Wahyu Rahmaniar's repositories
wahyurahmaniar.github.io
A CV generator/template using Github pages & Jekyll
basilisk
Astrodynamics simulation framework
BMAD
BMAD hold a Creative Commons Attribution-NonCommercial-ShareAlike (CC BY-NC-SA) license
chat-with-gpt
An open-source ChatGPT app with a voice
dynablox
Real-time detection of diverse dynamic objects in complex environments.
gptcli
ChatGPT in command line with open api (gpt-3.5/gpt-4)
Grounded-Segment-Anything-patch
Marrying Grounding DINO with Segment Anything & Stable Diffusion & BLIP - Automatically Detect , Segment and Generate Anything with Image and Text Inputs
ijepa
Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."
ImageBind
ImageBind One Embedding Space to Bind Them All
iml-dl
Deep Learning Framework
llama
Inference code for LLaMA models
LoGo
Re-thinking Federated Active Learning based on Inter-class Diversity (CVPR 2023)
lungmask
Automated lung segmentation in CT
LungTumorMask
Automatic end-to-end lung tumor segmentation from CT images.
MedicalNet
Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and relative code.
MedSAM
The official repository for MedSAM: Segment Anything in Medical Images.
MorphAEus
What Do AEs Learn? Challenging Common Assumptions in Unsupervised Anomaly Detection
Neural-Network-Diffusion
We introduce a novel approach for parameter generation, named neural network diffusion (\textbf{p-diff}, p stands for parameter), which employs a standard latent diffusion model to synthesize a new set of parameters
patchcore-few-shot
Implementation of our paper "Optimizing PatchCore for Few/many-shot Anomaly Detection"
PHANES
Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection
PRISM
[MICCAI 2024 Early Acceptance] PRISM: A Promptable and Robust Interactive Segmentation Model with Visual Prompts
pyllama
LLaMA: Open and Efficient Foundation Language Models
Swin-Unet
The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"
SyntheticTumors
[CVPR 2023] Label-Free Liver Tumor Segmentation
torchdistill
A coding-free framework built on PyTorch for reproducible deep learning studies. 🏆20 knowledge distillation methods presented at CVPR, ICLR, ECCV, NeurIPS, ICCV, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.
Track-Anything
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.