Python Examples of object_detection.utils.learning_schedules.exponential_decay_with

Source File: learning_schedules_test.py From object_detector_app with MIT License

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From multilabel-image-classification-tensorflow with MIT License

6 votes

def testExponentialDecayWithBurnin(self):
    def graph_fn(global_step):
      learning_rate_base = 1.0
      learning_rate_decay_steps = 3
      learning_rate_decay_factor = .1
      burnin_learning_rate = .5
      burnin_steps = 2
      min_learning_rate = .05
      learning_rate = learning_schedules.exponential_decay_with_burnin(
          global_step, learning_rate_base, learning_rate_decay_steps,
          learning_rate_decay_factor, burnin_learning_rate, burnin_steps,
          min_learning_rate)
      assert learning_rate.op.name.endswith('learning_rate')
      return (learning_rate,)

    output_rates = [
        self.execute(graph_fn, [np.array(i).astype(np.int64)]) for i in range(9)
    ]

    exp_rates = [.5, .5, 1, 1, 1, .1, .1, .1, .05]
    self.assertAllClose(output_rates, exp_rates, rtol=1e-4)

Source File: learning_schedules_test.py From mtl-ssl with Apache License 2.0

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From motion-rcnn with MIT License

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From models with Apache License 2.0

6 votes

def testExponentialDecayWithBurnin(self):
    def graph_fn(global_step):
      learning_rate_base = 1.0
      learning_rate_decay_steps = 3
      learning_rate_decay_factor = .1
      burnin_learning_rate = .5
      burnin_steps = 2
      min_learning_rate = .05
      learning_rate = learning_schedules.exponential_decay_with_burnin(
          global_step, learning_rate_base, learning_rate_decay_steps,
          learning_rate_decay_factor, burnin_learning_rate, burnin_steps,
          min_learning_rate)
      assert learning_rate.op.name.endswith('learning_rate')
      return (learning_rate,)

    output_rates = [
        self.execute(graph_fn, [np.array(i).astype(np.int64)]) for i in range(9)
    ]

    exp_rates = [.5, .5, 1, 1, 1, .1, .1, .1, .05]
    self.assertAllClose(output_rates, exp_rates, rtol=1e-4)

Source File: learning_schedules_test.py From g-tensorflow-models with Apache License 2.0

6 votes

def testExponentialDecayWithBurnin(self):
    def graph_fn(global_step):
      learning_rate_base = 1.0
      learning_rate_decay_steps = 3
      learning_rate_decay_factor = .1
      burnin_learning_rate = .5
      burnin_steps = 2
      min_learning_rate = .05
      learning_rate = learning_schedules.exponential_decay_with_burnin(
          global_step, learning_rate_base, learning_rate_decay_steps,
          learning_rate_decay_factor, burnin_learning_rate, burnin_steps,
          min_learning_rate)
      assert learning_rate.op.name.endswith('learning_rate')
      return (learning_rate,)

    output_rates = [
        self.execute(graph_fn, [np.array(i).astype(np.int64)]) for i in range(9)
    ]

    exp_rates = [.5, .5, 1, 1, 1, .1, .1, .1, .05]
    self.assertAllClose(output_rates, exp_rates, rtol=1e-4)

Source File: learning_schedules_test.py From MAX-Object-Detector with Apache License 2.0

6 votes

def testExponentialDecayWithBurnin(self):
    def graph_fn(global_step):
      learning_rate_base = 1.0
      learning_rate_decay_steps = 3
      learning_rate_decay_factor = .1
      burnin_learning_rate = .5
      burnin_steps = 2
      min_learning_rate = .05
      learning_rate = learning_schedules.exponential_decay_with_burnin(
          global_step, learning_rate_base, learning_rate_decay_steps,
          learning_rate_decay_factor, burnin_learning_rate, burnin_steps,
          min_learning_rate)
      assert learning_rate.op.name.endswith('learning_rate')
      return (learning_rate,)

    output_rates = [
        self.execute(graph_fn, [np.array(i).astype(np.int64)]) for i in range(9)
    ]

    exp_rates = [.5, .5, 1, 1, 1, .1, .1, .1, .05]
    self.assertAllClose(output_rates, exp_rates, rtol=1e-4)

