Clever Geek Handbook

Keras - weighted mean of tensors

If I have n T_i

shape tensors (?, k)

and one U

shape tensor (?, n)

, how can I get the tensor (?, k)

equal sum(T_i * U[i])

?

I've tried writing a layer for this:

class WeightedAverage(_Merge):
    """Layer that computes a mean between samples in several tensors according to weights computed in another tensor.
    E.g. if applied to k tensors `a_0` and `a_k` of shape `(batch_size, n)`, and a tensor `b` of shape `(batch_size, k)`
    the output will be a tensor of shape `(batch_size, n)`
    where each entry `i` will be the dot product between
    `sum(a_j[i] * b[j] over j)`.
    """
    def __init__(self, **kwargs):
        self.weight_tensor = None
        super(WeightedAverage, self).__init__(**kwargs)

    def _merge_function(self, inputs):
        if self.weight_tensor is None:
            raise ValueError('A `WeightedAverage` layer should have a weight layer')
        shape = inputs[0].get_shape().as_list()
        k = shape[1]
        n = len(inputs)
        all_inputs = K.reshape(Concatenate()(inputs), (-1, n, k))
        return K.reshape(K.batch_dot(all_inputs, self.weight_tensor, axes=(1, 2)), (-1, k))

    def call(self, inputs, weights):
        if weights.shape[1] != len(inputs):
            raise ValueError('A `WeightedAverage` weights layer should have as many'
                             'outputs as there are inputs.')
        shape = weights.get_shape().as_list()
        self.weight_tensor = K.reshape(weights, (-1, 1, shape[1]))
        return super(WeightedAverage, self).call(inputs)

with whom I called:

x = WeightedAverage(name="weightAverage")(Ts, weights=U)

however, this does not work with a rather long tensorflow trace:

W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
Traceback (most recent call last):
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 1022, in _do_call
    return fn(*args)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 1004, in _run_fn
    status, run_metadata)
  File "/usr/lib/python3.4/contextlib.py", line 66, in __exit__
    next(self.gen)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
   [[Node: batch_2_1/moments/sufficient_statistics/Gather/_519 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_9178_batch_2_1/moments/sufficient_statistics/Gather", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "train.py", line 118, in <module>
    cnn.fit(n_epoch=N_EPOCH, batch_size=BATCH_SIZE, generating=args["generate_data"])
  File "/home/ubuntu/models/model.py", line 125, in fit
    epochs=n_epoch
  File "/usr/local/lib/python3.4/dist-packages/keras/engine/training.py", line 1507, in fit
    initial_epoch=initial_epoch)
  File "/usr/local/lib/python3.4/dist-packages/keras/engine/training.py", line 1156, in _fit_loop
    outs = f(ins_batch)
  File "/usr/local/lib/python3.4/dist-packages/keras/backend/tensorflow_backend.py", line 2269, in __call__
    **self.session_kwargs)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 767, in run
    run_metadata_ptr)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 965, in _run
    feed_dict_string, options, run_metadata)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 1015, in _do_run
    target_list, options, run_metadata)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 1035, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
   [[Node: batch_2_1/moments/sufficient_statistics/Gather/_519 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_9178_batch_2_1/moments/sufficient_statistics/Gather", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

Caused by op 'input_1', defined at:
  File "train.py", line 103, in <module>
    weather_model = load_model(args["helper_model"])
  File "/usr/local/lib/python3.4/dist-packages/keras/models.py", line 246, in load_model
    model = model_from_config(model_config, custom_objects=custom_objects)
  File "/usr/local/lib/python3.4/dist-packages/keras/models.py", line 314, in model_from_config
    return layer_module.deserialize(config, custom_objects=custom_objects)
  File "/usr/local/lib/python3.4/dist-packages/keras/layers/__init__.py", line 54, in deserialize
    printable_module_name='layer')
  File "/usr/local/lib/python3.4/dist-packages/keras/utils/generic_utils.py", line 140, in deserialize_keras_object
    list(custom_objects.items())))
  File "/usr/local/lib/python3.4/dist-packages/keras/engine/topology.py", line 2450, in from_config
    process_layer(layer_data)
  File "/usr/local/lib/python3.4/dist-packages/keras/engine/topology.py", line 2419, in process_layer
    custom_objects=custom_objects)
  File "/usr/local/lib/python3.4/dist-packages/keras/layers/__init__.py", line 54, in deserialize
    printable_module_name='layer')
  File "/usr/local/lib/python3.4/dist-packages/keras/utils/generic_utils.py", line 142, in deserialize_keras_object
    return cls.from_config(config['config'])
  File "/usr/local/lib/python3.4/dist-packages/keras/engine/topology.py", line 1242, in from_config
    return cls(**config)
  File "/usr/local/lib/python3.4/dist-packages/keras/legacy/interfaces.py", line 88, in wrapper
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.4/dist-packages/keras/engine/topology.py", line 1337, in __init__
    name=self.name)
  File "/usr/local/lib/python3.4/dist-packages/keras/backend/tensorflow_backend.py", line 431, in placeholder
    x = tf.placeholder(dtype, shape=shape, name=name)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/ops/array_ops.py", line 1502, in placeholder
    name=name)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 2149, in _placeholder
    name=name)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/framework/op_def_library.py", line 763, in apply_op
    op_def=op_def)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/framework/ops.py", line 2327, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/framework/ops.py", line 1226, in __init__
    self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'input_1' with dtype float
   [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
   [[Node: batch_2_1/moments/sufficient_statistics/Gather/_519 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_9178_batch_2_1/moments/sufficient_statistics/Gather", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

Exception ignored in: <bound method Session.__del__ of <tensorflow.python.client.session.Session object at 0x7ff0256cf550>>
Traceback (most recent call last):
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 582, in __del__
UnboundLocalError: local variable 'status' referenced before assignment
*** Error in `python3': corrupted size vs. prev_size: 0x00000000021b4ac0 ***
Aborted (core dumped)
+3


source to share


No one has answered this question yet

Check out similar questions:



More articles:


All Articles