当前位置: 首页>>代码示例>>Python>>正文


Python cfg.MAX_NUM_GT_BOXES属性代码示例

本文整理汇总了Python中model.utils.config.cfg.MAX_NUM_GT_BOXES属性的典型用法代码示例。如果您正苦于以下问题:Python cfg.MAX_NUM_GT_BOXES属性的具体用法?Python cfg.MAX_NUM_GT_BOXES怎么用?Python cfg.MAX_NUM_GT_BOXES使用的例子?那么, 这里精选的属性代码示例或许可以为您提供帮助。您也可以进一步了解该属性所在model.utils.config.cfg的用法示例。


在下文中一共展示了cfg.MAX_NUM_GT_BOXES属性的12个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: __init__

# 需要导入模块: from model.utils.config import cfg [as 别名]
# 或者: from model.utils.config.cfg import MAX_NUM_GT_BOXES [as 别名]
def __init__(self, roidb, ratio_list, ratio_index, batch_size, num_classes, training=True, normalize=None):
    self._roidb = roidb
    self._num_classes = num_classes
    # we make the height of image consistent to trim_height, trim_width
    self.trim_height = cfg.TRAIN.TRIM_HEIGHT
    self.trim_width = cfg.TRAIN.TRIM_WIDTH
    self.max_num_box = cfg.MAX_NUM_GT_BOXES
    self.training = training
    self.normalize = normalize
    self.ratio_list = ratio_list
    self.ratio_index = ratio_index
    self.batch_size = batch_size
    self.data_size = len(self.ratio_list)

    # given the ratio_list, we want to make the ratio same for each batch.
    self.ratio_list_batch = torch.Tensor(self.data_size).zero_()
    num_batch = int(np.ceil(len(ratio_index) / batch_size))
    for i in range(num_batch):
        left_idx = i*batch_size
        right_idx = min((i+1)*batch_size-1, self.data_size-1)

        if ratio_list[right_idx] < 1:
            # for ratio < 1, we preserve the leftmost in each batch.
            target_ratio = ratio_list[left_idx]
        elif ratio_list[left_idx] > 1:
            # for ratio > 1, we preserve the rightmost in each batch.
            target_ratio = ratio_list[right_idx]
        else:
            # for ratio cross 1, we make it to be 1.
            target_ratio = 1

        self.ratio_list_batch[left_idx:(right_idx+1)] = target_ratio 
开发者ID:guoruoqian,项目名称:cascade-rcnn_Pytorch,代码行数:34,代码来源:roibatchLoader.py

示例2: __init__

# 需要导入模块: from model.utils.config import cfg [as 别名]
# 或者: from model.utils.config.cfg import MAX_NUM_GT_BOXES [as 别名]
def __init__(self, roidb, ratio_list, ratio_index, batch_size, num_classes, training=True, normalize=None):
    self._roidb = roidb
    self._num_classes = num_classes
    # we make the height of image consistent to trim_height, trim_width
    self.trim_height = cfg.TRAIN.TRIM_HEIGHT
    self.trim_width = cfg.TRAIN.TRIM_WIDTH
    self.max_num_box = cfg.MAX_NUM_GT_BOXES
    self.training = training
    self.normalize = normalize
    self.batch_size = batch_size
    self.ratio_list = ratio_list
    self.ratio_index = ratio_index
    self.data_size = len(self.ratio_list)
    # given the ratio_list, we want to make the ratio same for each batch.
    self.ratio_list_batch = torch.Tensor(self.data_size).zero_()
    num_batch = int(np.ceil(len(ratio_index) / batch_size))
    for i in range(num_batch):
        left_idx = i*batch_size
        right_idx = min((i+1)*batch_size-1, self.data_size-1)

        if ratio_list[right_idx] < 1:
            # for ratio < 1, we preserve the leftmost in each batch.
            target_ratio = ratio_list[left_idx]
        elif ratio_list[left_idx] > 1:
            # for ratio > 1, we preserve the rightmost in each batch.
            target_ratio = ratio_list[right_idx]
        else:
            # for ratio cross 1, we make it to be 1.
            target_ratio = 1


        self.ratio_list_batch[left_idx:(right_idx+1)] = target_ratio 
开发者ID:Feynman27,项目名称:pytorch-detect-to-track,代码行数:34,代码来源:roibatchLoader.py

