Merge branch 'master' of github.com:open-mmlab/mmdetection

README.md

@@ -194,7 +194,7 @@ Here is an example.
             'bboxes': <np.ndarray> (n, 4),
             'labels': <np.ndarray> (n, ),
             'bboxes_ignore': <np.ndarray> (k, 4),
-            'labels_ignore': <np.ndarray> (k, 4) (optional field)
+            'labels_ignore': <np.ndarray> (k, ) (optional field)
         }
     },
     ...
@@ -206,12 +206,12 @@ There are two ways to work with custom datasets.
 - online conversion
 
   You can write a new Dataset class inherited from `CustomDataset`, and overwrite two methods
-  `load_annotations(self, ann_file)` and `get_ann_info(self, idx)`, like [CocoDataset](mmdet/datasets/coco.py).
+  `load_annotations(self, ann_file)` and `get_ann_info(self, idx)`, like [CocoDataset](mmdet/datasets/coco.py) and [VOCDataset](mmdet/datasets/voc.py).
 
 - offline conversion
 
   You can convert the annotation format to the expected format above and save it to
-  a pickle file, like [pascal_voc.py](tools/convert_datasets/pascal_voc.py).
+  a pickle or json file, like [pascal_voc.py](tools/convert_datasets/pascal_voc.py).
   Then you can simply use `CustomDataset`.
 
 ## Technical details

configs/faster_rcnn_ohem_r50_fpn_1x.py

+# model settings
+model = dict(
+    type='FasterRCNN',
+    pretrained='modelzoo://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_scales=[8],
+        anchor_ratios=[0.5, 1.0, 2.0],
+        anchor_strides=[4, 8, 16, 32, 64],
+        target_means=[.0, .0, .0, .0],
+        target_stds=[1.0, 1.0, 1.0, 1.0],
+        use_sigmoid_cls=True),
+    bbox_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
+        out_channels=256,
+        featmap_strides=[4, 8, 16, 32]),
+    bbox_head=dict(
+        type='SharedFCBBoxHead',
+        num_fcs=2,
+        in_channels=256,
+        fc_out_channels=1024,
+        roi_feat_size=7,
+        num_classes=81,
+        target_means=[0., 0., 0., 0.],
+        target_stds=[0.1, 0.1, 0.2, 0.2],
+        reg_class_agnostic=False))
+# model training and testing settings
+train_cfg = dict(
+    rpn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.7,
+            neg_iou_thr=0.3,
+            min_pos_iou=0.3,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=256,
+            pos_fraction=0.5,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=False),
+        allowed_border=0,
+        pos_weight=-1,
+        smoothl1_beta=1 / 9.0,
+        debug=False),
+    rcnn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.5,
+            min_pos_iou=0.5,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='OHEMSampler',
+            num=512,
+            pos_fraction=0.25,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=True),
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    rpn=dict(
+        nms_across_levels=False,
+        nms_pre=2000,
+        nms_post=2000,
+        max_num=2000,
+        nms_thr=0.7,
+        min_bbox_size=0),
+    rcnn=dict(
+        score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100)
+    # soft-nms is also supported for rcnn testing
+    # e.g., nms=dict(type='soft_nms', iou_thr=0.5, min_score=0.05)
+)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0.5,
+        with_mask=False,
+        with_crowd=True,
+        with_label=True),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_crowd=True,
+        with_label=True),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_label=False,
+        test_mode=True))
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    step=[8, 11])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 12
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/faster_rcnn_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/pascal_voc/faster_rcnn_r50_fpn_1x_voc0712.py

