def testRandomFourierFeatures(self, batch_size, input_dims, output_dims,
bandwidth):
def _rff_hypothesis_test(rff_output, X, W, b, scale):
"""
Runs hypothesis test for Semi Random Features layer.
Inputs:
rff_output -- output of net after running random fourier features layer
X -- input data
W -- weight parameter from train_init_net
b -- bias parameter from train_init_net
scale -- value by which to scale the output vector
"""
output = workspace.FetchBlob(rff_output)
output_ref = scale * np.cos(np.dot(X, np.transpose(W)) + b)
npt.assert_allclose(output, output_ref, rtol=1e-3, atol=1e-3)
X = np.random.random((batch_size, input_dims)).astype(np.float32)
scale = np.sqrt(2.0 / output_dims)
input_record = self.new_record(
schema.Scalar((np.float32, (input_dims, ))))
schema.FeedRecord(input_record, [X])
input_blob = input_record.field_blobs()[0]
rff_output = self.model.RandomFourierFeatures(input_record,
output_dims, bandwidth)
self.model.output_schema = schema.Struct()
self.assertEqual(schema.Scalar((np.float32, (output_dims, ))),
rff_output)
train_init_net, train_net = self.get_training_nets()
# Init net assertions
init_ops_list = [
OpSpec("GaussianFill", None, None),
OpSpec("UniformFill", None, None),
]
init_ops = self._test_net(train_init_net, init_ops_list)
W = workspace.FetchBlob(self.model.layers[0].w)
b = workspace.FetchBlob(self.model.layers[0].b)
# Operation specifications
fc_spec = OpSpec(
"FC", [input_blob, init_ops[0].output[0], init_ops[1].output[0]],
None)
cosine_spec = OpSpec("Cos", None, None)
scale_spec = OpSpec("Scale", None, rff_output.field_blobs(),
{'scale': scale})
ops_list = [fc_spec, cosine_spec, scale_spec]
# Train net assertions
self._test_net(train_net, ops_list)
_rff_hypothesis_test(rff_output(), X, W, b, scale)
# Eval net assertions
eval_net = self.get_eval_net()
self._test_net(eval_net, ops_list)
_rff_hypothesis_test(rff_output(), X, W, b, scale)
# Predict net assertions
predict_net = self.get_predict_net()
self._test_net(predict_net, ops_list)
_rff_hypothesis_test(rff_output(), X, W, b, scale)
def create_net(self):
net = core.Net("feature_extractor")
init_net = core.Net("feature_extractor_init")
missing_scalar = self.create_const(init_net, "MISSING_SCALAR",
MISSING_VALUE)
input_schema = schema.Struct((
"float_features",
schema.Map(
keys=core.BlobReference("input/float_features.keys"),
values=core.BlobReference("input/float_features.values"),
lengths_blob=core.BlobReference(
"input/float_features.lengths"),
),
))
input_record = net.set_input_record(input_schema)
state = self.extract_float_features(
net,
"state",
input_record.float_features,
self.sorted_state_features,
missing_scalar,
)
if self.sorted_action_features:
action = self.extract_float_features(
net,
"action",
input_record.float_features,
self.sorted_action_features,
missing_scalar,
)
if self.normalize:
C2.set_net_and_init_net(net, init_net)
state, _ = PreprocessorNet().normalize_dense_matrix(
state,
self.sorted_state_features,
self.state_normalization_parameters,
blobname_prefix="state",
split_expensive_feature_groups=True,
)
if self.sorted_action_features:
action, _ = PreprocessorNet().normalize_dense_matrix(
action,
self.sorted_action_features,
self.action_normalization_parameters,
blobname_prefix="action",
split_expensive_feature_groups=True,
)
C2.set_net_and_init_net(None, None)
