Skip to content

Instantly share code, notes, and snippets.

View yoninachmany's full-sized avatar

Yoni Nachmany yoninachmany

92 followers · 467 following
View GitHub Profile
@yoninachmany
yoninachmany / index.html
Last active December 7, 2020 05:00
<html class="html">
<head>
<meta charset="UTF-8">
<title>Urban Scratchoff</title>
<link rel="stylesheet" href="https://unpkg.com/leaflet@1.7.1/dist/leaflet.css" />
<link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/css/bootstrap.min.css">
<style type="text/css">
html, body, .container {
height: 100%;
width: 100%;
@yoninachmany
yoninachmany / README.md
Last active July 11, 2019 10:04

If models not already downloaded in /home/ubuntu/models/ (need 8.6 G)

  1. Make models directory: sudo mkdir /home/ubuntu/models
  2. For view classification model: in models directory, download clf_urls.txt and run wget -i clf_urls.txt
  3. For image segmentation models: in models directory, download seg_urls.txt and run wget -i seg_urls.txt

Before running

  1. Replace ./models/ with /home/ubuntu/models/ in Python files

To run on your own study 0. If data comes from AWS, configure credentials: aws configure

@yoninachmany
yoninachmany / foss4g.md
Last active April 15, 2019 18:25
Deep Transfer Learning for Land Cover Classification on Open Multispectral Satellite Imagery

Automatic large-scale mapping of land cover classes facilitates applications in sustainable development, agriculture, and urban planning, and is therefore a commonly studied topic in remote sensing image processing, but typical deep learning approaches use models pretrained on everyday image datasets like ImageNet and retrain them using only three channels (usually RGB), not fully leveraging the unique properties and spectral information of multispectral satellite images.

The latest approach in our series of approaches, powered by new open satellite imagery datasets like BigEarthNet and machine learning libraries like fast.ai and eo-learn, explores the effect of pre-training convolutional neural networks on mul

@yoninachmany
yoninachmany / hw4.md
Last active February 18, 2019 18:14

Background

Last week, you trained an image classifier with modern machine learning methods to achieve state-of-the-art results, making use of transfer learning from the ImageNet dataset, which was collected with large-scale crowdsourcing.

AI encodes and magnifies bias, and Google researchers found that ImageNet and another popular dataset called Open Images "appear to exhibit an observable amerocentric and eurocentric representation bias," as demonstrated by the distribution of geographically identifiable images in the datasets, with 2/3 of the images from the Western world.

Chart from 'No Classification without Representation'

In addition, classifiers trained on the datasets show "strong differences in the relative performance on imag

@yoninachmany
yoninachmany / ghana.geojson
Created November 21, 2018 19:30
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@yoninachmany
yoninachmany / find_gap.py
Created September 9, 2018 23:41
#!/usr/bin/env python
import rospy
from sensor_msgs.msg import LaserScan
from geometry_msgs.msg import Vector3
from a_stars_gap_finding.msg import gaps
import math
import numpy as np
from time import time
@yoninachmany
yoninachmany / ranges
Last active September 9, 2018 23:40
ranges: [3.6582884788513184, 3.7396106719970703, 3.7712321281433105, 3.818552255630493, 3.885111093521118, 3.956218719482422, 4.017431259155273, 4.102952480316162, 4.155635833740234, 4.228012561798096, 4.300711154937744, 4.382401466369629, 4.448051929473877, 4.535812854766846, 4.606029033660889, 4.71834659576416, 4.795755386352539, 4.913707733154297, 5.017602920532227, 5.109529972076416, 5.225459098815918, 5.351624965667725, 5.452360153198242, 5.5881242752075195, 5.697434902191162, 5.827081680297852, 5.992712020874023, 6.131065368652344, 6.306288242340088, 6.469939708709717, 6.54928731918335, 6.61983585357666, 6.671141147613525, 6.733158588409424, 6.812592506408691, 6.896204948425293, 6.958384990692139, 7.0107645988464355, 7.111623287200928, 7.206821441650391, 7.275625228881836, 7.379377841949463, 7.440603733062744, 7.5278849601745605, 7.601227283477783, 7.686923027038574, 7.783066749572754, 7.853481769561768, 7.911307334899902, 7.968475818634033, 8.03852653503418, 8.10891056060791, 8.16934871673584, 8.198782
@yoninachmany
yoninachmany / DAO.sol
Created April 15, 2017 16:31
pragma solidity ^0.4.8;
contract StandardToken{
address public owner = msg.sender;
// This contract only defines a modifier but does not use
// it - it will be used in derived contracts.
// The function body is inserted where the special symbol
// "_;" in the definition of a modifier appears.
// This means that if the owner calls this function, the
// function is executed and otherwise, an exception is
@yoninachmany
yoninachmany / TokenExchange.sol
Last active April 3, 2017 04:02
pragma solidity ^0.4.8;
contract Token {
/// @return total amount of tokens
function totalSupply() constant returns (uint256 supply) {}
/// @param _owner The address from which the balance will be retrieved
/// @return The balance
function balanceOf(address _owner) constant returns (uint256 balance) {}
/// @notice send `_value` token to `_to` from `msg.sender`
/// @param _to The address of the recipient
@yoninachmany
yoninachmany / YCash.sol
Created March 14, 2017 16:23
pragma solidity ^0.4.8;
/// Contract that follows ERC token standard (https://github.com/ethereum/EIPs/issues/20).
contract YCash {
uint256 supply;
mapping (address => uint256) balances;
mapping (address => mapping (address => uint256)) allowances;
bool isApproved;
event Transfer(address indexed _from, address indexed _to, uint256 _value);