-
Concordia University
- MontrΓ©al, Quebec, Canada
- hasibzunair.github.io/
- @hasibzunair
Stars
Command-line program to download videos from YouTube.com and other video sites
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (Vβ¦
Datasets, Transforms and Models specific to Computer Vision
Code samples for my book "Neural Networks and Deep Learning"
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
A python library for user-friendly forecasting and anomaly detection on time series.
Time series forecasting with PyTorch
Effortless data labeling with AI support from Segment Anything and other awesome models.
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
Images to inference with no labeling (use foundation models to train supervised models).
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
Automatically find issues in image datasets and practice data-centric computer vision.
All image quality metrics you need in one package.
Identifying and removing near-duplicate images using perceptual hashing.
Estimate/count FLOPS for a given neural network using pytorch
A repo for training and finetuning models for hands segmentation.
Pytorch SimCLR on CIFAR10 (92.85% test accuracy)