techniques
d2l-en
| techniques | d2l-en | |
|---|---|---|
| 9 | 6 | |
| 7,865 | 21,922 | |
| 2.7% | 2.3% | |
| 8.8 | 8.5 | |
| 8 days ago | 9 days ago | |
| Python | ||
| Apache License 2.0 | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
techniques
- What satellite image analytics are in demand now?
-
Tools for object detection on satellite images
This repo has been useful to me: https://github.com/satellite-image-deep-learning/techniques
-
How to convert big TIF image to smaller jpgs
Here's an extensive github collection on anything related https://github.com/robmarkcole/satellite-image-deep-learning
- Deep Learning for Remote Sensing
- If you want to learn about Machine Learning on Satellite Imagery, this constantly updated github repo has links to hundreds of different tutorials
- CNN in satellite images
-
Sony teases ‘breakthrough AI project’ created with Gran Turismo studio Polyphony
Out of pure curiousity I checked and though theres a bunch of specialised categorisation/segmentation tools like the ones in the link, I didn't find any explicitly for generating realtime 3d assets: https://github.com/robmarkcole/satellite-image-deep-learning
- robmarkcole/satellite-image-deep-learning: Resources for deep learning with satellite & aerial imagery (incredibly comprehensive)
- Skills for a career in Remote Sensing?
d2l-en
- which book to chose for deep learning :lan Goodfellow or francois chollet
- d2l-en: Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 400 universities from 60 countries including Stanford, MIT, Harvard, and Cambridge.
-
How to pre-train BERT on different objective tasks using HuggingFace
There might is bert library for pre-train bert model in huggingface, But I suggestion that you train bert model in native pytorch to understand detail, Limu's course is recommended for you
-
The Transformer in Machine Translation
GitHub's article on Dive into Deep Learning
- D2l-En
-
I created a way to learn machine learning through Jupyter
There are actually some online books and courses built on Jupyter Notebook ([Dive to Deep Learning Book](https://github.com/d2l-ai/d2l-en) for example). However yours is more detail and could really helps beginners.
What are some alternatives?
awesome-satellite-imagery-datasets - 🛰️ List of satellite image training datasets with annotations for computer vision and deep learning
Pytorch-UNet - PyTorch implementation of the U-Net for image semantic segmentation with high quality images
AnimeGANv3 - Use AnimeGANv3 to make your own animation works, including turning photos or videos into anime.
DeepADoTS - Repository of the paper "A Systematic Evaluation of Deep Anomaly Detection Methods for Time Series".
godot-tensorflow-workspace - Machine learning for Godot Engine
TF-Watcher - Monitor your ML jobs on mobile devices📱, especially for Google Colab / Kaggle
datasets-for-good - List of datasets to apply stats/machine learning/technology to the world of social good.
99-ML-Learning-Projects - A list of 99 machine learning projects for anyone interested to learn from coding and building projects
ml4eo-bootcamp-2021 - Machine Learning for Earth Observation Training of Trainers Bootcamp
imbalanced-regression - [ICML 2021, Long Talk] Delving into Deep Imbalanced Regression
EESRGAN - Small-Object Detection in Remote Sensing (satellite) Images with End-to-End Edge-Enhanced GAN and Object Detector Network
petastorm - Petastorm library enables single machine or distributed training and evaluation of deep learning models from datasets in Apache Parquet format. It supports ML frameworks such as Tensorflow, Pytorch, and PySpark and can be used from pure Python code.