recurrent net don't operate after loading

[majidaldo]

if you create a RNN, save it, then load it, it might not operate (train, predict, ..etc). that's b/c some compilation info is not reinitialized.

in recurrent.Network.setup_encoder there is batch_size = kwargs.get('batch_size', 64). so if the network were created with a batch_size=32, this does not get recreated since setup_encoder is not invoked on loading.

you may wish to reevaluate how nets are saved in order to better generalize saving any network. i suggest saving all the args and kwargs that went into creating the net and calling __init__ with them on loading.

[lmjohns3]

Yes, this is a good idea. I think I've fixed up the code a bit to do this, but please reopen if this change didn't work.

[majidaldo]

hmm on second thought it would be more flexible to have load_weights() and another load_network() that would call load_weights for cases where you want to transfer weights. maybe there should be a load/save_param(param) for each set of parameters. i'm just thinking out load here.

[lmjohns3]

In a way, this is the way it's currently set up. There is a feedforward.Network.load_params() method that loads only the parameter values (weights and biases) from a pickled network. Then there is a feedforward.load() module-level function that loads a pickle file and creates a new network from it.

[majidaldo]

ah ok.. i was wondering what that was doing in the module...as i don't recall any code using it.