本文整理汇总了Python中model.config.cfg.POOLING_SIZE属性的典型用法代码示例。如果您正苦于以下问题：Python cfg.POOLING_SIZE属性的具体用法？Python cfg.POOLING_SIZE怎么用？Python cfg.POOLING_SIZE使用的例子？那么恭喜您, 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类model.config.cfg的用法示例。
在下文中一共展示了cfg.POOLING_SIZE属性的15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: _crop_pool_layer
# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import POOLING_SIZE [as 别名]
def _crop_pool_layer(self, bottom, rois, name):
with tf.variable_scope(name) as scope:
batch_ids = tf.squeeze(tf.slice(rois, [0, 0], [-1, 1], name="batch_id"), [1])
# Get the normalized coordinates of bboxes
bottom_shape = tf.shape(bottom)
height = (tf.to_float(bottom_shape[1]) - 1.) * np.float32(self._feat_stride[0])
width = (tf.to_float(bottom_shape[2]) - 1.) * np.float32(self._feat_stride[0])
x1 = tf.slice(rois, [0, 1], [-1, 1], name="x1") / width
y1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / height
x2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / width
y2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height #revised
# Won't be backpropagated to rois anyway, but to save time
bboxes = tf.stop_gradient(tf.concat(1,[y1, x1, y2, x2]))
pre_pool_size = cfg.POOLING_SIZE * 2
crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [pre_pool_size, pre_pool_size], name="crops")
return slim.max_pool2d(crops, [2, 2], padding='SAME') 示例2: _crop_pool_layer
# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import POOLING_SIZE [as 别名]
def _crop_pool_layer(self, bottom, rois, name):
with tf.variable_scope(name) as scope:
batch_ids = tf.squeeze(tf.slice(rois, [0, 0], [-1, 1], name="batch_id"), [1])
# Get the normalized coordinates of bboxes
bottom_shape = tf.shape(bottom)
height = (tf.to_float(bottom_shape[1]) - 1.) * np.float32(self._feat_stride[0])
width = (tf.to_float(bottom_shape[2]) - 1.) * np.float32(self._feat_stride[0])
x1 = tf.slice(rois, [0, 1], [-1, 1], name="x1") / width
y1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / height
x2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / width
y2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height
# Won't be backpropagated to rois anyway, but to save time
bboxes = tf.stop_gradient(tf.concat(1,[y1, x1, y2, x2]))
if cfg.RESNET.MAX_POOL:
pre_pool_size = cfg.POOLING_SIZE * 2
crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [pre_pool_size, pre_pool_size],
name="crops")
crops = slim.max_pool2d(crops, [2, 2], padding='SAME')
else:
crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [cfg.POOLING_SIZE, cfg.POOLING_SIZE],
name="crops")
return crops
# Do the first few layers manually, because 'SAME' padding can behave inconsistently
# for images of different sizes: sometimes 0, sometimes 1 示例3: _crop_pool_layer
# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import POOLING_SIZE [as 别名]
def _crop_pool_layer(self, bottom, rois, name):
with tf.variable_scope(name) as scope:
batch_ids = tf.squeeze(tf.slice(rois, [0, 0], [-1, 1], name="batch_id"), [1])
# Get the normalized coordinates of bboxes
bottom_shape = tf.shape(bottom)
height = (tf.to_float(bottom_shape[1]) - 1.) * np.float32(self._feat_stride[0])
width = (tf.to_float(bottom_shape[2]) - 1.) * np.float32(self._feat_stride[0])
x1 = tf.slice(rois, [0, 1], [-1, 1], name="x1") / width
y1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / height
x2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / width
y2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height
