Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: Pavel-Konarik/detectron2
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: master
Choose a base ref
...
head repository: facebookresearch/detectron2
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: main
Choose a head ref
Checking mergeability… Don’t worry, you can still create the pull request.

Commits on Aug 4, 2021

  1. RandomSubsetTrainingSampler to randomly sample training data subset f…

    …or accuracy-data curve
    
    Summary:
    Add a sampler class `RandomSubsetTrainingSampler`, which is similar to TrainingSampler but only sample a random subset (e.g., 50%) of indices.
    `RandomSubsetTrainingSampler` is useful when you want to estimate the accuracy vs data-volume curves by training the model with different `subset_ratio`.
    
    Reviewed By: ppwwyyxx
    
    Differential Revision: D29892290
    
    fbshipit-source-id: a342a6f1aa7852feb6566c648bd673028a3e0668
    FCChen authored and facebook-github-bot committed Aug 4, 2021
    Copy the full SHA
    f410d5b View commit details
  2. Added hook that prints detailed pytorch memory stats

    Reviewed By: ppwwyyxx
    
    Differential Revision: D30076586
    
    fbshipit-source-id: 72017b55bc99d6dab2b11b663cd7da98b814b544
    valentinandrei authored and facebook-github-bot committed Aug 4, 2021
    Copy the full SHA
    a7e86f5 View commit details

Commits on Aug 5, 2021

  1. avoid warnings of NCCL

    Summary:
    Pull Request resolved: facebookresearch#3322
    
    avoid warnings like the following:
    ```
    [W ProcessGroupNCCL.cpp:1569] Rank 0 using best-guess GPU 0 to perform barrier as devices used by
    this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is
    incorrect. Specify device_ids in barrier() to force use of a particular device.
    ```
    
    maybe can fix the hang in facebookresearch#3319
    
    Reviewed By: vaibhava0
    
    Differential Revision: D30077957
    
    fbshipit-source-id: b8827e66c5eecc06b650acde2e7ff44106327f69
    ppwwyyxx authored and facebook-github-bot committed Aug 5, 2021
    Copy the full SHA
    64e84c5 View commit details
  2. test opencv exif reading

    Differential Revision: D26773548
    
    fbshipit-source-id: 94bdd659b2bf35235de411795f20d6cd8f045fa4
    ppwwyyxx authored and facebook-github-bot committed Aug 5, 2021
    Copy the full SHA
    b669a88 View commit details
  3. remove warnings about cell_anchors

    Summary: close facebookresearch#3313
    
    Reviewed By: vaibhava0
    
    Differential Revision: D30062746
    
    fbshipit-source-id: ed548c2b0513933a1071364ac4824f5346675918
    ppwwyyxx authored and facebook-github-bot committed Aug 5, 2021
    Copy the full SHA
    8bdde38 View commit details
  4. fix copyright headers

    Summary: close T85305354
    
    Reviewed By: vaibhava0
    
    Differential Revision: D30063498
    
    fbshipit-source-id: 251a0700d92071bcb1f9eea1e8bc736119ab552a
    ppwwyyxx authored and facebook-github-bot committed Aug 5, 2021
    Copy the full SHA
    0fb7f04 View commit details

Commits on Aug 10, 2021

  1. cat Keypoints

    Summary: Add cat methods to Keypoints
    
    Reviewed By: ppwwyyxx
    
    Differential Revision: D30199199
    
    fbshipit-source-id: 7d2c63810e7e05931c90b7ea5102a734b7ce8af4
    Zhipeng Fan authored and facebook-github-bot committed Aug 10, 2021
    Copy the full SHA
    ace739a View commit details
  2. fix for pytorch1.7

    Reviewed By: alexander-kirillov, bowenc0221
    
    Differential Revision: D30215015
    
    fbshipit-source-id: 90c6a791c23f4edacdc7e7a95b41586582e8da93
    ppwwyyxx authored and facebook-github-bot committed Aug 10, 2021
    Copy the full SHA
    fefb626 View commit details
  3. Expose stats_mode N for NaiveSyncBN