+# model settings
+model = dict(
+    type='FasterRCNN',
+    pretrained='modelzoo://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_scales=[8],
+        anchor_ratios=[0.5, 1.0, 2.0],
+        anchor_strides=[4, 8, 16, 32, 64],
+        target_means=[.0, .0, .0, .0],
+        target_stds=[1.0, 1.0, 1.0, 1.0],
+        use_sigmoid_cls=True),
+    bbox_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
+        out_channels=256,
+        featmap_strides=[4, 8, 16, 32]),
+    bbox_head=dict(
+        type='SharedFCBBoxHead',
+        num_fcs=2,
+        in_channels=256,
+        fc_out_channels=1024,
+        roi_feat_size=7,
+        num_classes=21,
+        target_means=[0., 0., 0., 0.],
+        target_stds=[0.1, 0.1, 0.2, 0.2],
+        reg_class_agnostic=False))
+# model training and testing settings
+train_cfg = dict(
+    rpn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.7,
+            neg_iou_thr=0.3,
+            min_pos_iou=0.3,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=256,
+            pos_fraction=0.5,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=False),
+        allowed_border=0,
+        pos_weight=-1,
+        smoothl1_beta=1 / 9.0,
+        debug=False),
+    rcnn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.5,
+            min_pos_iou=0.5,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=512,
+            pos_fraction=0.25,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=True),
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    rpn=dict(
+        nms_across_levels=False,
+        nms_pre=2000,
+        nms_post=2000,
+        max_num=2000,
+        nms_thr=0.7,
+        min_bbox_size=0),
+    rcnn=dict(
+        score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100)
+    # soft-nms is also supported for rcnn testing
+    # e.g., nms=dict(type='soft_nms', iou_thr=0.5, min_score=0.05)
+)
+# dataset settings
+dataset_type = 'VOCDataset'
+data_root = 'data/VOCdevkit/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type='RepeatDataset',  # to avoid reloading datasets frequently
+        times=3,
+        dataset=dict(
+            type=dataset_type,
+            ann_file=[
+                data_root + 'VOC2007/ImageSets/Main/trainval.txt',
+                data_root + 'VOC2012/ImageSets/Main/trainval.txt'
+            ],
+            img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
+            img_scale=(1000, 600),
+            img_norm_cfg=img_norm_cfg,
+            size_divisor=32,
+            flip_ratio=0.5,
+            with_mask=False,
+            with_crowd=True,
+            with_label=True)),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
+        img_prefix=data_root + 'VOC2007/',
+        img_scale=(1000, 600),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_crowd=True,
+        with_label=True),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
+        img_prefix=data_root + 'VOC2007/',
+        img_scale=(1000, 600),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_label=False,
+        test_mode=True))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(policy='step', step=[3])  # actual epoch = 3 * 3 = 9
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 4  # actual epoch = 4 * 3 = 12
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/faster_rcnn_r50_fpn_1x_voc0712'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

mmdet/apis/train.py

@@ -6,8 +6,8 @@ import torch
 from mmcv.runner import Runner, DistSamplerSeedHook
 from mmcv.parallel import MMDataParallel, MMDistributedDataParallel
 
-from mmdet.core import (DistOptimizerHook, CocoDistEvalRecallHook,
-                        CocoDistEvalmAPHook)
+from mmdet.core import (DistOptimizerHook, DistEvalmAPHook,
+                        CocoDistEvalRecallHook, CocoDistEvalmAPHook)
 from mmdet.datasets import build_dataloader
 from mmdet.models import RPN
 from .env import get_root_logger
@@ -81,9 +81,13 @@ def _dist_train(model, dataset, cfg, validate=False):
     # register eval hooks
     if validate:
         if isinstance(model.module, RPN):
+            # TODO: implement recall hooks for other datasets
             runner.register_hook(CocoDistEvalRecallHook(cfg.data.val))
-        elif cfg.data.val.type == 'CocoDataset':
+        else:
+            if cfg.data.val.type == 'CocoDataset':
                 runner.register_hook(CocoDistEvalmAPHook(cfg.data.val))
+            else:
+                runner.register_hook(DistEvalmAPHook(cfg.data.val))
 
     if cfg.resume_from:
         runner.resume(cfg.resume_from)

mmdet/core/bbox/assign_sampling.py

@@ -3,23 +3,23 @@ import mmcv
 from . import assigners, samplers
 
 
-def build_assigner(cfg, default_args=None):
+def build_assigner(cfg, **kwargs):
     if isinstance(cfg, assigners.BaseAssigner):
         return cfg
     elif isinstance(cfg, dict):
         return mmcv.runner.obj_from_dict(
-            cfg, assigners, default_args=default_args)
+            cfg, assigners, default_args=kwargs)
     else:
         raise TypeError('Invalid type {} for building a sampler'.format(
             type(cfg)))
 
