Python datasets.ds_utils.filter_small_boxes() Examples

The following are 13 code examples of datasets.ds_utils.filter_small_boxes(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module datasets.ds_utils , or try the search function .
Example #1
Source File: pascal_voc.py    From face-py-faster-rcnn with MIT License 6 votes vote down vote up 
def _load_selective_search_roidb(self, gt_roidb):
        filename = os.path.abspath(os.path.join(cfg.DATA_DIR,
                                                'selective_search_data',
                                                self.name + '.mat'))
        assert os.path.exists(filename), \
               'Selective search data not found at: {}'.format(filename)
        raw_data = sio.loadmat(filename)['boxes'].ravel()

        box_list = []
        for i in xrange(raw_data.shape[0]):
            boxes = raw_data[i][:, (1, 0, 3, 2)] - 1
            keep = ds_utils.unique_boxes(boxes)
            boxes = boxes[keep, :]
            keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
            boxes = boxes[keep, :]
            box_list.append(boxes)

        return self.create_roidb_from_box_list(box_list, gt_roidb)
Example #2
Source File: pascal_voc.py    From faster-rcnn-resnet with MIT License 6 votes vote down vote up 
def _load_selective_search_roidb(self, gt_roidb):
        filename = os.path.abspath(os.path.join(cfg.DATA_DIR,
                                                'selective_search_data',
                                                self.name + '.mat'))
        assert os.path.exists(filename), \
               'Selective search data not found at: {}'.format(filename)
        raw_data = sio.loadmat(filename)['boxes'].ravel()

        box_list = []
        for i in xrange(raw_data.shape[0]):
            boxes = raw_data[i][:, (1, 0, 3, 2)] - 1
            keep = ds_utils.unique_boxes(boxes)
            boxes = boxes[keep, :]
            keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
            boxes = boxes[keep, :]
            box_list.append(boxes)

        return self.create_roidb_from_box_list(box_list, gt_roidb)
Example #3
Source File: pascal_voc.py    From rgz_rcnn with MIT License 6 votes vote down vote up 
def _load_selective_search_roidb(self, gt_roidb):
        filename = os.path.abspath(os.path.join(cfg.DATA_DIR,
                                                'selective_search_data',
                                                self.name + '.mat'))
        assert os.path.exists(filename), \
               'Selective search data not found at: {}'.format(filename)
        raw_data = sio.loadmat(filename)['boxes'].ravel()

        box_list = []
        for i in xrange(raw_data.shape[0]):
            boxes = raw_data[i][:, (1, 0, 3, 2)] - 1
            keep = ds_utils.unique_boxes(boxes)
            boxes = boxes[keep, :]
            keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
            boxes = boxes[keep, :]
            box_list.append(boxes)

        return self.create_roidb_from_box_list(box_list, gt_roidb)
Example #4
Source File: pascal_voc.py    From Faster-RCNN_TF with MIT License 6 votes vote down vote up 
def _load_selective_search_roidb(self, gt_roidb):
        filename = os.path.abspath(os.path.join(cfg.DATA_DIR,
                                                'selective_search_data',
                                                self.name + '.mat'))
        assert os.path.exists(filename), \
               'Selective search data not found at: {}'.format(filename)
        raw_data = sio.loadmat(filename)['boxes'].ravel()

        box_list = []
        for i in xrange(raw_data.shape[0]):
            boxes = raw_data[i][:, (1, 0, 3, 2)] - 1
            keep = ds_utils.unique_boxes(boxes)
            boxes = boxes[keep, :]
            keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
            boxes = boxes[keep, :]
            box_list.append(boxes)

        return self.create_roidb_from_box_list(box_list, gt_roidb)
Example #5
Source File: pascal_voc.py    From uai-sdk with Apache License 2.0 6 votes vote down vote up 
def _load_selective_search_roidb(self, gt_roidb):
        filename = os.path.abspath(os.path.join(cfg.DATA_DIR,
                                                'selective_search_data',
                                                self.name + '.mat'))
        assert os.path.exists(filename), \
               'Selective search data not found at: {}'.format(filename)
        raw_data = sio.loadmat(filename)['boxes'].ravel()

        box_list = []
        for i in xrange(raw_data.shape[0]):
            boxes = raw_data[i][:, (1, 0, 3, 2)] - 1
            keep = ds_utils.unique_boxes(boxes)
            boxes = boxes[keep, :]
            keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
            boxes = boxes[keep, :]
            box_list.append(boxes)

