當前位置: 首頁>>代碼示例>>Python>>正文


Python image.tensor_vstack方法代碼示例

本文整理匯總了Python中utils.image.tensor_vstack方法的典型用法代碼示例。如果您正苦於以下問題:Python image.tensor_vstack方法的具體用法?Python image.tensor_vstack怎麽用?Python image.tensor_vstack使用的例子?那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在utils.image的用法示例。


在下文中一共展示了image.tensor_vstack方法的7個代碼示例,這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚,您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: get_batch

# 需要導入模塊: from utils import image [as 別名]
# 或者: from utils.image import tensor_vstack [as 別名]
def get_batch(self):
        # slice roidb
        cur_from = self.cur
        cur_to = min(cur_from + self.batch_size, self.size)
        roidb = [self.roidb[self.index[i]] for i in range(cur_from, cur_to)]

        # decide multi device slices
        work_load_list = self.work_load_list
        ctx = self.ctx
        if work_load_list is None:
            work_load_list = [1] * len(ctx)
        assert isinstance(work_load_list, list) and len(work_load_list) == len(ctx), \
            "Invalid settings for work load. "
        slices = _split_input_slice(self.batch_size, work_load_list)

        # get each device
        data_list = []
        label_list = []
        for islice in slices:
            iroidb = [roidb[i] for i in range(islice.start, islice.stop)]
            data, label = get_rcnn_batch(iroidb, self.cfg)
            data_list.append(data)
            label_list.append(label)

        all_data = dict()
        for key in data_list[0].keys():
            all_data[key] = tensor_vstack([batch[key] for batch in data_list])

        all_label = dict()
        for key in label_list[0].keys():
            all_label[key] = tensor_vstack([batch[key] for batch in label_list])

        self.data = [mx.nd.array(all_data[name]) for name in self.data_name]
        self.label = [mx.nd.array(all_label[name]) for name in self.label_name] 
開發者ID:i-pan,項目名稱:kaggle-rsna18,代碼行數:36,代碼來源:loader.py

示例2: get_batch

# 需要導入模塊: from utils import image [as 別名]
# 或者: from utils.image import tensor_vstack [as 別名]
def get_batch(self, cur_from=None):
        # slice roidb
        if cur_from is None:
            cur_from = self.cur
        cur_to = min(cur_from + self.batch_size, self.size)
        roidb = [self.roidb[self.index[i]] for i in range(cur_from, cur_to)]

        # decide multi device slices
        work_load_list = self.work_load_list
        ctx = self.ctx
        if work_load_list is None:
            work_load_list = [1] * len(ctx)
        assert isinstance(work_load_list, list) and len(work_load_list) == len(ctx), \
            "Invalid settings for work load. "
        slices = _split_input_slice(self.batch_size, work_load_list)

        # get each device
        data_list = []
        label_list = []
        for islice in slices:
            iroidb = [roidb[i] for i in range(islice.start, islice.stop)]
            data, label = get_rcnn_batch(iroidb, self.cfg)
            data_list.append(data)
            label_list.append(label)

        all_data = dict()
        for key in data_list[0].keys():
            all_data[key] = tensor_vstack([batch[key] for batch in data_list])

        all_label = dict()
        for key in label_list[0].keys():
            all_label[key] = tensor_vstack([batch[key] for batch in label_list])

        data = [mx.nd.array(all_data[name]) for name in self.data_name]
        label = [mx.nd.array(all_label[name]) for name in self.label_name]
        
        self.lock_data.acquire()
        self.data = data
        self.label = label
        self.lock_data.release()

        return data, label 
開發者ID:i-pan,項目名稱:kaggle-rsna18,代碼行數:44,代碼來源:loader.py

示例3: get_batch

# 需要導入模塊: from utils import image [as 別名]
# 或者: from utils.image import tensor_vstack [as 別名]
def get_batch(self):
        # slice roidb
        cur_from = self.cur
        cur_to = min(cur_from + self.batch_size, self.size)
        roidb = [self.roidb[self.index[i]] for i in range(cur_from, cur_to)]

        # decide multi device slice
        work_load_list = self.work_load_list
        ctx = self.ctx
        if work_load_list is None:
            work_load_list = [1] * len(ctx)
        assert isinstance(work_load_list, list) and len(work_load_list) == len(ctx), \
            "Invalid settings for work load. "
        slices = _split_input_slice(self.batch_size, work_load_list)

