Gin's repositories
Practical_Python_Programming
北邮《Python编程与实践》课程资料
100-Days-Of-ML-Code
100-Days-Of-ML-Code中文版
annotated_deep_learning_paper_implementations
🧑🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
cnn_vti_inversion
Determination of the elastic parameters of a VTI medium from sonic logging data using deep learning
d2l-zh
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被60多个国家的400多所大学用于教学。
deep-learning-with-python-notebooks
Jupyter notebooks for the code samples of the book "Deep Learning with Python"
deeplearning-with-tensorflow-notes
龙曲良《TensorFlow深度学习》学习笔记及代码，采用TensorFlow2.0.0版本
DeepUnderstandingOfDeepLearning
Python code accompanying the course "A deep understanding of deep learning (with Python intro)"
dsmnet
Deep learning seismic waveform inversion using pydsm
ginan
The Australian Government, through Positioning Australia (part of Geoscience Australia), is funding the design, development and operational service of a Global Navigation Satellite System (GNSS) position correction system - the Ginan service and toolkit. The application of the Ginan correction service by a GNSS device has the potential to increase positioning accuracy from meters to centimetres across Australia. The suite of software systems in this repository (the Ginan toolkit) will be used to create the service. It is available now under an open source licence. Ginan will give individuals and organisations no-cost access to the Ginan software and service as a public good.
gravity-processing
Lesson on processing ground survey gravimetry data for geophysics
gravity-toolkit
Python tools for working with spherical harmonic coefficients from the GRACE and GRACE Follow-On missions
NumPy-Pandas-Matplotlib-Scikit-Learn-VanderPlas-2023
These examples provide an introduction to Data Science and classic Machine Learning using NumPy, Pandas, Matplotlib, and Scikit-learn. They are taken, with some changes, from the book "Python Data Science Handbook: Essential Tools for Working with Data", Second Edition, written by Jake VanderPlas and published by O'Reilly in 2023.
seismic-classification
Seismic events such as Earthquakes are very under-researched in global scientific domains but, with advancements in Machine Learning, classification and analysis of seismic data is becoming more feasible. This project focuses on developing techniques to effectively classify Seismic data into earthquake events and seismic noise (mining blasts, man-made noise etc.). The project not only focuses on developing deep learning models but, is also focused on collecting seismic data from credible repositories with proper labelling. An extensive research in seismology ensued proper knowledge of Earthquake waves, their propagation and behavior. Main motivation behind this project is to defy already accepted triggering (STA/LTA, Z Transform etc.) as well as Picking (AR picker, baer picker etc.) algorithms and formulate new techniques to extract P and S wave features. Problem with these algorithms is that different threshold values can produce entirely different triggers and accurate thresholds are hard to generalize for large number of events.
seismology101
Tutorials for absolute beginners in Seismology
SPECFEM3D_ANAT
A shell-script driven ambient noise adjoint tomography (ANAT) inversion package
time-series-analysis
Collection of notebooks for time series analysis