add voc training configs and eval script

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)]

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()