This is the Linux app named FastViT whose latest release can be downloaded as ml-fastvitsourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named FastViT with OnWorks for free.
Suivez ces instructions pour exécuter cette application :
- 1. Téléchargé cette application sur votre PC.
- 2. Entrez dans notre gestionnaire de fichiers https://www.onworks.net/myfiles.php?username=XXXXX avec le nom d'utilisateur que vous voulez.
- 3. Téléchargez cette application dans ce gestionnaire de fichiers.
- 4. Démarrez l'émulateur en ligne OnWorks Linux ou Windows en ligne ou l'émulateur en ligne MACOS à partir de ce site Web.
- 5. Depuis le système d'exploitation OnWorks Linux que vous venez de démarrer, accédez à notre gestionnaire de fichiers https://www.onworks.net/myfiles.php?username=XXXXX avec le nom d'utilisateur que vous souhaitez.
- 6. Téléchargez l'application, installez-la et exécutez-la.
CAPTURES D'ÉCRAN
Ad
FastViT
DESCRIPTION
FastViT is an efficient vision backbone family that blends convolutional inductive biases with transformer capacity to deliver strong accuracy at mobile and real-time inference budgets. Its design pursues a favorable latency-accuracy Pareto curve, targeting edge devices and server scenarios where throughput and tail latency matter. The models use lightweight attention and carefully engineered blocks to minimize token mixing costs while preserving representation power. Training and inference recipes highlight straightforward integration into common vision tasks such as classification, detection, and segmentation. The codebase provides reference implementations and checkpoints that make it easy to evaluate or fine-tune on downstream datasets. In practice, FastViT offers drop-in backbones that reduce compute and memory pressure without exotic training tricks.
Comment ça marche
- Hybrid Conv-Transformer blocks optimized for latency
- Competitive accuracy at mobile/edge inference budgets
- Reference training scripts and pretrained checkpoints
- Compatibility with standard detection/segmentation heads
- Memory-efficient attention and token mixing components
- Simple integration into existing PyTorch pipelines
Langage de programmation
Python
Catégories
This is an application that can also be fetched from https://sourceforge.net/projects/fastvit.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.
