def __init__(
self,
data,
batch_size=128,
dtype=None,
broadcastable=None,
name="Minibatch",
random_seed=42,
update_shared_f=None,
in_memory_size=None,
):
if dtype is None:
data = pm.smartfloatX(np.asarray(data))
else:
data = np.asarray(data, dtype)
in_memory_slc = self.make_static_slices(in_memory_size)
self.shared = theano.shared(data[in_memory_slc])
self.update_shared_f = update_shared_f
self.random_slc = self.make_random_slices(self.shared.shape,
batch_size, random_seed)
minibatch = self.shared[self.random_slc]
if broadcastable is None:
broadcastable = (False, ) * minibatch.ndim
minibatch = tt.patternbroadcast(minibatch, broadcastable)
self.minibatch = minibatch
super().__init__(self.minibatch.type, None, None, name=name)
theano.Apply(theano.compile.view_op,
inputs=[self.minibatch],
outputs=[self])
self.tag.test_value = copy(self.minibatch.tag.test_value)
def __init__(self, generator):
if not pm.vartypes.isgenerator(generator):
raise TypeError("Object should be generator like")
self.test_value = pm.smartfloatX(copy(next(generator)))
# make pickling potentially possible
self._yielded_test_value = False
self.gen = generator
self.tensortype = TensorType(self.test_value.dtype, ((False,) * self.test_value.ndim))
def __init__(self, generator):
if not pm.vartypes.isgenerator(generator):
raise TypeError('Object should be generator like')
self.test_value = pm.smartfloatX(copy(next(generator)))
# make pickling potentially possible
self._yielded_test_value = False
self.gen = generator
self.tensortype = tt.TensorType(
self.test_value.dtype,
((False, ) * self.test_value.ndim))
def pandas_to_array(data):
if hasattr(data, 'values'): # pandas
if data.isnull().any().any(): # missing values
ret = np.ma.MaskedArray(data.values, data.isnull().values)
else:
ret = data.values
elif hasattr(data, 'mask'):
ret = data
elif isinstance(data, theano.gof.graph.Variable):
ret = data
elif sps.issparse(data):
ret = data
elif isgenerator(data):
ret = generator(data)
else:
ret = np.asarray(data)
return pm.smartfloatX(ret)
def pandas_to_array(data):
if hasattr(data, 'values'): # pandas
if data.isnull().any().any(): # missing values
ret = np.ma.MaskedArray(data.values, data.isnull().values)
else:
ret = data.values
elif hasattr(data, 'mask'):
ret = data
elif isinstance(data, theano.gof.graph.Variable):
ret = data
elif sps.issparse(data):
ret = data
elif isgenerator(data):
ret = generator(data)
else:
ret = np.asarray(data)
return pm.smartfloatX(ret)
def __init__(self, data, batch_size=128, dtype=None, broadcastable=None, name='Minibatch',
random_seed=42, update_shared_f=None, in_memory_size=None):
if dtype is None:
data = pm.smartfloatX(np.asarray(data))
else:
data = np.asarray(data, dtype)
in_memory_slc = self.make_static_slices(in_memory_size)
self.shared = theano.shared(data[in_memory_slc])
self.update_shared_f = update_shared_f
self.random_slc = self.make_random_slices(self.shared.shape, batch_size, random_seed)
minibatch = self.shared[self.random_slc]
if broadcastable is None:
broadcastable = (False, ) * minibatch.ndim
minibatch = tt.patternbroadcast(minibatch, broadcastable)
self.minibatch = minibatch
super().__init__(self.minibatch.type, None, None, name=name)
theano.Apply(
theano.compile.view_op,
inputs=[self.minibatch], outputs=[self])
self.tag.test_value = copy(self.minibatch.tag.test_value)
def __next__(self):
if not self._yielded_test_value:
self._yielded_test_value = True
return self.test_value
else:
return pm.smartfloatX(copy(next(self.gen)))
def __next__(self):
if not self._yielded_test_value:
self._yielded_test_value = True
return self.test_value
else:
return pm.smartfloatX(copy(next(self.gen)))