output_record = schema.Struct(("state", state))
if self.sorted_action_features:
output_record += schema.Struct(("action", action))
net.set_output_record(output_record)
return FeatureExtractorNet(net, init_net)
def testSemiRandomFeatures(self, batch_size, input_dims, output_dims, s, scale,
set_weight_as_global_constant):
X = np.random.normal(size=(batch_size, input_dims)).astype(np.float32)
input_record = self.new_record(schema.Scalar((np.float32, (input_dims,))))
schema.FeedRecord(input_record, [X])
input_blob = input_record.field_blobs()[0]
srf_output = self.model.SemiRandomFeatures(
input_record,
output_dims,
s=s,
scale=scale,
set_weight_as_global_constant=set_weight_as_global_constant
)
self.model.output_schema = schema.Struct()
self.assertEqual(
schema.Scalar((np.float32, (output_dims, ))),
srf_output
)
init_ops_list = [
OpSpec("GaussianFill", None, None),
OpSpec("UniformFill", None, None),
OpSpec("GaussianFill", None, None),
OpSpec("UniformFill", None, None),
]
train_init_net, train_net = self.get_training_nets()
# Need to run to initialize the global constants for layer
workspace.RunNetOnce(self.model.create_init_net(name='init_net'))
if set_weight_as_global_constant:
# If weight params are global constants, they won't be in train_init_net
init_ops = self._test_net(train_init_net, init_ops_list[:2])
rand_w = workspace.FetchBlob(
self.model.global_constants['semi_random_features_fixed_rand_W']
)
rand_b = workspace.FetchBlob(
self.model.global_constants['semi_random_features_fixed_rand_b']
)
# Operation specifications
fc_random_spec = OpSpec("FC", [input_blob, None, None], None)
fc_learned_spec = OpSpec("FC", [input_blob, init_ops[0].output[0],
init_ops[1].output[0]], None)
else:
init_ops = self._test_net(train_init_net, init_ops_list)
rand_w = workspace.FetchBlob(self.model.layers[0].random_w)
rand_b = workspace.FetchBlob(self.model.layers[0].random_b)
# Operation specifications
fc_random_spec = OpSpec("FC", [input_blob, init_ops[0].output[0],
init_ops[1].output[0]], None)
fc_learned_spec = OpSpec("FC", [input_blob, init_ops[2].output[0],
init_ops[3].output[0]], None)
gt_spec = OpSpec("GT", None, None)
cast_spec = OpSpec("Cast", None, None)
relu_spec = OpSpec("Relu", None, None)
pow_spec = OpSpec("Pow", None, None, {'exponent': float(s - 1)})
mul_interim_spec = OpSpec("Mul", None, None)
mul_spec = OpSpec("Mul", None, srf_output.field_blobs())
if s == 0:
ops_list = [
fc_random_spec,
fc_learned_spec,
gt_spec,
cast_spec,
mul_spec,
]
elif s == 1:
ops_list = [
fc_random_spec,
fc_learned_spec,
relu_spec,
mul_spec,
]
else:
ops_list = [
fc_random_spec,
fc_learned_spec,
relu_spec,
pow_spec,
mul_interim_spec,
mul_spec,
]
# Train net assertions
self._test_net(train_net, ops_list)
self._semi_random_hypothesis_test(srf_output(), X, rand_w, rand_b, s)
# Eval net assertions
eval_net = self.get_eval_net()
self._test_net(eval_net, ops_list)
self._semi_random_hypothesis_test(srf_output(), X, rand_w, rand_b, s)
# Predict net assertions
predict_net = self.get_predict_net()
self._test_net(predict_net, ops_list)
self._semi_random_hypothesis_test(srf_output(), X, rand_w, rand_b, s)
def init_adjoint_model_with_schemas(model_name,
sig_input_dim,
tanh_input_dim,
pred_dim,
train_target=TrainTarget.ADJOINT):
'''
output_records have to filled with existing blobs.