示例3: __init__

# 需要导入模块: from model.utils.config import cfg [as 别名]
# 或者: from model.utils.config.cfg import MAX_NUM_GT_BOXES [as 别名]
def __init__(self, roidb, ratio_list, ratio_index, batch_size, num_classes,
                 training=True, normalize=None,
                 vis=False):
        self._roidb = roidb
        self._num_classes = num_classes
        # we make the height of image consistent to trim_height, trim_width
        self.trim_height = cfg.TRAIN.TRIM_HEIGHT
        self.trim_width = cfg.TRAIN.TRIM_WIDTH
        self.max_num_box = cfg.MAX_NUM_GT_BOXES
        self.training = training
        self.normalize = normalize
        self.ratio_list = ratio_list
        self.ratio_index = ratio_index
        self.batch_size = batch_size
        self.data_size = len(self.ratio_list)
        self.vis = vis

        # given the ratio_list, we want to make the ratio same for each batch.
        self.ratio_list_batch = torch.Tensor(self.data_size).zero_()
        num_batch = int(np.ceil(len(ratio_index) / batch_size))
        for i in range(num_batch):
            left_idx = i * batch_size
            right_idx = min((i + 1) * batch_size - 1, self.data_size - 1)

            if ratio_list[right_idx] < 1:
                # for ratio < 1, we preserve the leftmost in each batch.
                target_ratio = ratio_list[left_idx]
            elif ratio_list[left_idx] > 1:
                # for ratio > 1, we preserve the rightmost in each batch.
                target_ratio = ratio_list[right_idx]
            else:
                # for ratio cross 1, we make it to be 1.
                target_ratio = 1.

            self.ratio_list_batch[
            left_idx:(right_idx + 1)] = target_ratio.astype('float') 
开发者ID:ucbdrive,项目名称:3d-vehicle-tracking,代码行数:38,代码来源:roibatchLoader.py

示例4: __init__

# 需要导入模块: from model.utils.config import cfg [as 别名]
# 或者: from model.utils.config.cfg import MAX_NUM_GT_BOXES [as 别名]
def __init__(self, roidb, ratio_list, ratio_index, batch_size, num_classes, training=True, normalize=None):
    self._roidb = roidb
    self._num_classes = num_classes
    # we make the height of image consistent to trim_height, trim_width
    self.trim_height = cfg.TRAIN.TRIM_HEIGHT
    self.trim_width = cfg.TRAIN.TRIM_WIDTH
    self.max_num_box = cfg.MAX_NUM_GT_BOXES
    self.training = training
    self.normalize = normalize
    self.ratio_list = ratio_list
    self.ratio_index = ratio_index
    self.batch_size = batch_size
    self.data_size = len(self.ratio_list)

    # given the ratio_list, we want to make the ratio same for each batch.
    self.ratio_list_batch = torch.Tensor(self.data_size).zero_()
    self.target_size_batch = torch.Tensor(self.data_size).zero_()

    num_batch = int(np.ceil(len(ratio_index) / batch_size))
    for i in range(num_batch):
        left_idx = i*batch_size
        right_idx = min((i+1)*batch_size-1, self.data_size-1)

        if ratio_list[right_idx] < 1:
            # for ratio < 1, we preserve the leftmost in each batch.
            target_ratio = ratio_list[left_idx]
        elif ratio_list[left_idx] > 1:
            # for ratio > 1, we preserve the rightmost in each batch.
            target_ratio = ratio_list[right_idx]
        else:
            # for ratio cross 1, we make it to be 1.
            target_ratio = 1

        self.ratio_list_batch[left_idx:(right_idx+1)] = target_ratio 
开发者ID:princewang1994,项目名称:RFCN_CoupleNet.pytorch,代码行数:36,代码来源:roibatchLoader.py

示例5: __init__

# 需要导入模块: from model.utils.config import cfg [as 别名]
# 或者: from model.utils.config.cfg import MAX_NUM_GT_BOXES [as 别名]
def __init__(self, roidb, ratio_list, ratio_index, batch_size, num_classes, training=True, normalize=None):
    self._roidb = roidb
    self._num_classes = num_classes
    # we make the height of image consistent to trim_height, trim_width
    self.trim_height = cfg.TRAIN.TRIM_HEIGHT
    self.trim_width = cfg.TRAIN.TRIM_WIDTH
    self.max_num_box = cfg.MAX_NUM_GT_BOXES
    self.training = training
    self.normalize = normalize
    self.ratio_list = ratio_list
    self.ratio_index = ratio_index
    self.batch_size = batch_size
    self.data_size = len(self.ratio_list)

