How to use mmdet - 10 common examples

kernel_size=kernel_size,
            padding=(kernel_size - 1) // 2,
            deformable_groups=deformable_groups)
        self.relu = nn.ReLU(inplace=True)

    def init_weights(self):
        normal_init(self.conv_offset, std=0.1)
        normal_init(self.conv_adaption, std=0.01)

    def forward(self, x, shape):
        offset = self.conv_offset(shape.detach())
        x = self.relu(self.conv_adaption(x, offset))
        return x


@HEADS.register_module
class GuidedAnchorHead(AnchorHead):
    """Guided-Anchor-based head (GA-RPN, GA-RetinaNet, etc.).

    This GuidedAnchorHead will predict high-quality feature guided
    anchors and locations where anchors will be kept in inference.
    There are mainly 3 categories of bounding-boxes.
    - Sampled (9) pairs for target assignment. (approxes)
    - The square boxes where the predicted anchors are based on.
        (squares)
    - Guided anchors.
    Please refer to https://arxiv.org/abs/1901.03278 for more details.

    Args:
        num_classes (int): Number of classes.
        in_channels (int): Number of channels in the input feature map.
        feat_channels (int): Number of hidden channels.

raise ValueError(
                'Invalid upsample method {}, accepted methods '
                'are "deconv", "nearest", "bilinear"'.format(upsample_method))
        self.num_convs = num_convs
        self.roi_feat_size = roi_feat_size  # WARN: not used and reserved
        self.in_channels = in_channels
        self.conv_kernel_size = conv_kernel_size
        self.conv_out_channels = conv_out_channels
        self.upsample_method = upsample_method
        self.upsample_ratio = upsample_ratio
        self.num_classes = num_classes
        self.class_agnostic = class_agnostic
        self.conv_cfg = conv_cfg
        self.norm_cfg = norm_cfg
        self.fp16_enabled = False
        self.loss_mask = build_loss(loss_mask)

        self.convs = nn.ModuleList()
        for i in range(self.num_convs):
            in_channels = (
                self.in_channels if i == 0 else self.conv_out_channels)
            padding = (self.conv_kernel_size - 1) // 2
            self.convs.append(
                ConvModule(
                    in_channels,
                    self.conv_out_channels,
                    self.conv_kernel_size,
                    padding=padding,
                    conv_cfg=conv_cfg,
                    norm_cfg=norm_cfg))
        upsample_in_channels = (
            self.conv_out_channels if self.num_convs > 0 else in_channels)

'Invalid upsample method {}, accepted methods '
                'are "deconv", "nearest", "bilinear"'.format(upsample_method))
        self.num_convs = num_convs
        # WARN: roi_feat_size is reserved and not used
        self.roi_feat_size = _pair(roi_feat_size)
        self.in_channels = in_channels
        self.conv_kernel_size = conv_kernel_size
        self.conv_out_channels = conv_out_channels
        self.upsample_method = upsample_method
        self.upsample_ratio = upsample_ratio
        self.num_classes = num_classes
        self.class_agnostic = class_agnostic
        self.conv_cfg = conv_cfg
        self.norm_cfg = norm_cfg
        self.fp16_enabled = False
        self.loss_mask = build_loss(loss_mask)

        self.convs = nn.ModuleList()
        for i in range(self.num_convs):
            in_channels = (
                self.in_channels if i == 0 else self.conv_out_channels)
            padding = (self.conv_kernel_size - 1) // 2
            self.convs.append(
                ConvModule(
                    in_channels,
                    self.conv_out_channels,
                    self.conv_kernel_size,
                    padding=padding,
                    conv_cfg=conv_cfg,
                    norm_cfg=norm_cfg))
        upsample_in_channels = (
            self.conv_out_channels if self.num_convs > 0 else in_channels)

x,
                         img_meta,
                         det_bboxes,
                         det_labels,
                         rescale=False):
        # image shape of the first image in the batch (only one)
        ori_shape = img_meta[0]['ori_shape']
        scale_factor = img_meta[0]['scale_factor']
        if det_bboxes.shape[0] == 0:
            segm_result = [[] for _ in range(self.mask_head.num_classes - 1)]
        else:
            # if det_bboxes is rescaled to the original image size, we need to
            # rescale it back to the testing scale to obtain RoIs.
            _bboxes = (
                det_bboxes[:, :4] * scale_factor if rescale else det_bboxes)
            mask_rois = bbox2roi([_bboxes])
            mask_feats = self.mask_roi_extractor(
                x[:len(self.mask_roi_extractor.featmap_strides)], mask_rois)
            if self.with_shared_head:
                mask_feats = self.shared_head(mask_feats)
            mask_pred = self.mask_head(mask_feats)
            segm_result = self.mask_head.get_seg_masks(
                mask_pred, _bboxes, det_labels, self.test_cfg.rcnn, ori_shape,
                scale_factor, rescale)
        return segm_result