'''
workspace.ResetWorkspace()
print('>>> Training Target: ' + train_target)
if train_target == TrainTarget.ADJOINT:
# When training the adjoint network, we also need to forward pass
# through the origin network
input_record_schema = schema.Struct(
('sig_input', schema.Scalar(
(np.float32, (sig_input_dim, )))), # sig
('tanh_input', schema.Scalar(
(np.float32, (tanh_input_dim, )))), # tanh
('adjoint_input', schema.Scalar((np.float32, (pred_dim, )))))
output_record_schema = schema.Struct(
('loss', schema.Scalar((np.float32, (1, )))),
('origin_pred', schema.Scalar((np.float32, (pred_dim, )))),
('sig_adjoint_pred', schema.Scalar(
(np.float32, (sig_input_dim, )))),
('tanh_adjoint_pred',
schema.Scalar((np.float32, (tanh_input_dim, )))),
)
# use trainer_extra_schema as the loss input record
trainer_extra_schema = schema.Struct(
('sig_loss_record',
schema.Struct(
('label', schema.Scalar((np.float32, (sig_input_dim, )))),
('prediction', schema.Scalar(
(np.float32, (sig_input_dim, )))))),
('tanh_loss_record',
schema.Struct(
('label', schema.Scalar((np.float32, (tanh_input_dim, )))),
('prediction', schema.Scalar(
(np.float32, (tanh_input_dim, )))))),
('origin_loss_record',
schema.Struct(
('label', schema.Scalar((np.float32, (pred_dim, )))),
('prediction', schema.Scalar((np.float32, (pred_dim, )))))),
)
if train_target == TrainTarget.ORIGIN:
# When training the origin network, no need of the adjoint network
input_record_schema = schema.Struct(
('sig_input', schema.Scalar(
(np.float32, (sig_input_dim, )))), # sig
('tanh_input', schema.Scalar(
(np.float32, (tanh_input_dim, )))), # tanh
('adjoint_input', schema.Scalar((np.float32, (pred_dim, )))))
output_record_schema = schema.Struct(
('loss', schema.Scalar((np.float32, (1, )))),
('origin_pred', schema.Scalar((np.float32, (pred_dim, )))),
)
# use trainer_extra_schema as the loss input record
trainer_extra_schema = schema.Struct(
('origin_loss_record',
schema.Struct(
('label', schema.Scalar((np.float32, (pred_dim, )))),
('prediction', schema.Scalar((np.float32, (pred_dim, )))))), )
model = layer_model_helper.LayerModelHelper(model_name,
input_record_schema,
trainer_extra_schema)
model.output_schema = output_record_schema
return model
def __init__(self, model, input_record, output_names_or_num, function,
name='functional', output_dtypes=None, **kwargs):
# allow coercion
input_record = schema.as_record(input_record)
super(Functional, self).__init__(model, name, input_record, **kwargs)
self._function = function
self._kwargs = kwargs
return_struct = (
isinstance(output_names_or_num, list) or
(isinstance(output_names_or_num, six.integer_types) and
output_names_or_num != 1)
)
with scope.NameScope(self.name, reset=True):
if isinstance(output_names_or_num, int):
struct_output_schema = schema.NewRecord(
model.net, schema.RawTuple(output_names_or_num))
elif isinstance(output_names_or_num, schema.Field):
self.output_schema = output_names_or_num.clone(keep_blobs=True)
return
else:
if not isinstance(output_names_or_num, list):
output_names_or_num = [output_names_or_num]
out_tuple = [(out, np.void) for out in output_names_or_num]
struct_output_schema = schema.NewRecord(
model.net, schema.Struct(*out_tuple))
num_outputs = len(struct_output_schema.field_blobs())
# functional layer returns Struct if more than one outputs or output is
# a list, otherwise Scalar
if return_struct:
self.output_schema = struct_output_schema
else:
self.output_schema = struct_output_schema[0]
# If output_dtypes is provided, use it for output schema. Otherwise
# the shape and type will be inferred.
if output_dtypes is not None:
if not isinstance(output_dtypes, list):
output_dtypes = [output_dtypes] * num_outputs
assert len(output_dtypes) == num_outputs
for dtype, scalar in zip(output_dtypes,
self.output_schema.all_scalars()):
scalar.set_type(dtype)
return
# Fake execution of the function to infer shapes and types automatically
had_issues = False
try:
type_net = core.Net('_temp_type_and_shape_inference_net')