        return self.create_roidb_from_box_list(box_list, gt_roidb)
Example #6
Source File: pascal_voc.py    From caffe-faster-rcnn-resnet-fpn with MIT License 6 votes vote down vote up 
def _load_selective_search_roidb(self, gt_roidb):
        filename = os.path.abspath(os.path.join(cfg.DATA_DIR,
                                                'selective_search_data',
                                                self.name + '.mat'))
        assert os.path.exists(filename), \
               'Selective search data not found at: {}'.format(filename)
        raw_data = sio.loadmat(filename)['boxes'].ravel()

        box_list = []
        for i in xrange(raw_data.shape[0]):
            boxes = raw_data[i][:, (1, 0, 3, 2)] - 1
            keep = ds_utils.unique_boxes(boxes)
            boxes = boxes[keep, :]
            keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
            boxes = boxes[keep, :]
            box_list.append(boxes)

        return self.create_roidb_from_box_list(box_list, gt_roidb)
Example #7
Source File: pascal_voc.py    From py-R-FCN with MIT License 6 votes vote down vote up 
def _load_selective_search_roidb(self, gt_roidb):
        filename = os.path.abspath(os.path.join(cfg.DATA_DIR,
                                                'selective_search_data',
                                                self.name + '.mat'))
        assert os.path.exists(filename), \
               'Selective search data not found at: {}'.format(filename)
        raw_data = sio.loadmat(filename)['boxes'].ravel()

        box_list = []
        for i in xrange(raw_data.shape[0]):
            boxes = raw_data[i][:, (1, 0, 3, 2)] - 1
            keep = ds_utils.unique_boxes(boxes)
            boxes = boxes[keep, :]
            keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
            boxes = boxes[keep, :]
            box_list.append(boxes)

        return self.create_roidb_from_box_list(box_list, gt_roidb)
Example #8
Source File: coco.py    From face-py-faster-rcnn with MIT License 4 votes vote down vote up 
def _load_proposals(self, method, gt_roidb):
        """
        Load pre-computed proposals in the format provided by Jan Hosang:
        http://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-
          computing/research/object-recognition-and-scene-understanding/how-
          good-are-detection-proposals-really/
        For MCG, use boxes from http://www.eecs.berkeley.edu/Research/Projects/
          CS/vision/grouping/mcg/ and convert the file layout using
        lib/datasets/tools/mcg_munge.py.
        """
        box_list = []
        top_k = self.config['top_k']
        valid_methods = [
            'MCG',
            'selective_search',
            'edge_boxes_AR',
            'edge_boxes_70']
        assert method in valid_methods

        print 'Loading {} boxes'.format(method)
        for i, index in enumerate(self._image_index):
            if i % 1000 == 0:
                print '{:d} / {:d}'.format(i + 1, len(self._image_index))

            box_file = osp.join(
                cfg.DATA_DIR, 'coco_proposals', method, 'mat',
                self._get_box_file(index))

            raw_data = sio.loadmat(box_file)['boxes']
            boxes = np.maximum(raw_data - 1, 0).astype(np.uint16)
            if method == 'MCG':
                # Boxes from the MCG website are in (y1, x1, y2, x2) order
                boxes = boxes[:, (1, 0, 3, 2)]
            # Remove duplicate boxes and very small boxes and then take top k
            keep = ds_utils.unique_boxes(boxes)
            boxes = boxes[keep, :]
            keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
            boxes = boxes[keep, :]
            boxes = boxes[:top_k, :]
            box_list.append(boxes)
            # Sanity check
            im_ann = self._COCO.loadImgs(index)[0]
            width = im_ann['width']
            height = im_ann['height']
            ds_utils.validate_boxes(boxes, width=width, height=height)
        return self.create_roidb_from_box_list(box_list, gt_roidb)
Example #9
Source File: coco.py    From faster-rcnn-resnet with MIT License 4 votes vote down vote up 
def _load_proposals(self, method, gt_roidb):
        """
        Load pre-computed proposals in the format provided by Jan Hosang:
        http://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-
          computing/research/object-recognition-and-scene-understanding/how-
          good-are-detection-proposals-really/
        For MCG, use boxes from http://www.eecs.berkeley.edu/Research/Projects/
          CS/vision/grouping/mcg/ and convert the file layout using
        lib/datasets/tools/mcg_munge.py.
        """
        box_list = []
        top_k = self.config['top_k']
        valid_methods = [
            'MCG',
            'selective_search',
            'edge_boxes_AR',
            'edge_boxes_70']
        assert method in valid_methods