    # given the ratio_list, we want to make the ratio same for each batch.
    self.ratio_list_batch = torch.Tensor(self.data_size).zero_()
    num_batch = int(np.ceil(len(ratio_index) / batch_size))
    for i in range(num_batch):
        left_idx = i*batch_size
        right_idx = min((i+1)*batch_size-1, self.data_size-1)

        if ratio_list[right_idx] < 1:
            # for ratio < 1, we preserve the leftmost in each batch.
            target_ratio = ratio_list[left_idx]
        elif ratio_list[left_idx] > 1:
            # for ratio > 1, we preserve the rightmost in each batch.
            target_ratio = ratio_list[right_idx]
        else:
            # for ratio cross 1, we make it to be 1.
            target_ratio = 1

        self.ratio_list_batch[left_idx:(right_idx+1)] = torch.tensor(target_ratio.astype(np.float64)) # trainset ratio list ,each batch is same number 
开发者ID:jwyang,项目名称:faster-rcnn.pytorch,代码行数:34,代码来源:roibatchLoader.py

示例6: __init__

# 需要导入模块: from model.utils.config import cfg [as 别名]
# 或者: from model.utils.config.cfg import MAX_NUM_GT_BOXES [as 别名]
def __init__(self, roidb, ratio_list, ratio_index, batch_size, num_classes, training=True, normalize=None,
                 shuffle=True):
        self._roidb = roidb
        self._num_classes = num_classes
        # we make the height of image consistent to trim_height, trim_width
        self.trim_height = cfg.TRAIN.TRIM_HEIGHT
        self.trim_width = cfg.TRAIN.TRIM_WIDTH
        self.max_num_box = cfg.MAX_NUM_GT_BOXES
        self.training = training
        self.normalize = normalize
        self.ratio_list = ratio_list
        self.ratio_index = ratio_index
        self.batch_size = batch_size
        self.data_size = len(self.ratio_list)
        self.shuffle = shuffle

        # given the ratio_list, we want to make the ratio same for each batch.
        self.ratio_list_batch = torch.Tensor(self.data_size).zero_()
        num_batch = int(np.ceil(len(ratio_index) / batch_size))
        for i in range(num_batch):
            left_idx = i * batch_size
            right_idx = min((i + 1) * batch_size - 1, self.data_size - 1)

            if ratio_list[right_idx] < 1:
                # for ratio < 1, we preserve the leftmost in each batch.
                target_ratio = ratio_list[left_idx]
            elif ratio_list[left_idx] > 1:
                # for ratio > 1, we preserve the rightmost in each batch.
                target_ratio = ratio_list[right_idx]
            else:
                # for ratio cross 1, we make it to be 1.
                target_ratio = 1

            self.ratio_list_batch[left_idx:(right_idx + 1)] = target_ratio 
开发者ID:jinyu121,项目名称:CIOD,代码行数:36,代码来源:roibatchLoader.py

示例7: __init__

# 需要导入模块: from model.utils.config import cfg [as 别名]
# 或者: from model.utils.config.cfg import MAX_NUM_GT_BOXES [as 别名]
def __init__(self, roidb, ratio_list, ratio_index, batch_size, num_classes, training=True, normalize=None):
        self._roidb = roidb
        self._num_classes = num_classes
        # we make the height of image consistent to trim_height, trim_width
        self.trim_height = cfg.TRAIN.TRIM_HEIGHT
        self.trim_width = cfg.TRAIN.TRIM_WIDTH
        self.max_num_box = cfg.TRAIN.PROPOSAL_LIMIT #cfg.MAX_NUM_GT_BOXES
        self.training = training
        self.normalize = normalize
        self.ratio_list = ratio_list
        self.ratio_index = ratio_index
        self.batch_size = batch_size
        self.max_image_size = cfg.TRAIN.MAX_IMAGE_SIZE
        self.max_rois_size = cfg.TRAIN.MAX_ROIS_SIZE 
开发者ID:jd730,项目名称:OICR-pytorch,代码行数:16,代码来源:roibatchLoader.py

示例8: __init__

# 需要导入模块: from model.utils.config import cfg [as 别名]
# 或者: from model.utils.config.cfg import MAX_NUM_GT_BOXES [as 别名]
def __init__(self, roidb, ratio_list, ratio_index, batch_size, num_classes, training=True, normalize=None):
    self._roidb = roidb
    self._num_classes = num_classes
    # we make the height of image consistent to trim_height, trim_width
    self.trim_height = cfg.TRAIN.TRIM_HEIGHT
    self.trim_width = cfg.TRAIN.TRIM_WIDTH
    self.max_num_box = cfg.MAX_NUM_GT_BOXES
    self.training = training
    self.normalize = normalize
    self.ratio_list = ratio_list
    self.ratio_index = ratio_index
    self.batch_size = batch_size
    self.data_size = len(self.ratio_list)