    Summary:
    * Current code does not enable user to choose stats_mode="N" for naiveSyncBN. This change exposes that.
      - stats_mode="N" is necessary for supporting zero-length inputs. Without it:  `SyncBatchNorm(stats_mode="") does not support zero batch size.`
    
    ------------------------
    
    Reviewed By: jonmorton, vaibhava0, ppwwyyxx
    
    Differential Revision: D29362934
    
    fbshipit-source-id: f8d5a33cac599f706e6620c31495e8c1577970dc
    Carolyn Soo authored and facebook-github-bot committed Aug 10, 2021
    Copy the full SHA
    3924daf View commit details

Commits on Aug 11, 2021

  1. Use current device id in dist.barrier

    Summary:
    Pull Request resolved: facebookresearch#3350
    
    `get_local_rank` relies on a global variable set by Detectron2's `launch` utils.
    Since other frameworks might use Detectron2's distribute utils but don't launch with Detectron2's `launch` utils. Use `torch.cuda.current_device` to get the current device instead.
    
    Reviewed By: HarounH, ppwwyyxx
    
    Differential Revision: D30233746
    
    fbshipit-source-id: 0b140ed5c1e7cd87ccf05235127f338ffc40a53d
    kazhang authored and facebook-github-bot committed Aug 11, 2021
    Copy the full SHA
    42286d3 View commit details
  2. fix check of multinode

    Summary: rank is 0-based
    
    Reviewed By: bowenc0221
    
    Differential Revision: D30258674
    
    fbshipit-source-id: 1e8331e303fdcce8c96c500e520ffadc000f06ba
    ppwwyyxx authored and facebook-github-bot committed Aug 11, 2021
    Copy the full SHA
    7825f07 View commit details

Commits on Aug 19, 2021

  1. avoid list[ndarray] -> tensor conversion in Boxes

    Summary:
    avoid wanings like:
    ```
    detectron2/structures/boxes.py:158: UserWarning: Creating a tensor from a list
    of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray
    with numpy.array() before converting to a tensor. (Triggered internally at torch/csrc/utils/tensor_new.cpp:201.)
    ```
    
    Reviewed By: wat3rBro
    
    Differential Revision: D30172338
    
    fbshipit-source-id: fbe044fead72722b3c6eb9916faa2a7dca3e6eae
    ppwwyyxx authored and facebook-github-bot committed Aug 19, 2021
    Copy the full SHA
    dba3eec View commit details
  2. rename matched_boxlist_iou -> matched_pairwise_iou

    Summary:
    The naming "boxlist" comes from maskrcnn-benchmark. This functions is created when pairwise_iou is
    called `boxlist_iou`.
    
    Rename it to follow a consistent naming.
    
    Reviewed By: jonmorton
    
    Differential Revision: D30428372
    
    fbshipit-source-id: be73f5acb1c6a5a2266c2b7706394b1f84f23479
    ppwwyyxx authored and facebook-github-bot committed Aug 19, 2021
    Copy the full SHA
    de6416b View commit details

Commits on Aug 23, 2021

  1. let MapDataset support iterable

    Summary:
    Most production use cases needs error handling.
    This is not available in pytorch's `.map()`.
    
    This is useful as we move towards using more IterableDataset
    
    Differential Revision: D30123656
    
    fbshipit-source-id: 17c4caa3e4ed18c1b073bbfe8309ca3b3681a59b
    ppwwyyxx authored and facebook-github-bot committed Aug 23, 2021
    Copy the full SHA
    f327aac View commit details
  2. scripting support for C4 models

    Summary:
    Pull Request resolved: facebookresearch#3318
    
    Just add some typing.
    
    fix facebookresearch#3302
    
    Reviewed By: zhanghang1989, wat3rBro
    
    Differential Revision: D30062501
    
    fbshipit-source-id: c1f2a3cb42f8ee11d5e8c582fc5b8f5464c438d0
    ppwwyyxx authored and facebook-github-bot committed Aug 23, 2021
    Copy the full SHA
    93cfe42 View commit details
  3. stop using docker in circleci

