1. 09 May, 2020 2 commits
  2. 07 Apr, 2020 1 commit
  3. 03 Apr, 2020 10 commits
  4. 10 Feb, 2020 2 commits
  5. 09 Feb, 2020 2 commits
  6. 07 Feb, 2020 1 commit
  7. 31 Jan, 2020 3 commits
  8. 30 Jan, 2020 1 commit
  9. 29 Jan, 2020 1 commit
  10. 28 Jan, 2020 2 commits
  11. 27 Jan, 2020 1 commit
    • Jon Crall's avatar
      Enhance AssignResult and SamplingResult (#1995) · 8457bbab
      Jon Crall authored
      * Enhance AssignResult and SamplingResult
      
      Add runtime dependency on ubelt (pending approval)
      
      Fix issue in SamplingResult.__init__
      
      Add rng as attribute of RandomSampler
      
      * fix linters
      
      * remove ubelt
      
      * Fix linters
      
      * fix linters again
      8457bbab
  12. 22 Jan, 2020 2 commits
  13. 21 Jan, 2020 5 commits
    • Wenwei Zhang's avatar
      Encapsulate DCN into a ConvModule & Conv_layers (#1894) · 8bd1a5f7
      Wenwei Zhang authored
      * update code
      
      * reformat
      
      * fix load pretrain bug
      
      * reformat
      
      * fix key warnings
      
      * use build_conv_layer & ConvModule
      
      * rm unrelated file
      
      * fix resnext group bug
      
      * change cfg to pass test
      
      * use build_conv_layer to claim dcn in resnets
      
      * change _version = 2
      
      * MDCN to DCNv2
      
      * change dependency of mmcv from 0.2.15 to 0.2.16
      
      * resolve comments
      
      * rm comments
      
      * get_root_logger()
      8bd1a5f7
    • hust-kevin's avatar
      Code for Paper "Bridging the Gap Between Anchor-based and Anchor-free… (#1872) · 1ebb6cb8
      hust-kevin authored
      
      
      * Code for Paper "Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection"
      
      * fix format
      
      * changed the code according to the Changes requested
      
      * update benchmark
      
      * minor refactoring
      
      * minor fix
      
      * update model_zoo and support models
      Co-authored-by: default avatarCao Yuhang <yhcao6@gmail.com>
      1ebb6cb8
    • Kamran Melikov's avatar
      Non color images (#1976) · 8c86f74c
      Kamran Melikov authored
      * First Draft
      
      On branch non-color-images
      Changes to be committed:
      modified:   mmdet/datasets/pipelines/loading.py
      
      * Add option to load non color images
      
      Add 'color_type' parameter to LoadImageFromFile class
      Change __repr__ method accordingly
      Since non-color images maybe two dimensional expand image
      dimensions if necessary in DefaultFormatBundle and
      ImageToTensor classes
      
      Changes to be committed:
          modified:   mmdet/datasets/pipelines/formating.py
          modified:   mmdet/datasets/pipelines/loading.py
      
      * Fix RandomCrop to work with grayscale images
      
      Changes to be committed:
          modified:   mmdet/datasets/pipelines/transforms.py
      
      * Modify retrieving w, h of padded image in anchor heads
      
      This addreses problems with single channel images for which the
      shape is  tuple with 2 values
      
      Changes to be committed:
          modified:   mmdet/models/anchor_heads/anchor_head.py
          modified:   mmdet/models/anchor_heads/guided_anchor_head.py
          modified:   mmdet/models/anchor_heads/reppoints_head.py
      8c86f74c
    • Cao Yuhang's avatar
      Fix albu mask format bug (#1818) · e60d34af
      Cao Yuhang authored
      e60d34af
    • Kai Chen's avatar
      Fix CI by limiting the version of torchvision (#2005) · c67cf3c4
      Kai Chen authored
      * try pytorch 1.4 instead of 1.2
      
      * use pytorch 1.2 and torchvision 0.4.0
      c67cf3c4
  14. 20 Jan, 2020 1 commit
  15. 18 Jan, 2020 1 commit
  16. 13 Jan, 2020 2 commits
  17. 11 Jan, 2020 1 commit
  18. 07 Jan, 2020 2 commits