NVIDIA / Imageinary
Imageinary is a reproducible mechanism which is used to generate large image datasets at various resolutions. The tool supports multiple image types, including JPEGs, PNGs, BMPs, RecordIO, and TFRecord files
☆26Updated 2 years ago
Alternatives and similar repositories for Imageinary:
Users that are interested in Imageinary are comparing it to the libraries listed below
- ☆16Updated 3 years ago
- 3rd party dependencies for DALI project☆10Updated last week
- A server powering LAION's effort to filter CommonCrawl with CLIP, building a large scale image-text dataset.☆13Updated 2 years ago
- An open source implementation of CLIP.☆32Updated 2 years ago
- PyTorch ObjectDetection Modules and ONNX ops☆18Updated last year
- Load any clip model with a standardized interface☆21Updated 11 months ago
- Implements EvoNorms B0 and S0 as proposed in Evolving Normalization-Activation Layers.☆11Updated 4 years ago
- Utilities for sequential processing of tar files.☆24Updated 3 years ago
- Aggregating embeddings over time☆31Updated 2 years ago
- Updated last year
- Simple and easy stable diffusion inference with LightningModule on GPU, CPU and MPS (Possibly all devices supported by Lightning).☆17Updated last year
- Minimal implementation of adaptive gradient clipping (https://arxiv.org/abs/2102.06171) in TensorFlow 2.☆85Updated 3 years ago
- Official repository for the paper "End-to-End Visual Editing with a Generatively Pre-Trained Artist", which is accepted at ECCV 2022. Her…☆29Updated 2 years ago
- Needles in Haystacks: On Classifying Tiny Objects in Large Images☆22Updated 5 years ago
- Minimal implementation of Denoised Smoothing (https://arxiv.org/abs/2003.01908) in TensorFlow.☆20Updated 3 years ago
- Conversational AI Benchmark.☆66Updated last year
- PyTorch implementation of GLOM☆21Updated 3 years ago
- Experiments for the blog post "No, We Don't Have to Choose Batch Sizes As Powers Of 2"☆19Updated 2 years ago
- Efficient DataLoader for PyTorch and Keras for loading datasets from web servers and object stores.☆29Updated 5 years ago
- ☆27Updated 4 years ago
- NVIDIA Fleet Command is a hybrid-cloud platform for securely and remotely deploying, managing, and scaling AI across dozens or up to thou…☆12Updated 2 years ago
- Website for TextVQA dataset.☆28Updated last year
- MozoLM: A language model (LM) serving library☆44Updated last month
- Bugfixing fork of Python bindings for the NVIDIA GPU Management Library☆51Updated 7 years ago
- AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks☆27Updated 2 years ago
- A client library for LAION's effort to filter CommonCrawl with CLIP, building a large scale image-text dataset.☆33Updated 2 years ago
- A dashboard for exploring timm learning rate schedulers☆19Updated 4 months ago
- Contains my experiments with the `big_vision` repo to train ViTs on ImageNet-1k.☆22Updated 2 years ago
- High performance pytorch modules☆18Updated 2 years ago
- ☆15Updated 3 years ago