        # get testing data for multigpu
        data_list = []
        label_list = []
        for islice in slices:
            iroidb = [roidb[i] for i in range(islice.start, islice.stop)]
            data, label = get_rpn_triple_batch(iroidb, self.cfg)
            data_list.append(data)
            label_list.append(label)

        # pad data first and then assign anchor (read label)
        data_tensor = tensor_vstack([batch['data'] for batch in data_list])
        for data, data_pad in zip(data_list, data_tensor):
            data['data'] = data_pad[np.newaxis, :]

        new_label_list = []
        for data, label in zip(data_list, label_list):
            # infer label shape
            data_shape = {k: v.shape for k, v in data.items()}
            del data_shape['im_info']
            _, feat_shape, _ = self.feat_sym.infer_shape(**data_shape)
            feat_shape = [int(i) for i in feat_shape[0]]

            # add gt_boxes to data for e2e
            data['gt_boxes'] = label['gt_boxes'][np.newaxis, :, :]
            print data['gt_boxes']

            # assign anchor for label
            label = assign_anchor(feat_shape, label['gt_boxes'], data['im_info'], self.cfg,
                                  self.feat_stride, self.anchor_scales,
                                  self.anchor_ratios, self.allowed_border,
                                  self.normalize_target, self.bbox_mean, self.bbox_std)
            new_label_list.append(label)

        all_data = dict()
        for key in self.data_name:
            all_data[key] = tensor_vstack([batch[key] for batch in data_list])

        all_label = dict()
        for key in self.label_name:
            pad = -1 if key == 'label' else 0
            all_label[key] = tensor_vstack([batch[key] for batch in new_label_list], pad=pad)

        self.data = [mx.nd.array(all_data[key]) for key in self.data_name]
        self.label = [mx.nd.array(all_label[key]) for key in self.label_name] 
開發者ID:wangshy31,項目名稱:MANet_for_Video_Object_Detection,代碼行數:61,代碼來源:loader.py

示例4: get_batch

# 需要導入模塊: from utils import image [as 別名]
# 或者: from utils.image import tensor_vstack [as 別名]
def get_batch(self):
        # slice roidb
        cur_from = self.cur
        cur_to = min(cur_from + self.batch_size, self.size)
        roidb = [self.roidb[self.index[i]] for i in range(cur_from, cur_to)]

        # decide multi device slice
        work_load_list = self.work_load_list
        ctx = self.ctx
        if work_load_list is None:
            work_load_list = [1] * len(ctx)
        assert isinstance(work_load_list, list) and len(work_load_list) == len(ctx), \
            "Invalid settings for work load. "
        slices = _split_input_slice(self.batch_size, work_load_list)

        # get testing data for multigpu
        data_list = []
        label_list = []
        for islice in slices:
            iroidb = [roidb[i] for i in range(islice.start, islice.stop)]
            data, label = get_rpn_pair_batch(iroidb, self.cfg)
            data_list.append(data)
            label_list.append(label)

        # pad data first and then assign anchor (read label)
        data_tensor = tensor_vstack([batch['data'] for batch in data_list])
        for data, data_pad in zip(data_list, data_tensor):
            data['data'] = data_pad[np.newaxis, :]

        new_label_list = []
        for data, label in zip(data_list, label_list):
            # infer label shape
            data_shape = {k: v.shape for k, v in data.items()}
            del data_shape['im_info']
            _, feat_shape, _ = self.feat_sym.infer_shape(**data_shape)
            feat_shape = [int(i) for i in feat_shape[0]]

            # add gt_boxes to data for e2e
            data['gt_boxes'] = label['gt_boxes'][np.newaxis, :, :]

            # assign anchor for label
            label = assign_anchor(feat_shape, label['gt_boxes'], data['im_info'], self.cfg,
                                  self.feat_stride, self.anchor_scales,
                                  self.anchor_ratios, self.allowed_border,
                                  self.normalize_target, self.bbox_mean, self.bbox_std)
            new_label_list.append(label)

        all_data = dict()
        for key in self.data_name:
            all_data[key] = tensor_vstack([batch[key] for batch in data_list])

        all_label = dict()
        for key in self.label_name:
            pad = -1 if key == 'label' else 0
            all_label[key] = tensor_vstack([batch[key] for batch in new_label_list], pad=pad)

        self.data = [mx.nd.array(all_data[key]) for key in self.data_name]
        self.label = [mx.nd.array(all_label[key]) for key in self.label_name] 
開發者ID:msracver,項目名稱:Deep-Feature-Flow,代碼行數:60,代碼來源:loader.py

