Skip to content

D
detectron
Switch branch/tag
  1. 04 Nov, 2018 1 commit
  3. 30 Oct, 2018 2 commits
    • Jerry Zhang's avatar
      Renaming size() to numel() · c003e5af
      Jerry Zhang authored 
      Summary:
Codemod generated with clangr shard mode, 50 files per diff,
clangr code(size->numel): diffusion/FBS/browse/master/fbcode/caffe2/caffe2/fb/codemods/TensorMethodRename.cpp

Reviewed By: ezyang

Differential Revision: D12833487

fbshipit-source-id: 5dec5a64f91912620f3a5e48a2cc571be675c5fd
      c003e5af
    • Ilija Radosavovic's avatar
      Make yaml load/dump functions specific to the environment · ffb87f4c
      Ilija Radosavovic authored 
      Reviewed By: ashwinb

Differential Revision: D10496498

fbshipit-source-id: eb12fe573ec3270172e27c2fdb39a70fc92d8d99
      ffb87f4c
  5. 23 Oct, 2018 1 commit
  7. 19 Oct, 2018 2 commits
  9. 18 Oct, 2018 1 commit
  11. 10 Oct, 2018 1 commit
  13. 06 Oct, 2018 3 commits
  15. 02 Oct, 2018 8 commits
    • Junjie Bai's avatar
      Back out "Revert D10123245: Back out "codemod cuda_gpu_id to device_id"" (#12232) · 96147dec
      Junjie Bai authored 
      Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/12232

Original commit changeset: fca91fea58b7

This adds proper modifications to the DeviceType <->DeviceOption conversion code added in D10033396

Reviewed By: jerryzh168

Differential Revision: D10132473

fbshipit-source-id: 801ef777e2950982cb47b48051b1471a0a91e64b
      96147dec
    • Ilija Radosavovic's avatar
      Provide options for specifying vis thresholds for the demo tool · 1afde377
      Ilija Radosavovic authored 
      Reviewed By: rbgirshick

Differential Revision: D10131443

fbshipit-source-id: ee6df3147b94711eecbe558bcaf30d021976b593
      1afde377
    • Rick Ratmansky's avatar
      Revert D10123245: Back out "codemod cuda_gpu_id to device_id" · f7d394ce
      Rick Ratmansky authored 
      Differential Revision:
D10123245

Original commit changeset: d83da8e00a12

fbshipit-source-id: fca91fea58b7df208edc2e218a1d514f9821ec7b
      f7d394ce
    • Ashwin Bharambe's avatar
      Enable python3 builds · cbb0236d
      Ashwin Bharambe authored 
      Reviewed By: rbgirshick

Differential Revision: D9691247

fbshipit-source-id: 7a9c1a33698be6907dede589965f8f4f4d337f93
      cbb0236d
    • Ashwin Bharambe's avatar
      Prepare for Python3 compatibility [3] · 4dc5e92e
      Ashwin Bharambe authored 
      Summary:
A couple small issues pointed out by Ross.

 - Treating bytes as strings with a subprocess' output :/
 - Controling precision of logged floats using a workaround instead of
   FLOAT_REPR which doesn't work with newer versions of Python3.

Reviewed By: rbgirshick

Differential Revision: D9724292

fbshipit-source-id: a6aa1730f25df5d165291dc30b9350a9fff6fca6
      4dc5e92e
    • Ashwin Bharambe's avatar
      Prepare for python3 compatibility [2] · 9185b699
      Ashwin Bharambe authored 
      Summary:
There were two "bugs" associated with loading pickle files:

The first is easy: these files should have been `open()`ed as binary, but
weren't.

The second is slightly nuanced. The default encoding used wwhile unpickling
is 7-bit (ASCII.) However, the blobs are arbitrary 8-bit bytes which don't
agree. The absolute correct way to do this is to use `encoding="bytes"` and
then interpret the blob names either as ASCII, or better, as unicode utf-8. A
reasonable fix, however, is to treat it the encoding as 8-bit latin1 (which
agrees with the first 256 characters of Unicode anyway.)

As part of this, I also centralized all pickling operations into
`detectron.utils.io`.

This /still/ does not change the build to Python3, but I believe it is ready
now.

Reviewed By: rbgirshick

Differential Revision: D9689294

fbshipit-source-id: add1f2d784fe196df27b20e65e35922536d11a3c
      9185b699
    • Ashwin Bharambe's avatar
      Prepare for python3 compatibility [1] · 88dd4b1d
      Ashwin Bharambe authored 
      Summary:
This is a first step towards python3 compatibility. Specifically, it
tackles:

 - `cPickle`: uses six.moves
 - `Queue`: uses six.moves
 - `urllib2`: uses six.moves and changes `urllib2.urlopen` to `urllib.request.urlopen`

Also, fundamentally it changes the types of all config "byte" types to
"string" types. Those configurations aren't un-encoded byte streams but very
specifically ascii (or unicode encoded) strings which are specified and
consumed by human eyes.

