Python tensorflow.scatter_mul() Examples

The following are 12 code examples of tensorflow.scatter_mul(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module tensorflow , or try the search function .
Example #1
Source File: memory.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up 
def make_update_op(self, upd_idxs, upd_keys, upd_vals,
                     batch_size, use_recent_idx, intended_output):
    """Function that creates all the update ops."""
    base_update_op = super(LSHMemory, self).make_update_op(
        upd_idxs, upd_keys, upd_vals,
        batch_size, use_recent_idx, intended_output)

    # compute hash slots to be updated
    hash_slot_idxs = self.get_hash_slots(upd_keys)

    # make updates
    update_ops = []
    with tf.control_dependencies([base_update_op]):
      for i, slot_idxs in enumerate(hash_slot_idxs):
        # for each slot, choose which entry to replace
        entry_idx = tf.random_uniform([batch_size],
                                      maxval=self.num_per_hash_slot,
                                      dtype=tf.int32)
        entry_mul = 1 - tf.one_hot(entry_idx, self.num_per_hash_slot,
                                   dtype=tf.int32)
        entry_add = (tf.expand_dims(upd_idxs, 1) *
                     tf.one_hot(entry_idx, self.num_per_hash_slot,
                                dtype=tf.int32))

        mul_op = tf.scatter_mul(self.hash_slots[i], slot_idxs, entry_mul)
        with tf.control_dependencies([mul_op]):
          add_op = tf.scatter_add(self.hash_slots[i], slot_idxs, entry_add)
          update_ops.append(add_op)

    return tf.group(*update_ops)
Example #2
Source File: memory.py    From yolo_v2 with Apache License 2.0 5 votes vote down vote up 
def make_update_op(self, upd_idxs, upd_keys, upd_vals,
                     batch_size, use_recent_idx, intended_output):
    """Function that creates all the update ops."""
    base_update_op = super(LSHMemory, self).make_update_op(
        upd_idxs, upd_keys, upd_vals,
        batch_size, use_recent_idx, intended_output)

    # compute hash slots to be updated
    hash_slot_idxs = self.get_hash_slots(upd_keys)

    # make updates
    update_ops = []
    with tf.control_dependencies([base_update_op]):
      for i, slot_idxs in enumerate(hash_slot_idxs):
        # for each slot, choose which entry to replace
        entry_idx = tf.random_uniform([batch_size],
                                      maxval=self.num_per_hash_slot,
                                      dtype=tf.int32)
        entry_mul = 1 - tf.one_hot(entry_idx, self.num_per_hash_slot,
                                   dtype=tf.int32)
        entry_add = (tf.expand_dims(upd_idxs, 1) *
                     tf.one_hot(entry_idx, self.num_per_hash_slot,
                                dtype=tf.int32))

        mul_op = tf.scatter_mul(self.hash_slots[i], slot_idxs, entry_mul)
        with tf.control_dependencies([mul_op]):
          add_op = tf.scatter_add(self.hash_slots[i], slot_idxs, entry_add)
          update_ops.append(add_op)

    return tf.group(*update_ops)
Example #3
Source File: memory.py    From Gun-Detector with Apache License 2.0 5 votes vote down vote up 
def make_update_op(self, upd_idxs, upd_keys, upd_vals,
                     batch_size, use_recent_idx, intended_output):
    """Function that creates all the update ops."""
    base_update_op = super(LSHMemory, self).make_update_op(
        upd_idxs, upd_keys, upd_vals,
        batch_size, use_recent_idx, intended_output)

    # compute hash slots to be updated
    hash_slot_idxs = self.get_hash_slots(upd_keys)

    # make updates
    update_ops = []
    with tf.control_dependencies([base_update_op]):
      for i, slot_idxs in enumerate(hash_slot_idxs):
        # for each slot, choose which entry to replace
        entry_idx = tf.random_uniform([batch_size],
                                      maxval=self.num_per_hash_slot,
                                      dtype=tf.int32)
        entry_mul = 1 - tf.one_hot(entry_idx, self.num_per_hash_slot,
                                   dtype=tf.int32)
        entry_add = (tf.expand_dims(upd_idxs, 1) *
                     tf.one_hot(entry_idx, self.num_per_hash_slot,
                                dtype=tf.int32))

        mul_op = tf.scatter_mul(self.hash_slots[i], slot_idxs, entry_mul)
        with tf.control_dependencies([mul_op]):
          add_op = tf.scatter_add(self.hash_slots[i], slot_idxs, entry_add)
          update_ops.append(add_op)

    return tf.group(*update_ops)
Example #4
Source File: scatter_ops_test.py    From deep_image_model with Apache License 2.0 5 votes vote down vote up 
def testVariableRankMul(self):
    self._VariableRankTests(tf.scatter_mul)
Example #5
Source File: scatter_ops_test.py    From deep_image_model with Apache License 2.0 5 votes vote down vote up 
def testRepeatIndicesMul(self):
    self._VariableRankTests(tf.scatter_mul, True)
Example #6
Source File: memory.py    From hands-detection with MIT License 5 votes vote down vote up 
def make_update_op(self, upd_idxs, upd_keys, upd_vals,
                     batch_size, use_recent_idx, intended_output):
    """Function that creates all the update ops."""
    base_update_op = super(LSHMemory, self).make_update_op(
        upd_idxs, upd_keys, upd_vals,
        batch_size, use_recent_idx, intended_output)

