zhuxb's starred repositories
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
gpt-engineer
Platform to experiment with the AI Software Engineer. Terminal based. NOTE: Very different from https://gptengineer.app
LAVFilters
LAV Filters - Open-Source DirectShow Media Splitter and Decoders
GPT2-Chinese
Chinese version of GPT2 training code, using BERT tokenizer.
YOLO_v3_tutorial_from_scratch
Accompanying code for Paperspace tutorial series "How to Implement YOLO v3 Object Detector from Scratch"
transformers_tasks
⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.
ChatIE
The online version is temporarily unavailable because we cannot afford the key. You can clone and run it locally. Note: we set defaul openai key. If keys exceed plan and are invalid, please tell us. The response speed depends on openai. ( sometimes, the official is too crowded and slow)
BertWithPretrained
An implementation of the BERT model and its related downstream tasks based on the PyTorch framework
numpy_neural_network
仅使用numpy从头开始实现神经网络,包括反向传播公式推导过程; numpy构建全连接层、卷积层、池化层、Flatten层；以及图像分类案例及精调网络案例等,持续更新中... ...
SelfDrivingCar
A collection of all projects pertaining to different layers in the SDC software stack
TransformerTranslation
A Transformer Framework Based Translation Task
bert-intent-slot-detector
BERT-based intent and slots detector for chatbots.
pytorch_bert
Tutorial for how to build BERT from scratch
AdvancedLaneLines
Lane identification system for camera based systems.
transformer
A codebase implementing a simple GPT-like model from scratch based on the Attention is All You Need paper.
Real-Time-Lane-Detection
Real-Time Lane Detection using OpenCV
Android-Driving-Assistant
Android app for lane detection and speed recognition
lstm-from-scratch
LSTM Network from Scratch in C++
DriveSafe_App
Driver drowsiness is the most critical cause of road accidents so detection of drowsiness play a vital role in preventing road accidents. We are developing an android app that will alert drivers before an accident occurs. This will reduce the number of road accidents on a road. Drowsiness is a natural phenomenon that happens in human body due to different factors. Machine learning was applied to predict drowsiness and improve drowsiness prediction using facial recognition technology and eye-blink recognition technology. In this app, front camera will take a picture of drowsy driver then this picture will be taken as input. In processing the detected image, we are using OpenCV Library. OpenCV Library uses Haar Cascade Classifier for detection images such as eyes and face. Eyes and face will be the target in this system. This application will be implemented on Android Operating System. Drowsiness detection system will send alert to the driver when the driver feels asleep while driving a car, this can avoid accidents. Driver which is the user in this application, if they close their eyes within one second, the sensor which is the front camera in the smartphone will catch and process this event and then trigger the system to give voice alert to the user. Moreover, if the driver is willing to turn on back camera then it will detect the lane detection violation and will calculate the distance from the vehicle ahead of it. If the distance is too close, then it will generate an alarm. It will also generate an alarm if there is a violation of the lane on the road.
lane-detector
Lane detection using Kotlin and OpenCV with Java bindings
pytorch_bert
Tutorial for how to build BERT from scratch