schema.InitEmptyRecord(type_net, input_record, enforce_types=True)
function(type_net, self.input_record, self.output_schema, **kwargs)
(shapes, types) = workspace.InferShapesAndTypes([type_net], {})
for i in range(num_outputs):
scalar_schema = (self.output_schema[i] if return_struct
else self.output_schema)
blob = scalar_schema()
if blob not in types or blob not in shapes:
had_issues = True
continue
if shapes[blob] == []:
# Scalar type
shape = tuple()
elif shapes[blob][0] == 0:
shape = tuple(shapes[blob][1:])
else:
logger.warning("unexpeced shape: {}".format(shapes[blob]))
# If batch dimension is not first - give up on shape
# inference for that blob
had_issues = True
continue
# TODO(amalevich): Move it to some shared library
dtype = None
if types[blob] == caffe2_pb2.TensorProto.DOUBLE:
dtype = (np.float64, shape)
elif types[blob] == caffe2_pb2.TensorProto.FLOAT:
dtype = (np.float32, shape)
elif types[blob] == caffe2_pb2.TensorProto.INT32:
dtype = (np.int32, shape)
elif types[blob] == caffe2_pb2.TensorProto.INT64:
dtype = (np.int64, shape)
if dtype is not None:
scalar_schema.set_type(dtype)
except TypeError as ex:
had_issues = True
logger.warning(str(ex))
if had_issues:
logger.warning(
"Type inference had problems for layer: {}".format(self.name))
def run_train_net(self):
self.model.output_schema = schema.Struct()
train_init_net, train_net = \
layer_model_instantiator.generate_training_nets(self.model)
workspace.RunNetOnce(train_init_net)
workspace.RunNetOnce(train_net)
def testBatchSigmoidCrossEntropyLoss(self):
input_record = self.new_record(
schema.Struct(('label', schema.Scalar((np.float32, (32, )))),
('prediction', schema.Scalar((np.float32, (32, ))))))
loss = self.model.BatchSigmoidCrossEntropyLoss(input_record)
self.assertEqual(schema.Scalar((np.float32, tuple())), loss)
def testArcCosineFeatureMap(self, batch_size, input_dims, output_dims, s,
scale):
X = np.random.normal(size=(batch_size, input_dims)).astype(np.float32)
input_record = self.new_record(
schema.Scalar((np.float32, (input_dims, ))))
schema.FeedRecord(input_record, [X])
input_blob = input_record.field_blobs()[0]
ac_output = self.model.ArcCosineFeatureMap(input_record,
output_dims,
s=s,
scale=scale)
self.model.output_schema = schema.Struct()
self.assertEqual(schema.Scalar((np.float32, (output_dims, ))),
ac_output)
init_ops_list = [
OpSpec("GaussianFill", None, None),
OpSpec("UniformFill", None, None),
]
train_init_net, train_net = self.get_training_nets()
# Init net assertions
init_ops = self._test_net(train_init_net, init_ops_list)
workspace.RunNetOnce(self.model.param_init_net)
W = workspace.FetchBlob(self.model.layers[0].random_w)
b = workspace.FetchBlob(self.model.layers[0].random_b)
# Operation specifications
fc_spec = OpSpec(
"FC", [input_blob, init_ops[0].output[0], init_ops[1].output[0]],
None)
gt_spec = OpSpec("GT", None, None, {'broadcast': 1})
cast_spec = OpSpec("Cast", None, ac_output.field_blobs())
relu_spec = OpSpec("Relu", None, None)
relu_spec_output = OpSpec("Relu", None, ac_output.field_blobs())
pow_spec = OpSpec("Pow", None, None, {'exponent': float(s - 1)})
mul_spec = OpSpec("Mul", None, ac_output.field_blobs())
if s == 0:
ops_list = [
fc_spec,
gt_spec,
cast_spec,
]
elif s == 1:
ops_list = [
fc_spec,
relu_spec_output,
]
else:
ops_list = [
fc_spec,
relu_spec,
pow_spec,
mul_spec,
]
# Train net assertions
self._test_net(train_net, ops_list)
self._arc_cosine_hypothesis_test(ac_output(), X, W, b, s)
# Eval net assertions
eval_net = self.get_eval_net()
self._test_net(eval_net, ops_list)
self._arc_cosine_hypothesis_test(ac_output(), X, W, b, s)
# Predict net assertions
predict_net = self.get_predict_net()
self._test_net(predict_net, ops_list)
self._arc_cosine_hypothesis_test(ac_output(), X, W, b, s)
def testBatchNormalization(self, X):
input_record = self.new_record(schema.Scalar((np.float32, (5,))))
schema.FeedRecord(input_record, [X])