示例5: get_batch

# 需要導入模塊: from utils import image [as 別名]
# 或者: from utils.image import tensor_vstack [as 別名]
def get_batch(self):
        # slice roidb
        cur_from = self.cur
        cur_to = min(cur_from + self.batch_size, self.size)
        roidb = [self.roidb[self.index[i]] for i in range(cur_from, cur_to)]

        # decide multi device slice
        work_load_list = self.work_load_list
        ctx = self.ctx
        if work_load_list is None:
            work_load_list = [1] * len(ctx)
        assert isinstance(work_load_list, list) and len(work_load_list) == len(ctx), \
            "Invalid settings for work load. "
        slices = _split_input_slice(self.batch_size, work_load_list)

        # get testing data for multigpu
        data_list = []
        label_list = []
        for islice in slices:
            iroidb = [roidb[i] for i in range(islice.start, islice.stop)]
            data, label = get_rpn_batch(iroidb, self.cfg)
            data_list.append(data)
            label_list.append(label)

        # pad data first and then assign anchor (read label)
        data_tensor = tensor_vstack([batch['data'] for batch in data_list])
        for data, data_pad in zip(data_list, data_tensor):
            data['data'] = data_pad[np.newaxis, :]

        new_label_list = []
        for data, label in zip(data_list, label_list):
            # infer label shape
            data_shape = {k: v.shape for k, v in data.items()}
            del data_shape['im_info']
            _, feat_shape, _ = self.feat_sym.infer_shape(**data_shape)
            feat_shape = [int(i) for i in feat_shape[0]]

            # add gt_boxes to data for e2e
            data['gt_boxes'] = label['gt_boxes'][np.newaxis, :, :]

            # assign anchor for label
            label = assign_anchor(feat_shape, label['gt_boxes'], data['im_info'], self.cfg,
                                  self.feat_stride, self.anchor_scales,
                                  self.anchor_ratios, self.allowed_border,
                                  self.normalize_target, self.bbox_mean, self.bbox_std)
            new_label_list.append(label)

        all_data = dict()
        for key in self.data_name:
            all_data[key] = tensor_vstack([batch[key] for batch in data_list])

        all_label = dict()
        for key in self.label_name:
            pad = -1 if key == 'label' else 0
            all_label[key] = tensor_vstack([batch[key] for batch in new_label_list], pad=pad)

        self.data = [mx.nd.array(all_data[key]) for key in self.data_name]
        self.label = [mx.nd.array(all_label[key]) for key in self.label_name] 
開發者ID:msracver,項目名稱:Deep-Feature-Flow,代碼行數:60,代碼來源:loader.py

示例6: get_batch

# 需要導入模塊: from utils import image [as 別名]
# 或者: from utils.image import tensor_vstack [as 別名]
def get_batch(self):
        # slice roidb
        cur_from = self.cur
        cur_to = min(cur_from + self.batch_size, self.size)
        roidb = [self.roidb[self.index[i]] for i in range(cur_from, cur_to)]

        # decide multi device slice
        work_load_list = self.work_load_list
        ctx = self.ctx
        if work_load_list is None:
            work_load_list = [1] * len(ctx)
        assert isinstance(work_load_list, list) and len(work_load_list) == len(ctx), \
            "Invalid settings for work load. "
        slices = _split_input_slice(self.batch_size, work_load_list)

        # get testing data for multigpu
        data_list = []
        label_list = []
        for islice in slices:
            iroidb = [roidb[i] for i in range(islice.start, islice.stop)]
            data, label = get_rpn_triple_batch(iroidb, self.cfg)
            data_list.append(data)
            label_list.append(label)

