本文整理汇总了Python中object_detection.core.losses.WeightedSoftmaxClassificationAgainstLogitsLoss方法的典型用法代码示例。如果您正苦于以下问题：Python losses.WeightedSoftmaxClassificationAgainstLogitsLoss方法的具体用法？Python losses.WeightedSoftmaxClassificationAgainstLogitsLoss怎么用？Python losses.WeightedSoftmaxClassificationAgainstLogitsLoss使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类object_detection.core.losses的用法示例。
在下文中一共展示了losses.WeightedSoftmaxClassificationAgainstLogitsLoss方法的10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: test_build_weighted_logits_softmax_classification_loss
# 需要导入模块: from object_detection.core import losses [as 别名]
# 或者: from object_detection.core.losses import WeightedSoftmaxClassificationAgainstLogitsLoss [as 别名]
def test_build_weighted_logits_softmax_classification_loss(self):
losses_text_proto = """
classification_loss {
weighted_logits_softmax {
}
}
localization_loss {
weighted_l2 {
}
}
"""
losses_proto = losses_pb2.Loss()
text_format.Merge(losses_text_proto, losses_proto)
classification_loss, _, _, _, _, _, _ = losses_builder.build(losses_proto)
self.assertTrue(
isinstance(classification_loss,
losses.WeightedSoftmaxClassificationAgainstLogitsLoss)) 开发者ID:ShivangShekhar，项目名称:Live-feed-object-device-identification-using-Tensorflow-and-OpenCV，代码行数:19，代码来源:losses_builder_test.py
示例2: testReturnsCorrectLoss
# 需要导入模块: from object_detection.core import losses [as 别名]
# 或者: from object_detection.core.losses import WeightedSoftmaxClassificationAgainstLogitsLoss [as 别名]
def testReturnsCorrectLoss(self):
prediction_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
[0, 0, -100],
[-100, -100, 100]],
[[-100, 0, 0],
[-100, 100, -100],
[-100, 100, -100],
[100, -100, -100]]], tf.float32)
target_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
[100, -100, -100],
[-100, -100, 100]],
[[-100, -100, 100],
[-100, 100, -100],
[-100, 100, -100],
[100, -100, -100]]], tf.float32)
weights = tf.constant([[1, 1, .5, 1],
[1, 1, 1, 1]], tf.float32)
weights_shape = tf.shape(weights)
weights_multiple = tf.concat(
[tf.ones_like(weights_shape), tf.constant([3])],
axis=0)
weights = tf.tile(tf.expand_dims(weights, 2), weights_multiple)
loss_op = losses.WeightedSoftmaxClassificationAgainstLogitsLoss()
loss = loss_op(prediction_tensor, target_tensor, weights=weights)
loss = tf.reduce_sum(loss)
exp_loss = - 1.5 * math.log(.5)
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, exp_loss) 示例3: testReturnsCorrectAnchorWiseLoss
# 需要导入模块: from object_detection.core import losses [as 别名]
# 或者: from object_detection.core.losses import WeightedSoftmaxClassificationAgainstLogitsLoss [as 别名]
def testReturnsCorrectAnchorWiseLoss(self):
prediction_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
[0, 0, -100],
[-100, -100, 100]],
[[-100, 0, 0],
[-100, 100, -100],
[-100, 100, -100],
[100, -100, -100]]], tf.float32)
target_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
[100, -100, -100],
[-100, -100, 100]],
[[-100, -100, 100],
[-100, 100, -100],
[-100, 100, -100],
[100, -100, -100]]], tf.float32)
weights = tf.constant([[1, 1, .5, 1],
[1, 1, 1, 0]], tf.float32)
weights_shape = tf.shape(weights)
weights_multiple = tf.concat(
[tf.ones_like(weights_shape), tf.constant([3])],
axis=0)
weights = tf.tile(tf.expand_dims(weights, 2), weights_multiple)
loss_op = losses.WeightedSoftmaxClassificationAgainstLogitsLoss()
loss = loss_op(prediction_tensor, target_tensor, weights=weights)
exp_loss = np.matrix([[0, 0, - 0.5 * math.log(.5), 0],
[-math.log(.5), 0, 0, 0]])
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, exp_loss) 示例4: build_faster_rcnn_classification_loss
# 需要导入模块: from object_detection.core import losses [as 别名]
# 或者: from object_detection.core.losses import WeightedSoftmaxClassificationAgainstLogitsLoss [as 别名]
def build_faster_rcnn_classification_loss(loss_config):
"""Builds a classification loss for Faster RCNN based on the loss config.