    Summary: see context in T88568338
    
    Reviewed By: wat3rBro
    
    Differential Revision: D30063970
    
    fbshipit-source-id: 1ad0ac0dfb72a6c7aba6e4263724550e4042c664
    ppwwyyxx authored and facebook-github-bot committed Aug 23, 2021
    Copy the full SHA
    d7848aa View commit details
  4. Add linear box2box transform and pairwise distance

    Summary: both used in FCOS
    
    Reviewed By: zhanghang1989
    
    Differential Revision: D30470063
    
    fbshipit-source-id: 495494a669acd9f706c3845551252ced4acc9888
    ppwwyyxx authored and facebook-github-bot committed Aug 23, 2021
    Copy the full SHA
    2866c43 View commit details
  5. fix support for empty annotations

    Summary: fix facebookresearch#3401
    
    Reviewed By: wat3rBro
    
    Differential Revision: D30491149
    
    fbshipit-source-id: 0af0d850afcb4aa451da2975aa46c4c854138523
    ppwwyyxx authored and facebook-github-bot committed Aug 23, 2021
    Copy the full SHA
    dbe2c9c View commit details
  6. check for errors in SemSegFPNHead

    Summary: close facebookresearch#3316
    
    Reviewed By: wat3rBro
    
    Differential Revision: D30062593
    
    fbshipit-source-id: e8b614c21f62012e081f425dd9df850179f1f2a7
    ppwwyyxx authored and facebook-github-bot committed Aug 23, 2021
    Copy the full SHA
    2538c9d View commit details
  7. raise clear error message for mismatched keypoint metadata

    Summary:
    The error message in facebookresearch#3341
    is not informative
    
    Reviewed By: wat3rBro
    
    Differential Revision: D30185963
    
    fbshipit-source-id: 11fda5e6e22851942b5da9df09b6ec4e315eddef
    ppwwyyxx authored and facebook-github-bot committed Aug 23, 2021
    Copy the full SHA
    2413859 View commit details

Commits on Aug 24, 2021

  1. use OmegaConf.select in omegaconf2.1

    Reviewed By: wat3rBro
    
    Differential Revision: D29738743
    
    fbshipit-source-id: 08b49cabe5c1c43478418600e3f0076e443d2e22
    ppwwyyxx authored and facebook-github-bot committed Aug 24, 2021
    Copy the full SHA
    ff638c9 View commit details
  2. allow torchscript tests to run on CPUs

    Summary: close T88689498
    
    Reviewed By: vaibhava0
    
    Differential Revision: D30063379
    
    fbshipit-source-id: 23cddad66c17857f96bd60f59cf9f67291aedfff
    ppwwyyxx authored and facebook-github-bot committed Aug 24, 2021
    Copy the full SHA
    6e7def9 View commit details
  3. Best Checkpointing Hook

    Summary:
    Implemented hook for saving best model, as discussed in facebookresearch#2114
    
    Pull Request resolved: facebookresearch#3222
    
    Reviewed By: zhanghang1989
    
    Differential Revision: D29764303
    
    Pulled By: ppwwyyxx
    
    fbshipit-source-id: b5cb42b34a15ea151cce8fe992a9f35a964a6afe
    levan92 authored and facebook-github-bot committed Aug 24, 2021
    Copy the full SHA
    fe4d35b View commit details
  4. suppress errors in fbcode/vision - batch 1

    Differential Revision: D30514760
    
    fbshipit-source-id: f80b301ae5ea779588a9d634c1baa35f8f2d3e99
    Pyre Bot Jr authored and facebook-github-bot committed Aug 24, 2021
    Copy the full SHA
    2a345c1 View commit details

Commits on Aug 25, 2021

  1. support IterableDataset in build_detection_train_loader

    Differential Revision: D24677397
    
    fbshipit-source-id: 1e4a991c521da1e139ccc7fe40b715dc921d3294
    ppwwyyxx authored and facebook-github-bot committed Aug 25, 2021
    Copy the full SHA
    05bc843 View commit details

