Caleb Robinson calebrob6
calebrob6
/ Download seasonal data from PC.ipynb
Created
April 9, 2023 23:15
An example of how to download seasonal patches from the Planetary Computer
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
calebrob6
/ Example for creating a Landsat and NLCD dataset.ipynb
Created
April 7, 2023 22:01
Example notebook that shows how to create TorchGeo datasets from Landsat and NLCD data downloaded from the Planetary Computer.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env python | |
| """""" | |
| import argparse | |
| import math | |
| import os | |
| import time | |
| import numpy as np | |
| import rasterio |
calebrob6
/ Finetuning with TorchGeo pre-trained models.ipynb
Created
February 8, 2023 21:58
Example notebook that shows how to do linear-probing with a TorchGeo pre-trained model.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
calebrob6
/ fast_ious.ipynb
Last active
February 2, 2023 19:05
This notebook compares the speed of scikit-learn's implementation for computing the per-class IoU between two arrays to a simple custom implementation with numpy. We find that the custom implementation scales better by a constant exponent.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
calebrob6
/ landcoverai_randomforest.py
Created
January 22, 2023 18:21
Script for training a random forest on the LandCover.AI dataset
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import time | |
| import numpy as np | |
| from sklearn.ensemble import RandomForestClassifier | |
| from sklearn.metrics import jaccard_score | |
| from torch.utils.data import DataLoader | |
| from tqdm import tqdm | |
| from torchgeo.datasets import LandCoverAI |
calebrob6
/ Chesapeake training example.ipynb
Created
December 21, 2022 21:10
Example of how to use TorchGeo to train a semantic segmentation model on the ChesapeakeCVPR dataset.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
calebrob6
/ bing_geodata_api.py
Created
November 24, 2022 00:15
A class / command line script for interacting with Bing's Geodata API -- https://learn.microsoft.com/en-us/bingmaps/spatial-data-services/geodata-api
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import argparse | |
| import math | |
| import time | |
| import fiona | |
| import fiona.transform | |
| import requests | |
| import shapely.geometry | |
calebrob6
/ Torchgeo EuroSAT training demo.ipynb
Created
November 3, 2022 17:11
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
calebrob6
/ Greedy polygon merging.ipynb
Created
October 26, 2022 04:55
A notebook that merges adjacent polygons up to a maximum area cutoff
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.