A issue about float types

[LHhan1996]

when I run the interact.py, it has error report like this:

Traceback (most recent call last):
File "interact.py", line 137, in
name=params['model_name'])
File "/home/lhh/PycharmProjects/Msc_Project/KB-InfoBot/deep_dialog/agents/agent_simpleRL_allact.py", line 47, in init
ment=ment)
File "/home/lhh/PycharmProjects/Msc_Project/KB-InfoBot/deep_dialog/agents/agent_rl.py", line 60, in _init_model
pol_out = L.get_output(l_pol_rnn)[:, -1, :]
File "/home/lhh/.local/lib/python2.7/site-packages/lasagne/layers/helper.py", line 185, in get_output
all_outputs[layer] = layer.get_output_for(layer_inputs, **kwargs)
File "/home/lhh/.local/lib/python2.7/site-packages/lasagne/layers/recurrent.py", line 1407, in get_output_for
strict=True)[0]
File "/home/lhh/.local/lib/python2.7/site-packages/theano/scan_module/scan.py", line 1041, in scan
scan_outs = local_op(*scan_inputs)
File "/home/lhh/.local/lib/python2.7/site-packages/theano/gof/op.py", line 611, in call
node = self.make_node(*inputs, **kwargs)
File "/home/lhh/.local/lib/python2.7/site-packages/theano/scan_module/scan_op.py", line 538, in make_node
inner_sitsot_out.type.dtype))
ValueError: When compiling the inner function of scan the following error has been encountered: The initial state (outputs_info in scan nomenclature) of variable IncSubtensor{Set;:int64:}.0 (argument number 2) has dtype float32, while the result of the inner function (fn) has dtype float64. This can happen if the inner function of scan results in an upcast or downcast.

I have tried to use floatX=float32 like you said, but it still does not work. @bdhingra