to me during my training, but for this course I created very detailed diagrams to give you easy and precise explanations of this (some times very) complex topic!Additionally I created a document for you, which will support you on your learning path! Even though the topic is not easy, and there is much to learn, I am confident this course will help you to become a proficient TF developer quickly.Let's start…Florian.

Overview

Section 1: Introduction.

Lecture 1 Welcome to this course!

Lecture 2 What to expect?

Lecture 3 What you need…and start!

Lecture 4 Let's start…

Section 2: Introduction to Tensors

Lecture 5 Simple Tensors

Lecture 6 Creating larger Tensors

Lecture 7 Basic operations on Tensors

Lecture 8 A typical data Tensor

Lecture 9 Copyright information.

Section 3: Let's get the basics right! How neuronal networks work.

Lecture 10 Neuron.

Lecture 11 Perceptron.

Lecture 12 Multi layer perceptron (MLP).

Lecture 13 Inference and Learning intro.

Lecture 14 Inference and Learning in a nutshell.

Lecture 15 Inference: Calculating the sum of weights.

Lecture 16 Inference: Activation function, threshold and output calculation.

Lecture 17 Learning introduction.

Lecture 18 Learning formula.

Section 4: Our first model: Image classification.

Lecture 19 Understanding the classification task.

Lecture 20 Import the data.

Lecture 21 Explore the data.

Lecture 22 Preprocess the data.

Lecture 23 Building our first model.

Lecture 24 Train the model and evaluate its accuracy.

Lecture 25 Let the model make predictions.

Lecture 26 Visualize predictions for easy model verification.

Lecture 27 Copyright information.

Section 5: Computer Vision

Lecture 28 Limitations of MLPs.

Lecture 29 Solution with CNNs.

Lecture 30 CNN 1. Load data.

Lecture 31 CNN 2: Create the CNN layers.

Lecture 32 CNN 3: Add dense layers.

Lecture 33 CNN 4: Train, run and verify model performance.

Lecture 34 Copyright information.

Section 6: Prevent overfitting.

Lecture 35 Intro to overfitting.

Lecture 36 Understanding the task, data and model

Lecture 37 Expose overfitting.

Lecture 38 Minimize overfitting 1: Apply augmentation.

Lecture 39 Minimize overfitting 2: Use dropout regularization.

Lecture 40 How to approach overfitting in real life.

Lecture 41 Copyright information.

Section 7: Use transfer learning using pre-trained models.

Lecture 42 Intro to transfer learning.

Lecture 43 Load and preprocess the data.

Lecture 44 A quick look at MobileNetV2.

Lecture 45 Create the base model.

Lecture 46 Add more layers for the final model.

Lecture 47 Compile, train and evaluate the model.

Lecture 48 Intro to finetuning.

Lecture 49 Fine-tuning the model and plot the results.

Lecture 50 Make predictions on new images.

Lecture 51 Copyright information.

Section 8: Natural Language Processing (NLP)

Lecture 52 What are word embeddings?

Lecture 53 Visualize word embeddings in the "Embedding Projector"

Lecture 54 Add 1: Handwritten images embeddings.

Lecture 55 Add 2: Handwritten images clustering 1.

Lecture 56 Add 3: Handwritten images clustering 2.

Lecture 57 Text classification of movie reviews.

Lecture 58 Understand and embed the text.

Lecture 59 Vectorize and embed the text.

Lecture 60 Create and train the model and display in TensorBoard.

Lecture 61 Do some predictions.

Lecture 62 Show the text embeddings in "Embedding Projector".

Lecture 63 Copyright information.

Section 9: Writing your own training callbacks.

Lecture 64 Introduction.

Lecture 65 Own callback fit().

Lecture 66 Own callback evaluate().

Lecture 67 Early stopping 1.

Lecture 68 Early stopping 2.

Lecture 69 Adjust learning rate throughout the training.

Lecture 70 Copyright information.

Section 10: Time series, sequences and predictions. A) Single-step models.

Lecture 71 Time series forecasting intro.

Lecture 72 Intro 2.

Lecture 73 Weather forecasting understanding the data.

Lecture 74 Data windowing 1.

Lecture 75 Data windowing 2.

Lecture 76 Data windowing 3.

Lecture 77 Data windowing 4.

Lecture 78 Defining the plot function.

Lecture 79 Include the creation of datasets.

Lecture 80 Single step models: Intro.

Lecture 81 Single step models: Create the baseline model.

Lecture 82 Single step models: Evaluate the baseline model.

Lecture 83 Extend the baseline for 24h.

Lecture 84 Plot the baselines prediction for 1 day.

Lecture 85 Linear model intro.

Lecture 86 A generic compile_and_fit procedure.

Lecture 87 Train the linear model.

Lecture 88 Plot the predictions of the linear model.

Lecture 89 Dense model intro.

Lecture 90 Multi-step dense model.

Lecture 91 The problem with the dense model.

Lecture 92 The solution: Multi-step CNN.

Lecture 93 The recurrent neural network (RNN).

Lecture 94 Analyzing the model performances.

Lecture 95 Copyright information.

Section 11: Time series, sequences and predictions. B) Multi-step models.

Lecture 96 Multi-step models introduction.

Lecture 97 A simple baseline model.

Lecture 98 A more advanced baseline model.

Lecture 99 Single-shot models intro.

Lecture 100 Plot of the linear model.

Lecture 101 Single-shot multi-dense model.

Lecture 102 Single-shot CNN model.

Lecture 103 Single-shot LSTM model (RNN).

Lecture 104 Advanced: The autoregressive RNN model.

Lecture 105 Build the autoregressive model 1.

Lecture 106 Build the autoregressive model 2.

Lecture 107 Train the autoregressive model and plot its predictions.

Lecture 108 Final performance check of all models.

Lecture 109 Copyright information.

Section 12: Congratulations and your personal training plan.

Lecture 110 Congratulations, you made it through this course!

Lecture 111 Your next steps…

Lecture 112 Your personal training plan.

Programmers who like to prepare for the exam to became a TF Certified Developer.,Programmers who like to become a TensorFlow Developer.,Researchers who like to become proficient with TensorFlow.