bn_output = self.model.BatchNormalization(input_record)
self.assertEqual(schema.Scalar((np.float32, (5,))), bn_output)
self.model.output_schema = schema.Struct()
train_init_net, train_net = self.get_training_nets()
init_ops = self.assertNetContainOps(
train_init_net,
[
OpSpec("ConstantFill", None, None),
OpSpec("ConstantFill", None, None),
OpSpec("ConstantFill", None, None),
OpSpec("ConstantFill", None, None),
]
)
input_blob = input_record.field_blobs()[0]
output_blob = bn_output.field_blobs()[0]
expand_dims_spec = OpSpec(
"ExpandDims",
[input_blob],
[input_blob],
)
train_bn_spec = OpSpec(
"SpatialBN",
[input_blob, init_ops[0].output[0], init_ops[1].output[0],
init_ops[2].output[0], init_ops[3].output[0]],
[output_blob, init_ops[2].output[0], init_ops[3].output[0], None, None],
{'is_test': 0, 'order': 'NCHW', 'momentum': 0.9},
)
test_bn_spec = OpSpec(
"SpatialBN",
[input_blob, init_ops[0].output[0], init_ops[1].output[0],
init_ops[2].output[0], init_ops[3].output[0]],
[output_blob],
{'is_test': 1, 'order': 'NCHW', 'momentum': 0.9},
)
squeeze_spec = OpSpec(
"Squeeze",
[output_blob],
[output_blob],
)
self.assertNetContainOps(
train_net,
[expand_dims_spec, train_bn_spec, squeeze_spec]
)
eval_net = self.get_eval_net()
self.assertNetContainOps(
eval_net,
[expand_dims_spec, test_bn_spec, squeeze_spec]
)
predict_net = self.get_predict_net()
self.assertNetContainOps(
predict_net,
[expand_dims_spec, test_bn_spec, squeeze_spec]
)
workspace.RunNetOnce(train_init_net)
workspace.RunNetOnce(train_net)
schema.FeedRecord(input_record, [X])
workspace.RunNetOnce(eval_net)
schema.FeedRecord(input_record, [X])
workspace.RunNetOnce(predict_net)
def __init__(self,
model,
input_record,
name='batch_lr_loss',
average_loss=True,
jsd_weight=0.0,
pos_label_target=1.0,
neg_label_target=0.0,
homotopy_weighting=False,
log_D_trick=False,
unjoined_lr_loss=False,
uncertainty_penalty=1.0,
focal_gamma=0.0,
stop_grad_in_focal_factor=False,
task_gamma=1.0,
task_gamma_lb=0.1,
**kwargs):
super(BatchLRLoss, self).__init__(model, name, input_record, **kwargs)
self.average_loss = average_loss
assert (schema.is_schema_subset(
schema.Struct(('label', schema.Scalar()),
('logit', schema.Scalar())), input_record))
self.jsd_fuse = False
assert jsd_weight >= 0 and jsd_weight <= 1
if jsd_weight > 0 or homotopy_weighting:
assert 'prediction' in input_record
self.init_weight(jsd_weight, homotopy_weighting)
self.jsd_fuse = True
self.homotopy_weighting = homotopy_weighting
assert pos_label_target <= 1 and pos_label_target >= 0
assert neg_label_target <= 1 and neg_label_target >= 0
assert pos_label_target >= neg_label_target
self.pos_label_target = pos_label_target
self.neg_label_target = neg_label_target
assert not (log_D_trick and unjoined_lr_loss)
self.log_D_trick = log_D_trick
self.unjoined_lr_loss = unjoined_lr_loss
assert uncertainty_penalty >= 0
self.uncertainty_penalty = uncertainty_penalty
self.tags.update([Tags.EXCLUDE_FROM_PREDICTION])
self.output_schema = schema.Scalar(
np.float32, self.get_next_blob_reference('output'))
self.focal_gamma = focal_gamma
self.stop_grad_in_focal_factor = stop_grad_in_focal_factor
self.apply_exp_decay = False
if task_gamma < 1.0:
self.apply_exp_decay = True
self.task_gamma_cur = self.create_param(
param_name=('%s_task_gamma_cur' % self.name),
shape=[1],
initializer=('ConstantFill', {
'value': 1.0,
'dtype': core.DataType.FLOAT
}),
optimizer=self.model.NoOptim,
)
self.task_gamma = self.create_param(
param_name=('%s_task_gamma' % self.name),
shape=[1],
initializer=('ConstantFill', {
'value': task_gamma,
'dtype': core.DataType.FLOAT
}),
optimizer=self.model.NoOptim,
)
self.task_gamma_lb = self.create_param(
param_name=('%s_task_gamma_lb' % self.name),
shape=[1],
initializer=('ConstantFill', {
'value': task_gamma_lb,
'dtype': core.DataType.FLOAT
}),
optimizer=self.model.NoOptim,
)
def __init__(self,
model,
input_record,
output_names_or_num,
function,
name='functional',
**kwargs):
super(Functional, self).__init__(model, name, input_record, **kwargs)