    # compute hash slots to be updated
    hash_slot_idxs = self.get_hash_slots(upd_keys)

    # make updates
    update_ops = []
    with tf.control_dependencies([base_update_op]):
      for i, slot_idxs in enumerate(hash_slot_idxs):
        # for each slot, choose which entry to replace
        entry_idx = tf.random_uniform([batch_size],
                                      maxval=self.num_per_hash_slot,
                                      dtype=tf.int32)
        entry_mul = 1 - tf.one_hot(entry_idx, self.num_per_hash_slot,
                                   dtype=tf.int32)
        entry_add = (tf.expand_dims(upd_idxs, 1) *
                     tf.one_hot(entry_idx, self.num_per_hash_slot,
                                dtype=tf.int32))

        mul_op = tf.scatter_mul(self.hash_slots[i], slot_idxs, entry_mul)
        with tf.control_dependencies([mul_op]):
          add_op = tf.scatter_add(self.hash_slots[i], slot_idxs, entry_add)
          update_ops.append(add_op)

    return tf.group(*update_ops)
Example #7
Source File: memory.py    From object_detection_kitti with Apache License 2.0 5 votes vote down vote up 
def make_update_op(self, upd_idxs, upd_keys, upd_vals,
                     batch_size, use_recent_idx, intended_output):
    """Function that creates all the update ops."""
    base_update_op = super(LSHMemory, self).make_update_op(
        upd_idxs, upd_keys, upd_vals,
        batch_size, use_recent_idx, intended_output)

    # compute hash slots to be updated
    hash_slot_idxs = self.get_hash_slots(upd_keys)

    # make updates
    update_ops = []
    with tf.control_dependencies([base_update_op]):
      for i, slot_idxs in enumerate(hash_slot_idxs):
        # for each slot, choose which entry to replace
        entry_idx = tf.random_uniform([batch_size],
                                      maxval=self.num_per_hash_slot,
                                      dtype=tf.int32)
        entry_mul = 1 - tf.one_hot(entry_idx, self.num_per_hash_slot,
                                   dtype=tf.int32)
        entry_add = (tf.expand_dims(upd_idxs, 1) *
                     tf.one_hot(entry_idx, self.num_per_hash_slot,
                                dtype=tf.int32))

        mul_op = tf.scatter_mul(self.hash_slots[i], slot_idxs, entry_mul)
        with tf.control_dependencies([mul_op]):
          add_op = tf.scatter_add(self.hash_slots[i], slot_idxs, entry_add)
          update_ops.append(add_op)

    return tf.group(*update_ops)
Example #8
Source File: memory.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up 
def make_update_op(self, upd_idxs, upd_keys, upd_vals,
                     batch_size, use_recent_idx, intended_output):
    """Function that creates all the update ops."""
    base_update_op = super(LSHMemory, self).make_update_op(
        upd_idxs, upd_keys, upd_vals,
        batch_size, use_recent_idx, intended_output)

    # compute hash slots to be updated
    hash_slot_idxs = self.get_hash_slots(upd_keys)

    # make updates
    update_ops = []
    with tf.control_dependencies([base_update_op]):
      for i, slot_idxs in enumerate(hash_slot_idxs):
        # for each slot, choose which entry to replace
        entry_idx = tf.random_uniform([batch_size],
                                      maxval=self.num_per_hash_slot,
                                      dtype=tf.int32)
        entry_mul = 1 - tf.one_hot(entry_idx, self.num_per_hash_slot,
                                   dtype=tf.int32)
        entry_add = (tf.expand_dims(upd_idxs, 1) *
                     tf.one_hot(entry_idx, self.num_per_hash_slot,
                                dtype=tf.int32))

        mul_op = tf.scatter_mul(self.hash_slots[i], slot_idxs, entry_mul)
        with tf.control_dependencies([mul_op]):
          add_op = tf.scatter_add(self.hash_slots[i], slot_idxs, entry_add)
          update_ops.append(add_op)

    return tf.group(*update_ops)
Example #9
Source File: memory.py    From HumanRecognition with MIT License 5 votes vote down vote up 
def make_update_op(self, upd_idxs, upd_keys, upd_vals,
                     batch_size, use_recent_idx, intended_output):
    """Function that creates all the update ops."""
    base_update_op = super(LSHMemory, self).make_update_op(
        upd_idxs, upd_keys, upd_vals,
        batch_size, use_recent_idx, intended_output)

