本文整理匯總了Python中object_detection.utils.learning_schedules.cosine_decay_with_warmup方法的典型用法代碼示例。如果您正苦於以下問題：Python learning_schedules.cosine_decay_with_warmup方法的具體用法？Python learning_schedules.cosine_decay_with_warmup怎麽用？Python learning_schedules.cosine_decay_with_warmup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.utils.learning_schedules的用法示例。
在下文中一共展示了learning_schedules.cosine_decay_with_warmup方法的5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: testCosineDecayWithWarmup
# 需要導入模塊: from object_detection.utils import learning_schedules [as 別名]
# 或者: from object_detection.utils.learning_schedules import cosine_decay_with_warmup [as 別名]
def testCosineDecayWithWarmup(self):
def graph_fn(global_step):
learning_rate_base = 1.0
total_steps = 100
warmup_learning_rate = 0.1
warmup_steps = 9
learning_rate = learning_schedules.cosine_decay_with_warmup(
global_step, learning_rate_base, total_steps,
warmup_learning_rate, warmup_steps)
assert learning_rate.op.name.endswith('learning_rate')
return (learning_rate,)
exp_rates = [0.1, 0.5, 0.9, 1.0, 0]
input_global_steps = [0, 4, 8, 9, 100]
output_rates = [
self.execute(graph_fn, [np.array(step).astype(np.int64)])
for step in input_global_steps
]
self.assertAllClose(output_rates, exp_rates) 示例2: testCosineDecayAfterTotalSteps
# 需要導入模塊: from object_detection.utils import learning_schedules [as 別名]
# 或者: from object_detection.utils.learning_schedules import cosine_decay_with_warmup [as 別名]
def testCosineDecayAfterTotalSteps(self):
def graph_fn(global_step):
learning_rate_base = 1.0
total_steps = 100
warmup_learning_rate = 0.1
warmup_steps = 9
learning_rate = learning_schedules.cosine_decay_with_warmup(
global_step, learning_rate_base, total_steps,
warmup_learning_rate, warmup_steps)
assert learning_rate.op.name.endswith('learning_rate')
return (learning_rate,)
exp_rates = [0]
input_global_steps = [101]
output_rates = [
self.execute(graph_fn, [np.array(step).astype(np.int64)])
for step in input_global_steps
]
self.assertAllClose(output_rates, exp_rates) 示例3: testCosineDecayWithHoldBaseLearningRateSteps
# 需要導入模塊: from object_detection.utils import learning_schedules [as 別名]
# 或者: from object_detection.utils.learning_schedules import cosine_decay_with_warmup [as 別名]
def testCosineDecayWithHoldBaseLearningRateSteps(self):
def graph_fn(global_step):
learning_rate_base = 1.0
total_steps = 120
warmup_learning_rate = 0.1
warmup_steps = 9
hold_base_rate_steps = 20
learning_rate = learning_schedules.cosine_decay_with_warmup(
global_step, learning_rate_base, total_steps,
warmup_learning_rate, warmup_steps, hold_base_rate_steps)
assert learning_rate.op.name.endswith('learning_rate')
return (learning_rate,)
exp_rates = [0.1, 0.5, 0.9, 1.0, 1.0, 1.0, 0.999702, 0.874255, 0.577365,
0.0]
input_global_steps = [0, 4, 8, 9, 10, 29, 30, 50, 70, 120]
output_rates = [
self.execute(graph_fn, [np.array(step).astype(np.int64)])
for step in input_global_steps
]
self.assertAllClose(output_rates, exp_rates) 示例4: testCosineDecayWithWarmup
# 需要導入模塊: from object_detection.utils import learning_schedules [as 別名]
# 或者: from object_detection.utils.learning_schedules import cosine_decay_with_warmup [as 別名]
def testCosineDecayWithWarmup(self):
global_step = tf.placeholder(tf.int32, [])
learning_rate_base = 1.0
total_steps = 100
warmup_learning_rate = 0.1
warmup_steps = 9
input_global_steps = [0, 4, 8, 9, 100]
exp_rates = [0.1, 0.5, 0.9, 1.0, 0]
learning_rate = learning_schedules.cosine_decay_with_warmup(
global_step, learning_rate_base, total_steps,
warmup_learning_rate, warmup_steps)
with self.test_session() as sess:
output_rates = []
for input_global_step in input_global_steps:
output_rate = sess.run(learning_rate,
feed_dict={global_step: input_global_step})
output_rates.append(output_rate)
self.assertAllClose(output_rates, exp_rates) 示例5: testCosineDecayWithWarmup
# 需要導入模塊: from object_detection.utils import learning_schedules [as 別名]
# 或者: from object_detection.utils.learning_schedules import cosine_decay_with_warmup [as 別名]
def testCosineDecayWithWarmup(self):
def graph_fn(global_step):
learning_rate_base = 1.0
total_steps = 100
warmup_learning_rate = 0.1
warmup_steps = 9
learning_rate = learning_schedules.cosine_decay_with_warmup(
global_step, learning_rate_base, total_steps,
warmup_learning_rate, warmup_steps)
return (learning_rate,)
exp_rates = [0.1, 0.5, 0.9, 1.0, 0]
input_global_steps = [0, 4, 8, 9, 100]
output_rates = [
self.execute(graph_fn, [np.array(step).astype(np.int64)])
for step in input_global_steps
]
self.assertAllClose(output_rates, exp_rates)