Commits

Breadcrumbs

History for

on7333979

User selector

All users

Datepicker

All time

Commit History

Commits on May 6, 2021

• add link to official repo for levit

  lucidrains

  committed
  7333979

Commits on May 2, 2021

• add image

  lucidrains

  committed
  74b4023

• link to yannic

  lucidrains

  committed
  41d2d46

• implement SOTA new self-supervised learning technique from facebook for vision transformers, Dino

  lucidrains

  committed
  04f86de

• be able to accept non-square patches, thanks to @FilipAndersson245

  lucidrains

  committed
  6549522

Commits on May 1, 2021

• update readme

  lucidrains

  committed
  6a80a4e

Commits on Apr 29, 2021

• fix small bug

  lucidrains

  committed
  7807f24

• readme

  lucidrains

  authored
  a612327

• release twins svt

  lucidrains

  committed
  30a1335

• add Twins SVT (small)

  lucidrains

  committed
  ab781f7

Commits on Apr 21, 2021

• cite

  lucidrains

  authored
  fbced01

Commits on Apr 13, 2021

• add LocalViT

  lucidrains

  committed
  30b37c4

Commits on Apr 6, 2021

• cleanup levit

  lucidrains

  committed
  b50d3e1

• complete levit

  lucidrains

  committed
  2cb6b35

Commits on Apr 2, 2021

• add layer dropout for CaiT

  lucidrains

  committed
  3a3038c

Commits on Apr 1, 2021

• offer hard distillation as well

  lucidrains

  committed
  b1f1044

• readme

  lucidrains

  authored
  deb9620

• add CaiT, new vision transformer out of facebook AI, complete with layerscale, talking heads, and cls -> patch cross attention

  lucidrains

  committed
  9ef8da4

Commits on Mar 31, 2021

• add documentation for three recent vision transformer follow-up papers

  lucidrains

  committed
  506fcf8

• cite

  lucidrains

  committed
  9332b9e

Commits on Mar 30, 2021

• add CvT

  lucidrains

  committed
  518924e

• add CrossViT

  lucidrains

  committed
  e712003

Commits on Mar 29, 2021

• use hooks to retrieve attention maps for user without modifying ViT

  lucidrains

  committed
  8135d70

• add recorder class, for recording attention across layers, for researchers

  lucidrains

  committed
  3067155

Commits on Mar 28, 2021

• cleanup

  lucidrains

  committed
  ab7315c

Commits on Mar 23, 2021

• remove masking, as it complicates with little benefit

  lucidrains

  committed
  15294c3

• add deep vit

  lucidrains

  committed
  b900850

Commits on Mar 10, 2021

• readme

  lucidrains

  authored
  7848904

Commits on Mar 8, 2021

• cleanup and release 0.8.0

  lucidrains

  committed
  173e07e

• Merge pull request lucidrains#66 from zankner/masked_patch_pred

  Show description for 0e63766
  lucidrains

  authored
  0e63766

• added to readme

  zankner

  committed
  a6cbda3

Commits on Feb 22, 2021

• remove patch size from T2TViT

  lucidrains

  committed
  3744ac6

Commits on Feb 20, 2021

• add token to token ViT

  lucidrains

  committed
  e3205c0

Commits on Feb 17, 2021

• incept idea for using nystromformer

  lucidrains

  committed
  4fc7365

Commits on Jan 12, 2021

• update readme about non-square images

  lucidrains

  authored
  5db8d9d

Pagination

PreviousNext