 
-def build_sampler(cfg, default_args=None):
+def build_sampler(cfg, **kwargs):
     if isinstance(cfg, samplers.BaseSampler):
         return cfg
     elif isinstance(cfg, dict):
         return mmcv.runner.obj_from_dict(
-            cfg, samplers, default_args=default_args)
+            cfg, samplers, default_args=kwargs)
     else:
         raise TypeError('Invalid type {} for building a sampler'.format(
             type(cfg)))

mmdet/core/bbox/samplers/__init__.py

@@ -4,10 +4,11 @@ from .random_sampler import RandomSampler
 from .instance_balanced_pos_sampler import InstanceBalancedPosSampler
 from .iou_balanced_neg_sampler import IoUBalancedNegSampler
 from .combined_sampler import CombinedSampler
+from .ohem_sampler import OHEMSampler
 from .sampling_result import SamplingResult
 
 __all__ = [
     'BaseSampler', 'PseudoSampler', 'RandomSampler',
     'InstanceBalancedPosSampler', 'IoUBalancedNegSampler', 'CombinedSampler',
-    'SamplingResult'
+    'OHEMSampler', 'SamplingResult'
 ]

mmdet/core/bbox/samplers/base_sampler.py

@@ -7,19 +7,33 @@ from .sampling_result import SamplingResult
 
 class BaseSampler(metaclass=ABCMeta):
 
-    def __init__(self):
+    def __init__(self,
+                 num,
+                 pos_fraction,
+                 neg_pos_ub=-1,
+                 add_gt_as_proposals=True,
+                 **kwargs):
+        self.num = num
+        self.pos_fraction = pos_fraction
+        self.neg_pos_ub = neg_pos_ub
+        self.add_gt_as_proposals = add_gt_as_proposals
         self.pos_sampler = self
         self.neg_sampler = self
 
     @abstractmethod
-    def _sample_pos(self, assign_result, num_expected):
+    def _sample_pos(self, assign_result, num_expected, **kwargs):
         pass
 
     @abstractmethod
-    def _sample_neg(self, assign_result, num_expected):
+    def _sample_neg(self, assign_result, num_expected, **kwargs):
         pass
 
-    def sample(self, assign_result, bboxes, gt_bboxes, gt_labels=None):
+    def sample(self,
+               assign_result,
+               bboxes,
+               gt_bboxes,
+               gt_labels=None,
+               **kwargs):
         """Sample positive and negative bboxes.
 
         This is a simple implementation of bbox sampling given candidates,
@@ -44,8 +58,8 @@ class BaseSampler(metaclass=ABCMeta):
             gt_flags = torch.cat([gt_ones, gt_flags])
 
         num_expected_pos = int(self.num * self.pos_fraction)
-        pos_inds = self.pos_sampler._sample_pos(assign_result,
-                                                num_expected_pos)
+        pos_inds = self.pos_sampler._sample_pos(
+            assign_result, num_expected_pos, bboxes=bboxes, **kwargs)
         # We found that sampled indices have duplicated items occasionally.
         # (may be a bug of PyTorch)
         pos_inds = pos_inds.unique()
@@ -56,8 +70,8 @@ class BaseSampler(metaclass=ABCMeta):
             neg_upper_bound = int(self.neg_pos_ub * _pos)
             if num_expected_neg > neg_upper_bound:
                 num_expected_neg = neg_upper_bound
-        neg_inds = self.neg_sampler._sample_neg(assign_result,
-                                                num_expected_neg)
+        neg_inds = self.neg_sampler._sample_neg(
+            assign_result, num_expected_neg, bboxes=bboxes, **kwargs)
         neg_inds = neg_inds.unique()
 
         return SamplingResult(pos_inds, neg_inds, bboxes, gt_bboxes,

mmdet/core/bbox/samplers/combined_sampler.py

-from .random_sampler import RandomSampler
+from .base_sampler import BaseSampler
 from ..assign_sampling import build_sampler
 