    # compute hash slots to be updated
    hash_slot_idxs = self.get_hash_slots(upd_keys)

    # make updates
    update_ops = []
    with tf.control_dependencies([base_update_op]):
      for i, slot_idxs in enumerate(hash_slot_idxs):
        # for each slot, choose which entry to replace
        entry_idx = tf.random_uniform([batch_size],
                                      maxval=self.num_per_hash_slot,
                                      dtype=tf.int32)
        entry_mul = 1 - tf.one_hot(entry_idx, self.num_per_hash_slot,
                                   dtype=tf.int32)
        entry_add = (tf.expand_dims(upd_idxs, 1) *
                     tf.one_hot(entry_idx, self.num_per_hash_slot,
                                dtype=tf.int32))

        mul_op = tf.scatter_mul(self.hash_slots[i], slot_idxs, entry_mul)
        with tf.control_dependencies([mul_op]):
          add_op = tf.scatter_add(self.hash_slots[i], slot_idxs, entry_add)
          update_ops.append(add_op)

    return tf.group(*update_ops)
Example #10
Source File: memory.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def make_update_op(self, upd_idxs, upd_keys, upd_vals,
                     batch_size, use_recent_idx, intended_output):
    """Function that creates all the update ops."""
    base_update_op = super(LSHMemory, self).make_update_op(
        upd_idxs, upd_keys, upd_vals,
        batch_size, use_recent_idx, intended_output)

    # compute hash slots to be updated
    hash_slot_idxs = self.get_hash_slots(upd_keys)

    # make updates
    update_ops = []
    with tf.control_dependencies([base_update_op]):
      for i, slot_idxs in enumerate(hash_slot_idxs):
        # for each slot, choose which entry to replace
        entry_idx = tf.random_uniform([batch_size],
                                      maxval=self.num_per_hash_slot,
                                      dtype=tf.int32)
        entry_mul = 1 - tf.one_hot(entry_idx, self.num_per_hash_slot,
                                   dtype=tf.int32)
        entry_add = (tf.expand_dims(upd_idxs, 1) *
                     tf.one_hot(entry_idx, self.num_per_hash_slot,
                                dtype=tf.int32))

        mul_op = tf.scatter_mul(self.hash_slots[i], slot_idxs, entry_mul)
        with tf.control_dependencies([mul_op]):
          add_op = tf.scatter_add(self.hash_slots[i], slot_idxs, entry_add)
          update_ops.append(add_op)

    return tf.group(*update_ops)
Example #11
Source File: memory.py    From models with Apache License 2.0 5 votes vote down vote up 
def make_update_op(self, upd_idxs, upd_keys, upd_vals,
                     batch_size, use_recent_idx, intended_output):
    """Function that creates all the update ops."""
    base_update_op = super(LSHMemory, self).make_update_op(
        upd_idxs, upd_keys, upd_vals,
        batch_size, use_recent_idx, intended_output)

    # compute hash slots to be updated
    hash_slot_idxs = self.get_hash_slots(upd_keys)

    # make updates
    update_ops = []
    with tf.control_dependencies([base_update_op]):
      for i, slot_idxs in enumerate(hash_slot_idxs):
        # for each slot, choose which entry to replace
        entry_idx = tf.random_uniform([batch_size],
                                      maxval=self.num_per_hash_slot,
                                      dtype=tf.int32)
        entry_mul = 1 - tf.one_hot(entry_idx, self.num_per_hash_slot,
                                   dtype=tf.int32)
        entry_add = (tf.expand_dims(upd_idxs, 1) *
                     tf.one_hot(entry_idx, self.num_per_hash_slot,
                                dtype=tf.int32))

        mul_op = tf.scatter_mul(self.hash_slots[i], slot_idxs, entry_mul)
        with tf.control_dependencies([mul_op]):
          add_op = tf.scatter_add(self.hash_slots[i], slot_idxs, entry_add)
          update_ops.append(add_op)

    return tf.group(*update_ops)
Example #12
Source File: memory.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
def make_update_op(self, upd_idxs, upd_keys, upd_vals,
                     batch_size, use_recent_idx, intended_output):
    """Function that creates all the update ops."""
    base_update_op = super(LSHMemory, self).make_update_op(
        upd_idxs, upd_keys, upd_vals,
        batch_size, use_recent_idx, intended_output)

    # compute hash slots to be updated
    hash_slot_idxs = self.get_hash_slots(upd_keys)

    # make updates
    update_ops = []
    with tf.control_dependencies([base_update_op]):
      for i, slot_idxs in enumerate(hash_slot_idxs):
        # for each slot, choose which entry to replace
        entry_idx = tf.random_uniform([batch_size],
                                      maxval=self.num_per_hash_slot,
                                      dtype=tf.int32)
        entry_mul = 1 - tf.one_hot(entry_idx, self.num_per_hash_slot,
                                   dtype=tf.int32)
        entry_add = (tf.expand_dims(upd_idxs, 1) *
                     tf.one_hot(entry_idx, self.num_per_hash_slot,
                                dtype=tf.int32))

        mul_op = tf.scatter_mul(self.hash_slots[i], slot_idxs, entry_mul)
        with tf.control_dependencies([mul_op]):
          add_op = tf.scatter_add(self.hash_slots[i], slot_idxs, entry_add)
          update_ops.append(add_op)

    return tf.group(*update_ops)