1. 02 Jul, 2021 3 commits
    • Zaida Zhou's avatar
      [Docs] Refactor docs (#1102) · 66cefaff
      Zaida Zhou authored
      * [Docs] Refactor documentation
      
      * [Docs] Refactor documentation
      
      * refactor docs
      
      * refactor docs
      
      * set sphinx==3.1.2
      
      * fix typo
      
      * modify according to comment
      
      * modify according to comment
      
      * modify according to comment
      
      * [Docs] delete unnecessary file
      
      * fix title
      
      * rename
      
      * rename
      66cefaff
    • Zaida Zhou's avatar
      add citation in readme.md (#1160) · cdcbc03c
      Zaida Zhou authored
      cdcbc03c
    • Haodong Duan's avatar
      [Fix] Fix saconv (#1147) · 7e285d35
      Haodong Duan authored
      * fix saconv
      
      * update
      
      * update
      
      * fix
      
      * use LooseVersion
      7e285d35
  2. 29 Jun, 2021 3 commits
  3. 28 Jun, 2021 1 commit
  4. 27 Jun, 2021 1 commit
  5. 25 Jun, 2021 7 commits
  6. 24 Jun, 2021 5 commits
  7. 23 Jun, 2021 2 commits
  8. 22 Jun, 2021 2 commits
  9. 16 Jun, 2021 3 commits
  10. 14 Jun, 2021 1 commit
  11. 11 Jun, 2021 7 commits
    • Zaida Zhou's avatar
      bump version to v1.3.6 (#1095) · 6cb534b7
      Zaida Zhou authored
      6cb534b7
    • LXXXXR's avatar
      fix typo (#1094) · c9b009f1
      LXXXXR authored
      c9b009f1
    • pc's avatar
      add border_align support in parrots (#1086) · 3d7bcc8f
      pc authored
      3d7bcc8f
    • Shilong Zhang's avatar
      Refactor the baseclass related to transformer (#978) · e05fb560
      Shilong Zhang authored
      
      
      * minor changes
      
      * change to modulist
      
      * change to Sequential
      
      * replace dropout with attn_drop and proj_drop in MultiheadAttention
      
      * add operation_name for attn
      
      * add drop path and move all ffn args to ffncfgs
      
      * fix typo
      
      * fix a bug when use default value of ffn_cfgs
      
      * fix ffns
      
      * add deprecate warning
      
      * fix deprecate warning
      
      * change to pop kwargs
      
      * support register FFN of transformer
      
      * support batch first
      
      * fix batch first wapper
      
      * fix forward wapper
      
      * fix typo
      
      * fix lint
      
      * add unitest for transformer
      
      * fix unitest
      
      * fix equal
      
      * use allclose
      
      * fix comments
      
      * fix comments
      
      * change configdict to dict
      
      * move drop to a file
      
      * add comments for drop path
      
      * add noqa 501
      
      * move bnc wapper to MultiheadAttention
      
      * move bnc wapper to MultiheadAttention
      
      * use dep warning
      
      * resolve comments
      
      * add unitest:
      
      * rename residual to identity
      
      * revert runner
      
      * msda residual to identity
      
      * rename inp_identity to identity
      
      * fix name
      
      * fix transformer
      
      * remove key in msda
      
      * remove assert for key
      Co-authored-by: default avatarHIT-cwh <2892770585@qq.com>
      Co-authored-by: default avatarbkhuang <congee524@gmail.com>
      Co-authored-by: default avatarWenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>
      e05fb560
    • Y. Xiong's avatar
      Support resume for fp16 training (#1013) · 11629d52
      Y. Xiong authored
      * fix cast nn.Module bug
      
      * fix misleading doc
      
      * add resume function
      
      * del useless; fix typo
      
      * change meta structure; set resume default
      11629d52
    • pc's avatar
      add load_ext warning (#1089) · 69146fe3
      pc authored
      69146fe3
    • Dmitry Sidnev's avatar
      [Feature] enable exporting to onnx for PointRend (#953) · a88d1d28
      Dmitry Sidnev authored
      
      
      * Fix export to onnx for PointRend
      
      * Fix codestyle
      
      * Fix codestyle
      
      * Fix type in docstring
      
      * Minor fix
      
      * Fix export with custom ops
      
      * Fix codestyle
      
      * Add tests for bilinear_grid_sample function
      
      * Remove redundant operation and rename variables
      
      * Fix bug in bilinear_grid_sample and update test
      
      * Fix getting batch size
      
      * skip torch==1.3.1
      
      * remove unused import
      
      * fix lint
      
      * support export with batch
      
      * fix dynamic clip
      
      * skip test for torch<1.5.0
      
      * Add docstrings and comments
      
      * Minor fix
      
      * Recover clipping code
      
      * Fix clamping in pytorch 1.7.0
      
      * Fix bilinear_grid_sampler
      
      * Minor fix
      Co-authored-by: default avatarmaningsheng <maningsheng@sensetime.com>
      a88d1d28
  12. 09 Jun, 2021 1 commit
  13. 08 Jun, 2021 1 commit
  14. 01 Jun, 2021 3 commits