Commits on Aug 26, 2021

  1. remove FastRCNNOutputs

    Summary: it has been deprecated for 1 year. moving to internal
    
    Reviewed By: jonmorton
    
    Differential Revision: D25876263
    
    fbshipit-source-id: 2ee8cab3b25b66664792578bb40194d813208f2e
    ppwwyyxx authored and facebook-github-bot committed Aug 26, 2021
    Copy the full SHA
    11528ce View commit details

Commits on Aug 27, 2021

  1. fix MapDataset creation in python 3.9

    Summary:
    fix facebookresearch#3405
    
    The old code works for python 3.6 & 3.7; fails for python 3.9
    
    Reviewed By: zhanghang1989
    
    Differential Revision: D30599139
    
    fbshipit-source-id: ab9e5d68387b68e1095112e9c2531a971567accc
    ppwwyyxx authored and facebook-github-bot committed Aug 27, 2021
    Copy the full SHA
    01120e4 View commit details
  2. fix linter

    Summary: run ./dev/linter.sh
    
    Reviewed By: zhanghang1989
    
    Differential Revision: D30599861
    
    fbshipit-source-id: 8957443bb1ca9e143ca11a2e2675b8513ed63d16
    ppwwyyxx authored and facebook-github-bot committed Aug 27, 2021
    Copy the full SHA
    d67c7f3 View commit details
  3. Always detach tensor in visualization

    Summary:
    Thanks for your contribution!.
    Fixed the following runtime Error : numpy() fails when visualizing an output element of a input batch during inference
    
    Pull Request resolved: facebookresearch#3400
    
    Reviewed By: jonmorton
    
    Differential Revision: D30560943
    
    Pulled By: ppwwyyxx
    
    fbshipit-source-id: abe94a12b67a5c8bad2a60fff989072f99b70d16
    harishsg99 authored and facebook-github-bot committed Aug 27, 2021
    Copy the full SHA
    b9d83a3 View commit details
  4. add python 3.9 to CircleCI

    Summary:
    Pull Request resolved: facebookresearch#3410
    
    avoid bugs like the last diff
    
    Reviewed By: zhanghang1989
    
    Differential Revision: D30599205
    
    fbshipit-source-id: 3b2abd2885d384bd3f2a29b454d3da5e023e01a3
    ppwwyyxx authored and facebook-github-bot committed Aug 27, 2021
    Copy the full SHA
    ea3b3f2 View commit details

Commits on Aug 30, 2021

  1. add __len__ for ToIterableDataset

    Reviewed By: zhanghang1989
    
    Differential Revision: D30635073
    
    fbshipit-source-id: 664ba17b768a69fed97ca94b944e43d186336966
    ppwwyyxx authored and facebook-github-bot committed Aug 30, 2021
    Copy the full SHA
    cbbc1ce View commit details

Commits on Sep 1, 2021

  1. Update mmdetection to latest github master

    Summary:
    Wanted to use some of the latest additions to mmdetection; in particular, the UniformAssignment from YOLOF (Free box AP win, even in two stage models!).
    
    I just cloned latest mmdetection and copied into `deeplearning/projects/third_party/mmdetection`.
    
    Reviewed By: ppwwyyxx
    
    Differential Revision: D30598178
    
    fbshipit-source-id: 05fc559534a2fde41b36fc8c088c4e5c1729e7a2
    jonmorton authored and facebook-github-bot committed Sep 1, 2021
    Copy the full SHA
    faf6587 View commit details

Commits on Sep 2, 2021

  1. Make vis module importable, remove required torch and torchvision

    Summary:
    In PR facebookresearch#3311 we made densepose a pip-installable Python package. However, we forgot to include an `__init__.py` so that the `vis` module is importable. This PR adds that `__init__.py`.
    
    It was also mentioned in that PR that there is a preference not to require torch and torchvision requirements versions:
    facebookresearch#3311 (comment)
    
    This PR also removes those requirements from the `setup.py` and lists them instead in the prerequisites in the documentation.
    