Source File: learning_schedules_test.py From AniSeg with Apache License 2.0

6 votes

def testExponentialDecayWithBurnin(self):
    def graph_fn(global_step):
      learning_rate_base = 1.0
      learning_rate_decay_steps = 3
      learning_rate_decay_factor = .1
      burnin_learning_rate = .5
      burnin_steps = 2
      learning_rate = learning_schedules.exponential_decay_with_burnin(
          global_step, learning_rate_base, learning_rate_decay_steps,
          learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
      return (learning_rate,)

    output_rates = [
        self.execute(graph_fn, [np.array(i).astype(np.int64)]) for i in range(8)
    ]

    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    self.assertAllClose(output_rates, exp_rates, rtol=1e-4)

Source File: learning_schedules_test.py From object_detection_with_tensorflow with MIT License

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From object_detection_with_tensorflow with MIT License

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From Elphas with Apache License 2.0

6 votes

def testExponentialDecayWithBurnin(self):
    def graph_fn(global_step):
      learning_rate_base = 1.0
      learning_rate_decay_steps = 3
      learning_rate_decay_factor = .1
      burnin_learning_rate = .5
      burnin_steps = 2
      learning_rate = learning_schedules.exponential_decay_with_burnin(
          global_step, learning_rate_base, learning_rate_decay_steps,
          learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
      return (learning_rate,)

    output_rates = [
        self.execute(graph_fn, [np.array(i).astype(np.int64)]) for i in range(8)
    ]

    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    self.assertAllClose(output_rates, exp_rates, rtol=1e-4)

Source File: learning_schedules_test.py From MBMD with MIT License

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From object_detection_kitti with Apache License 2.0

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0

6 votes

def testExponentialDecayWithBurnin(self):
    def graph_fn(global_step):
      learning_rate_base = 1.0
      learning_rate_decay_steps = 3
      learning_rate_decay_factor = .1
      burnin_learning_rate = .5
      burnin_steps = 2
      min_learning_rate = .05
      learning_rate = learning_schedules.exponential_decay_with_burnin(
          global_step, learning_rate_base, learning_rate_decay_steps,
          learning_rate_decay_factor, burnin_learning_rate, burnin_steps,
          min_learning_rate)
      assert learning_rate.op.name.endswith('learning_rate')
      return (learning_rate,)

    output_rates = [
        self.execute(graph_fn, [np.array(i).astype(np.int64)]) for i in range(9)
    ]

    exp_rates = [.5, .5, 1, 1, 1, .1, .1, .1, .05]
    self.assertAllClose(output_rates, exp_rates, rtol=1e-4)

Source File: learning_schedules_test.py From hands-detection with MIT License

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From moveo_ros with MIT License

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From BMW-TensorFlow-Training-GUI with Apache License 2.0

6 votes

def testExponentialDecayWithBurnin(self):
    def graph_fn(global_step):
      learning_rate_base = 1.0
      learning_rate_decay_steps = 3
      learning_rate_decay_factor = .1
      burnin_learning_rate = .5
      burnin_steps = 2
      min_learning_rate = .05
      learning_rate = learning_schedules.exponential_decay_with_burnin(
          global_step, learning_rate_base, learning_rate_decay_steps,
          learning_rate_decay_factor, burnin_learning_rate, burnin_steps,
          min_learning_rate)
      assert learning_rate.op.name.endswith('learning_rate')
      return (learning_rate,)

    output_rates = [
        self.execute(graph_fn, [np.array(i).astype(np.int64)]) for i in range(9)
    ]

    exp_rates = [.5, .5, 1, 1, 1, .1, .1, .1, .05]
    self.assertAllClose(output_rates, exp_rates, rtol=1e-4)