# Won't be backpropagated to rois anyway, but to save time
bboxes = tf.stop_gradient(tf.concat(1,[y1, x1, y2, x2]))
pre_pool_size = cfg.POOLING_SIZE * 2
crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [pre_pool_size, pre_pool_size], name="crops")
return slim.max_pool2d(crops, [2, 2], padding='SAME') 示例4: _crop_pool_layer
# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import POOLING_SIZE [as 别名]
def _crop_pool_layer(self, bottom, rois, name):
with tf.variable_scope(name) as scope:
batch_ids = tf.squeeze(tf.slice(rois, [0, 0], [-1, 1], name="batch_id"), [1])
# Get the normalized coordinates of bounding boxes
bottom_shape = tf.shape(bottom)
height = (tf.to_float(bottom_shape[1]) - 1.) * np.float32(self._feat_stride[0])
width = (tf.to_float(bottom_shape[2]) - 1.) * np.float32(self._feat_stride[0])
x1 = tf.slice(rois, [0, 1], [-1, 1], name="x1") / width
y1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / height
x2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / width
y2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height
# Won't be back-propagated to rois anyway, but to save time
bboxes = tf.stop_gradient(tf.concat([y1, x1, y2, x2], axis=1))
pre_pool_size = cfg.POOLING_SIZE * 2
crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [pre_pool_size, pre_pool_size], name="crops")
return slim.max_pool2d(crops, [2, 2], padding='SAME') 示例5: _crop_pool_layer
# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import POOLING_SIZE [as 别名]
def _crop_pool_layer(self, bottom, rois, name):
with tf.variable_scope(name) as scope:
batch_ids = tf.squeeze(tf.slice(rois, [0, 0], [-1, 1], name="batch_id"), [1])
# Get the normalized coordinates of bboxes
bottom_shape = tf.shape(bottom)
height = (tf.to_float(bottom_shape[1]) - 1.) * np.float32(self._feat_stride[0])
width = (tf.to_float(bottom_shape[2]) - 1.) * np.float32(self._feat_stride[0])
x1 = tf.slice(rois, [0, 1], [-1, 1], name="x1") / width
y1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / height
x2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / width
y2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height
# Won't be back-propagated to rois anyway, but to save time
bboxes = tf.stop_gradient(tf.concat([y1, x1, y2, x2], 1))
if cfg.RESNET.MAX_POOL:
pre_pool_size = cfg.POOLING_SIZE * 2
crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [pre_pool_size, pre_pool_size],
name="crops")
crops = slim.max_pool2d(crops, [2, 2], padding='SAME')
else:
crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [cfg.POOLING_SIZE, cfg.POOLING_SIZE],
name="crops")
return crops
# Do the first few layers manually, because 'SAME' padding can behave inconsistently
# for images of different sizes: sometimes 0, sometimes 1 示例6: gen_mask_parsing_labels
# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import POOLING_SIZE [as 别名]
def gen_mask_parsing_labels(parsing_labels, mask_rois):
# parsing_labels (48, 320, 320) mask_rois (48, 5)
# rois = rois.detach()
x1 = mask_rois[:, 1::4]
y1 = mask_rois[:, 2::4]
x2 = mask_rois[:, 3::4]
y2 = mask_rois[:, 4::4]
height = parsing_labels.size(1)
width = parsing_labels.size(2)
# affine theta
theta = Variable(mask_rois.data.new(mask_rois.size(0), 2, 3).zero_())
theta[:, 0, 0] = (x2 - x1) / (width - 1)
theta[:, 0, 2] = (x1 + x2 - width + 1) / (width - 1)
theta[:, 1, 1] = (y2 - y1) / (height - 1)
theta[:, 1, 2] = (y1 + y2 - height + 1) / (height - 1)
pre_pool_size = cfg.POOLING_SIZE * 8
grid = F.affine_grid(theta, torch.Size((mask_rois.size(0), 1, pre_pool_size, pre_pool_size)))
