Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/ivanbongiorni/tensorflow2.0_notebooks
Implementation of a series of Neural Network architectures in TensorFow 2.0
https://github.com/ivanbongiorni/tensorflow2.0_notebooks
autoencoder autograph batch-gradient-descent classifier cnn-classifier convolutional-neural-networks data-science deep-learning dimensionality-reduction forecast-model lstm machine-learning neural-network python python-3 rnn rnn-tensorflow tensorflow tensorflow-tutorials tensorflow2
Last synced: 4 months ago
JSON representation
Implementation of a series of Neural Network architectures in TensorFow 2.0
- Host: GitHub
- URL: https://github.com/ivanbongiorni/tensorflow2.0_notebooks
- Owner: IvanBongiorni
- License: mit
- Created: 2019-03-28T11:14:25.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2021-04-18T01:02:34.000Z (almost 4 years ago)
- Last Synced: 2024-10-10T17:23:10.436Z (4 months ago)
- Topics: autoencoder, autograph, batch-gradient-descent, classifier, cnn-classifier, convolutional-neural-networks, data-science, deep-learning, dimensionality-reduction, forecast-model, lstm, machine-learning, neural-network, python, python-3, rnn, rnn-tensorflow, tensorflow, tensorflow-tutorials, tensorflow2
- Language: Jupyter Notebook
- Homepage:
- Size: 1.66 MB
- Stars: 38
- Watchers: 3
- Forks: 22
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
Author: Ivan Bongiorni, Data Scientist at GfK; [LinkedIn](https://www.linkedin.com/in/ivan-bongiorni-b8a583164/).
# TensorFlow 2.0 Notebooks
This is a collection of my Notebooks on TensorFlow 2.0
The training of models is based on TensorFlow's **eager execution** method. I'll try to minimize referencese to Keras.
## Summary of Contents:
- Basic feed forward stuff
- Autoencoders
- Convolutional Neural Networks
- Recurrent Neural Networks
- Applications to NLP---
---## Contents:
**Basic feed forward stuff**:
1. [Basic classifier](https://github.com/IvanBongiorni/TensorFlow2.0_Notebooks/blob/master/TensorFlow2.0__00.01_basic_Classifier.ipynb): implementation of a **feed forward Classifier** with simple, full-Batch Gradient Descent in **Eager execution**.
2. [Mini batch gradient descent](https://github.com/IvanBongiorni/TensorFlow2.0_Notebooks/blob/master/TensorFlow2.0__00.02_MiniBatch_Gradient_Descent.ipynb): training a model with **Mini Batch Gradient Descent**.
3. [Save and restore models](https://github.com/IvanBongiorni/TensorFlow2.0_Notebooks/blob/master/TensorFlow2.0__00.03_Save_and_Restore_models.ipynb): how to train a model, save it, then restore it and keep training.
0. Train a Neural Network with frozen layers
---
**Autoencoders**:
1. [Autoencoder for dimensionality reduction](https://github.com/IvanBongiorni/TensorFlow2.0_Notebooks/blob/master/TensorFlow2.0__02.01_Autoencoder_for_Dimensionality_Reduction.ipynb): implementation of a stacked **Autoencoder for dimensionality reduction** of datasets.
2. Denoising Autoencoder (see CNN section below).
0. Recurrent Autoencoder (see RNN section below).
---
**Convolutional Neural Networks**:
1. [Basic CNN classifier](https://github.com/IvanBongiorni/TensorFlow2.0_Notebooks/blob/master/TensorFlow2.0__03.01_Convolutional_Neural_Network.ipynb): a basic **Convolutional Neural Network** for multiclass classification.
2. Advanced CNN classifier with custom data augmentation.
3. Mixed-CNN classifier.
4. Denoising Autoencoder.
---
**Recurrent Neural Networks**:
1. [LSTM many-to-one forecast model](https://github.com/IvanBongiorni/TensorFlow2.0_Notebooks/blob/master/TensorFlow2.0__04.01_RNN_many2one.ipynb)
2. [LSTM many-to-many forecast model](https://github.com/IvanBongiorni/TensorFlow2.0_Notebooks/blob/master/TensorFlow2.0__04.02_RNN_many2many.ipynb)
3. [Multivariate LSTM regression](https://github.com/IvanBongiorni/TensorFlow2.0_Notebooks/blob/master/TensorFlow2__04.03_RNN_multivariate_regression.ipynb).
0. Seq2seq models.
---
**RNN + Natural Language Processing**
1. LSTM [Text generator](https://github.com/IvanBongiorni/TensorFlow2-RNN_text_generator-Dante_DivineComedy/blob/master/RNN_text_generator_00.ipynb) from [this repository of mine](https://github.com/IvanBongiorni/TensorFlow2-RNN_text_generator-Dante_DivineComedy).