        # pad data first and then assign anchor (read label)
        data_tensor = tensor_vstack([batch['data'] for batch in data_list])
        for data, data_pad in zip(data_list, data_tensor):
            data['data'] = data_pad[np.newaxis, :]

        new_label_list = []
        for data, label in zip(data_list, label_list):
            # infer label shape
            data_shape = {k: v.shape for k, v in data.items()}
            del data_shape['im_info']
            _, feat_shape, _ = self.feat_sym.infer_shape(**data_shape)
            feat_shape = [int(i) for i in feat_shape[0]]

            # add gt_boxes to data for e2e
            data['gt_boxes'] = label['gt_boxes'][np.newaxis, :, :]

            # assign anchor for label
            label = assign_anchor(feat_shape, label['gt_boxes'], data['im_info'], self.cfg,
                                  self.feat_stride, self.anchor_scales,
                                  self.anchor_ratios, self.allowed_border,
                                  self.normalize_target, self.bbox_mean, self.bbox_std)
            new_label_list.append(label)

        all_data = dict()
        for key in self.data_name:
            all_data[key] = tensor_vstack([batch[key] for batch in data_list])

        all_label = dict()
        for key in self.label_name:
            pad = -1 if key == 'label' else 0
            all_label[key] = tensor_vstack([batch[key] for batch in new_label_list], pad=pad)

        self.data = [mx.nd.array(all_data[key]) for key in self.data_name]
        self.label = [mx.nd.array(all_label[key]) for key in self.label_name] 
開發者ID:msracver,項目名稱:Flow-Guided-Feature-Aggregation,代碼行數:60,代碼來源:loader.py

示例7: get_batch

# 需要導入模塊: from utils import image [as 別名]
# 或者: from utils.image import tensor_vstack [as 別名]
def get_batch(self):
        # slice roidb
        cur_from = self.cur
        cur_to = min(cur_from + self.batch_size, self.size)
        roidb = [self.roidb[self.index[i]] for i in range(cur_from, cur_to)]

        # decide multi device slice
        work_load_list = self.work_load_list
        ctx = self.ctx
        if work_load_list is None:
            work_load_list = [1] * len(ctx)
        assert isinstance(work_load_list, list) and len(work_load_list) == len(ctx), \
            "Invalid settings for work load. "
        slices = _split_input_slice(self.batch_size, work_load_list)

        # get testing data for multigpu
        data_list = []
        label_list = []
        for islice in slices:
            iroidb = [roidb[i] for i in range(islice.start, islice.stop)]
            data, label = get_rpn_triple_batch(iroidb, self.cfg)
            data_list.append(data)
            label_list.append(label)

        # pad data first and then assign anchor (read label)
        data_tensor = tensor_vstack([batch['data'] for batch in data_list])
        for data, data_pad in zip(data_list, data_tensor):
            data['data'] = data_pad[np.newaxis, :]

        new_label_list = []
        for data, label in zip(data_list, label_list):
            # infer label shape
            data_shape = {k: v.shape for k, v in data.items()}
            del data_shape['im_info']
            _, feat_shape, _ = self.feat_sym.infer_shape(**data_shape)
            feat_shape = [int(i) for i in feat_shape[0]]

            # add gt_boxes to data for e2e
            data['gt_boxes'] = label['gt_boxes'][np.newaxis, :, :]

            # assign anchor for label
            label_f = assign_anchor(feat_shape, label['gt_boxes'], data['im_info'], self.cfg,
                                    self.feat_stride, self.anchor_scales,
                                    self.anchor_ratios, self.allowed_border,
                                    self.normalize_target, self.bbox_mean, self.bbox_std)

            new_label_list.append(label_f)

        all_data = dict()
        for key in self.data_name:
            all_data[key] = tensor_vstack([batch[key] for batch in data_list])

        all_label = dict()
        for key in self.label_name:
            pad = -1 if key == 'label' else 0
            all_label[key] = tensor_vstack([batch[key] for batch in new_label_list], pad=pad)

        self.data = [mx.nd.array(all_data[key]) for key in self.data_name]
        self.label = [mx.nd.array(all_label[key]) for key in self.label_name] 
開發者ID:happywu,項目名稱:Sequence-Level-Semantics-Aggregation,代碼行數:61,代碼來源:loader.py


注:本文中的utils.image.tensor_vstack方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台,相關代碼片段篩選自各路編程大神貢獻的開源項目,源碼版權歸原作者所有,傳播和使用請參考對應項目的License;未經允許,請勿轉載。