Error with the example notebook

[erhanbas]

I am following the example when I train the model with:

geom_model, morph_model, disc_model, gan_model = \
    train.train_model(training_data=training_data,
                      n_nodes=n_nodes,
                      input_dim=input_dim,
                      n_epochs=n_epochs,
                      batch_size=batch_size,
                      n_batch_per_epoch=n_batch_per_epoch,
                      d_iters=d_iters,
                      lr_discriminator=lr_discriminator,
                      lr_generator=lr_generator,
                      d_weight_constraint=d_weight_constraint,
                      g_weight_constraint=g_weight_constraint,
                      m_weight_constraint=m_weight_constraint,
                      rule=rule,
                      train_loss=train_loss,
                      verbose=True)

I get the following typeError

.../BonsaiNet/layers.py in feature_extractor(inputs, n_nodes, batch_size)
    187     """
    188     print inputs
--> 189     geometry_input = inputs[:, :, :3]
    190     morphology_input = inputs[:, :, 3:]
    191 

TypeError: list indices must be integers, not tuple

it looks like merged input has the "[<tf.Tensor 'merge_1/concat:0' shape=(?, 19, 23) dtype=float32>]" format.

It doesn't look like installation problem just based on the error, any idea what is going on?
Thanks!!

[pavanramkumar]

@GENEZIN we aren't maintaining this code too actively at this point. we do have certain custom theano routines so i'd suggest using a theano backend instead of tensorflow. let us know if this works!

[RoozbehFarhoodi]

@erhanbas Hi, so sorry to come back to your issue late. I ran the code today. It seems it works fine. I have also run example.ipynb for a longer time to demonstrate a few examples. Please inform us if you are still facing the problem.