ameya005
A computer vision engineer with an attraction to 'deep' insights
New York UniversityCambridge, Massachusetts
Pinned Repositories
AntColonyAlgorithms
Implementation of various ACO's.
Deep-Segmentation
Deep Learning methods for semantic segmentation with weakly labelled data
Fisher-Vectors
An utility to generate fisher vectors with MR8 localized descriptors. Can be used with any other feature descriptors as well.
MNISTOpenCV
Generates the images from the MNIST dataset for ease of visualization. Also generates text files of labels.
pascal-voc-python
Repository for reading Pascal VOC data in Python, rather than requiring MATLAB to read the XML files.
Phys-GAN
GAN with effective realistic behavior
Semantic_Adversarial_Attacks
Code for Semantic Adversarial Attacks
tf_unet
Generic convolutional neural network U-Net implementation in Tensorflow
Virtual-canvas
A skin pixel tracker using color predicates. Currently detects horizontal hand swipes to start vlc media player.
VLAD-Implementation
Implements Vector of Locally Aggregated Descriptors according to Jegou's paper, for TagMe Image Categorization Competition, 2014
ameya005's Repositories
ameya005/Semantic_Adversarial_Attacks
Code for Semantic Adversarial Attacks
ameya005/Phys-GAN
GAN with effective realistic behavior
ameya005/Adversarial_attacks_comparisons
ameya005/ameya005.github.io
Github IO page
ameya005/CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
ameya005/clip_playground
ameya005/Conn_InvNet
Invnet with constraints on connected components
ameya005/dynamic-reparameterization
ameya005/ECE9163_project
Neural cleanse
ameya005/glid-3-xl-stable
stable diffusion training
ameya005/ice
Interactive Composition Explorer: a Python library for compositional language model programs
ameya005/introml-notes
ameya005/invnet
ameya005/l1_structured_pruning
ameya005/Multires-Deep-Image-Priors
Deep Image priors for in-painting that leverage multi-resolution image pyramids.
ameya005/Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
ameya005/optlearningcontrol
Optimal and learning control for robotics (ECE-9243 / ME-GY 7973)
ameya005/pytorch-image-models
PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2, MNASNet, Single-Path NAS, FBNet, and more
ameya005/pytorch-retinanet
Pytorch implementation of RetinaNet object detection.
ameya005/ResnetClassiifier
Simple resnet classifier with Keras like dataloaders
ameya005/robust-physical-attack
Physical adversarial attack for fooling the Faster R-CNN object detector
ameya005/scenic
Scenic: A Jax Library for Computer Vision Research and Beyond
ameya005/scGPT
ameya005/smoothing-adversarial
Code for our NeurIPS 2019 spotlight "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers"
ameya005/stable-diffusion
A latent text-to-image diffusion model
ameya005/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
ameya005/vision_transformer
ameya005/VisML_CLIP_Mapper_Exploration
ameya005/vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
ameya005/whisper