Comments (6)
Watched and implemented this, it was useful:
https://youtu.be/CAeWjoP525M?si=k-iceKTo34cPQ4g0
from hm.jetscapeml.
Project Structure
-
Identify The Problem: Jet event paramters (energy loss,
$alpha_s$ , and$Q_0$ ) values classification -
Have A Plan
- Implmenting/training/testing machine learning (ML) and deep learning models until finding successfull classifier models with high fidelity
- Technology Stack: Python, Tensorflow, Colab, Grib, GPU, Kaggle, [Todo: Hadoop File System]
-
Structure Your Directories
Including one directory for models, and one directory for each parameters (jet_parameters-> [param_name]) -
Use Version Control: Github
-
Modularize and Componentize Your Code: Having short, reusable, and easy to understand componets
-
Documentation: A directory in the project root for general documentations, having following documents will helps
- Installiation guideline
- Troubleshooting guideline
- Contribution guideline
- Issue template
-
Testing
- Unit Testing
- Integration Testing
-
Dependency Management
- pip
-
CI & CD: Google Test (If applicable), Github actions, [A website that shows the classifier resutls (maybe in annimation)]
-
Code Review
from hm.jetscapeml.
another useful one
https://youtu.be/MaIfDPuSlw8?si=-flYixkx1QzTGBnW
from hm.jetscapeml.
for now, it's a good idea to go with cookiecutter structure and choose what's the best for the project meanwhile
from hm.jetscapeml.
having a preprocess_dataset.py and model_validation.py can be useful for each parameter classification folder, I'm trying to practice this to see how practical it is for our case
from hm.jetscapeml.
adding an scirpt _ruuner directory can help to keep the code base clean
from hm.jetscapeml.
Related Issues (20)
- building dataset with the size of 1k, 10k, 100k, 1m events from the mixed dataset HOT 1
- implementing cloud point classifier model HOT 1
- Implementing and training previous ML models with the different dataset size and draw error bar of them HOT 2
- Implement a visualization code two show a sample events in the array formal, 2-D plot format, and 3D cloud point representation HOT 1
- Implementing pointnet binary classifier model for eloss with k-folding for all dataset HOT 1
- Impmenting a Diffusion model to produce an event by getting eloss, alpha_s, and q0 params
- Implementing synthesis model based on pointnet HOT 1
- Implementing/Training PointNet for alpha_s with various epochs and folds and finding the best learning rate HOT 18
- Implementing GridSearchCV Hyper Tuning for PointNet to classify alpha_s HOT 3
- implementing/training pointnet for eloss with various 100 epochs and 1 fold various dataset sizes
- Making croissant metadata
- Refactoring project structure
- alpha_s Classification with MNIST Net
- alpha_s Classification with VGG16 Net HOT 1
- alpha_s Classification with Point Net
- alpha_s Classification with GAN
- alpha_s Classification with Transfer Learning
- alpha_s Classification with Test Net HOT 1
- Implementing Validation methods for alpha_s models HOT 5
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from hm.jetscapeml.