aws-samples / Aws Ai Bootcamp Labs
Licence: apache-2.0
This library holds a collection of Notebooks and code examples for AWS AI Bootcamps.
Stars: ✭ 107
Labels
Projects that are alternatives of or similar to Aws Ai Bootcamp Labs
Msu Datascience Ml Tutorial 2018
Machine learning with Python tutorial at MSU Data Science 2018
Stars: ✭ 106 (-0.93%)
Mutual labels: jupyter-notebook
Beymani
Hadoop, Spark and Storm based anomaly detection implementations for data quality, cyber security, fraud detection etc.
Stars: ✭ 106 (-0.93%)
Mutual labels: jupyter-notebook
Amazon Sagemaker Stock Prediction Archived
Workshop to demonstrate how to apply NN based algorithms to stock market data and forecast price movements.
Stars: ✭ 106 (-0.93%)
Mutual labels: jupyter-notebook
Are You Fake News
Bias detection in the news. Back and front end for areyoufakenews.com
Stars: ✭ 105 (-1.87%)
Mutual labels: jupyter-notebook
Cnn Yelp Challenge 2016 Sentiment Classification
IPython Notebook for training a word-level Convolutional Neural Network model for sentiment classification task on Yelp-Challenge-2016 review dataset.
Stars: ✭ 106 (-0.93%)
Mutual labels: jupyter-notebook
Sklearn tutorial
Materials for my scikit-learn tutorial
Stars: ✭ 1,521 (+1321.5%)
Mutual labels: jupyter-notebook
Capsnet
CapsNet (from "Dynamic Routing Between Capsules") implemented in pytorch.
Stars: ✭ 107 (+0%)
Mutual labels: jupyter-notebook
Cs570
Code for CS570, Essentials of Data Science
Stars: ✭ 106 (-0.93%)
Mutual labels: jupyter-notebook
Bilibli notes2
攻城狮之家B站视频课程课件合集2,1号仓库https://github.com/JokerJohn/bilibili_notes.git
Stars: ✭ 107 (+0%)
Mutual labels: jupyter-notebook
Jupyterworkflow
Reproducible Data Analysis Workflow in Jupyter
Stars: ✭ 106 (-0.93%)
Mutual labels: jupyter-notebook
Stylegan2 Projecting Images
Projecting images to latent space with StyleGAN2.
Stars: ✭ 102 (-4.67%)
Mutual labels: jupyter-notebook
Dog Breeds Classification
Set of scripts and data for reproducing dog breed classification model training, analysis, and inference.
Stars: ✭ 105 (-1.87%)
Mutual labels: jupyter-notebook
Reinforcement learning
Reinforcement Learning research
Stars: ✭ 107 (+0%)
Mutual labels: jupyter-notebook
Bayesian Methods For Ml
Materials for "Bayesian Methods for Machine Learning" Coursera MOOC
Stars: ✭ 107 (+0%)
Mutual labels: jupyter-notebook
Bingham Rotation Learning
A Smooth Representation of SO(3) for Deep Rotation Learning with Uncertainty.
Stars: ✭ 106 (-0.93%)
Mutual labels: jupyter-notebook
AWS-AI-Bootcamp-Labs
This library has a collection of Notebooks and code examples for AWS AI Bootcamps.
Content
Amazon Rekognition Demo Notebook
Amazon Comprehend Demo Notebook
Amazon Machine Learning Demo Notebook
Serverless Predictions at Scale
Launch EC2 instance using the deep learning AMI and open fashion MNIST MXNet demo
- Create EC2 IAM role for the workshop as described here. We will apply permission policies as documented in each notebook
- Launch EC2 Instance using the Ubuntu deep learning AMI in eu-west-1, Ireland (p2.xlarge - $0.972/hour) http://amzn.to/2j3FdOZ
- Connect via SSH and tunnel port 8888:
- Linux, Mac:
ssh -i user.pem -L 8888:localhost:8888 [email protected]
- Windows:
- Follow the instructions here to download PuTTY and to convert your private key
- Host Name:
[email protected]
- Expand Connection and choose Auth, select your .ppk file
- Expand Connection > SSH, choose Tunnels, specify Source Port:
8888
, Destination:localhost:8888
- Choose Add and Open
- Linux, Mac:
- Clone aws-ai-bootcamp-labs github repository
git clone https://github.com/awslabs/aws-ai-bootcamp-labs
- Start jupyter notebook:
nohup jupyter notebook &
-
tail nohup.out
to get the login token- look for
http://localhost:8888/?token=<your_login_token>
- look for
- Open demo notebook (FashionMNIST_MXNet_Demo.ipynb)
- Select Kernel > Change kernel > Python 2
- Follow steps in notebook
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].