mask_parsing_labels = F.grid_sample(parsing_labels.unsqueeze(1), grid) # (48,1, 320, 320)
mask_parsing_labels = torch.round(mask_parsing_labels)
# mask_parsing_labels[mask_parsing_labels >=0.5] = 1
# mask_parsing_labels[mask_parsing_labels < 0.5] = 0
return mask_parsing_labels 示例7: _roi_pool_layer
# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import POOLING_SIZE [as 别名]
def _roi_pool_layer(self, bottom, rois): # done
return RoIPoolFunction(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1. / 16.)(bottom, rois) 开发者ID:Sunarker，项目名称:Collaborative-Learning-for-Weakly-Supervised-Object-Detection，代码行数:4，代码来源:network.py
示例8: _crop_pool_layer
# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import POOLING_SIZE [as 别名]
def _crop_pool_layer(self, bottom, rois, max_pool=True): # done
# implement it using stn
# box to affine
# input (x1,y1,x2,y2)
"""
[ x2-x1 x1 + x2 - W + 1 ]
[ ----- 0 --------------- ]
[ W - 1 W - 1 ]
[ ]
[ y2-y1 y1 + y2 - H + 1 ]
[ 0 ----- --------------- ]
[ H - 1 H - 1 ]
"""
rois = rois.detach()
x1 = rois[:, 1::4] / 16.0
y1 = rois[:, 2::4] / 16.0
x2 = rois[:, 3::4] / 16.0
y2 = rois[:, 4::4] / 16.0
height = bottom.size(2)
width = bottom.size(3)
# affine theta
theta = Variable(rois.data.new(rois.size(0), 2, 3).zero_())
theta[:, 0, 0] = (x2 - x1) / (width - 1)
theta[:, 0 ,2] = (x1 + x2 - width + 1) / (width - 1)
theta[:, 1, 1] = (y2 - y1) / (height - 1)
theta[:, 1, 2] = (y1 + y2 - height + 1) / (height - 1)
if max_pool:
pre_pool_size = cfg.POOLING_SIZE * 2
grid = F.affine_grid(theta, torch.Size((rois.size(0), 1, pre_pool_size, pre_pool_size)))
crops = F.grid_sample(bottom.expand(rois.size(0), bottom.size(1), bottom.size(2), bottom.size(3)), grid)
crops = F.max_pool2d(crops, 2, 2)
else:
grid = F.affine_grid(theta, torch.Size((rois.size(0), 1, cfg.POOLING_SIZE, cfg.POOLING_SIZE)))
crops = F.grid_sample(bottom.expand(rois.size(0), bottom.size(1), bottom.size(2), bottom.size(3)), grid)
return crops 开发者ID:Sunarker，项目名称:Collaborative-Learning-for-Weakly-Supervised-Object-Detection，代码行数:42，代码来源:network.py
示例9: _roi_pool_layer
# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import POOLING_SIZE [as 别名]
def _roi_pool_layer(self, bottom, rois):
return RoIPoolFunction(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1. / 16.)(bottom, rois) 示例10: _crop_pool_layer
# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import POOLING_SIZE [as 别名]
def _crop_pool_layer(self, bottom, rois, name):
with tf.variable_scope(name) as scope:
batch_ids = tf.squeeze(tf.slice(rois, [0, 0], [-1, 1], name="batch_id"), [1])
# Get the normalized coordinates of bboxes
bottom_shape = tf.shape(bottom)
height = (tf.to_float(bottom_shape[1]) - 1.) * np.float32(self._feat_stride[0])
width = (tf.to_float(bottom_shape[2]) - 1.) * np.float32(self._feat_stride[0])
x1 = tf.slice(rois, [0, 1], [-1, 1], name="x1") / width
y1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / height
x2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / width
y2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height
# Won't be back-propagated to rois anyway, but to save time
bboxes = tf.stop_gradient(tf.concat([y1, x1, y2, x2], 1))
if cfg.RESNET.MAX_POOL:
pre_pool_size = cfg.POOLING_SIZE * 2
crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [pre_pool_size, pre_pool_size],
name="crops")
crops = slim.max_pool2d(crops, [2, 2], padding='SAME')
else:
crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids),
[cfg.POOLING_SIZE, cfg.POOLING_SIZE],
name="crops")
return crops