self._function = function
with scope.NameScope(self.name):
if isinstance(output_names_or_num, int):
self.output_schema = schema.NewRecord(
model.net, schema.RawTuple(output_names_or_num))
else:
if not isinstance(output_names_or_num, list):
output_names_or_num = [output_names_or_num]
out_tuple = [(out, np.void) for out in output_names_or_num]
self.output_schema = schema.NewRecord(
model.net, schema.Struct(*out_tuple))
num_outputs = len(self.output_schema.field_blobs())
# Fake execution of the function to infer shapes and types automatically
had_issues = False
try:
type_net = core.Net('_temp_type_and_shape_inference_net')
schema.InitEmptyRecord(type_net, input_record, enforce_types=True)
function(type_net, self.input_record, self.output_schema)
(shapes, types) = workspace.InferShapesAndTypes([type_net], {})
for i in range(num_outputs):
blob = self.output_schema[i]()
if blob not in types or blob not in shapes:
had_issues = True
continue
if shapes[blob] == []:
# Scalar type
shape = tuple()
elif shapes[blob][0] == 0:
shape = tuple(shapes[blob][1:])
else:
# If batch dimension is not first - give up on shape
# inference for that blob
had_issues = True
continue
# TODO(amalevich): Move it to some shared library
dtype = None
if types[blob] == caffe2_pb2.TensorProto.DOUBLE:
dtype = (np.float64, shape)
elif types[blob] == caffe2_pb2.TensorProto.FLOAT:
dtype = (np.float32, shape)
elif types[blob] == caffe2_pb2.TensorProto.INT32:
dtype = (np.int32, shape)
elif types[blob] == caffe2_pb2.TensorProto.INT64:
dtype = (np.int64, shape)
if dtype is not None:
self.output_schema[i].set_type(dtype)
except TypeError as ex:
had_issues = True
logger.warning(str(ex))
if had_issues:
logger.warning("Type inference had problems for layer: {}".format(
self.name))
def __init__(self,
model,
input_record,
input_specs,
name='sparse_to_dense',
**kwargs):
"""
`input_specs` follows the format of FeatureSpec from schema. To be more
precise it's a namedtuple that should have:
'feature_type', 'feature_names', 'feature_ids'
"""
super(SparseToDense, self).__init__(model, name, input_record,
**kwargs)
self.input_specs = input_specs
outputs = []
for field, feature_specs in self.input_specs:
assert len(feature_specs.feature_names) ==\
len(feature_specs.feature_ids)
if feature_specs.feature_type == 'FLOAT':
outputs.append(
(field,
schema.Scalar(
(np.float32, len(feature_specs.feature_ids)),
core.ScopedBlobReference(
model.net.NextName(self.name + field +
'_output')))))
elif feature_specs.feature_type == 'ID_LIST':
outputs.append(
(field,
schema.Struct(
(
'ranges',
schema.Scalar(
(np.int32,
(len(feature_specs.feature_ids), 2)),
core.ScopedBlobReference(
model.net.NextName(self.name + field +
'_ranges'))),
),
('values', input_record[field].values.items),
)))
else:
raise TypeError("Unsupported input type: {0}".format(
feature_specs.feature_type))
# TODO(amalevich): This schema is producing ranges. And thus if there is
# something using it it should support ranges as well. It might be
# confusing, if we don't add better support for ranges/have it as a
# first layer
self.output_schema = schema.Struct(*outputs)
# TODO(amalevich): Consider moving this data to schema, instead
# Structs doens't support attaching metadata to them and clonning
# will break things badly, but this is the most elegant way to pass
# this info around. Should we change it or it'll be too much work and
# not worse it?
for field, feature_specs in input_specs:
schema.attach_metadata_to_scalars(
self.output_schema[field],
schema.Metadata(feature_specs=feature_specs))
self.zero = model.global_constants['ZERO']
self.zero_range = model.global_constants['ZERO_RANGE']
def testSemiRandomFeatures(self, batch_size, input_dims, output_dims, s,
scale, set_weight_as_global_constant,
use_struct_input):
def _semi_random_hypothesis_test(srf_output, X_full, X_random, rand_w,
rand_b, s):
"""
Runs hypothesis test for Semi Random Features layer.