 
-class CombinedSampler(RandomSampler):
+class CombinedSampler(BaseSampler):
 
-    def __init__(self, num, pos_fraction, pos_sampler, neg_sampler, **kwargs):
-        super(CombinedSampler, self).__init__(num, pos_fraction, **kwargs)
-        default_args = dict(num=num, pos_fraction=pos_fraction)
-        default_args.update(kwargs)
-        self.pos_sampler = build_sampler(
-            pos_sampler, default_args=default_args)
-        self.neg_sampler = build_sampler(
-            neg_sampler, default_args=default_args)
+    def __init__(self, pos_sampler, neg_sampler, **kwargs):
+        super(CombinedSampler, self).__init__(**kwargs)
+        self.pos_sampler = build_sampler(pos_sampler, **kwargs)
+        self.neg_sampler = build_sampler(neg_sampler, **kwargs)
+
+    def _sample_pos(self, **kwargs):
+        raise NotImplementedError
+
+    def _sample_neg(self, **kwargs):
+        raise NotImplementedError

mmdet/core/bbox/samplers/instance_balanced_pos_sampler.py

@@ -6,7 +6,7 @@ from .random_sampler import RandomSampler
 
 class InstanceBalancedPosSampler(RandomSampler):
 
-    def _sample_pos(self, assign_result, num_expected):
+    def _sample_pos(self, assign_result, num_expected, **kwargs):
         pos_inds = torch.nonzero(assign_result.gt_inds > 0)
         if pos_inds.numel() != 0:
             pos_inds = pos_inds.squeeze(1)

mmdet/core/bbox/samplers/iou_balanced_neg_sampler.py

@@ -19,7 +19,7 @@ class IoUBalancedNegSampler(RandomSampler):
         self.hard_thr = hard_thr
         self.hard_fraction = hard_fraction
 
-    def _sample_neg(self, assign_result, num_expected):
+    def _sample_neg(self, assign_result, num_expected, **kwargs):
         neg_inds = torch.nonzero(assign_result.gt_inds == 0)
         if neg_inds.numel() != 0:
             neg_inds = neg_inds.squeeze(1)

mmdet/core/bbox/samplers/ohem_sampler.py

+import torch
+
+from .base_sampler import BaseSampler
+from ..transforms import bbox2roi
+
+
+class OHEMSampler(BaseSampler):
+
+    def __init__(self,
+                 num,
+                 pos_fraction,
+                 context,
+                 neg_pos_ub=-1,
+                 add_gt_as_proposals=True,
+                 **kwargs):
+        super(OHEMSampler, self).__init__(num, pos_fraction, neg_pos_ub,
+                                          add_gt_as_proposals)
+        self.bbox_roi_extractor = context.bbox_roi_extractor
+        self.bbox_head = context.bbox_head
+
+    def hard_mining(self, inds, num_expected, bboxes, labels, feats):
+        with torch.no_grad():
+            rois = bbox2roi([bboxes])
+            bbox_feats = self.bbox_roi_extractor(
+                feats[:self.bbox_roi_extractor.num_inputs], rois)
+            cls_score, _ = self.bbox_head(bbox_feats)
+            loss = self.bbox_head.loss(
+                cls_score=cls_score,
+                bbox_pred=None,
+                labels=labels,
+                label_weights=cls_score.new_ones(cls_score.size(0)),
+                bbox_targets=None,
+                bbox_weights=None,
+                reduce=False)['loss_cls']
+            _, topk_loss_inds = loss.topk(num_expected)
+        return inds[topk_loss_inds]
+
+    def _sample_pos(self,
+                    assign_result,
+                    num_expected,
+                    bboxes=None,
+                    feats=None,
+                    **kwargs):
+        # Sample some hard positive samples
+        pos_inds = torch.nonzero(assign_result.gt_inds > 0)
+        if pos_inds.numel() != 0:
+            pos_inds = pos_inds.squeeze(1)
+        if pos_inds.numel() <= num_expected:
+            return pos_inds
+        else:
+            return self.hard_mining(pos_inds, num_expected, bboxes[pos_inds],
+                                    assign_result.labels[pos_inds], feats)
+
+    def _sample_neg(self,
+                    assign_result,
+                    num_expected,
+                    bboxes=None,
+                    feats=None,
+                    **kwargs):
+        # Sample some hard negative samples
+        neg_inds = torch.nonzero(assign_result.gt_inds == 0)
+        if neg_inds.numel() != 0:
+            neg_inds = neg_inds.squeeze(1)
+        if len(neg_inds) <= num_expected:
+            return neg_inds
+        else:
+            return self.hard_mining(neg_inds, num_expected, bboxes[neg_inds],
+                                    assign_result.labels[neg_inds], feats)

