CaffePresso: An optimized library for Deep Learning on embedded accelerator-based platforms
By Gopalakrishna Hegde, Siddhartha, Nachiappan Ramasamy, Nachiket Kapre. 2016
50 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Electrical and Electronic Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Antonio Loquercio
- Davide Scaramuzza
- Francesco Conti
- Luca Benini
- Daniele Palossi
- Eric Flamand
- Vladlen Koltun
- Daniel Cremers
In Electrical and Electronic Engineering
- Antonio Loquercio
- Davide Scaramuzza
- Daniele Palossi
- Luca Benini
- Francesco Conti
- Eric Flamand
- Henri Rebecq
- Guillermo Gallego
Citations in the corpus
- A 64-mW DNN-Based Visual Navigation Engine for Autonomous Nano-Drones (2018, background): “While significant work has been done within academia [25], [26], [27] and industry (e.g., TensorFlow Lite and ARM Compute Library 3 ) to ease the embedding of deep neural networks on mobile ARM-based SoC’s, there is no general consensus yet on how to “correctly” deploy complex AI-powered algorithms,…”
- FINN-R (2018, unknown): “16 Zhang etal. [67] VGG16 VC709 150 - - 354(-) 26 14 W16A16 Aydonat etal. [6] AlexNet GX1150 303 - - 1,382(-) ∼45 31 WHPAHP Zhang etal. [69] VGG16 GX1150 385 - - 1,790(-) ∼37.46 48 W16A16 Hedge etal. [23] Caltech101 ZC706 180 - - 11.5(-) 19 <1 W16A16 Ma etal. [38] VGG16 GX1150 150 - - 645.25(-) -”
- Edge Computing for Autonomous Driving: Opportunities and Challenges (2019, unknown): “[50] propose a framework for easy mapping of CNN specifications to accelerators such as FPGAs, DSPs, GPUs, and Reduced Instruction Set Computer (RISC) multicores.”
- C-GOOD: C-code Generation Framework for Optimized On-device Deep Learning (2018, unknown): “Caffepresso[12] has chosen this approach.”