        print 'Loading {} boxes'.format(method)
        for i, index in enumerate(self._image_index):
            if i % 1000 == 0:
                print '{:d} / {:d}'.format(i + 1, len(self._image_index))

            box_file = osp.join(
                cfg.DATA_DIR, 'coco_proposals', method, 'mat',
                self._get_box_file(index))

            raw_data = sio.loadmat(box_file)['boxes']
            boxes = np.maximum(raw_data - 1, 0).astype(np.uint16)
            if method == 'MCG':
                # Boxes from the MCG website are in (y1, x1, y2, x2) order
                boxes = boxes[:, (1, 0, 3, 2)]
            # Remove duplicate boxes and very small boxes and then take top k
            keep = ds_utils.unique_boxes(boxes)
            boxes = boxes[keep, :]
            keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
            boxes = boxes[keep, :]
            boxes = boxes[:top_k, :]
            box_list.append(boxes)
            # Sanity check
            im_ann = self._COCO.loadImgs(index)[0]
            width = im_ann['width']
            height = im_ann['height']
            ds_utils.validate_boxes(boxes, width=width, height=height)
        return self.create_roidb_from_box_list(box_list, gt_roidb)
Example #10
Source File: coco.py    From Faster-RCNN_TF with MIT License 4 votes vote down vote up 
def _load_proposals(self, method, gt_roidb):
        """
        Load pre-computed proposals in the format provided by Jan Hosang:
        http://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-
          computing/research/object-recognition-and-scene-understanding/how-
          good-are-detection-proposals-really/
        For MCG, use boxes from http://www.eecs.berkeley.edu/Research/Projects/
          CS/vision/grouping/mcg/ and convert the file layout using
        lib/datasets/tools/mcg_munge.py.
        """
        box_list = []
        top_k = self.config['top_k']
        valid_methods = [
            'MCG',
            'selective_search',
            'edge_boxes_AR',
            'edge_boxes_70']
        assert method in valid_methods

        print 'Loading {} boxes'.format(method)
        for i, index in enumerate(self._image_index):
            if i % 1000 == 0:
                print '{:d} / {:d}'.format(i + 1, len(self._image_index))

            box_file = osp.join(
                cfg.DATA_DIR, 'coco_proposals', method, 'mat',
                self._get_box_file(index))

            raw_data = sio.loadmat(box_file)['boxes']
            boxes = np.maximum(raw_data - 1, 0).astype(np.uint16)
            if method == 'MCG':
                # Boxes from the MCG website are in (y1, x1, y2, x2) order
                boxes = boxes[:, (1, 0, 3, 2)]
            # Remove duplicate boxes and very small boxes and then take top k
            keep = ds_utils.unique_boxes(boxes)
            boxes = boxes[keep, :]
            keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
            boxes = boxes[keep, :]
            boxes = boxes[:top_k, :]
            box_list.append(boxes)
            # Sanity check
            im_ann = self._COCO.loadImgs(index)[0]
            width = im_ann['width']
            height = im_ann['height']
            ds_utils.validate_boxes(boxes, width=width, height=height)
        return self.create_roidb_from_box_list(box_list, gt_roidb)
Example #11
Source File: coco.py    From uai-sdk with Apache License 2.0 4 votes vote down vote up 
def _load_proposals(self, method, gt_roidb):
        """
        Load pre-computed proposals in the format provided by Jan Hosang:
        http://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-
          computing/research/object-recognition-and-scene-understanding/how-
          good-are-detection-proposals-really/
        For MCG, use boxes from http://www.eecs.berkeley.edu/Research/Projects/
          CS/vision/grouping/mcg/ and convert the file layout using
        lib/datasets/tools/mcg_munge.py.
        """
        box_list = []
        top_k = self.config['top_k']
        valid_methods = [
            'MCG',
            'selective_search',
            'edge_boxes_AR',
            'edge_boxes_70']
        assert method in valid_methods

        print 'Loading {} boxes'.format(method)
        for i, index in enumerate(self._image_index):
            if i % 1000 == 0:
                print '{:d} / {:d}'.format(i + 1, len(self._image_index))

            box_file = osp.join(
                cfg.DATA_DIR, 'coco_proposals', method, 'mat',
                self._get_box_file(index))