    Pull Request resolved: facebookresearch#3382
    
    Reviewed By: patricklabatut
    
    Differential Revision: D30462761
    
    Pulled By: vkhalidov
    
    fbshipit-source-id: e58985ff24cc75ff1d7905a863fa040e3be99bc3
    pjbull authored and facebook-github-bot committed Sep 2, 2021
    Copy the full SHA
    55c0078 View commit details
  2. Increase limit on number of detections per image in {COCO,LVIS}Evaluator

    Summary:
    ## Context
    - The current limit on the number of detections per image (`K`) in LVIS is 300.
    - Implementing AP_pool/AP_fixed requires removing this default limit on `K`
    - [Literature](https://arxiv.org/pdf/2102.01066.pdf) has shown that increasing `K` correlates with AP gains
    
    ## This Diff
    - Changed limit on number of detections per image (`K`) to be customizable for LVIS and COCO through `TEST.DETECTIONS_PER_IMAGE` in the config
       - For COCO:
           - Maintain the default `max_dets_per_image` to be [1, 10, 100] as from [COCOEval](https://www.internalfb.com/code/fbsource/[88bb57c3054a]/fbcode/deeplearning/projects/cocoApi/PythonAPI/pycocotools/cocoeval.py?lines=28-29)
           - Allow users to input a custom integer for `TEST.DETECTIONS_PER_IMAGE` in the config, and use  [1, 10, `TEST.DETECTIONS_PER_IMAGE`] for COCOEval
       - For LVIS:
           - Maintain the default `max_dets_per_image` to be 300 as from [LVISEval](https://www.internalfb.com/code/fbsource/[f6b86d023721]/fbcode/deeplearning/projects/lvisApi/lvis/eval.py?lines=528-529)
           - Allow users to input a custom integer for `TEST.DETECTIONS_PER_IMAGE` in the config, and use this in LVISEval
    - Added `COCOevalMaxDets` for evaluating AP with the custom limit on number of detections per image (since default `COCOeval` uses 100 as limit on detections per image for evaluating AP)
    
    ## Inference Runs using this Diff
    - Performed inference using `K = {300, 1000, 10000, 100000}`
    - Launched fblearner flows for object detector baseline models with N1055536 (LVIS) and N1055756 (COCO)
      - Recorded [results of running inference](https://docs.google.com/spreadsheets/d/1rgdjN2KvxcYfKCkGUC4tMw0XQJ5oZL0dwjOIh84YRg8/edit?usp=sharing)
    
    Reviewed By: ppwwyyxx
    
    Differential Revision: D30077359
    
    fbshipit-source-id: 372eb5e0d7c228fb77fe23bf80d53597ec66287b
    Lydia Chan authored and facebook-github-bot committed Sep 2, 2021
    Copy the full SHA
    23486b6 View commit details

Commits on Sep 8, 2021

  1. add a scriptable ResizeShortestEdge.get_output_shape

    Summary: this function alone is useful in deployment
    
    Reviewed By: zhanghang1989
    
    Differential Revision: D30801733
    
    fbshipit-source-id: 792f8ca016f2c6782fc25c9bbaa302588597d087
    ppwwyyxx authored and facebook-github-bot committed Sep 8, 2021
    Copy the full SHA
    e9cbe90 View commit details
  2. Correct typo

    Summary:
    Correct typo
    to to swap -> to swap
    Regarding issue facebookresearch#3458
    
    Thanks for your contribution!
    
    If you're sending a large PR (e.g., >100 lines),
    please open an issue first about the feature / bug, and indicate how you want to contribute.
    
    We do not always accept features.
    See https://detectron2.readthedocs.io/notes/contributing.html#pull-requests about how we handle PRs.
    
    Before submitting a PR, please run `dev/linter.sh` to lint the code.
    