Inputs:
srf_output -- output of net after running semi random features layer
X_full -- full input data
X_random -- random-output input data
rand_w -- random-initialized weight parameter from train_init_net
rand_b -- random-initialized bias parameter from train_init_net
s -- degree parameter
"""
# Get output from net
net_output = workspace.FetchBlob(srf_output)
# Fetch learned parameter blobs
learned_w = workspace.FetchBlob(self.model.layers[0].learned_w)
learned_b = workspace.FetchBlob(self.model.layers[0].learned_b)
# Computing output directly
x_rand = np.matmul(X_random, np.transpose(rand_w)) + rand_b
x_learn = np.matmul(X_full, np.transpose(learned_w)) + learned_b
x_pow = np.power(x_rand, s)
if s > 0:
h_rand_features = np.piecewise(x_rand,
[x_rand <= 0, x_rand > 0],
[0, 1])
else:
h_rand_features = np.piecewise(x_rand,
[x_rand <= 0, x_rand > 0],
[0, lambda x: x / (1 + x)])
output_ref = np.multiply(np.multiply(x_pow, h_rand_features),
x_learn)
# Comparing net output and computed output
npt.assert_allclose(net_output, output_ref, rtol=1e-3, atol=1e-3)
X_full = np.random.normal(size=(batch_size,
input_dims)).astype(np.float32)
if use_struct_input:
X_random = np.random.normal(size=(batch_size, input_dims)).\
astype(np.float32)
input_data = [X_full, X_random]
input_record = self.new_record(
schema.Struct(
('full', schema.Scalar((np.float32, (input_dims, )))),
('random', schema.Scalar((np.float32, (input_dims, ))))))
else:
X_random = X_full
input_data = [X_full]
input_record = self.new_record(
schema.Scalar((np.float32, (input_dims, ))))
schema.FeedRecord(input_record, input_data)
srf_output = self.model.SemiRandomFeatures(
input_record,
output_dims,
s=s,
scale_random=scale,
scale_learned=scale,
set_weight_as_global_constant=set_weight_as_global_constant)
self.model.output_schema = schema.Struct()
self.assertEqual(
schema.Struct(
('full', schema.Scalar((np.float32, (output_dims, )))),
('random', schema.Scalar((np.float32, (output_dims, ))))),
srf_output)
init_ops_list = [
OpSpec("GaussianFill", None, None),
OpSpec("UniformFill", None, None),
OpSpec("GaussianFill", None, None),
OpSpec("UniformFill", None, None),
]
train_init_net, train_net = self.get_training_nets()
# Need to run to initialize the global constants for layer
workspace.RunNetOnce(self.model.create_init_net(name='init_net'))
if set_weight_as_global_constant:
# If weight params are global constants, they won't be in train_init_net
init_ops = self._test_net(train_init_net, init_ops_list[:2])
rand_w = workspace.FetchBlob(
self.model.
global_constants['semi_random_features_fixed_rand_W'])
rand_b = workspace.FetchBlob(
self.model.
global_constants['semi_random_features_fixed_rand_b'])
# Operation specifications
fc_random_spec = OpSpec("FC", [None, None, None], None)
fc_learned_spec = OpSpec(
"FC", [None, init_ops[0].output[0], init_ops[1].output[0]],
None)
else:
init_ops = self._test_net(train_init_net, init_ops_list)
rand_w = workspace.FetchBlob(self.model.layers[0].random_w)
rand_b = workspace.FetchBlob(self.model.layers[0].random_b)
# Operation specifications
fc_random_spec = OpSpec(
"FC", [None, init_ops[0].output[0], init_ops[1].output[0]],
None)
fc_learned_spec = OpSpec(
"FC", [None, init_ops[2].output[0], init_ops[3].output[0]],
None)
softsign_spec = OpSpec("Softsign", None, None)
relu_spec = OpSpec("Relu", None, None)
relu_output_spec = OpSpec("Relu", None,
srf_output.random.field_blobs())
pow_spec = OpSpec("Pow", None, None, {'exponent': float(s - 1)})
mul_interim_spec = OpSpec("Mul", None, srf_output.random.field_blobs())
mul_spec = OpSpec("Mul", None, srf_output.full.field_blobs())
if s == 0:
ops_list = [
fc_learned_spec,
fc_random_spec,
softsign_spec,
relu_output_spec,
mul_spec,
]
elif s == 1:
ops_list = [
fc_learned_spec,
fc_random_spec,
relu_output_spec,
mul_spec,
]
else:
ops_list = [
fc_learned_spec,
fc_random_spec,
relu_spec,
pow_spec,
mul_interim_spec,
mul_spec,
]
# Train net assertions
self._test_net(train_net, ops_list)
_semi_random_hypothesis_test(srf_output.full(), X_full, X_random,
rand_w, rand_b, s)
# Eval net assertions
eval_net = self.get_eval_net()
self._test_net(eval_net, ops_list)
_semi_random_hypothesis_test(srf_output.full(), X_full, X_random,
rand_w, rand_b, s)
# Predict net assertions
predict_net = self.get_predict_net()
self._test_net(predict_net, ops_list)
_semi_random_hypothesis_test(srf_output.full(), X_full, X_random,
rand_w, rand_b, s)
def testArcCosineFeatureMap(self, batch_size, input_dims, output_dims, s,
scale, set_weight_as_global_constant):
def _arc_cosine_hypothesis_test(ac_output, X, W, b, s):
"""
Runs hypothesis test for Arc Cosine layer.
