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

mmdet/datasets/custom.py

@@ -32,6 +32,8 @@ class CustomDataset(Dataset):
     The `ann` field is optional for testing.
     """
 
+    CLASSES = None
+
     def __init__(self,
                  ann_file,
                  img_prefix,
@@ -45,6 +47,8 @@ class CustomDataset(Dataset):
                  with_crowd=True,
                  with_label=True,
                  test_mode=False):
+        # prefix of images path
+        self.img_prefix = img_prefix
         # load annotations (and proposals)
         self.img_infos = self.load_annotations(ann_file)
         if proposal_file is not None:
@@ -58,8 +62,6 @@ class CustomDataset(Dataset):
             if self.proposals is not None:
                 self.proposals = [self.proposals[i] for i in valid_inds]
 
-        # prefix of images path
-        self.img_prefix = img_prefix
         # (long_edge, short_edge) or [(long1, short1), (long2, short2), ...]
         self.img_scales = img_scale if isinstance(img_scale,
                                                   list) else [img_scale]

mmdet/datasets/repeat_dataset.py

@@ -6,12 +6,14 @@ class RepeatDataset(object):
     def __init__(self, dataset, times):
         self.dataset = dataset
         self.times = times
+        self.CLASSES = dataset.CLASSES
         if hasattr(self.dataset, 'flag'):
             self.flag = np.tile(self.dataset.flag, times)
-        self._original_length = len(self.dataset)
+
+        self._ori_len = len(self.dataset)
 
     def __getitem__(self, idx):
-        return self.dataset[idx % self._original_length]
+        return self.dataset[idx % self._ori_len]
 
     def __len__(self):
-        return self.times * self._original_length
+        return self.times * self._ori_len

mmdet/datasets/voc.py

+from .xml_style import XMLDataset
+
+
+class VOCDataset(XMLDataset):
+
+    CLASSES = ('aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car',
+               'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse',
+               'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train',
+               'tvmonitor')
+
+    def __init__(self, **kwargs):
+        super(VOCDataset, self).__init__(**kwargs)
+        if 'VOC2007' in self.img_prefix:
+            self.year = 2007
+        elif 'VOC2012' in self.img_prefix:
+            self.year = 2012
+        else:
+            raise ValueError('Cannot infer dataset year from img_prefix')

mmdet/datasets/xml_style.py

+import os.path as osp
+import xml.etree.ElementTree as ET
+
+import mmcv
+import numpy as np
+
+from .custom import CustomDataset
+
+
+class XMLDataset(CustomDataset):
+
+    def __init__(self, **kwargs):
+        super(XMLDataset, self).__init__(**kwargs)
+        self.cat2label = {cat: i + 1 for i, cat in enumerate(self.CLASSES)}
+
+    def load_annotations(self, ann_file):
+        img_infos = []
+        img_ids = mmcv.list_from_file(ann_file)
+        for img_id in img_ids:
+            filename = 'JPEGImages/{}.jpg'.format(img_id)
+            xml_path = osp.join(self.img_prefix, 'Annotations',
+                                '{}.xml'.format(img_id))
+            tree = ET.parse(xml_path)
+            root = tree.getroot()
+            size = root.find('size')
+            width = int(size.find('width').text)
+            height = int(size.find('height').text)
+            img_infos.append(
+                dict(id=img_id, filename=filename, width=width, height=height))
+        return img_infos
+
+    def get_ann_info(self, idx):
+        img_id = self.img_infos[idx]['id']
+        xml_path = osp.join(self.img_prefix, 'Annotations',
+                            '{}.xml'.format(img_id))
+        tree = ET.parse(xml_path)
+        root = tree.getroot()
+        bboxes = []
+        labels = []
+        bboxes_ignore = []
+        labels_ignore = []
+        for obj in root.findall('object'):
+            name = obj.find('name').text
+            label = self.cat2label[name]
+            difficult = int(obj.find('difficult').text)
+            bnd_box = obj.find('bndbox')
+            bbox = [
+                int(bnd_box.find('xmin').text),
+                int(bnd_box.find('ymin').text),
+                int(bnd_box.find('xmax').text),
+                int(bnd_box.find('ymax').text)
+            ]
+            if difficult:
+                bboxes_ignore.append(bbox)
+                labels_ignore.append(label)
+            else:
+                bboxes.append(bbox)
+                labels.append(label)
+        if not bboxes:
+            bboxes = np.zeros((0, 4))
+            labels = np.zeros((0, ))
+        else:
+            bboxes = np.array(bboxes, ndmin=2) - 1
+            labels = np.array(labels)
+        if not bboxes_ignore:
+            bboxes_ignore = np.zeros((0, 4))
+            labels_ignore = np.zeros((0, ))
+        else:
+            bboxes_ignore = np.array(bboxes_ignore, ndmin=2) - 1
+            labels_ignore = np.array(labels_ignore)
+        ann = dict(
+            bboxes=bboxes.astype(np.float32),
+            labels=labels.astype(np.int64),
+            bboxes_ignore=bboxes_ignore.astype(np.float32),
+            labels_ignore=labels_ignore.astype(np.int64))
+        return ann

mmdet/models/bbox_heads/bbox_head.py

@@ -79,11 +79,11 @@ class BBoxHead(nn.Module):
         return cls_reg_targets
 
     def loss(self, cls_score, bbox_pred, labels, label_weights, bbox_targets,
-             bbox_weights):
+             bbox_weights, reduce=True):
         losses = dict()
         if cls_score is not None:
             losses['loss_cls'] = weighted_cross_entropy(
-                cls_score, labels, label_weights)
+                cls_score, labels, label_weights, reduce=reduce)
             losses['acc'] = accuracy(cls_score, labels)
         if bbox_pred is not None:
             losses['loss_reg'] = weighted_smoothl1(

