Skip to content

Instantly share code, notes, and snippets.

Show Gist options
  • Save HabibMrad/dc4d59bd3461055f08e0d9b269606fc6 to your computer and use it in GitHub Desktop.
Save HabibMrad/dc4d59bd3461055f08e0d9b269606fc6 to your computer and use it in GitHub Desktop.
Image Processing with Keras in Python.ipynb
Display the source blob
Display the rendered blob
Raw
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "Image Processing with Keras in Python.ipynb",
"provenance": [],
"collapsed_sections": [],
"authorship_tag": "ABX9TyPVeaQRfgl7wnwXND5YNDA5",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/michaelmallari/05a2639cbc034b591eb4f142c3cdc704/image-processing-with-keras-in-python.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "gAlRe3G-S2Lv",
"colab_type": "text"
},
"source": [
"# Image Processing with Keras in Python (DataCamp)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "6IG7zym2S3jl",
"colab_type": "text"
},
"source": [
"\n",
"---\n",
"\n",
"## Ch. 1 - Image Processing With Neural Networks\n",
"\n",
"### Introducing convolutional neural networks\n",
"\n",
"### Images as data: visualizations\n",
"\n",
"### Images as data: changing images\n",
"\n",
"### Classifying images\n",
"\n",
"### Using one-hot encoding to represent images\n",
"\n",
"### Evaluating a classifier\n",
"\n",
"### Classification with Keras\n",
"\n",
"### Build a neural network\n",
"\n",
"### Compile a neural network\n",
"\n",
"### Fitting a neural network model to clothing data\n",
"\n",
"### Cross-validation for neural network evaluation"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "CFJ_zxFmS41M",
"colab_type": "text"
},
"source": [
"\n",
"---\n",
"\n",
"## Ch. 2 - Using Convolutions\n",
"\n",
"### Convolutions\n",
"\n",
"### One dimensional convolutions\n",
"\n",
"### Image convolutions\n",
"\n",
"### Defining image convolution kernels\n",
"\n",
"### Implementing image convolutions in Keras\n",
"\n",
"### Convolutional network for image classification\n",
"\n",
"### Training a CNN to classify clothing types\n",
"\n",
"### Evaluating a CNN with test data\n",
"\n",
"### Tweaking your convolutions\n",
"\n",
"### Add padding to a CNN\n",
"\n",
"### Add strides to a convolutional network\n",
"\n",
"### Calculate the size of convolutional layer output"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "J1ecybGaS6DW",
"colab_type": "text"
},
"source": [
"\n",
"---\n",
"\n",
"## Ch. 3 - Going Deeper\n",
"\n",
"### Going deeper\n",
"\n",
"### Creating a deep learning network\n",
"\n",
"### Train a deep CNN to classify clothing images\n",
"\n",
"### What is special about a deep network?\n",
"\n",
"### How many parameters?\n",
"\n",
"### How many parameters in a CNN?\n",
"\n",
"### How many parameters in a deep CNN?\n",
"\n",
"### Pooling operations\n",
"\n",
"### Write your own pooling operation\n",
"\n",
"### Keras pooling layers\n",
"\n",
"### Train a deep CNN with pooling to classify images"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "xy7bnZyVS7YN",
"colab_type": "text"
},
"source": [
"\n",
"---\n",
"\n",
"## Ch. 4 - Understanding and Improving Deep Convolutional Networks\n",
"\n",
"### Tracking learning\n",
"\n",
"### Plot the learning curves\n",
"\n",
"### Using stored weights to predict in a test set\n",
"\n",
"### Regularization\n",
"\n",
"### Adding dropout to your network\n",
"\n",
"### Add batch normalization to your network\n",
"\n",
"### Interpreting the model\n",
"\n",
"### Extracting a kernel from a trained network\n",
"\n",
"### Shape of the weights\n",
"\n",
"### Visualizing kernel responses\n",
"\n",
"### Next steps"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "YvrkLaJ_S8i-",
"colab_type": "text"
},
"source": [
"\n",
"---\n",
"\n",
"#### About Michael Mallari\n",
"\n",
"Michael is a [hybrid thinker and doer](http://www.michaelmallari.com)—a byproduct of being a [StrengthsFinder \"Learner\"](https://news.gallup.com/businessjournal/694/learner.aspx) over time. With nearly 20 years of engineering, design, and product experience, he helps organizations identify market needs, mobilize internal and external resources, and deliver delightful digital customer experiences that align with business goals. He has been entrusted with problem-solving for brands—ranging from Fortune 500 companies to early-stage startups to not-for-profit organizations.\n",
"\n",
"Michael earned his BS in Computer Science from New York Institute of Technology and his MBA from the University of Maryland, College Park. He is also a candidate to receive his MS in Applied Analytics from Columbia University.\n",
"\n",
"[LinkedIn](https://www.linkedin.com/in/mmallari) | [Twitter](https://twitter.com/MichaelMallari) | [michaelmallari.com](http://www.michaelmallari.com)"
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment