fec7cd61d6
Support reading video from url ( #531 )
...
* add url support for VideoReader
* add a comment
* add unittest
* use a connectable url for ci
2020-09-07 00:52:33 +08:00
9769024fbd
Add Translate augmentation. ( #538 )
...
* add imtranslate
* add imtranslate
* update comments
* reformat
2020-09-04 20:30:42 +08:00
c6987937fe
[fix] Fix compilation bug in windows and add instruction for windows ( #540 )
...
* Add windows instruction and fix compilation bug
* reformat codebase
2020-09-04 15:08:12 +08:00
16071ed011
[Fix]: fix missing pad_val in impad_to_multiple ( #539 )
2020-09-04 15:05:14 +08:00
0664f9b3ed
bump version to 1.1.2 ( #537 )
2020-09-03 21:30:13 +08:00
fe07f09e0a
Add more default types for json dump ( #536 )
2020-09-03 19:28:45 +08:00
8dfe58d197
Fix TypeError: Scalar value for argument borderValue is longer than 4 ( #535 )
...
* fix TypeError: Scalar value for argument borderValue is longer than 4
* add comments for imshear with case that border_value has more than 3 elements
2020-09-03 17:14:49 +08:00
cfd337bb22
Support load with mmcls:// ( #511 )
...
* [Feature] Support load models from mmcls
* [Feature] Support load with mmcls://
* hard-code load mmcls
* fixed wrong commit
* add json
* remove cifar
2020-09-02 19:27:47 +08:00
06556c8459
Add shear augmentation ( #526 )
...
* Add shear augmentation
* Update geometric.py
* Update geometric.py
2020-09-02 10:57:36 +08:00
15b37b0b78
Allow imshow_det_bboxes to return image with bboxes. ( #527 )
2020-09-02 00:39:57 +08:00
fc4993cdec
[feature] Use cu92 & ubuntu1604 for torch 1.3.1 ( #524 )
...
* [feature] Use cu92 & ubuntu1604 for torch 1.3.1
* [fix]Use ubuntu-16.04 rather than latest for cu92
* [fix]: soft link cuda path
* Debug cu101 bug
* Update usr/include for cublas with cu101
* Check default nvcc version
* rm :
* add cuda root
* Try to locate cublas_v2.h
* Set cublas version
* Force cublas version
* check usr/local/cuda-10.2
* Add tree
* cp cublas files
* cp cublas files to lib64
* do not tree cuda
* fix path cp error
* cp dir
* Keep using CUDA10.1 only
* recover empty line
2020-09-01 16:15:03 +08:00
c3d8eb34ff
add Swish activation ( #522 )
...
* update impad
* fix docstring
* add shape for impad
* fix unit test
* remove old version & fix doc
* fix linting
* fix doc
* add linear decay learning rate scheduler
* fix impad
* fix setup.cfg
* fix linting
* add yapf
* add swish
* fix lr_updater
* fix lr_updater.py
* update swish
* add swish
* fix inplace
* fix typo
Co-authored-by: lixiaojie <lixiaojie@sensetime.com>
2020-08-27 00:39:17 +08:00
66a38c86f8
Move unit tests to specific folders ( #520 )
...
* move unit tests to specific folders
* fix path error
* remove some assertions
* fix ignore path
2020-08-25 20:11:56 +08:00
89e1716afe
Bump version to v1.1.1 ( #518 )
...
* bump version to 1.1.1
* add more version utils
* move parse_version_info to version.py
2020-08-24 16:30:45 +08:00
09b7d6c7dd
Import modules from a string list ( #514 )
...
* Custom imports
* Resolve comments
* Add unittest
* Add unittest
* Rename custom_imports to import_modules_from_strings
* Move import_modules_from_strings ito misc.py and allow failed imports
* small change
* small change
* change mmcv.runner to os.path
2020-08-24 13:45:34 +08:00
270e470ee1
[feature] Add collect_env() to collect environment info ( #517 )
...
* [feature] Add collect_env() to collect environment info
* fix unit tests
* fix the case when ops are not compiled
* fix docstring
2020-08-24 13:41:54 +08:00
aebdcb6661
Fix inconsistent return types in pybind11 function prototypes ( #509 )
...
* Fix function types
* Remove const
2020-08-24 12:46:04 +08:00
f4a5446e15
Support to split batched_nms when box number is too large ( #516 )
...
* Support to split batched_nms when box number is too large
* mv data from gpu to cpu
* Set split_thr through nms_cfg
* clean code
* Update motivation in docstring
* fix typos
2020-08-24 00:32:39 +08:00
83d9a9c89b
[Feature] Add diagonal flip ( #515 )
2020-08-22 14:29:27 +08:00
eb0414f495
Fix windows compile issues ( #510 )
2020-08-22 14:24:16 +08:00
5e7f785364
fix regex bugs in Widows paths ( #513 )
2020-08-21 14:04:42 +08:00
95a9728c42
Support pickle.loads ( #499 ) ( #500 )
2020-08-21 13:06:00 +08:00
77c03f44b8
bump version to 1.1.0 ( #508 )
2020-08-20 01:05:28 +08:00
11d8dd533d
support ONNX adaptive average pooling ( #504 )
...
* support ONNX adaptive average pooling
* fix double quotes
Co-authored-by: Kai Chen <chenkaidev@gmail.com>
2020-08-20 00:43:35 +08:00
5e3f56f8a6
fix mdconv addmm bug for parrots ( #450 )
...
