Cnn

EasyOCRPython

A ready-to-use OCR Python library supporting 80+ languages and popular writing scripts like Latin, Chinese, Arabic, and Cyrillic.

pytorch-grad-camPython

A PyTorch library providing state-of-the-art methods for generating visual explanations (Class Activation Maps) for computer vision models.

libfacedetectionC++

A high-performance CNN-based face detection library written in pure C++ with SIMD optimizations, achieving up to 1000 FPS.

cnn-explainerJavaScript

An interactive visualization system for learning how Convolutional Neural Networks work through hands-on exploration.

stockpredictionaiJavaScript

A complete AI-driven process using GANs with LSTM and CNN to predict stock price movements, incorporating diverse data sources and hyperparameter optimization.

SRGANPython

Implementation of SRGAN for photo-realistic single image super-resolution using generative adversarial networks.

captcha_trainerPython

A deep learning framework for training image classification models to solve complex captcha and OCR tasks.

cnn_captchaPython

A TensorFlow-based CNN solution for recognizing character-based CAPTCHAs, providing training, validation, and API modules.

Education

A curated collection of high-quality deep learning resources, including courses, books, papers, libraries, and datasets.

MatConvNet: CNNs for MATLABCuda

A MATLAB toolbox implementing Convolutional Neural Networks (CNNs) for computer vision applications.

QANetPython

A TensorFlow implementation of QANet for machine reading comprehension on the SQuAD dataset.

LLVIPJupyter Notebook

A visible-infrared paired dataset for low-light vision tasks like pedestrian detection, image fusion, and image-to-image translation.

Character-Aware Neural Language ModelsPython

TensorFlow implementation of character-aware neural language models using CNN, highway networks, and LSTM.

Terry Um’s TensorFlow ExercisesJupyter Notebook

A collection of TensorFlow practice exercises covering fundamental machine learning concepts from linear regression to CNNs.

cnn_handwritten_chinese_recognitionPython

A web application that uses a CNN model to recognize handwritten Chinese characters from an online drawing canvas.

neural-fortranFortran

A parallel deep learning framework written in modern Fortran for training and inference of dense, convolutional, and transformer networks.

Crop Yield PredictionPython

Deep learning models for crop yield prediction using remote sensing data, with CNN/LSTM and Gaussian Process approaches.

Chinese-Character-RecognitionPython

A TensorFlow CNN implementation for Chinese character recognition, achieving 92.5% top-1 accuracy with batch normalization.

BeautyNetPython

A simple, flexible, and extensible object-oriented template for PyTorch projects.

mmWave-localization-learningPython

A machine learning algorithm for accurate, energy-efficient outdoor positioning using 5G mmWave beamformed fingerprints.

Introduction to Deep Learning Using Python (GitHub)Python

A hands-on workshop introducing deep learning concepts with practical examples using neural networks, CNNs, RNNs, and autoencoders.

Hyperopt for a Keras CNN on CIFAR-100Python

A tutorial and demo using Hyperopt to auto-optimize CNN architecture and hyperparameters for the CIFAR-100 dataset with Keras/TensorFlow.