recurrentshop issues

combining readout and teacher_force

1

i cannot find a way of combining the two examples from the documentation. E.g., i want to decode a 13-dimensional state vector `s0` into a sequence of length 11. Each...

temporaer

bug

Installation issue

Hello, I have just done the following installation: ``` git clone https://www.github.com/farizrahman4u/recurrentshop.git cd recurrentshop python setup.py install ``` but if I execute the following code: ``` # The RNN logic...

mg64ve

RNN with missing inputs

I would like to develop an RNN that can handle missing inputs by inferring these as outputs and inserting them into the input vector at the next time step. The...

miguellacerda

Setting states for rnn forecasting

Below is a simple rnn that runs on some input to generate the output. The input and output are split into train / test. The model is fitted with the...

JohnVorwald

Error when combining teacherforce/readout with return_states

I get an error stating that the output_tensors and output_masks are not of equal length when using readout and return_states and nesting the RecurrentModel into a keras model. I believe...

Aerylia

Error with stateful RecurrentModel

1

Hello, I am trying to build a recurrentshop.RecurrentModel() as follows. It builds the graph if `stateful=False` but raises an error when `stateful=True`. Ì worked with stateful RNNs in Keras before...

manuelknott

AssertionError: Required 2 inputs, received 3.

I was trying out your library today as shown below: ``` vocab_len=1000 hidden_units = 150 getShape= Lambda(lambda a: a,output_shape=(2*hidden_units,)) in_x = Input(shape=(None,)) in_y = Input(shape=(None,)) embedding = Embedding(1000,100) x_emb =...

kaeflint