Mark Peng's repositories
tesseract-web-service
An implementation of RESTful web service for tesseract-OCR using tornado
kaggle_moa_winner_hungry_for_gold
Winning Solution of Kaggle Mechanisms of Action (MoA) Prediction.
reinforcement_learning_in_python
Practice Code for the "Reinforcement Learning in Python" Course in Udemy.
ai4code-baseline
Early solution for Google AI4Code competition
bi-lstm-crf
A PyTorch implementation of the BI-LSTM-CRF model.
ConstraintGraph4NSO
AAAI 2021: Neural Sentence Ordering Based on Constraint Graphs
DeepInsight
A methodology to transform a non-image data to an image for convolution neural network architecture
dockerfiles
Useful Dockerfiles made for different purposes.
EEG-ATCNet
Attention temporal convolutional network for EEG-based motor imagery classification
elastic-infogan
Official PyTorch implementation of Elastic-InfoGAN [NeurIPS 2020]
HPA-competition-solutions
Team original solutions for the Human Protein Atlas image classification competition
improved-bagan-gp
Generate high quality images for each class even with an imbalanced dataset. An improved version of Balancing GAN.
LearnablePromptSAM
Try to use the SAM-ViT as the backbone to create the learnable prompt for semantic segmentation
mega.pytorch
Memory Enhanced Global-Local Aggregation for Video Object Detection, CVPR2020
MLPrimitives
Primitives for machine learning and data science.
Open-GroundingDino
This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.
pytorch-grad-cam
Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM
pytorch-lightning
The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.
SegFormer
Official PyTorch implementation of SegFormer
Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
timeseriescv
Scikit-learn style cross-validation classes for time series data
UniAD
[NeurIPS 2022 Spotlight] A Unified Model for Multi-class Anomaly Detection