Args:
loss_config: A losses_pb2.ClassificationLoss object.
Returns:
Loss based on the config.
Raises:
ValueError: On invalid loss_config.
"""
if not isinstance(loss_config, losses_pb2.ClassificationLoss):
raise ValueError('loss_config not of type losses_pb2.ClassificationLoss.')
loss_type = loss_config.WhichOneof('classification_loss')
if loss_type == 'weighted_sigmoid':
return losses.WeightedSigmoidClassificationLoss()
if loss_type == 'weighted_softmax':
config = loss_config.weighted_softmax
return losses.WeightedSoftmaxClassificationLoss(
logit_scale=config.logit_scale)
if loss_type == 'weighted_logits_softmax':
config = loss_config.weighted_logits_softmax
return losses.WeightedSoftmaxClassificationAgainstLogitsLoss(
logit_scale=config.logit_scale)
if loss_type == 'weighted_sigmoid_focal':
config = loss_config.weighted_sigmoid_focal
alpha = None
if config.HasField('alpha'):
alpha = config.alpha
return losses.SigmoidFocalClassificationLoss(
gamma=config.gamma,
alpha=alpha)
# By default, Faster RCNN second stage classifier uses Softmax loss
# with anchor-wise outputs.
config = loss_config.weighted_softmax
return losses.WeightedSoftmaxClassificationLoss(
logit_scale=config.logit_scale) 示例5: test_build_logits_softmax_loss
# 需要导入模块: from object_detection.core import losses [as 别名]
# 或者: from object_detection.core.losses import WeightedSoftmaxClassificationAgainstLogitsLoss [as 别名]
def test_build_logits_softmax_loss(self):
losses_text_proto = """
weighted_logits_softmax {
}
"""
losses_proto = losses_pb2.ClassificationLoss()
text_format.Merge(losses_text_proto, losses_proto)
classification_loss = losses_builder.build_faster_rcnn_classification_loss(
losses_proto)
self.assertTrue(
isinstance(classification_loss,
losses.WeightedSoftmaxClassificationAgainstLogitsLoss)) 示例6: testReturnsCorrectLoss
# 需要导入模块: from object_detection.core import losses [as 别名]
# 或者: from object_detection.core.losses import WeightedSoftmaxClassificationAgainstLogitsLoss [as 别名]
def testReturnsCorrectLoss(self):
prediction_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
[0, 0, -100],
[-100, -100, 100]],
[[-100, 0, 0],
[-100, 100, -100],
[-100, 100, -100],
[100, -100, -100]]], tf.float32)
target_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
[100, -100, -100],
[-100, -100, 100]],
[[-100, -100, 100],
[-100, 100, -100],
[-100, 100, -100],
[100, -100, -100]]], tf.float32)
weights = tf.constant([[1, 1, .5, 1],
[1, 1, 1, 1]], tf.float32)
loss_op = losses.WeightedSoftmaxClassificationAgainstLogitsLoss()
loss = loss_op(prediction_tensor, target_tensor, weights=weights)
loss = tf.reduce_sum(loss)
exp_loss = - 1.5 * math.log(.5)
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, exp_loss) 示例7: testReturnsCorrectAnchorWiseLoss
# 需要导入模块: from object_detection.core import losses [as 别名]
# 或者: from object_detection.core.losses import WeightedSoftmaxClassificationAgainstLogitsLoss [as 别名]
def testReturnsCorrectAnchorWiseLoss(self):
prediction_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
[0, 0, -100],
[-100, -100, 100]],
[[-100, 0, 0],
[-100, 100, -100],
[-100, 100, -100],
[100, -100, -100]]], tf.float32)
target_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
[100, -100, -100],
[-100, -100, 100]],
[[-100, -100, 100],
[-100, 100, -100],
[-100, 100, -100],
[100, -100, -100]]], tf.float32)
weights = tf.constant([[1, 1, .5, 1],
[1, 1, 1, 0]], tf.float32)
loss_op = losses.WeightedSoftmaxClassificationAgainstLogitsLoss()
loss = loss_op(prediction_tensor, target_tensor, weights=weights)
exp_loss = np.matrix([[0, 0, - 0.5 * math.log(.5), 0],
[-math.log(.5), 0, 0, 0]])
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, exp_loss) 示例8: build_faster_rcnn_classification_loss
# 需要导入模块: from object_detection.core import losses [as 别名]
# 或者: from object_detection.core.losses import WeightedSoftmaxClassificationAgainstLogitsLoss [as 别名]
def build_faster_rcnn_classification_loss(loss_config):
"""Builds a classification loss for Faster RCNN based on the loss config.
