Pinned Loading
-
Vit-on-small-data
Vit-on-small-data Publiclightest Vision Transformer (ViT) trained from scratch to achieve 93.37 ± 0.07%” top-1 accuracy on CIFAR-10 within just 50 epochs.
Python 4
-
training_models_from_scratch
training_models_from_scratch PublicTraining tiny models from scratch using NumPy in code and linear algebra on a piece of paper.
Python 11
-
optimizers-from-scratch
optimizers-from-scratch PublicImplementations of deep learning optimizers using NumPy. Featuring SGD, Adam, Adagrad, NAG, RMSProp, and Momentum. This repo also includes a benchmark against Pytorch developed optims.
-
BatchNorm-Interactive-Playground
BatchNorm-Interactive-Playground PublicInteractive visualization simulating how Gamma and Beta control ICS (Internal Covariate Shift) for faster convergence in BatchNorm.
-
food101-preprocessing
food101-preprocessing PublicA clean and modular pipeline for preprocessing the Food-101 dataset using both folder-based and CSV-based workflows.
Python 5
-
COCO-CONVERTER
COCO-CONVERTER PublicA CLI that converts CSV files and folders with image data to a JSON file with COCO annotations and builds a custom dataset off of it ready to train with pytorch.
Python 5
If the problem persists, check the GitHub status page or contact support.