Source File: learning_schedules_test.py From DOTA_models with Apache License 2.0

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From vehicle_counting_tensorflow with MIT License

6 votes

def testExponentialDecayWithBurnin(self):
    def graph_fn(global_step):
      learning_rate_base = 1.0
      learning_rate_decay_steps = 3
      learning_rate_decay_factor = .1
      burnin_learning_rate = .5
      burnin_steps = 2
      min_learning_rate = .05
      learning_rate = learning_schedules.exponential_decay_with_burnin(
          global_step, learning_rate_base, learning_rate_decay_steps,
          learning_rate_decay_factor, burnin_learning_rate, burnin_steps,
          min_learning_rate)
      assert learning_rate.op.name.endswith('learning_rate')
      return (learning_rate,)

    output_rates = [
        self.execute(graph_fn, [np.array(i).astype(np.int64)]) for i in range(9)
    ]

    exp_rates = [.5, .5, 1, 1, 1, .1, .1, .1, .05]
    self.assertAllClose(output_rates, exp_rates, rtol=1e-4)

Source File: learning_schedules_test.py From ros_people_object_detection_tensorflow with Apache License 2.0

6 votes

def testExponentialDecayWithBurnin(self):
    def graph_fn(global_step):
      learning_rate_base = 1.0
      learning_rate_decay_steps = 3
      learning_rate_decay_factor = .1
      burnin_learning_rate = .5
      burnin_steps = 2
      learning_rate = learning_schedules.exponential_decay_with_burnin(
          global_step, learning_rate_base, learning_rate_decay_steps,
          learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
      assert learning_rate.op.name.endswith('learning_rate')
      return (learning_rate,)

    output_rates = [
        self.execute(graph_fn, [np.array(i).astype(np.int64)]) for i in range(8)
    ]

    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    self.assertAllClose(output_rates, exp_rates, rtol=1e-4)

Source File: learning_schedules_test.py From Person-Detection-and-Tracking with MIT License

6 votes

def testExponentialDecayWithBurnin(self):
    def graph_fn(global_step):
      learning_rate_base = 1.0
      learning_rate_decay_steps = 3
      learning_rate_decay_factor = .1
      burnin_learning_rate = .5
      burnin_steps = 2
      learning_rate = learning_schedules.exponential_decay_with_burnin(
          global_step, learning_rate_base, learning_rate_decay_steps,
          learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
      assert learning_rate.op.name.endswith('learning_rate')
      return (learning_rate,)

    output_rates = [
        self.execute(graph_fn, [np.array(i).astype(np.int64)]) for i in range(8)
    ]

    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    self.assertAllClose(output_rates, exp_rates, rtol=1e-4)

Source File: learning_schedules_test.py From garbage-object-detection-tensorflow with MIT License

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From HereIsWally with MIT License

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From yolo_v2 with Apache License 2.0

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From Traffic-Rule-Violation-Detection-System with MIT License

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From Hands-On-Machine-Learning-with-OpenCV-4 with MIT License

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From tensorflow with BSD 2-Clause "Simplified" License

6 votes

def testExponentialDecayWithBurnin(self):
    global_step = tf.placeholder(tf.int32, [])
    learning_rate_base = 1.0
    learning_rate_decay_steps = 3
    learning_rate_decay_factor = .1
    burnin_learning_rate = .5
    burnin_steps = 2
    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        global_step, learning_rate_base, learning_rate_decay_steps,
        learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
    with self.test_session() as sess:
      output_rates = []
      for input_global_step in range(8):
        output_rate = sess.run(learning_rate,
                               feed_dict={global_step: input_global_step})
        output_rates.append(output_rate)
      self.assertAllClose(output_rates, exp_rates)

Source File: learning_schedules_test.py From Gun-Detector with Apache License 2.0