# Do the first few layers manually, because 'SAME' padding can behave inconsistently
# for images of different sizes: sometimes 0, sometimes 1 示例11: _roi_pool_layer
# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import POOLING_SIZE [as 别名]
def _roi_pool_layer(self, bootom, rois, name):
with tf.variable_scope(name) as scope:
return tf.image.roi_pooling(bootom, rois,
pooled_height=cfg.POOLING_SIZE,
pooled_width=cfg.POOLING_SIZE,
spatial_scale=1. / 16.)[0] 示例12: _crop_pool_layer
# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import POOLING_SIZE [as 别名]
def _crop_pool_layer(self, bottom, rois, batch_ids, name):
with tf.variable_scope(name):
pre_pool_size = cfg.POOLING_SIZE * 2
crops = tf.image.crop_and_resize(bottom,
rois,
batch_ids,
[pre_pool_size, pre_pool_size],
name="crops")
return slim.max_pool2d(crops, [2, 2], padding='SAME') 示例13: _crop_pool_layer
# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import POOLING_SIZE [as 别名]
def _crop_pool_layer(self, bottom, rois, batch_ids, name):
with tf.variable_scope(name):
if cfg.RESNET.MAX_POOL:
pre_pool_size = cfg.POOLING_SIZE * 2
crops = tf.image.crop_and_resize(bottom, rois, batch_ids, [pre_pool_size, pre_pool_size],
name="crops")
crops = slim.max_pool2d(crops, [2, 2], padding='SAME')
else:
crops = tf.image.crop_and_resize(bottom, rois, batch_ids, [cfg.POOLING_SIZE, cfg.POOLING_SIZE],
name="crops")
return crops
# Do the first few layers manually, because 'SAME' padding can behave inconsistently
# for images of different sizes: sometimes 0, sometimes 1 示例14: _roi_pool_layer
# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import POOLING_SIZE [as 别名]
def _roi_pool_layer(self, bottom, rois):
return RoIPoolFunction(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1. / 16.)(bottom, rois)
# mode nearest, bilinear 示例15: _crop_pool_layer
# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import POOLING_SIZE [as 别名]
def _crop_pool_layer(self, bottom, rois, max_pool=True):
# implement it using stn
# box to affine
# input (x1,y1,x2,y2)
"""
[ x2-x1 x1 + x2 - W + 1 ]
[ ----- 0 --------------- ]
[ W - 1 W - 1 ]
[ ]
[ y2-y1 y1 + y2 - H + 1 ]
[ 0 ----- --------------- ]
[ H - 1 H - 1 ]
"""
rois = rois.detach()
x1 = rois[:, 1::4] / 16.0
y1 = rois[:, 2::4] / 16.0
x2 = rois[:, 3::4] / 16.0
y2 = rois[:, 4::4] / 16.0
height = bottom.size(2)
width = bottom.size(3)
# affine theta
theta = Variable(rois.data.new(rois.size(0), 2, 3).zero_())
theta[:, 0, 0] = (x2 - x1) / (width - 1)
theta[:, 0 ,2] = (x1 + x2 - width + 1) / (width - 1)
theta[:, 1, 1] = (y2 - y1) / (height - 1)
theta[:, 1, 2] = (y1 + y2 - height + 1) / (height - 1)
if max_pool:
pre_pool_size = cfg.POOLING_SIZE * 2
grid = F.affine_grid(theta, torch.Size((rois.size(0), 1, pre_pool_size, pre_pool_size)))
all_roi = []
for j in range(rois.size(0)):
_grid = grid.narrow(0, j, 1)
_roi_feature = F.grid_sample(bottom.view(1,bottom.size(1), bottom.size(2), bottom.size(3)), _grid)
all_roi.append(_roi_feature)
crops = torch.cat(all_roi)
# crops = F.grid_sample(bottom.expand(rois.size(0), bottom.size(1), bottom.size(2), bottom.size(3)), grid)
crops = F.max_pool2d(crops, 2, 2)
else:
grid = F.affine_grid(theta, torch.Size((rois.size(0), 1, cfg.POOLING_SIZE, cfg.POOLING_SIZE)))
all_roi = []
for j in range(rois.size(0)):
_grid = grid.narrow(0, j, 1)
_roi_feature = F.grid_sample(bottom.view(1,bottom.size(1), bottom.size(2), bottom.size(3)), _grid)
all_roi.append(_roi_feature)
crops = torch.cat(all_roi)
# crops = F.grid_sample(bottom.expand(rois.size(0), bottom.size(1), bottom.size(2), bottom.size(3)), grid)
return crops