    Pull Request resolved: facebookresearch#3459
    
    Reviewed By: zhanghang1989
    
    Differential Revision: D30802143
    
    Pulled By: ppwwyyxx
    
    fbshipit-source-id: a820fa521d9e54c32d4af614ea48df3207dc6515
    puhuk authored and facebook-github-bot committed Sep 8, 2021
    Copy the full SHA
    f88b04f View commit details

Commits on Sep 10, 2021

  1. support creating bitmasks from empty polygons

    Reviewed By: HannaMao
    
    Differential Revision: D30795434
    
    fbshipit-source-id: 7a841e0f980f6c8ff40411acff9c732a53ac2c3b
    ppwwyyxx authored and facebook-github-bot committed Sep 10, 2021
    Copy the full SHA
    5c923c6 View commit details

Commits on Sep 13, 2021

  1. pre compute trimap weights

    Summary:
    Pre-computing trimap weights avoids unnecessary CPU <--> GPU copy during
    loss calculation and leads to 45% training speed up. In addition to that, this
    also brings accuracy improvements. For xirp17e res 160 Portal model
    pre-computing trimap weights got +0.7 IOU, +1.2 B-IOU and +0.2 BT-IOU. Note
    that the Portal model still uses the trimap computation and not boundary loss.
    In fact, for xirp17e boundary loss did not show additional gains compared to
    trimap.
    
    Reviewed By: wenliangzhao2018
    
    Differential Revision: D30200036
    
    fbshipit-source-id: 4e6c5f022b341757c93678e81d73d2e8c259b43a
    Siddharth Shah authored and facebook-github-bot committed Sep 13, 2021
    Copy the full SHA
    23f61b8 View commit details

Commits on Sep 15, 2021

  1. Fix the coco_evaluation for keypoints

    Summary: Fix the keypoint evaluation pipeline.
    
    Reviewed By: ppwwyyxx
    
    Differential Revision: D30904414
    
    fbshipit-source-id: ef8bff166fccf2ef059013ae97ff119f8a9b4df0
    XiaoliangDai authored and facebook-github-bot committed Sep 15, 2021
    Copy the full SHA
    ce5b1c5 View commit details

Commits on Sep 16, 2021

  1. fix ColorMode.IMAGE_BW of visualizer

    Summary: fix facebookresearch#3486
    
    Reviewed By: zhanghang1989
    
    Differential Revision: D30974958
    
    fbshipit-source-id: 68c7d041f3b5b64eb0c32b4fcc99ad6d13e3542f
    ppwwyyxx authored and facebook-github-bot committed Sep 16, 2021
    Copy the full SHA
    6545979 View commit details

Commits on Sep 17, 2021

  1. Visualizer: make keypoint threshold configurable

    Summary: Make the keypoint threshold a class member, so it can be changed.
    
    Reviewed By: ppwwyyxx
    
    Differential Revision: D30690598
    
    fbshipit-source-id: 29499eaf12257e5bb4871ea318dc4ab5523d304e
    jonmorton authored and facebook-github-bot committed Sep 17, 2021
    Copy the full SHA
    018fca8 View commit details

Commits on Sep 20, 2021

  1. Fix reduction of cross_entropy

    Summary:
    Reduction of cross_entropy is always set to "mean".
    Fixed to receive the reduction.
    
    Pull Request resolved: facebookresearch#3454
    
    Reviewed By: zhanghang1989
    
    Differential Revision: D31052191
    
    Pulled By: ppwwyyxx
    
    fbshipit-source-id: 0bd992cac13c67a772fac8539ab5cc4f7c8e5c3c
    Sukjun Hwang authored and facebook-github-bot committed Sep 20, 2021
    Copy the full SHA
    8b38097 View commit details
  2. Fix typo (provid -> provide)

    Summary:
    Thanks for your contribution!
    
    If you're sending a large PR (e.g., >100 lines),
    please open an issue first about the feature / bug, and indicate how you want to contribute.
    
    We do not always accept features.
    See https://detectron2.readthedocs.io/notes/contributing.html#pull-requests about how we handle PRs.
    
    Before submitting a PR, please run `dev/linter.sh` to lint the code.
    