def aug_test_bboxes(self, feats, img_metas, proposal_list, rcnn_test_cfg):
        aug_bboxes = []
        aug_scores = []
        for x, img_meta in zip(feats, img_metas):
            # only one image in the batch
            img_shape = img_meta[0]['img_shape']
            scale_factor = img_meta[0]['scale_factor']
            flip = img_meta[0]['flip']
            # TODO more flexible
            proposals = bbox_mapping(proposal_list[0][:, :4], img_shape,
                                     scale_factor, flip)
            rois = bbox2roi([proposals])
            # recompute feature maps to save GPU memory
            roi_feats = self.bbox_roi_extractor(
                x[:len(self.bbox_roi_extractor.featmap_strides)], rois)
            if self.with_shared_head:
                roi_feats = self.shared_head(roi_feats)
            cls_score, bbox_pred = self.bbox_head(roi_feats)
            bboxes, scores = self.bbox_head.get_det_bboxes(
                rois,
                cls_score,
                bbox_pred,
                img_shape,
                scale_factor,
                rescale=False,
                cfg=None)
            aug_bboxes.append(bboxes)
            aug_scores.append(scores)

roi_feats = self.shared_head(roi_feats)
            cls_score, bbox_pred = self.bbox_head(roi_feats)
            bboxes, scores = self.bbox_head.get_det_bboxes(
                rois,
                cls_score,
                bbox_pred,
                img_shape,
                scale_factor,
                rescale=False,
                cfg=None)
            aug_bboxes.append(bboxes)
            aug_scores.append(scores)
        # after merging, bboxes will be rescaled to the original image size
        merged_bboxes, merged_scores = merge_aug_bboxes(
            aug_bboxes, aug_scores, img_metas, rcnn_test_cfg)
        det_bboxes, det_labels = multiclass_nms(
            merged_bboxes, merged_scores, rcnn_test_cfg.score_thr,
            rcnn_test_cfg.nms, rcnn_test_cfg.max_per_img)
        return det_bboxes, det_labels

def test_retina_ghm_forward():
    model, train_cfg, test_cfg = _get_detector_cfg(
        'ghm/retinanet_ghm_r50_fpn_1x.py')
    model['pretrained'] = None

    from mmdet.models import build_detector
    detector = build_detector(model, train_cfg=train_cfg, test_cfg=test_cfg)

    input_shape = (3, 3, 224, 224)
    mm_inputs = _demo_mm_inputs(input_shape)

    imgs = mm_inputs.pop('imgs')
    img_metas = mm_inputs.pop('img_metas')

    # Test forward train
    gt_bboxes = mm_inputs['gt_bboxes']
    gt_labels = mm_inputs['gt_labels']
    losses = detector.forward(
        imgs,
        img_metas,
        gt_bboxes=gt_bboxes,
        gt_labels=gt_labels,
        return_loss=True)

def test_cascade_forward():
    try:
        from torchvision import _C as C  # NOQA
    except ImportError:
        import pytest
        raise pytest.skip('requires torchvision on cpu')

    model, train_cfg, test_cfg = _get_detector_cfg(
        'cascade_rcnn_r50_fpn_1x.py')
    model['pretrained'] = None
    # torchvision roi align supports CPU
    model['bbox_roi_extractor']['roi_layer']['use_torchvision'] = True

    from mmdet.models import build_detector
    detector = build_detector(model, train_cfg=train_cfg, test_cfg=test_cfg)

    input_shape = (1, 3, 256, 256)

    # Test forward train with a non-empty truth batch
    mm_inputs = _demo_mm_inputs(input_shape, num_items=[10])
    imgs = mm_inputs.pop('imgs')
    img_metas = mm_inputs.pop('img_metas')
    gt_bboxes = mm_inputs['gt_bboxes']
    gt_labels = mm_inputs['gt_labels']
    losses = detector.forward(
        imgs,
        img_metas,
        gt_bboxes=gt_bboxes,
        gt_labels=gt_labels,
        return_loss=True)
    assert isinstance(losses, dict)

def test_rpn_forward():
    model, train_cfg, test_cfg = _get_detector_cfg('rpn_r50_fpn_1x.py')
    model['pretrained'] = None

    from mmdet.models import build_detector
    detector = build_detector(model, train_cfg=train_cfg, test_cfg=test_cfg)

    input_shape = (1, 3, 224, 224)
    mm_inputs = _demo_mm_inputs(input_shape)

    imgs = mm_inputs.pop('imgs')
    img_metas = mm_inputs.pop('img_metas')

    # Test forward train
    gt_bboxes = mm_inputs['gt_bboxes']
    losses = detector.forward(
        imgs, img_metas, gt_bboxes=gt_bboxes, return_loss=True)
    assert isinstance(losses, dict)

    # Test forward test
    with torch.no_grad():
        img_list = [g[None, :] for g in imgs]

type='Corrupt',
                    corruption=corruption,
                    severity=corruption_severity)
                # TODO: hard coded "1", we assume that the first step is
                # loading images, which needs to be fixed in the future
                test_data_cfg['pipeline'].insert(1, corruption_trans)

            # print info
            print('\nTesting {} at severity {}'.format(corruption,
                                                       corruption_severity))

            # build the dataloader
            # TODO: support multiple images per gpu
            #       (only minor changes are needed)
            dataset = build_dataset(test_data_cfg)
            data_loader = build_dataloader(
                dataset,
                imgs_per_gpu=1,
                workers_per_gpu=args.workers,
                dist=distributed,
                shuffle=False)

            # build the model and load checkpoint
            model = build_detector(
                cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
            fp16_cfg = cfg.get('fp16', None)
            if fp16_cfg is not None:
                wrap_fp16_model(model)
            checkpoint = load_checkpoint(
                model, args.checkpoint, map_location='cpu')
            # old versions did not save class info in checkpoints,
            # this walkaround is for backward compatibility