Reviewed By: rbgirshick

Differential Revision: D9662024

fbshipit-source-id: b8372f685b57ec4260ae881a2f8bb7967f337b10
      88dd4b1d
    • Yang Liu's avatar
      Back out "codemod cuda_gpu_id to device_id" · fd09e37a
      Yang Liu authored 
      Summary:
Original commit changeset: f5614a5d2607

D9986213 is causing Multifeed Aggregator a [huge performance different](https://our.intern.facebook.com/intern/ads/analyze_canary/412951953278781781/) and is blocking aggregator push since last Friday night: https://fburl.com/feedtools/b6izvwjz
We need to land this revert ASAP to unblock aggregator push.

Reviewed By: orionr

Differential Revision: D10123245

fbshipit-source-id: d83da8e00a1250f5d09811a0a587c127e377aab2
      fd09e37a
  17. 28 Sep, 2018 1 commit
  19. 26 Sep, 2018 2 commits
  21. 22 Sep, 2018 1 commit
    • Ashwin Bharambe's avatar
      Allow overriding "regresion weights" used in GenerateProposalsOp · e8942c88
      Ashwin Bharambe authored 
      Summary:
Detectron code is inconsistent about when it uses (1, 1, 1, 1) as the
regression weights vs. `cfg.MODEL.BBOX_REG_WEIGHTS` (which has a default
value of (10, 10, 5, 5)). This change allows the caller to make the call
(heh!) about what to use.

Reviewed By: rbgirshick

Differential Revision: D9981875

fbshipit-source-id: 8798408bd2592486eb1a2e40ccb70b9bedfdbf46
      e8942c88
  23. 19 Sep, 2018 1 commit
  25. 15 Sep, 2018 1 commit
  27. 06 Sep, 2018 1 commit
    • Ashwin Bharambe's avatar
      Fix a bug in RPN proposal label generation · 3a38b7bc
      Ashwin Bharambe authored 
      Summary:
Negative labels were never set if `len(bg_inds) <= num_bg`. This
condition happens when there aren't as many negative anchor samples compared to the
typical batch size (256). Since detection scales are typically ~800, there are
plenty of negative samples and this bug is likely never hit. In any case, it
is certainly a bug which should be fixed!

Reviewed By: rbgirshick

Differential Revision: D9647703

fbshipit-source-id: fada9f4f2e0a0b5c1619940328c505e73f9a1c7e
      3a38b7bc
  29. 03 Sep, 2018 1 commit
  31. 31 Aug, 2018 1 commit
  33. 29 Aug, 2018 1 commit
  35. 24 Aug, 2018 1 commit
    • Ross Girshick's avatar
      Make data loader threads daemonic · c9ed587c
      Ross Girshick authored 
      Summary: Make data loader threads daemonic so the main process can exit when an exception is raised.

Reviewed By: ashwinb, newstzpz

Differential Revision: D9478059

fbshipit-source-id: 00bfaab51295b63c2f95ac1be99ae56a0ccf9d94
      c9ed587c
  37. 21 Aug, 2018 1 commit
    • Ross Girshick's avatar
      Avoid negatives areas found exception · 47e457a5
      Ross Girshick authored 
      Summary:
In some cases, eg training from scratch with a high LR or w/o activation normalization, we saw a "Negative Areas Found" exception. The RPN proposal generation code filters proposals that have a height or width that are too small. By default we use a `min_size` of 0. In a distant other part of the code, it computes the area of the proposals in order to determine FPN scale assignment. An issue arises because the `+ 1` in the `x2 - x1 + 1` width (and height) computation is not scale invariant. It turns out that the filter based on `min_size` was performed in the scaled input coordinates while the FPN scale assignment areas are computed using the unscaled, original image size. Thus a `min_size` of 0 can result in proposals with a negative area as measured wrt the original image. Uuuugh :P.

This diff addresses the issue by filtering based on the area in the unscaled input image and also using a generous (though still small) margin of 1 pixel for `min_size`.

Reviewed By: KaimingHe

Differential Revision: D8773216

fbshipit-source-id: b4ffbc5b6a831176b2656810edea3d3d4e52d687
      47e457a5
  39. 17 Aug, 2018 1 commit
  41. 08 Aug, 2018 1 commit
  43. 03 Aug, 2018 1 commit
  45. 02 Aug, 2018 1 commit
    • Ashwin Bharambe's avatar
      Set logging level correctly in utils/net.py · 40c39925
      Ashwin Bharambe authored 
      Summary:
AFAIK, this is what the rest of the codebase does. I don't want to
see logger.debug() messages show up during normal runs.

Differential Revision: D9071531

fbshipit-source-id: 4ac5ef57ee47bf958e35d723c379f695554f0ef0
      40c39925
  47. 31 Jul, 2018 1 commit
  49. 27 Jul, 2018 1 commit
  51. 14 Jul, 2018 1 commit
  53. 04 Jul, 2018 1 commit
    • Kaiming He's avatar
      Allow copy TRAIN.WEIGHTS to checkpoint folder · b2d24147
      Kaiming He authored 
      Summary:
Add TRAIN.COPY_WEIGHTS (default False):

When setting True, training will copy TRAIN.WEIGHTS to checkpoint folder and treat it as a candidate checkpoint. This is useful if we want to resume a checkpoint from another job (instead of using ImageNet pre-training).

Reviewed By: rbgirshick

Differential Revision: D8710711

fbshipit-source-id: 9c011227867c52eaaeb40e3c2679cff1cfccdc66
      b2d24147
  55. 03 Jul, 2018 1 commit