本文整理匯總了Python中object_detection.core.losses.WeightedL2LocalizationLoss方法的典型用法代碼示例。如果您正苦於以下問題：Python losses.WeightedL2LocalizationLoss方法的具體用法？Python losses.WeightedL2LocalizationLoss怎麽用？Python losses.WeightedL2LocalizationLoss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類object_detection.core.losses的用法示例。
在下文中一共展示了losses.WeightedL2LocalizationLoss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: testReturnsCorrectLoss
# 需要導入模塊: from object_detection.core import losses [as 別名]
# 或者: from object_detection.core.losses import WeightedL2LocalizationLoss [as 別名]
def testReturnsCorrectLoss(self):
batch_size = 3
num_anchors = 10
code_size = 4
prediction_tensor = tf.ones([batch_size, num_anchors, code_size])
target_tensor = tf.zeros([batch_size, num_anchors, code_size])
weights = tf.constant([[1, 1, 1, 1, 1, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 0, 0, 0, 0, 0]], tf.float32)
loss_op = losses.WeightedL2LocalizationLoss()
loss = loss_op(prediction_tensor, target_tensor, weights=weights)
expected_loss = (3 * 5 * 4) / 2.0
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, expected_loss) 示例2: testReturnsCorrectNanLoss
# 需要導入模塊: from object_detection.core import losses [as 別名]
# 或者: from object_detection.core.losses import WeightedL2LocalizationLoss [as 別名]
def testReturnsCorrectNanLoss(self):
batch_size = 3
num_anchors = 10
code_size = 4
prediction_tensor = tf.ones([batch_size, num_anchors, code_size])
target_tensor = tf.concat([
tf.zeros([batch_size, num_anchors, code_size / 2]),
tf.ones([batch_size, num_anchors, code_size / 2]) * np.nan
], axis=2)
weights = tf.ones([batch_size, num_anchors])
loss_op = losses.WeightedL2LocalizationLoss()
loss = loss_op(prediction_tensor, target_tensor, weights=weights,
ignore_nan_targets=True)
expected_loss = (3 * 5 * 4) / 2.0
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, expected_loss) 示例3: testReturnsCorrectWeightedLoss
# 需要導入模塊: from object_detection.core import losses [as 別名]
# 或者: from object_detection.core.losses import WeightedL2LocalizationLoss [as 別名]
def testReturnsCorrectWeightedLoss(self):
batch_size = 3
num_anchors = 10
code_size = 4
prediction_tensor = tf.ones([batch_size, num_anchors, code_size])
target_tensor = tf.zeros([batch_size, num_anchors, code_size])
weights = tf.constant([[1, 1, 1, 1, 1, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 0, 0, 0, 0, 0]], tf.float32)
loss_op = losses.WeightedL2LocalizationLoss()
loss = tf.reduce_sum(loss_op(prediction_tensor, target_tensor,
weights=weights))
expected_loss = (3 * 5 * 4) / 2.0
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, expected_loss) 示例4: testReturnsCorrectNanLoss
# 需要導入模塊: from object_detection.core import losses [as 別名]
# 或者: from object_detection.core.losses import WeightedL2LocalizationLoss [as 別名]
def testReturnsCorrectNanLoss(self):
batch_size = 3
num_anchors = 10
code_size = 4
prediction_tensor = tf.ones([batch_size, num_anchors, code_size])
target_tensor = tf.concat([
tf.zeros([batch_size, num_anchors, code_size / 2]),
tf.ones([batch_size, num_anchors, code_size / 2]) * np.nan
], axis=2)
weights = tf.ones([batch_size, num_anchors])
loss_op = losses.WeightedL2LocalizationLoss()
loss = loss_op(prediction_tensor, target_tensor, weights=weights,
ignore_nan_targets=True)
loss = tf.reduce_sum(loss)
expected_loss = (3 * 5 * 4) / 2.0
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, expected_loss) 示例5: testReturnsCorrectWeightedLossWithLossesMask
# 需要導入模塊: from object_detection.core import losses [as 別名]
# 或者: from object_detection.core.losses import WeightedL2LocalizationLoss [as 別名]
def testReturnsCorrectWeightedLossWithLossesMask(self):
batch_size = 4
num_anchors = 10
code_size = 4
prediction_tensor = tf.ones([batch_size, num_anchors, code_size])
target_tensor = tf.zeros([batch_size, num_anchors, code_size])
weights = tf.constant([[1, 1, 1, 1, 1, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 1, 1, 1, 0, 0],
[1, 1, 1, 1, 1, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 0, 0, 0, 0, 0]], tf.float32)
losses_mask = tf.constant([True, False, True, True], tf.bool)
loss_op = losses.WeightedL2LocalizationLoss()
loss = tf.reduce_sum(loss_op(prediction_tensor, target_tensor,
weights=weights, losses_mask=losses_mask))
expected_loss = (3 * 5 * 4) / 2.0
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, expected_loss) 示例6: test_build_weighted_l2_localization_loss
# 需要導入模塊: from object_detection.core import losses [as 別名]
# 或者: from object_detection.core.losses import WeightedL2LocalizationLoss [as 別名]
def test_build_weighted_l2_localization_loss(self):
losses_text_proto = """
localization_loss {
weighted_l2 {
}
}
classification_loss {
weighted_softmax {
}
}
"""
losses_proto = losses_pb2.Loss()
text_format.Merge(losses_text_proto, losses_proto)
_, localization_loss, _, _, _ = losses_builder.build(losses_proto)
self.assertTrue(isinstance(localization_loss,
losses.WeightedL2LocalizationLoss)) 示例7: test_build_weighted_l2_localization_loss
# 需要導入模塊: from object_detection.core import losses [as 別名]
# 或者: from object_detection.core.losses import WeightedL2LocalizationLoss [as 別名]
def test_build_weighted_l2_localization_loss(self):
losses_text_proto = """
localization_loss {
weighted_l2 {
}
}
classification_loss {
weighted_softmax {
}
}
"""
losses_proto = losses_pb2.Loss()
text_format.Merge(losses_text_proto, losses_proto)
_, localization_loss, _, _, _, _ = losses_builder.build(losses_proto)
self.assertTrue(isinstance(localization_loss,
losses.WeightedL2LocalizationLoss))