CODEWITHSUNDEEP
pythonnumpytensorflowlstmrecurrent-neural-network
Nicolas REY
Nicolas REY

Reputation: 467

Estimator with numpy array input_fn

I am creating an estimator with numpy array to feed to model with using tf.estimator.inputs.numpy_input_fn. Like the following:

def input_fun(data):
    x, y = data

    x, y = np.reshape(x, (batch_size, -1, 1)), \
           np.reshape(y, (batch_size, -1, 1))

    return tf.estimator.inputs.numpy_input_fn({'x': x}, y)

def forward(x, params, mode):

    layers = [tf.nn.rnn_cell.LSTMCell(n_neurons) for _ in range(n_layers)]
    cells = tf.nn.rnn_cell.MultiRNNCell(layers)
    outputs, state = tf.nn.dynamic_rnn(cells, x)

    predictions = ...

    return predictions

def model_fn(features, labels, mode, params):
    predict = forward(features, params, mode)

    return tf.estimator.EstimatorSpec(predict , ...)

def experiment_fn(config, params):
    return learn.Experiment(
        estimator = estimator(model_fn,...),
        train_input_fn = lambda: input_fun(train_set),
        eval_input_fn = lambda: input_fun(eval_set))

It throws the following:

Traceback (most recent call last):

File "", line 1, in runfile('/Experiment.py', wdir='/TensorFlow')

File "C:\Users\hp\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 710, in runfile execfile(filename, namespace)

File "C:\Users\hp\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 101, in execfile exec(compile(f.read(), filename, 'exec'), namespace)

File "/Experiment.py", line 490, in hparams = params

File "C:\Users\hp\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\learn_runner.py", line 218, in run return _execute_schedule(experiment, schedule)

File "C:\Users\hp\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\learn_runner.py", line 46, in _execute_schedule return task()

File "C:\Users\hp\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\experiment.py", line 367, in train hooks=self._train_monitors + extra_hooks)

File "C:\Users\hp\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\experiment.py", line 807, in _call_train hooks=hooks)

File "C:\Users\hp\Anaconda3\lib\site-packages\tensorflow\python\estimator\estimator.py", line 302, in train loss = self._train_model(input_fn, hooks, saving_listeners)

File "C:\Users\hp\Anaconda3\lib\site-packages\tensorflow\python\estimator\estimator.py", line 711, in _train_model features, labels, model_fn_lib.ModeKeys.TRAIN, self.config)

File "C:\Users\hp\Anaconda3\lib\site-packages\tensorflow\python\estimator\estimator.py", line 694, in _call_model_fn model_fn_results = self._model_fn(features=features, **kwargs)

File "/Experiment.py", line 350, in model_fn predict = forward(features, params, mode)

File "/Experiment.py", line 335, in forward dtype = tf.float32

File "C:\Users\hp\Anaconda3\lib\site-packages\tensorflow\python\ops\rnn.py", line 562, in dynamic_rnn flat_input = [ops.convert_to_tensor(input_) for input_ in flat_input]

File "C:\Users\hp\Anaconda3\lib\site-packages\tensorflow\python\ops\rnn.py", line 562, in flat_input = [ops.convert_to_tensor(input_) for input_ in flat_input]

File "C:\Users\hp\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 836, in convert_to_tensor as_ref=False)

File "C:\Users\hp\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 926, in internal_convert_to_tensor ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)

File "C:\Users\hp\Anaconda3\lib\site-packages\tensorflow\python\framework\constant_op.py", line 229, in _constant_tensor_conversion_function return constant(v, dtype=dtype, name=name)

File "C:\Users\hp\Anaconda3\lib\site-packages\tensorflow\python\framework\constant_op.py", line 208, in constant value, dtype=dtype, shape=shape, verify_shape=verify_shape))

File "C:\Users\hp\Anaconda3\lib\site-packages\tensorflow\python\framework\tensor_util.py", line 472, in make_tensor_proto "supported type." % (type(values), values))

TypeError: Failed to convert object of type <class 'function'> to Tensor. Contents: <function numpy_input_fn.<locals>.input_fn at 0x000001AB2B1DBEA0>. Consider casting elements to a supported type.

Does anyone know why ?

Upvotes: 0

Views: 1694

Answers (2)

caspillaga
caspillaga

Reputation: 563

I had a similar problem. In my case the exception was raised because inside my model (I guess "forward", in your case) x was used as a Tensor, but it was actually a function (specifically tf.estimator.inputs.numpy_input_fn). I figured it out by adding this:

print(x)
print(type(x))

Which printed something like this:

<function numpy_input_fn.<locals>.input_fn at 0x7fcc6f065740>
<class 'function'>

I'm still not sure what is the correct way to solve it, but I was able to fix it by doing something similar to this:

input_dict, y = x()
x = input_dict['x']

Hope it helps

Upvotes: 1

Maxim
Maxim

Reputation: 53758

You should pass a list of cells into MultiRNNCell:

Args:

cells: list of RNNCells that will be composed in this order.

state_is_tuple: If True, accepted and returned states are n-tuples, where n = len(cells). If False, the states are all concatenated along the column axis. This latter behavior will soon be deprecated.

If you really want to make a one-layer RNN, change the code to

cells = tf.nn.rnn_cell.MultiRNNCell([layers])

... or create more layers.

Upvotes: 0

Related Questions