mmdet/models/detectors/base.py

@@ -99,11 +99,12 @@ class BaseDetector(nn.Module):
 
         if isinstance(dataset, str):
             class_names = get_classes(dataset)
-        elif isinstance(dataset, list):
+        elif isinstance(dataset, (list, tuple)) or dataset is None:
             class_names = dataset
         else:
-            raise TypeError('dataset must be a valid dataset name or a list'
-                            ' of class names, not {}'.format(type(dataset)))
+            raise TypeError(
+                'dataset must be a valid dataset name or a sequence'
+                ' of class names, not {}'.format(type(dataset)))
 
         for img, img_meta in zip(imgs, img_metas):
             h, w, _ = img_meta['img_shape']

mmdet/models/detectors/two_stage.py

@@ -4,7 +4,7 @@ import torch.nn as nn
 from .base import BaseDetector
 from .test_mixins import RPNTestMixin, BBoxTestMixin, MaskTestMixin
 from .. import builder
-from mmdet.core import (assign_and_sample, bbox2roi, bbox2result, multi_apply)
+from mmdet.core import bbox2roi, bbox2result, build_assigner, build_sampler
 
 
 class TwoStageDetector(BaseDetector, RPNTestMixin, BBoxTestMixin,
@@ -102,13 +102,22 @@ class TwoStageDetector(BaseDetector, RPNTestMixin, BBoxTestMixin,
 
         # assign gts and sample proposals
         if self.with_bbox or self.with_mask:
-            assign_results, sampling_results = multi_apply(
-                assign_and_sample,
-                proposal_list,
-                gt_bboxes,
-                gt_bboxes_ignore,
-                gt_labels,
-                cfg=self.train_cfg.rcnn)
+            bbox_assigner = build_assigner(self.train_cfg.rcnn.assigner)
+            bbox_sampler = build_sampler(
+                self.train_cfg.rcnn.sampler, context=self)
+            num_imgs = img.size(0)
+            sampling_results = []
+            for i in range(num_imgs):
+                assign_result = bbox_assigner.assign(
+                    proposal_list[i], gt_bboxes[i], gt_bboxes_ignore[i],
+                    gt_labels[i])
+                sampling_result = bbox_sampler.sample(
+                    assign_result,
+                    proposal_list[i],
+                    gt_bboxes[i],
+                    gt_labels[i],
+                    feats=[lvl_feat[i][None] for lvl_feat in x])
+                sampling_results.append(sampling_result)
 
         # bbox head forward and loss
         if self.with_bbox:

mmdet/models/mask_heads/fcn_mask_head.py

@@ -97,7 +97,11 @@ class FCNMaskHead(nn.Module):
 
     def loss(self, mask_pred, mask_targets, labels):
         loss = dict()
-        loss_mask = mask_cross_entropy(mask_pred, mask_targets, labels)
+        if self.class_agnostic:
+            loss_mask = mask_cross_entropy(mask_pred, mask_targets,
+                                           torch.zeros_like(labels))
+        else:
+            loss_mask = mask_cross_entropy(mask_pred, mask_targets, labels)
         loss['loss_mask'] = loss_mask
         return loss
 

tools/test.py

@@ -14,15 +14,16 @@ from mmdet.models import build_detector, detectors
 def single_test(model, data_loader, show=False):
     model.eval()
     results = []
-    prog_bar = mmcv.ProgressBar(len(data_loader.dataset))
+    dataset = data_loader.dataset
+    prog_bar = mmcv.ProgressBar(len(dataset))
     for i, data in enumerate(data_loader):
         with torch.no_grad():
             result = model(return_loss=False, rescale=not show, **data)
         results.append(result)
 
         if show:
-            model.module.show_result(data, result,
-                                     data_loader.dataset.img_norm_cfg)
+            model.module.show_result(data, result, dataset.img_norm_cfg,
+                                     dataset.CLASSES)
 
         batch_size = data['img'][0].size(0)
         for _ in range(batch_size):

tools/voc_eval.py

+from argparse import ArgumentParser
+
+import mmcv
+import numpy as np
+
+from mmdet import datasets
+from mmdet.core import eval_map
+
+
+def voc_eval(result_file, dataset, iou_thr=0.5):
+    det_results = mmcv.load(result_file)
+    gt_bboxes = []
+    gt_labels = []
+    gt_ignore = []
+    for i in range(len(dataset)):
+        ann = dataset.get_ann_info(i)
+        bboxes = ann['bboxes']
+        labels = ann['labels']
+        if 'bboxes_ignore' in ann:
+            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 not gt_ignore:
+        gt_ignore = gt_ignore
+    if hasattr(dataset, 'year') and dataset.year == 2007:
+        dataset_name = 'voc07'
+    else:
+        dataset_name = dataset.CLASSES
+    eval_map(
+        det_results,
+        gt_bboxes,
+        gt_labels,
+        gt_ignore=gt_ignore,
+        scale_ranges=None,
+        iou_thr=iou_thr,
+        dataset=dataset_name,
+        print_summary=True)
+
+
+def main():
+    parser = ArgumentParser(description='VOC Evaluation')
+    parser.add_argument('result', help='result file path')
+    parser.add_argument('config', help='config file path')
+    parser.add_argument(
+        '--iou-thr',
+        type=float,
+        default=0.5,
+        help='IoU threshold for evaluation')
+    args = parser.parse_args()
+    cfg = mmcv.Config.fromfile(args.config)
+    test_dataset = mmcv.runner.obj_from_dict(cfg.data.test, datasets)
+    voc_eval(args.result, test_dataset, args.iou_thr)
+
+
+if __name__ == '__main__':
+    main()