Args:
loss_config: A losses_pb2.ClassificationLoss object.
Returns:
Loss based on the config.
Raises:
ValueError: On invalid loss_config.
"""
if not isinstance(loss_config, losses_pb2.ClassificationLoss):
raise ValueError('loss_config not of type losses_pb2.ClassificationLoss.')
loss_type = loss_config.WhichOneof('classification_loss')
if loss_type == 'weighted_sigmoid':
return losses.WeightedSigmoidClassificationLoss()
if loss_type == 'weighted_softmax':
config = loss_config.weighted_softmax
return losses.WeightedSoftmaxClassificationLoss(
logit_scale=config.logit_scale)
if loss_type == 'weighted_logits_softmax':
config = loss_config.weighted_logits_softmax
return losses.WeightedSoftmaxClassificationAgainstLogitsLoss(
logit_scale=config.logit_scale)
# By default, Faster RCNN second stage classifier uses Softmax loss
# with anchor-wise outputs.
config = loss_config.weighted_softmax
return losses.WeightedSoftmaxClassificationLoss(
logit_scale=config.logit_scale) 示例9: testReturnsCorrectLoss
# 需要导入模块: from object_detection.core import losses [as 别名]
# 或者: from object_detection.core.losses import WeightedSoftmaxClassificationAgainstLogitsLoss [as 别名]
def testReturnsCorrectLoss(self):
prediction_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
[0, 0, -100],
[-100, -100, 100]],
[[-100, 0, 0],
[-100, 100, -100],
[-100, 100, -100],
[100, -100, -100]]], tf.float32)
target_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
[100, -100, -100],
[-100, -100, 100]],
[[-100, -100, 100],
[-100, 100, -100],
[-100, 100, -100],
[100, -100, -100]]], tf.float32)
weights = tf.constant([[1, 1, .5, 1],
[1, 1, 1, 1]], tf.float32)
loss_op = losses.WeightedSoftmaxClassificationAgainstLogitsLoss()
loss = loss_op(prediction_tensor, target_tensor, weights=weights)
loss = tf.reduce_sum(loss)
exp_loss = - 1.5 * math.log(.5)
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, exp_loss) 示例10: testReturnsCorrectAnchorWiseLoss
# 需要导入模块: from object_detection.core import losses [as 别名]
# 或者: from object_detection.core.losses import WeightedSoftmaxClassificationAgainstLogitsLoss [as 别名]
def testReturnsCorrectAnchorWiseLoss(self):
prediction_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
[0, 0, -100],
[-100, -100, 100]],
[[-100, 0, 0],
[-100, 100, -100],
[-100, 100, -100],
[100, -100, -100]]], tf.float32)
target_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
[100, -100, -100],
[-100, -100, 100]],
[[-100, -100, 100],
[-100, 100, -100],
[-100, 100, -100],
[100, -100, -100]]], tf.float32)
weights = tf.constant([[1, 1, .5, 1],
[1, 1, 1, 0]], tf.float32)
loss_op = losses.WeightedSoftmaxClassificationAgainstLogitsLoss()
loss = loss_op(prediction_tensor, target_tensor, weights=weights)
exp_loss = np.matrix([[0, 0, - 0.5 * math.log(.5), 0],
[-math.log(.5), 0, 0, 0]])
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, exp_loss)