* fix mdconv addmm bug for parrots
* fix mdconv ctv save tensor
Co-authored-by: hanyachao <hanyachao@sensetime.com>
2020-08-19 23:58:14 +08:00
6159dac24c
Update darknet url ( #507 )
2020-08-19 18:29:49 +08:00
eb65c21da2
Fix issue#505 ( #506 )
2020-08-19 16:13:20 +08:00
7a6285b190
Fix mmcv-dataparallel ( #497 )
...
* Fix mmcv-dataparallel
* Fix (parallel): fix CPU inference with MMDataParallel
* Update docstrings
* Doc (parallel): refine docstrings
* Fix (parallel): fix missing changes of train/val step function
* resolve comments
* Fix (data_parallel): fix bug when single gpu test return None
2020-08-19 14:22:40 +08:00
4ec73abbcc
Logging mode by using runner.mode ( #495 )
...
* log mode by using runner.mode
* add IterTimerHook to fix unittest
* correct the logic
* display fix when using EvalHook in train mode
* simplify logic
2020-08-17 18:50:19 +08:00
7b18b97791
fix saconv ( #489 )
...
* fix saconv
* add parrots condition
* add unittest
* fix torch version
2020-08-16 01:45:01 +08:00
eacaf475f7
fix some pavi logger hooks ( #481 )
...
* fix some pavi logger hooks
* fix unittest
* fix small bugs
* small change
* fix unittest
* Add EpochBasedRunner conditions
* Add session text
* fix small bug
* fetch runner mode from log buffer
* Add max_iter to pavi session text
* change yaml.dump to yamp.dump(yaml.load(mmcv.dump))
* Directly use by_epoch
* fix unittest
* add comments
* Use runner.epoch + 1 in pavi log
* fix runner.epoch issue for runner.mode=='val'
* fix runner.epoch issue for runner.mode=='val'
* Use abspath instead of realpath
* Add meta dump unittest
* small change
* Add comments
2020-08-16 01:20:08 +08:00
c8e85b28e4
Add `tin_shift` function ( #492 )
...
* add tin shift
* add unittest
* add docstring
* add docstring
* parrots for tin_shift
* fix lint
* fix lint
Co-authored-by: jiaomenglei <jiaomenglei@sensetime.com>
2020-08-15 22:29:07 +08:00
15537c5a39
Add LOCAL_RANK env var for slurm ( #496 )
2020-08-14 20:35:05 +08:00
d19fad02ba
Add json set_default for unserializable values ( #485 )
...
* Add json set_default for unserializable values
* kwargs.setdefault
2020-08-13 22:05:43 +08:00
dc778481cb
add op trouble shooting ( #479 )
...
* add op trouble shooting
* update trouble_shooting.md
* clean ops.md
* add trouble shooting to index.rst
* reorder
* add troubleshooting in readme
2020-08-13 22:04:58 +08:00
5ade35f4cf
use elif rather than if ( #491 )
2020-08-13 20:38:27 +08:00
4cc48073bc
Change pretrain url from aws to aliyun ( #490 )
2020-08-13 19:32:28 +08:00
e7e0c89f5c
fix the bug ( #472 ) ( #484 )
...
* fix the bug (#472 )
* fix the bug (#472 )
* fix the bug (#472 )
Co-authored-by: hezijian <hezijian@dm-ai.cn>
2020-08-13 19:30:28 +08:00
51c65c97ec
fix syncbn parameter order mismatch and parrots bug ( #488 )
2020-08-13 19:27:05 +08:00
17e4732c49
Change the epoch runner to use the data_loader from attributes rather than args. ( #483 )
2020-08-12 22:09:07 +08:00
e92f826abc
close the config file after opening ( #480 )
2020-08-11 21:28:44 +08:00
cac22f8cf5
Add pytorch 1.6 to CI ( #476 )
...
* add pytorch 1.6 to CI
* fix typo
* fix ci error
Co-authored-by: Cao Yuhang <yhcao6@gmail.com>
2020-08-09 21:56:15 +08:00
56e71a718b
Add Depthwise Seperable ConvModule ( #477 )
2020-08-09 17:29:02 +08:00
530ae20046
add pre-build packages for pytorch 1.6 ( #475 )
2020-08-09 15:44:44 +08:00
9b36c1ab3e
Fixed iter_base_runner logger ( #474 )
2020-08-09 00:04:48 +08:00
edbbc0f215
fix bug for self.warmup_iters when warmup_by_epoch ( #470 )
2020-08-06 22:07:31 +08:00
6b43ae3700
Update cnn.md ( #466 )
2020-08-06 16:51:58 +08:00
0a1cea73c1
Add dot to yml extension ( #469 )
2020-08-06 16:51:32 +08:00
045629c280
Fix torch installation in github action ( #462 )
...
* bump version to 1.0.5
* fix pytorch name
* fix version
* disable the cache
2020-08-03 23:10:39 +08:00
d36850f517
Add git hash ( #461 )
...
* Add git hash
* Add fallback
* Add func in mmcv.utils
2020-08-03 21:00:33 +08:00
Jintao Lin
Qiaofei Li
Wenwei Zhang
Kai Chen
Wang Xinjiang
Jerry Jiarui XU
Xiaojie Li
Matthew Dawkins
Matthew Dawkins
John Zhu
Kevin
robin Han
ychan
su
Jintao Lin
Cao Yuhang
Zijian He
Yuanhao Zhu
ChaseMonsterAway
Danil