mmdet/core/bbox/samplers/pseudo_sampler.py

@@ -6,16 +6,16 @@ from .sampling_result import SamplingResult
 
 class PseudoSampler(BaseSampler):
 
-    def __init__(self):
+    def __init__(self, **kwargs):
         pass
 
-    def _sample_pos(self):
+    def _sample_pos(self, **kwargs):
         raise NotImplementedError
 
-    def _sample_neg(self):
+    def _sample_neg(self, **kwargs):
         raise NotImplementedError
 
-    def sample(self, assign_result, bboxes, gt_bboxes):
+    def sample(self, assign_result, bboxes, gt_bboxes, **kwargs):
         pos_inds = torch.nonzero(
             assign_result.gt_inds > 0).squeeze(-1).unique()
         neg_inds = torch.nonzero(

mmdet/core/bbox/samplers/random_sampler.py

@@ -10,12 +10,10 @@ class RandomSampler(BaseSampler):
                  num,
                  pos_fraction,
                  neg_pos_ub=-1,
-                 add_gt_as_proposals=True):
-        super(RandomSampler, self).__init__()
-        self.num = num
-        self.pos_fraction = pos_fraction
-        self.neg_pos_ub = neg_pos_ub
-        self.add_gt_as_proposals = add_gt_as_proposals
+                 add_gt_as_proposals=True,
+                 **kwargs):
+        super(RandomSampler, self).__init__(num, pos_fraction, neg_pos_ub,
+                                            add_gt_as_proposals)
 
     @staticmethod
     def random_choice(gallery, num):
@@ -34,7 +32,7 @@ class RandomSampler(BaseSampler):
             rand_inds = torch.from_numpy(rand_inds).long().to(gallery.device)
         return gallery[rand_inds]
 
-    def _sample_pos(self, assign_result, num_expected):
+    def _sample_pos(self, assign_result, num_expected, **kwargs):
         """Randomly sample some positive samples."""
         pos_inds = torch.nonzero(assign_result.gt_inds > 0)
         if pos_inds.numel() != 0:
@@ -44,7 +42,7 @@ class RandomSampler(BaseSampler):
         else:
             return self.random_choice(pos_inds, num_expected)
 
-    def _sample_neg(self, assign_result, num_expected):
+    def _sample_neg(self, assign_result, num_expected, **kwargs):
         """Randomly sample some negative samples."""
         neg_inds = torch.nonzero(assign_result.gt_inds == 0)
         if neg_inds.numel() != 0:

