AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

KerasCV and KerasNLP: Multi-framework Models

Matthew Watson, Divyashree Shivakumar Sreepathihalli, François Chollet, Martin Górner, Kiranbir Sodhia, Ramesh Sampath, Tirth Patel, Haifeng Jin, Neel Kovelamudi, Gabriel Rasskin, Samaneh Saadat, Luke Wood and 5 more

JMLR 2024 · Vision-language and multimodal › Human and embodied modeling · approach: Human-like visual cognition in VLMs

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
select the fastest Keras 3 backend instead of Keras 2 (TF)Segment Anything · Segment Anything predict (batch size 7)time per step (ms): 3,187.09 -> 660.16Improved
select the fastest Keras 3 backend instead of Keras 2 (TF)Segment Anything · Segment Anything train (batch size 1)time per step (ms): 386.93 -> 355.25Improved
select the fastest Keras 3 backend instead of Keras 2 (TF)BERT · BERT train (batch size 54)time per step (ms): 841.84 -> 404.17Improved
select the fastest Keras 3 backend instead of Keras 2 (TF)BERT · BERT predict (batch size 531)time per step (ms): 965.21 -> 865.29Improved
use PyTorch backend instead of JAX in Keras 3Segment Anything · Segment Anything train (batch size 1)time per step (ms): 361.69 -> 1,388.87Hurt
use PyTorch backend instead of JAX in Keras 3Mistral · Mistral predict (batch size 32)time per step (ms): 957.25 -> 10932.59Hurt
use PyTorch backend instead of TF in Keras 3Gemma · Gemma predict (batch size 32)time per step (ms): 1,134.91 -> 7, 952.67Hurt
use JAX backend instead of TF in Keras 3Gemma · Gemma train (batch size 8)time per step (ms): 232.52 -> 273.67Hurt
use JAX backend instead of TF in Keras 3BERT · BERT predict (batch size 531)time per step (ms): 962.11 -> 865.29Improved
use JAX backend instead of TF in Keras 3Mistral · Mistral train (batch size 8)time per step (ms): 185.92 -> 213.22Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy