1. 28 Apr, 2021 1 commit
  2. 26 Apr, 2021 2 commits
  3. 24 Apr, 2021 7 commits
  4. 23 Apr, 2021 2 commits
  5. 22 Apr, 2021 8 commits
    • suilin0432's avatar
      update · a8d1cee4
      suilin0432 authored
      a8d1cee4
    • Elbek Khoshimjonov's avatar
      Sample image instead of dataset for exporting model · c3b671e2
      Elbek Khoshimjonov authored
      Summary:
      [export_model.py](https://github.com/facebookresearch/detectron2/blob/master/tools/deploy/export_model.py)
       requires to process sample input, and current implementation requires whole dataset to be imported, it is not a easy way for custom models, so instead of dataset, user can pass a sample image.
      
      Pull Request resolved: https://github.com/facebookresearch/detectron2/pull/2931
      
      Reviewed By: alexander-kirillov
      
      Differential Revision: D27903407
      
      Pulled By: ppwwyyxx
      
      fbshipit-source-id: 1e5d9b5770d2a8200abc46aad01121f0012cf5e7
      c3b671e2
    • Marc Szafraniec's avatar
      Add Confidence Based CSE data samplers · 7adca49d
      Marc Szafraniec authored
      Summary: Add Confidence Based CSE data samplers (coarse segm only for the moment)
      
      Reviewed By: vkhalidov
      
      Differential Revision: D27188563
      
      fbshipit-source-id: f220448e87c0f31e25c1c3f98d7061c16aa68b6c
      7adca49d
    • Marc Szafraniec's avatar
      Adapt CSE Bootstrapping to use ground truth category data · 9a4fc562
      Marc Szafraniec authored
      Summary: Adapt CSE Bootstrapping to use ground truth category data
      
      Reviewed By: vkhalidov
      
      Differential Revision: D27045679
      
      fbshipit-source-id: 7130931a4cb66e8a9a015309814410f5f8ded171
      9a4fc562
    • Marc Szafraniec's avatar
      Create CSE Base and Uniform Data Samplers · 5727791f
      Marc Szafraniec authored
      Summary: Create CSE Base and Uniform Data Samplers
      
      Reviewed By: vkhalidov
      
      Differential Revision: D26691586
      
      fbshipit-source-id: 2688698d612220b4047322ecd91df24186f2efb5
      5727791f
    • Marc Szafraniec's avatar
      Refactor image transform · b990b71f
      Marc Szafraniec authored
      Summary:
      Refactor image transform so it does nothing else than the resizing.
      
      Before it was a bit confusing because it was resizing AND assuming that the input data was RGB and in NHWC format, and applying corresponding transforms, which depends on the input dataset
      
      Reviewed By: vkhalidov
      
      Differential Revision: D27081805
      
      fbshipit-source-id: e12a23ff843e24f86feccf9f0dfd00cf628a5a5b
      b990b71f
    • Marc Szafraniec's avatar
      Correct Image List Dataset · 6e029299
      Marc Szafraniec authored
      Summary: Correct Image List Dataset to use one image with 3 channels instead of 3 images with 1 channel
      
      Reviewed By: vkhalidov
      
      Differential Revision: D27080295
      
      fbshipit-source-id: 4b90f02302858af800d6e0514972a002f92a3a3d
      6e029299
    • Marc Szafraniec's avatar
      Add animal category to bootstrapping datasets · 3634173a
      Marc Szafraniec authored
      Summary:
      In the bootstrapping datasets, we might not have annotated images, but we often know very well to which animal categories they belong. This diff aims to pass down this information.
      
      For the details of the Instagram Datasets and `build_fb`, check the following diff D27045763
      
      Category to class mapping should look like that and aims to convert "layman's terms" categories, used in the datasets, to category classes (and then to mesh names with CLASS_TO_MESH_NAME_MAPPING)
      
      {F506421983}
      
      Reviewed By: vkhalidov
      
      Differential Revision: D27045669
      
      fbshipit-source-id: 3865c36e622813b7591a3a969a2fa58295a48744
      3634173a
  6. 21 Apr, 2021 3 commits
  7. 20 Apr, 2021 3 commits
  8. 17 Apr, 2021 1 commit
    • Yuxin Wu's avatar
      Add ROIMasks · 72059968
      Yuxin Wu authored
      Summary: A structure to represent masks in RoIs.
      
