CompACT-Deep

Published

Jul 19, 2015

CompACT-Deep is an AI model developed by University of California San Diego (United States), first published in July 2015. It works in the vision domain, on tasks such as object detection.

Epoch AI has no training-compute estimate for this model. Training ran on 1 NVIDIA Tesla K40m.

Access: Unreleased. Its weights are not openly released. It is built on top of AlexNet,VGG16. Epoch AI rates the confidence of this record as confident.

Full record

Organization: University of California San Diego
Country of organization: United States
Domain: Vision
Task: Object detection
Training hardware: NVIDIA Tesla K40m
Chips used: 1
Training power draw: 286 W
Model accessibility: Unreleased
Open weights: No
Base model: AlexNet, VGG16
Epoch confidence: Confident

More from University of California San Diego

GPT-2 (fine-tuned with HYDRA)MEGNet (crystal band gap model)MEGNet (crystal elasticity model)MEGNet (molecule model)MEGNet (crystal formation energy model)RESP AI M3GNet SRN-Encoded Grammatical Structures

SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.

← All ai models