Mohd Fitri Alif Bin Mohd Kasai's repositories
4-simple-steps-in-Builiding-OCR
Optical character recognition (OCR) is process of classification of opti- cal patterns contained in a digital image. The character recognition is achieved through segmentation, feature extraction and classification. Keras Deep learning Network is used at here in recognising the Text characters and OpenCV is used in segmenting the text and Noise normalization.
Alpha-Car
Alpha car (딥러닝 기반 자율 주행 버스 RC카)
attention-is-all-you-need-keras-1
Implementation of the Transformer architecture described by Vaswani et al. in "Attention Is All You Need"
AutoAugment
Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow
awesome-datascience
:memo: An awesome Data Science repository to learn and apply for real world problems.
awesome-zero-shot-learning
A curated list of papers, code and resources pertaining to zero shot learning
awsome-domain-adaptation
A collection of AWESOME things about domian adaptation
cpp-sdk-samples
Example apps for the Affdex SDK for Windows and Linux
Data-Augmentation-for-Building-an-Ensemble-of-Convolutional-Neural-Networks
Data Augmentation for Building an Ensemble of Convolutional Neural Networks
Dataset_Preparation_For_Fer2013
Dataset Preparation software version that allows you to prepare the Fer2013 dataset for training a neural network capable of recognizing human emotions.
DEmoClassi
DEmoClassi stands for Demographic (age, gender, race) and Emotions (happy, sad, angry, ...) Classification from face images, using deep learning.
EEGLearn
A set of functions for supervised feature learning/classification of mental states from EEG based on "EEG images" idea.
Evolutionary-Machine-Learning---Keras-Model-LSTM-DEAP
Please read the instructions.pdf for a better understanding of the workflow of the project.
face-frontalization
This is a port of the Face Frontalization code provided by Hassner et al. at http://www.openu.ac.il/home/hassner/projects/frontalize
ferattention
FERAtt: Facial Expression Recognition with Attention Net
Genetic-CNN-for-Computer-Vision
Evolving CNN Hyper-Parameters for Computer Vision
go
The Open Source Data Science Masters
keras-LAMB-Optimizer
Implementation of the LAMB optimizer for Keras from the paper "Reducing BERT Pre-Training Time from 3 Days to 76 Minutes"
libfacedetection
An open source library for face detection in images. The face detection speed can reach 1500FPS.
MNIST-digit-recognizer
Featuring engineering for making tree ensemble methods Like Extreme Gradient Boosting competitive with Convolutional Neural Networks (CNN) on classification tasks.
my_orc_keras_verification_code_identification
本项目实现了ocr主流算法gru/lstm+ctc+cnn架构,进行不定长度验证码识别,达到不分割字符而识别验证码内容的效果。验证码内容包含了大小字母以及数字,并增加点、线、颜色、位置、字体等干扰项。本项目对gru +ctc+cnn、lstm+ctc+cnn、cnn三种架构进行了对比,实践说明同等训练下gru/lstm+ctc+cnn架构准确率和速度均明显优于cnn架构,gru +ctc+cnn优于lstm+ctc+cnn,在实验2500个样本数据200轮训练时,gru +ctc+cnn架构在500样本测试准确率达90.2%。本项目技术能够训练长序列的ocr识别,更换数据集和相关调整,即可用于比如身份证号码、车牌、手机号、邮编等识别任务,也可用于汉字识别。
Named-Entity-Recognition-with-Bidirectional-LSTM-CNNs
Named-Entity-Recognition-with-Bidirectional-LSTM-CNNs
panda
code powering the comma.ai panda
probability
Probabilistic reasoning and statistical analysis in TensorFlow
Python
All Algorithms implemented in Python
python-openbnmapi
Unofficial Python Wrapper for Bank Negara Malaysia's Open API (https://api.bnm.gov.my/portal)
tf_EEGLearn
A tensorflow implementation for EEGLearn
vision
Datasets, Transforms and Models specific to Computer Vision