Skip to content
프로젝트 카테고리

머신러닝 · GitHub

모델 학습, 평가, 추론 프레임워크를 찾고 커뮤니티의 관심도를 비교하세요.

유용한 GitHub 프로젝트

12,809 프로젝트

PyHessian

amirgholami

797스타
PyHessian preview

PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks

머신러닝Jupyter NotebookMITGitHub

mlx3D

amirhossein-razlighi

43스타
mlx3D preview

Differentiable 3D computer vision on Apple Silicon, built on MLX — meshes, NeRF, and 3D Gaussian Splatting with Metal kernels

  • Structures — batched Meshes / Pointclouds with list, packed and padded views; differentiable normals, areas, edges.
  • Cameras & transforms — OpenCV/COLMAP-convention pinhole cameras (ray generation, projection, look-at) and batched rotation conversions (quaternion, axis-angle, Euler, 6D).

Python-Learning

AmirHosseinBabaeayan

226스타

This repository is dedicated to Python courses with a focus on artificial intelligence, data science, and practical machine learning. I have been conducting these courses in various levels since 2021.

머신러닝Jupyter NotebookGitHub

Fake-News-Detector

AmirhosseinHonardoust

112스타
Fake-News-Detector preview

A professional TF-IDF + Logistic Regression style-risk classifier for educational fake-news detection, with a Streamlit dashboard, honest evaluation, uncertainty handling, and leakage analysis.

  • TF-IDF vectorization with word n-grams for text feature extraction
  • Logistic Regression baseline classifier

Handwritten-Digit-GAN

AmirhosseinHonardoust

29스타
Handwritten-Digit-GAN preview

A PyTorch implementation of a Deep Convolutional GAN (DCGAN) trained on MNIST. Includes training scripts, generator & discriminator models, random sample generation, latent space interpolation, and loss curve visualization to create realistic handwritten digit images.

  • DCGAN architecture in PyTorch (transposed-convolution Generator, convolutional Discriminator)
  • Trainable on MNIST by default, with a CIFAR-10 path built in

Image-Captioning-CNN-LSTM

AmirhosseinHonardoust

44스타
Image-Captioning-CNN-LSTM preview

An end-to-end image captioning project using a CNN encoder (ResNet-50) and LSTM decoder in PyTorch. Includes vocabulary building, preprocessing, training with BLEU evaluation, and inference. Generates natural language captions for images with saved metrics, model checkpoints, and visualization outputs.

  • CNN-LSTM encoder-decoder architecture
  • ResNet-50 image encoder

Image-Classification-CNN

AmirhosseinHonardoust

27스타
Image-Classification-CNN preview

Image classification with PyTorch using Convolutional Neural Networks (CNNs). Trains on MNIST with convolution, pooling, and fully connected layers. Achieves over 99% accuracy with early stopping and checkpoints. Includes training/evaluation scripts, metrics, confusion matrix, training curves, and sample prediction visualizations.

  • CNN architecture with two convolution + ReLU + pooling blocks followed by fully connected layers
  • Adam optimizer with CrossEntropyLoss

Sentiment-Analysis-BERT

AmirhosseinHonardoust

37스타
Sentiment-Analysis-BERT preview

End-to-end sentiment analysis of tweets using BERT. Includes preprocessing, training, and evaluation with classification reports, confusion matrices, ROC curves, and word clouds. Demonstrates fine-tuning of transformer models for text classification with modular, reproducible code.

  • Shared preprocessing pipeline producing consistent train.csv / val.csv / test.csv splits
  • BERT fine-tuning via Hugging Face Transformers (bert-base-uncased)

Sentiment-Analysis-NLP

AmirhosseinHonardoust

26스타
Sentiment-Analysis-NLP preview

Customer reviews sentiment analysis with Python and NLP. Generates a synthetic dataset of positive, neutral, and negative reviews, applies preprocessing (tokenization, stopwords, lemmatization), and builds TF-IDF features. Trains classifiers (Naive Bayes, Logistic Regression, Random Forest) with evaluation, confusion matrix and top features.

  • TF-IDF vectorization with unigrams + bigrams (min_df=2, up to 50,000 features)
  • Three-model comparison: Multinomial Naive Bayes, Logistic Regression, Random Forest

hackermath

amitkaps

1,453스타
hackermath preview

Introduction to Statistics and Basics of Mathematics for Data Science - The Hacker's Way

머신러닝Jupyter NotebookMITGitHub

ampyfin

AmpyFin

426스타

End-to-end ensemble trading framework that trains, backtests, and promotes validated strategies to live execution.