This repository has the code for the Hands-on Deep Learning: TensorFlow Coding Sessions. The videos will be uploaded on a weekly basis.
The series consist of the introductory TensorFlow tutorials outlined below:
| # | Tutorial | Code | Video |
|---|---|---|---|
| 1 | Introduction to TensorFlow: graphs, sessions, constants, and variables | S1 and S1_notebook.ipynb | Video #1 |
| 2 | Training a multilayer perceptron | S2_live.py | Video #2 |
| 3 | Setting up the training and validation pipeline | S3_live.py | Video #3 |
| 4 | Regularization, saving and resuming from checkpoints, and TensorBoard | S4_live.py | Video #4 |
| 5 | Convolutional neural networks, batchnorm, learning rate schedules, optimizers | S5_live.py | Video #5 |
| 6 | Converting a dataset into TFRecords, training an image classifier, and freezing the model for deployment | S6 | Video #6 |
| 7 | Transfer learning: fine tuning a model in TensorFlow | S7 | Video #7 |
| 8 | Using a Python iterator as a data generator and training a denoising autoencoder | S8 | N/A |
| 9 | What is new in TensorFlow 2.0 [new] | S9 | Video #8 |
A series of mini-lectures on the fundamentals of machine learning, with a focus on neural networks and deep learning.
- Lecture #1: Introduction
- Lecture #2: Artificial Neural Networks Demystified
- Lecture #3: Artificial Neural Networks: Going Deeper
- Lecture #4: Overfitting, Underfitting, and Model Capacity
- Lecture #5: Regularization
- Lecture #6: Data Collection and Preprocessing
- Lecture #7: Convolutional Neural Networks Explained
- Lecture #8: How to Design a Convolutional Neural Network
- Lecture #9: Transfer Learning
- Lecture #10: Optimization Tricks: momentum, batch-norm, and more
- Lecture #11: Recurrent Neural Networks
- Lecture #12: Deep Unsupervised Learning
- Lecture #13: Generative Adversarial Networks
- Lecture #14: Practical Methodology in Deep Learning