    Pull Request resolved: facebookresearch#3476
    
    Reviewed By: zhanghang1989
    
    Differential Revision: D31052262
    
    Pulled By: ppwwyyxx
    
    fbshipit-source-id: d1f7ab357ce48e4d7735e024d6441a96b863bd71
    jordan-bonecutter authored and facebook-github-bot committed Sep 20, 2021
    Copy the full SHA
    7c2173b View commit details
  3. set default pre-trained model to empty

    Summary: Empty is a better default
    
    Reviewed By: zhanghang1989
    
    Differential Revision: D30980361
    
    fbshipit-source-id: 9ad2bde6b9d9462ccf7cf953c33894a0c0279ad1
    ppwwyyxx authored and facebook-github-bot committed Sep 20, 2021
    Copy the full SHA
    5b29850 View commit details
  4. Update document (training.md)

    Summary:
    Correct typo
    standarized -> standardized
    Regarding issue facebookresearch#3467
    
    Thanks for your contribution!
    
    If you're sending a large PR (e.g., >100 lines),
    please open an issue first about the feature / bug, and indicate how you want to contribute.
    
    We do not always accept features.
    See https://detectron2.readthedocs.io/notes/contributing.html#pull-requests about how we handle PRs.
    
    Before submitting a PR, please run `dev/linter.sh` to lint the code.
    
    Pull Request resolved: facebookresearch#3468
    
    Reviewed By: zhanghang1989
    
    Differential Revision: D31052099
    
    Pulled By: ppwwyyxx
    
    fbshipit-source-id: 4128566943cfa54fcebd357d6c1a1f9dda70a7da
    puhuk authored and facebook-github-bot committed Sep 20, 2021
    Copy the full SHA
    d6a5e64 View commit details
  5. config: warning when the dumped yaml is invalid

    Summary: if dumped yaml is unloadable, print warning and save a pkl
    
    Reviewed By: zhanghang1989
    
    Differential Revision: D30975516
    
    fbshipit-source-id: c2eb839c9ffcdee7951d78b01e5c10939debec77
    ppwwyyxx authored and facebook-github-bot committed Sep 20, 2021
    Copy the full SHA
    a8b8aa3 View commit details
  6. let LazyCall support dataclasses

    Summary: it was unsupported due to omegaconf
    
    Reviewed By: zhanghang1989
    
    Differential Revision: D30753898
    
    fbshipit-source-id: d47b014bdc806023ebc95364359d8695865cd3c7
    ppwwyyxx authored and facebook-github-bot committed Sep 20, 2021
    Copy the full SHA
    730ccef View commit details

Commits on Sep 25, 2021

  1. remove caffe2-export of panopticfpn

    Summary: Caffe2 export should be deprecated. Start from the least used model.
    
    Reviewed By: wat3rBro
    
    Differential Revision: D31038278
    
    fbshipit-source-id: 18fd26942dd35f3a542f2da1e593b6c629a22ba1
    ppwwyyxx authored and facebook-github-bot committed Sep 25, 2021
    Copy the full SHA
    be945b3 View commit details
  2. support using bitmask with LSJ

    Summary:
    `polygons_to_bitmask` fails with empty polygon which could happen with LSJ.
    
    Pull Request resolved: fairinternal/detectron2#564
    
    Reviewed By: HannaMao
    
    Differential Revision: D31181422
    
    Pulled By: ppwwyyxx
    
    fbshipit-source-id: 5f955e04518bae153401df0760840f5daf0da66a
    bowenc0221 authored and facebook-github-bot committed Sep 25, 2021
    Copy the full SHA
    2a1cec4 View commit details

Commits on Sep 28, 2021

  1. support iterable dataset in build_detection_test_loader

    Summary: Like D24677397 (facebookresearch@05bc843), but for test loader
    
    Differential Revision: D31161853
    
    fbshipit-source-id: 6c101843a2be681fc23b2ff241070876a77be80f
    ppwwyyxx authored and facebook-github-bot committed Sep 28, 2021
    Copy the full SHA
    0a2a4a3 View commit details
Loading