6 votes

def testExponentialDecayWithBurnin(self):
    def graph_fn(global_step):
      learning_rate_base = 1.0
      learning_rate_decay_steps = 3
      learning_rate_decay_factor = .1
      burnin_learning_rate = .5
      burnin_steps = 2
      learning_rate = learning_schedules.exponential_decay_with_burnin(
          global_step, learning_rate_base, learning_rate_decay_steps,
          learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
      assert learning_rate.op.name.endswith('learning_rate')
      return (learning_rate,)

    output_rates = [
        self.execute(graph_fn, [np.array(i).astype(np.int64)]) for i in range(8)
    ]

    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    self.assertAllClose(output_rates, exp_rates, rtol=1e-4)

Source File: learning_schedules_test.py From ros_tensorflow with Apache License 2.0

6 votes

def testExponentialDecayWithBurnin(self):
    def graph_fn(global_step):
      learning_rate_base = 1.0
      learning_rate_decay_steps = 3
      learning_rate_decay_factor = .1
      burnin_learning_rate = .5
      burnin_steps = 2
      learning_rate = learning_schedules.exponential_decay_with_burnin(
          global_step, learning_rate_base, learning_rate_decay_steps,
          learning_rate_decay_factor, burnin_learning_rate, burnin_steps)
      assert learning_rate.op.name.endswith('learning_rate')
      return (learning_rate,)

    output_rates = [
        self.execute(graph_fn, [np.array(i).astype(np.int64)]) for i in range(8)
    ]

    exp_rates = [.5, .5, 1, .1, .1, .1, .01, .01]
    self.assertAllClose(output_rates, exp_rates, rtol=1e-4)

Source File: optimizer_builder.py From MAX-Object-Detector with Apache License 2.0

4 votes

def _create_learning_rate(learning_rate_config):
  """Create optimizer learning rate based on config.

  Args:
    learning_rate_config: A LearningRate proto message.

  Returns:
    A learning rate.

  Raises:
    ValueError: when using an unsupported input data type.
  """
  learning_rate = None
  learning_rate_type = learning_rate_config.WhichOneof('learning_rate')
  if learning_rate_type == 'constant_learning_rate':
    config = learning_rate_config.constant_learning_rate
    learning_rate = tf.constant(config.learning_rate, dtype=tf.float32,
                                name='learning_rate')

  if learning_rate_type == 'exponential_decay_learning_rate':
    config = learning_rate_config.exponential_decay_learning_rate
    learning_rate = learning_schedules.exponential_decay_with_burnin(
        tf.train.get_or_create_global_step(),
        config.initial_learning_rate,
        config.decay_steps,
        config.decay_factor,
        burnin_learning_rate=config.burnin_learning_rate,
        burnin_steps=config.burnin_steps,
        min_learning_rate=config.min_learning_rate,
        staircase=config.staircase)

  if learning_rate_type == 'manual_step_learning_rate':
    config = learning_rate_config.manual_step_learning_rate
    if not config.schedule:
      raise ValueError('Empty learning rate schedule.')
    learning_rate_step_boundaries = [x.step for x in config.schedule]
    learning_rate_sequence = [config.initial_learning_rate]
    learning_rate_sequence += [x.learning_rate for x in config.schedule]
    learning_rate = learning_schedules.manual_stepping(
        tf.train.get_or_create_global_step(), learning_rate_step_boundaries,
        learning_rate_sequence, config.warmup)

  if learning_rate_type == 'cosine_decay_learning_rate':
    config = learning_rate_config.cosine_decay_learning_rate
    learning_rate = learning_schedules.cosine_decay_with_warmup(
        tf.train.get_or_create_global_step(),
        config.learning_rate_base,
        config.total_steps,
        config.warmup_learning_rate,
        config.warmup_steps,
        config.hold_base_rate_steps)

  if learning_rate is None:
    raise ValueError('Learning_rate %s not supported.' % learning_rate_type)

  return learning_rate

Python object_detection.utils.learning_schedules.exponential_decay_with_burnin() Examples