    # given the ratio_list, we want to make the ratio same for each batch.
    self.ratio_list_batch = torch.Tensor(self.data_size).zero_()
    num_batch = int(np.ceil(len(ratio_index) / batch_size))
    for i in range(num_batch):
        left_idx = i*batch_size
        right_idx = min((i+1)*batch_size-1, self.data_size-1)

        if ratio_list[right_idx] < 1:
            # for ratio < 1, we preserve the leftmost in each batch.
            target_ratio = ratio_list[left_idx]
        elif ratio_list[left_idx] > 1:
            # for ratio > 1, we preserve the rightmost in each batch.
            target_ratio = ratio_list[right_idx]
        else:
            # for ratio cross 1, we make it to be 1.
            target_ratio = 1

        # self.ratio_list_batch[left_idx:(right_idx+1)] = np.asscalar(target_ratio)
        self.ratio_list_batch[left_idx:(right_idx + 1)] = target_ratio 
开发者ID:TKKim93,项目名称:DivMatch,代码行数:35,代码来源:roibatchLoader.py

示例9: __init__

# 需要导入模块: from model.utils.config import cfg [as 别名]
# 或者: from model.utils.config.cfg import MAX_NUM_GT_BOXES [as 别名]
def __init__(self, roidb, ratio_list, ratio_index, batch_size, num_classes, training=True, normalize=None):
    self._roidb = roidb
    self._num_classes = num_classes
    # we make the height of image consistent to trim_height, trim_width
    self.trim_height = cfg.TRAIN.TRIM_HEIGHT
    self.trim_width = cfg.TRAIN.TRIM_WIDTH
    self.max_num_box = cfg.MAX_NUM_GT_BOXES
    self.training = training
    self.normalize = normalize
    self.ratio_list = ratio_list
    self.ratio_index = ratio_index
    self.batch_size = batch_size
    self.data_size = len(self.ratio_list)

    # given the ratio_list, we want to make the ratio same for each batch.
    self.ratio_list_batch = torch.Tensor(self.data_size).zero_()
    num_batch = int(np.ceil(len(ratio_index) / batch_size))
    for i in range(num_batch):
        left_idx = i*batch_size
        right_idx = min((i+1)*batch_size-1, self.data_size-1)

        if ratio_list[right_idx] < 1:
            # for ratio < 1, we preserve the leftmost in each batch.
            target_ratio = ratio_list[left_idx]
        elif ratio_list[left_idx] > 1:
            # for ratio > 1, we preserve the rightmost in each batch.
            target_ratio = ratio_list[right_idx]
        else:
            # for ratio cross 1, we make it to be 1.
            target_ratio = 1
        
        target_ratio = float(target_ratio)
        self.ratio_list_batch[left_idx:(right_idx+1)] = target_ratio 
开发者ID:divyam02,项目名称:dafrcnn-pytorch,代码行数:35,代码来源:roibatchLoader.py

示例10: __init__

# 需要导入模块: from model.utils.config import cfg [as 别名]
# 或者: from model.utils.config.cfg import MAX_NUM_GT_BOXES [as 别名]
def __init__(self, roidb, ratio_list, ratio_index, batch_size, num_classes, training=True, normalize=None):
    self._roidb = roidb
    self._num_classes = num_classes
    self.max_num_box = cfg.MAX_NUM_GT_BOXES
    self.training = training
    self.normalize = normalize
    self.ratio_list = ratio_list
    self.ratio_index = ratio_index
    self.batch_size = batch_size
    self.data_size = len(self.ratio_list)

    # given the ratio_list, we want to make the ratio same for each batch.
    self.ratio_list_batch = torch.Tensor(self.data_size).zero_()
    num_batch = int(np.ceil(len(ratio_index) / batch_size))
    for i in range(num_batch):
        left_idx = i*batch_size
        right_idx = min((i+1)*batch_size-1, self.data_size-1)

        if ratio_list[right_idx] < 1:
            # for ratio < 1, we preserve the leftmost in each batch.
            target_ratio = ratio_list[left_idx]
        elif ratio_list[left_idx] > 1:
            # for ratio > 1, we preserve the rightmost in each batch.
            target_ratio = ratio_list[right_idx]
        else:
            # for ratio cross 1, we make it to be 1.
            target_ratio = 1

        self.ratio_list_batch[left_idx:(right_idx+1)] = target_ratio 
开发者ID:HKUST-Aerial-Robotics,项目名称:Stereo-RCNN,代码行数:31,代码来源:roibatchLoader.py