mmdet/core/evaluation/__init__.py

@@ -2,7 +2,7 @@ from .class_names import (voc_classes, imagenet_det_classes,
                           imagenet_vid_classes, coco_classes, dataset_aliases,
                           get_classes)
 from .coco_utils import coco_eval, fast_eval_recall, results2json
-from .eval_hooks import (DistEvalHook, CocoDistEvalRecallHook,
+from .eval_hooks import (DistEvalHook, DistEvalmAPHook, CocoDistEvalRecallHook,
                          CocoDistEvalmAPHook)
 from .mean_ap import average_precision, eval_map, print_map_summary
 from .recall import (eval_recalls, print_recall_summary, plot_num_recall,
@@ -11,7 +11,7 @@ from .recall import (eval_recalls, print_recall_summary, plot_num_recall,
 __all__ = [
     'voc_classes', 'imagenet_det_classes', 'imagenet_vid_classes',
     'coco_classes', 'dataset_aliases', 'get_classes', 'coco_eval',
-    'fast_eval_recall', 'results2json', 'DistEvalHook',
+    'fast_eval_recall', 'results2json', 'DistEvalHook', 'DistEvalmAPHook',
     'CocoDistEvalRecallHook', 'CocoDistEvalmAPHook', 'average_precision',
     'eval_map', 'print_map_summary', 'eval_recalls', 'print_recall_summary',
     'plot_num_recall', 'plot_iou_recall'

mmdet/core/evaluation/class_names.py

@@ -63,18 +63,18 @@ def imagenet_vid_classes():
 def coco_classes():
     return [
         'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train',
-        'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign',
-        'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep',
+        'truck', 'boat', 'traffic_light', 'fire_hydrant', 'stop_sign',
+        'parking_meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep',
         'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella',
         'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard',
-        'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard',
-        'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork',
+        'sports_ball', 'kite', 'baseball_bat', 'baseball_glove', 'skateboard',
+        'surfboard', 'tennis_racket', 'bottle', 'wine_glass', 'cup', 'fork',
         'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange',
-        'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair',
-        'couch', 'potted plant', 'bed', 'dining table', 'toilet', 'tv',
-        'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave',
+        'broccoli', 'carrot', 'hot_dog', 'pizza', 'donut', 'cake', 'chair',
+        'couch', 'potted_plant', 'bed', 'dining_table', 'toilet', 'tv',
+        'laptop', 'mouse', 'remote', 'keyboard', 'cell_phone', 'microwave',
         'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase',
-        'scissors', 'teddy bear', 'hair drier', 'toothbrush'
+        'scissors', 'teddy_bear', 'hair_drier', 'toothbrush'
     ]
 
 

mmdet/core/evaluation/eval_hooks.py

@@ -12,6 +12,7 @@ from pycocotools.cocoeval import COCOeval
 from torch.utils.data import Dataset
 
 from .coco_utils import results2json, fast_eval_recall
+from .mean_ap import eval_map
 from mmdet import datasets
 
 
@@ -102,6 +103,44 @@ class DistEvalHook(Hook):
         raise NotImplementedError
 
 
+class DistEvalmAPHook(DistEvalHook):
+
+    def evaluate(self, runner, results):
+        gt_bboxes = []
+        gt_labels = []
+        gt_ignore = [] if self.dataset.with_crowd else None
+        for i in range(len(self.dataset)):
+            ann = self.dataset.get_ann_info(i)
+            bboxes = ann['bboxes']
+            labels = ann['labels']
+            if gt_ignore is not None:
+                ignore = np.concatenate([
+                    np.zeros(bboxes.shape[0], dtype=np.bool),
+                    np.ones(ann['bboxes_ignore'].shape[0], dtype=np.bool)
+                ])
+                gt_ignore.append(ignore)
+                bboxes = np.vstack([bboxes, ann['bboxes_ignore']])
+                labels = np.concatenate([labels, ann['labels_ignore']])
+            gt_bboxes.append(bboxes)
+            gt_labels.append(labels)
+        # If the dataset is VOC2007, then use 11 points mAP evaluation.
+        if hasattr(self.dataset, 'year') and self.dataset.year == 2007:
+            ds_name = 'voc07'
+        else:
+            ds_name = self.dataset.CLASSES
+        mean_ap, eval_results = eval_map(
+            results,
+            gt_bboxes,
+            gt_labels,
+            gt_ignore=gt_ignore,
+            scale_ranges=None,
+            iou_thr=0.5,
+            dataset=ds_name,
+            print_summary=True)
+        runner.log_buffer.output['mAP'] = mean_ap
+        runner.log_buffer.ready = True
+
+
 class CocoDistEvalRecallHook(DistEvalHook):
 
     def __init__(self,

mmdet/core/loss/losses.py

@@ -10,11 +10,15 @@ def weighted_nll_loss(pred, label, weight, avg_factor=None):
     return torch.sum(raw * weight)[None] / avg_factor
 