            raw_data = sio.loadmat(box_file)['boxes']
            boxes = np.maximum(raw_data - 1, 0).astype(np.uint16)
            if method == 'MCG':
                # Boxes from the MCG website are in (y1, x1, y2, x2) order
                boxes = boxes[:, (1, 0, 3, 2)]
            # Remove duplicate boxes and very small boxes and then take top k
            keep = ds_utils.unique_boxes(boxes)
            boxes = boxes[keep, :]
            keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
            boxes = boxes[keep, :]
            boxes = boxes[:top_k, :]
            box_list.append(boxes)
            # Sanity check
            im_ann = self._COCO.loadImgs(index)[0]
            width = im_ann['width']
            height = im_ann['height']
            ds_utils.validate_boxes(boxes, width=width, height=height)
        return self.create_roidb_from_box_list(box_list, gt_roidb)
Example #12
Source File: coco.py    From caffe-faster-rcnn-resnet-fpn with MIT License 4 votes vote down vote up 
def _load_proposals(self, method, gt_roidb):
        """
        Load pre-computed proposals in the format provided by Jan Hosang:
        http://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-
          computing/research/object-recognition-and-scene-understanding/how-
          good-are-detection-proposals-really/
        For MCG, use boxes from http://www.eecs.berkeley.edu/Research/Projects/
          CS/vision/grouping/mcg/ and convert the file layout using
        lib/datasets/tools/mcg_munge.py.
        """
        box_list = []
        top_k = self.config['top_k']
        valid_methods = [
            'MCG',
            'selective_search',
            'edge_boxes_AR',
            'edge_boxes_70']
        assert method in valid_methods

        print 'Loading {} boxes'.format(method)
        for i, index in enumerate(self._image_index):
            if i % 1000 == 0:
                print '{:d} / {:d}'.format(i + 1, len(self._image_index))

            box_file = osp.join(
                cfg.DATA_DIR, 'coco_proposals', method, 'mat',
                self._get_box_file(index))

            raw_data = sio.loadmat(box_file)['boxes']
            boxes = np.maximum(raw_data - 1, 0).astype(np.uint16)
            if method == 'MCG':
                # Boxes from the MCG website are in (y1, x1, y2, x2) order
                boxes = boxes[:, (1, 0, 3, 2)]
            # Remove duplicate boxes and very small boxes and then take top k
            keep = ds_utils.unique_boxes(boxes)
            boxes = boxes[keep, :]
            keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
            boxes = boxes[keep, :]
            boxes = boxes[:top_k, :]
            box_list.append(boxes)
            # Sanity check
            im_ann = self._COCO.loadImgs(index)[0]
            width = im_ann['width']
            height = im_ann['height']
            ds_utils.validate_boxes(boxes, width=width, height=height)
        return self.create_roidb_from_box_list(box_list, gt_roidb)
Example #13
Source File: coco.py    From py-R-FCN with MIT License 4 votes vote down vote up 
def _load_proposals(self, method, gt_roidb):
        """
        Load pre-computed proposals in the format provided by Jan Hosang:
        http://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-
          computing/research/object-recognition-and-scene-understanding/how-
          good-are-detection-proposals-really/
        For MCG, use boxes from http://www.eecs.berkeley.edu/Research/Projects/
          CS/vision/grouping/mcg/ and convert the file layout using
        lib/datasets/tools/mcg_munge.py.
        """
        box_list = []
        top_k = self.config['top_k']
        valid_methods = [
            'MCG',
            'selective_search',
            'edge_boxes_AR',
            'edge_boxes_70']
        assert method in valid_methods

        print 'Loading {} boxes'.format(method)
        for i, index in enumerate(self._image_index):
            if i % 1000 == 0:
                print '{:d} / {:d}'.format(i + 1, len(self._image_index))

            box_file = osp.join(
                cfg.DATA_DIR, 'coco_proposals', method, 'mat',
                self._get_box_file(index))

            raw_data = sio.loadmat(box_file)['boxes']
            boxes = np.maximum(raw_data - 1, 0).astype(np.uint16)
            if method == 'MCG':
                # Boxes from the MCG website are in (y1, x1, y2, x2) order
                boxes = boxes[:, (1, 0, 3, 2)]
            # Remove duplicate boxes and very small boxes and then take top k
            keep = ds_utils.unique_boxes(boxes)
            boxes = boxes[keep, :]
            keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
            boxes = boxes[keep, :]
            boxes = boxes[:top_k, :]
            box_list.append(boxes)
            # Sanity check
            im_ann = self._COCO.loadImgs(index)[0]
            width = im_ann['width']
            height = im_ann['height']
            ds_utils.validate_boxes(boxes, width=width, height=height)
        return self.create_roidb_from_box_list(box_list, gt_roidb)