      Reviewed By: rbgirshick
      
      Differential Revision: D27810570
      
      fbshipit-source-id: 53e4772c91a16119650d44f7bd895f2ce60d82cb
      72059968
  9. 15 Apr, 2021 4 commits
    • Yuxin Wu's avatar
      update milestones signature for latest fvcore; update docs · f50ec07c
      Yuxin Wu authored
      Reviewed By: alexander-kirillov
      
      Differential Revision: D27771715
      
      fbshipit-source-id: afad994dcc7ef1e578b59fd8de9273323e42560d
      f50ec07c
    • Yuxin Wu's avatar
      MultiStepParamScheduler: allow num_updates to be at the end of milestones · 3755562c
      Yuxin Wu authored
      Summary: This is easier to config: just use [30, 60, 90, 120] instead of two separate configs
      
      Reviewed By: theschnitz
      
      Differential Revision: D27108999
      
      fbshipit-source-id: f8ad25c62656c429d30ea29b7fa4dcbe960540a5
      3755562c
    • Yuxin Wu's avatar
      model_zoo API for py configs · 7ce4d123
      Yuxin Wu authored
      Reviewed By: alexander-kirillov
      
      Differential Revision: D27770785
      
      fbshipit-source-id: 0128bdcc64ad22862b072946dabcc7b261204a2f
      7ce4d123
    • Yuxin Wu's avatar
      perform training logic in train_net.py · 2bfa3fb0
      Yuxin Wu authored
      Summary:
      The new system no longer has pre-defined structure, so using a DefaultTrainer(cfg) makes it confusing what cfg keys are needed.
      
      The code in DefaultTrainer is short enough to live in train_net so users can see directly what config is needed. This way we also avoid reinventing a trainer that takes new configs. We'll be able to remove newconfig/defaults.py then (or keep it private for reference)
      
      Reviewed By: theschnitz, alexander-kirillov
      
      Differential Revision: D27716057
      
      fbshipit-source-id: 248446d19bfaf601653bb25bb09765f99e3a8432
      2bfa3fb0
  10. 14 Apr, 2021 6 commits
    • Vasil Khalidov's avatar
      produce fake losses if no valid data · 6139b6f5
      Vasil Khalidov authored
      Summary: Early exit from loss iterations / methods in case where no valid points are provided.
      
      Reviewed By: MarcSzafraniec
      
      Differential Revision: D27519651
      
      fbshipit-source-id: e78df3da2e9186d98247c1c306a769641e4ddfa0
      6139b6f5
    • Yuxin Wu's avatar
      add a few py configs · 163549b0
      Yuxin Wu authored
      Summary: Others to be added later
      
      Reviewed By: alexander-kirillov
      
      Differential Revision: D27759645
      
      fbshipit-source-id: 0b41b434eb6302fbe310fa2a8cf45cef17b5682f
      163549b0
    • Yuxin Wu's avatar
      CI install iopath from master · 500ba45c
      Yuxin Wu authored
      Reviewed By: wat3rBro
      
      Differential Revision: D27752054
      
      fbshipit-source-id: 6828d65f09cf922fd61cff1860a5e0b2ed644e5a
      500ba45c
    • Yanghan Wang's avatar
      support pickle for LazyPath · 63122ac7
      Yanghan Wang authored
      Reviewed By: sujitoc, ppwwyyxx
      
      Differential Revision: D27721286
      
      fbshipit-source-id: 2869610272308314ce913a1d94c78cf809f0d485
      63122ac7
    • Yuxin Wu's avatar
      add semantic highlight when printing configs · 8b834e0b
      Yuxin Wu authored
      Reviewed By: alexander-kirillov
      
      Differential Revision: D27742322
      
      fbshipit-source-id: 6cb6f3607b3baecf897ec6e824118f143e715712
      8b834e0b
    • Yuxin Wu's avatar
      shorten import statements · f2fe041e
      Yuxin Wu authored
      Summary: expose more modules to higher level
      
      Reviewed By: alexander-kirillov
      
      Differential Revision: D27730955
      
      fbshipit-source-id: f8912959e382c4b56b8012d0bd2a4540f75740d4
      f2fe041e
  11. 13 Apr, 2021 3 commits
    • Yuxin Wu's avatar
      add checkpointable states to trainer · 085be5a3
      Yuxin Wu authored
      Summary:
      Trainer can now checkpoint its states about:
      1. optimizer & grad_scaler
      2. current iter
      3. hooks (now including scheduler)
      
      Reviewed By: alexander-kirillov
      
      Differential Revision: D27715660
      
      fbshipit-source-id: 20c4a0a613c7182fe484e5c99775e4d525137bac
      085be5a3
    • Yuxin Wu's avatar
      move broadcast logic into checkpointer · a92596c3
      Yuxin Wu authored
      Summary: simplify DefaultTrainer
      
      Reviewed By: alexander-kirillov
      
      Differential Revision: D27710586
      
      fbshipit-source-id: 77e9d8e6e2b40bf91af16af6cd236dbcbf86eca7
      a92596c3
    • Yuxin Wu's avatar
      use default_setup for new config · 7606b55c
      Yuxin Wu authored
      Reviewed By: alexander-kirillov
      
      Differential Revision: D27692660
      
      fbshipit-source-id: a7019f9b97b9b3918bcd129ed02717d77aa0bd68
      7606b55c