 
-def weighted_cross_entropy(pred, label, weight, avg_factor=None):
+def weighted_cross_entropy(pred, label, weight, avg_factor=None,
+                           reduce=True):
     if avg_factor is None:
         avg_factor = max(torch.sum(weight > 0).float().item(), 1.)
     raw = F.cross_entropy(pred, label, reduction='none')
+    if reduce:
         return torch.sum(raw * weight)[None] / avg_factor
+    else:
+        return raw * weight / avg_factor
 
 
 def weighted_binary_cross_entropy(pred, label, weight, avg_factor=None):

mmdet/datasets/__init__.py

 from .custom import CustomDataset
+from .xml_style import XMLDataset
 from .coco import CocoDataset
+from .voc import VOCDataset
 from .loader import GroupSampler, DistributedGroupSampler, build_dataloader
 from .utils import to_tensor, random_scale, show_ann, get_dataset
 from .concat_dataset import ConcatDataset
 from .repeat_dataset import RepeatDataset
 
 __all__ = [
-    'CustomDataset', 'CocoDataset', 'GroupSampler', 'DistributedGroupSampler',
-    'build_dataloader', 'to_tensor', 'random_scale', 'show_ann',
-    'get_dataset', 'ConcatDataset', 'RepeatDataset',
+    'CustomDataset', 'XMLDataset', 'CocoDataset', 'VOCDataset', 'GroupSampler',
+    'DistributedGroupSampler', 'build_dataloader', 'to_tensor', 'random_scale',
+    'show_ann', 'get_dataset', 'ConcatDataset', 'RepeatDataset'
 ]

mmdet/datasets/coco.py

@@ -6,6 +6,21 @@ from .custom import CustomDataset
 
 class CocoDataset(CustomDataset):
 
+    CLASSES = ('person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
+               'train', 'truck', 'boat', 'traffic_light', 'fire_hydrant',
+               'stop_sign', 'parking_meter', 'bench', 'bird', 'cat', 'dog',
+               'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe',
+               'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
+               'skis', 'snowboard', 'sports_ball', 'kite', 'baseball_bat',
+               'baseball_glove', 'skateboard', 'surfboard', 'tennis_racket',
+               'bottle', 'wine_glass', 'cup', 'fork', 'knife', 'spoon', 'bowl',
+               'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot',
+               'hot_dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
+               'potted_plant', 'bed', 'dining_table', 'toilet', 'tv', 'laptop',
+               'mouse', 'remote', 'keyboard', 'cell_phone', 'microwave',
+               'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock',
+               'vase', 'scissors', 'teddy_bear', 'hair_drier', 'toothbrush')
+
     def load_annotations(self, ann_file):
         self.coco = COCO(ann_file)
         self.cat_ids = self.coco.getCatIds()

mmdet/datasets/concat_dataset.py

@@ -3,16 +3,18 @@ from torch.utils.data.dataset import ConcatDataset as _ConcatDataset
 
 
 class ConcatDataset(_ConcatDataset):
-    """
-    Same as torch.utils.data.dataset.ConcatDataset, but
+    """A wrapper of concatenated dataset.
+
+    Same as :obj:`torch.utils.data.dataset.ConcatDataset`, but
     concat the group flag for image aspect ratio.
+
+    Args:
+        datasets (list[:obj:`Dataset`]): A list of datasets.
     """
+
     def __init__(self, datasets):
-        """
-        flag: Images with aspect ratio greater than 1 will be set as group 1,
-              otherwise group 0.
-        """
         super(ConcatDataset, self).__init__(datasets)
+        self.CLASSES = datasets[0].CLASSES
         if hasattr(datasets[0], 'flag'):
             flags = []
             for i in range(0, len(datasets)):