示例11: __init__

# 需要导入模块: from model.utils.config import cfg [as 别名]
# 或者: from model.utils.config.cfg import MAX_NUM_GT_BOXES [as 别名]
def __init__(self, roidb, ratio_list, ratio_index, batch_size, num_classes, training=True, normalize=None,seg_return=False,path_return=False):
    self._roidb = roidb
    self._num_classes = num_classes
    # we make the height of image consistent to trim_height, trim_width
    self.trim_height = cfg.TRAIN.TRIM_HEIGHT
    self.trim_width = cfg.TRAIN.TRIM_WIDTH
    self.max_num_box = cfg.MAX_NUM_GT_BOXES
    self.training = training
    self.normalize = normalize
    self.ratio_list = ratio_list
    self.ratio_index = ratio_index
    self.batch_size = batch_size
    self.data_size = len(self.ratio_list)
    self.seg_return = seg_return
    self.path_return = path_return
    # given the ratio_list, we want to make the ratio same for each batch.
    self.ratio_list_batch = torch.Tensor(self.data_size).zero_()
    num_batch = int(np.ceil(len(ratio_index) / batch_size))
    for i in range(num_batch):
        left_idx = i*batch_size
        right_idx = min((i+1)*batch_size-1, self.data_size-1)

        if ratio_list[right_idx] < 1:
            # for ratio < 1, we preserve the leftmost in each batch.
            target_ratio = ratio_list[left_idx]
        elif ratio_list[left_idx] > 1:
            # for ratio > 1, we preserve the rightmost in each batch.
            target_ratio = ratio_list[right_idx]
        else:
            # for ratio cross 1, we make it to be 1.
            target_ratio = 1

        self.ratio_list_batch[left_idx:(right_idx+1)] = target_ratio 
开发者ID:VisionLearningGroup,项目名称:DA_Detection,代码行数:35,代码来源:roibatchLoader.py

示例12: __init__

# 需要导入模块: from model.utils.config import cfg [as 别名]
# 或者: from model.utils.config.cfg import MAX_NUM_GT_BOXES [as 别名]
def __init__(self, roidb, ratio_list, ratio_index, query, batch_size, num_classes, training=True, normalize=None, seen=True):
    self._roidb = roidb
    self._query = query
    self._num_classes = num_classes
    # we make the height of image consistent to trim_height, trim_width
    self.trim_height = cfg.TRAIN.TRIM_HEIGHT
    self.trim_width = cfg.TRAIN.TRIM_WIDTH
    self.max_num_box = cfg.MAX_NUM_GT_BOXES
    self.training = training
    self.normalize = normalize
    self.ratio_list = ratio_list
    self.query_position = 0

    if training:
        self.ratio_index = ratio_index
    else:
        self.cat_list = ratio_index[1]
        self.ratio_index = ratio_index[0]

    self.batch_size = batch_size
    self.data_size = len(self.ratio_list)

    # given the ratio_list, we want to make the ratio same for each batch.
    self.ratio_list_batch = torch.Tensor(self.data_size).zero_()
    num_batch = int(np.ceil(len(ratio_index) / batch_size))
    if self.training:
        for i in range(num_batch):
            left_idx = i*batch_size
            right_idx = min((i+1)*batch_size-1, self.data_size-1)

            if ratio_list[right_idx] < 1:
                # for ratio < 1, we preserve the leftmost in each batch.
                target_ratio = ratio_list[left_idx]
            elif ratio_list[left_idx] > 1:
                # for ratio > 1, we preserve the rightmost in each batch.
                target_ratio = ratio_list[right_idx]
            else:
                # for ratio cross 1, we make it to be 1.
                target_ratio = 1

            self.ratio_list_batch[left_idx:(right_idx+1)] = target_ratio

    self._cat_ids = [
            1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 
            14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 
            24, 25, 27, 28, 31, 32, 33, 34, 35, 36, 
            37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 
            48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 
            58, 59, 60, 61, 62, 63, 64, 65, 67, 70, 
            72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 
            82, 84, 85, 86, 87, 88, 89, 90
        ]
    self._classes = {
            ind + 1: cat_id for ind, cat_id in enumerate(self._cat_ids)
        }
    self._classes_inv = {
            value: key for key, value in self._classes.items()
        }
    
    self.filter(seen)
    self.probability() 
开发者ID:timy90022,项目名称:One-Shot-Object-Detection,代码行数:63,代码来源:roibatchLoader.py


注:本文中的model.utils.config.cfg.MAX_NUM_GT_BOXES属性示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。