- 05 Jul, 2019 1 commit
-
-
吴升宇 authored
-
- 26 May, 2019 1 commit
-
-
任婷婷 authored
-
- 24 May, 2019 1 commit
-
-
吴升宇 authored
-
- 23 May, 2019 15 commits
- 22 May, 2019 2 commits
- 21 May, 2019 5 commits
- 20 May, 2019 1 commit
-
-
吴升宇 authored
-
- 03 May, 2019 1 commit
-
-
Qizhu Li authored
Avoids naming clash with torchvision CocoDetection class
-
- 25 Apr, 2019 1 commit
-
-
zimenglan authored
* make pixel indexes 0-based for bounding box in pascal voc dataset * replacing all instances of torch.distributed.deprecated with torch.distributed * replacing all instances of torch.distributed.deprecated with torch.distributed * add GroupNorm * add GroupNorm -- sort out yaml files * use torch.nn.GroupNorm instead, replace 'use_gn' with 'conv_block' and use 'BaseStem'&'Bottleneck' to simply codes * modification on 'group_norm' and 'conv_with_kaiming_uniform' function * modification on yaml files in configs/gn_baselines/ and reduce the amount of indentation and code duplication * use 'kaiming_uniform' to initialize resnet, disable gn after fc layer, and add dilation into ResNetHead * agnostic-regression for bbox * please set 'STRIDE_IN_1X1' to be 'False' when backbone use GN * add README.md for GN * add dcn from mmdetection * add documentation for finetuning cityscapes * add documentation for finetuning cityscapes * add documentation for finetuning cityscapes * add 'once_differentiable' for dcn and modify 'configs/cityscapes/README.md' * rectify the 'padding' for 'DFConv2d'
-
- 24 Apr, 2019 1 commit
-
-
Thibault FEVRY authored
-
- 22 Apr, 2019 1 commit
-
-
Jacobew authored
* Update documentation for testing and calculating mAP for each class * Update documentation for testing and calculating mAP for each class
-
- 21 Apr, 2019 2 commits
-
-
Rodrigo Berriel authored
* Add ImportError to generic except * Black formatter * OpenCV is no longer optional * Update README w.r.t. FPN_POST_NMS_PER_BATCH
-
Ren Jin authored
-
- 20 Apr, 2019 5 commits
-
-
zimenglan authored
* make pixel indexes 0-based for bounding box in pascal voc dataset * replacing all instances of torch.distributed.deprecated with torch.distributed * replacing all instances of torch.distributed.deprecated with torch.distributed * add GroupNorm * add GroupNorm -- sort out yaml files * use torch.nn.GroupNorm instead, replace 'use_gn' with 'conv_block' and use 'BaseStem'&'Bottleneck' to simply codes * modification on 'group_norm' and 'conv_with_kaiming_uniform' function * modification on yaml files in configs/gn_baselines/ and reduce the amount of indentation and code duplication * use 'kaiming_uniform' to initialize resnet, disable gn after fc layer, and add dilation into ResNetHead * agnostic-regression for bbox * please set 'STRIDE_IN_1X1' to be 'False' when backbone use GN * add README.md for GN * add dcn from mmdetection * add documentation for finetuning cityscapes * add documentation for finetuning cityscapes * add documentation for finetuning cityscapes * add 'once_differentiable' for dcn and modify 'configs/cityscapes/README.md'
-
Rodrigo Berriel authored
-
Rodrigo Berriel authored
-
zimenglan authored
* make pixel indexes 0-based for bounding box in pascal voc dataset * replacing all instances of torch.distributed.deprecated with torch.distributed * replacing all instances of torch.distributed.deprecated with torch.distributed * add GroupNorm * add GroupNorm -- sort out yaml files * use torch.nn.GroupNorm instead, replace 'use_gn' with 'conv_block' and use 'BaseStem'&'Bottleneck' to simply codes * modification on 'group_norm' and 'conv_with_kaiming_uniform' function * modification on yaml files in configs/gn_baselines/ and reduce the amount of indentation and code duplication * use 'kaiming_uniform' to initialize resnet, disable gn after fc layer, and add dilation into ResNetHead * agnostic-regression for bbox * please set 'STRIDE_IN_1X1' to be 'False' when backbone use GN * add README.md for GN * add dcn from mmdetection * add documentation for finetuning cityscapes * add documentation for finetuning cityscapes * add documentation for finetuning cityscapes
-
qianyizhang authored
-
- 19 Apr, 2019 3 commits
-
-
Simon Layton authored
* Initial multi-precision training Adds fp16 support via apex.amp Also switches communication to apex.DistributedDataParallel * Add Apex install to dockerfile * Fixes from @fmassa review Added support to tools/test_net.py SOLVER.MIXED_PRECISION -> DTYPE \in {float32, float16} apex.amp not installed now raises ImportError * Remove extraneous apex DDP import * Move to new amp API -
ChenJoya authored
* proposals from RPN per image during training * README * Update README for setting FPN_POST_NMS_TOP_N_TRAIN * Update README.md * removing extra space change
-
CoinCheung authored
* add color jitter augmentation * fix spelling
-