Inputs:
ac_output -- output of net after running arc cosine layer
X -- input data
W -- weight parameter from train_init_net
b -- bias parameter from train_init_net
s -- degree parameter
"""
# Get output from net
net_output = workspace.FetchBlob(ac_output)
# Computing output directly
x_rand = np.matmul(X, np.transpose(W)) + b
x_pow = np.power(x_rand, s)
if s > 0:
h_rand_features = np.piecewise(x_rand,
[x_rand <= 0, x_rand > 0],
[0, 1])
else:
h_rand_features = np.piecewise(x_rand,
[x_rand <= 0, x_rand > 0],
[0, lambda x: x / (1 + x)])
output_ref = np.multiply(x_pow, h_rand_features)
# Comparing net output and computed output
npt.assert_allclose(net_output, output_ref, rtol=1e-3, atol=1e-3)
X = np.random.normal(size=(batch_size, input_dims)).astype(np.float32)
input_record = self.new_record(
schema.Scalar((np.float32, (input_dims, ))))
schema.FeedRecord(input_record, [X])
input_blob = input_record.field_blobs()[0]
ac_output = self.model.ArcCosineFeatureMap(
input_record,
output_dims,
s=s,
scale=scale,
set_weight_as_global_constant=set_weight_as_global_constant)
self.model.output_schema = schema.Struct()
self.assertEqual(schema.Scalar((np.float32, (output_dims, ))),
ac_output)
train_init_net, train_net = self.get_training_nets()
# Run create_init_net to initialize the global constants, and W and b
workspace.RunNetOnce(train_init_net)
workspace.RunNetOnce(self.model.create_init_net(name='init_net'))
if set_weight_as_global_constant:
W = workspace.FetchBlob(
self.model.
global_constants['arc_cosine_feature_map_fixed_rand_W'])
b = workspace.FetchBlob(
self.model.
global_constants['arc_cosine_feature_map_fixed_rand_b'])
else:
W = workspace.FetchBlob(self.model.layers[0].random_w)
b = workspace.FetchBlob(self.model.layers[0].random_b)
# Operation specifications
fc_spec = OpSpec("FC", [input_blob, None, None], None)
softsign_spec = OpSpec("Softsign", None, None)
relu_spec = OpSpec("Relu", None, None)
relu_spec_output = OpSpec("Relu", None, ac_output.field_blobs())
pow_spec = OpSpec("Pow", None, None, {'exponent': float(s - 1)})
mul_spec = OpSpec("Mul", None, ac_output.field_blobs())
if s == 0:
ops_list = [
fc_spec,
softsign_spec,
relu_spec_output,
]
elif s == 1:
ops_list = [
fc_spec,
relu_spec_output,
]
else:
ops_list = [
fc_spec,
relu_spec,
pow_spec,
mul_spec,
]
# Train net assertions
self._test_net(train_net, ops_list)
_arc_cosine_hypothesis_test(ac_output(), X, W, b, s)
# Eval net assertions
eval_net = self.get_eval_net()
self._test_net(eval_net, ops_list)
_arc_cosine_hypothesis_test(ac_output(), X, W, b, s)
# Predict net assertions
predict_net = self.get_predict_net()
self._test_net(predict_net, ops_list)
_arc_cosine_hypothesis_test(ac_output(), X, W, b, s)
def testAssignToField(self):
with self.assertRaises(TypeError):
s = schema.Struct(('a', schema.Scalar()))
s.a = schema.Scalar()
def testMapToRange(self):
input_record = self.new_record(schema.Scalar(np.int32))
map_to_range_output = self.model.MapToRange(input_record,
max_index=100)
self.model.output_schema = schema.Struct()
train_init_net, train_net = self.get_training_nets()
schema.FeedRecord(
input_record,
[np.array([10, 3, 20, 99, 15, 11, 3, 11], dtype=np.int32)]
)
workspace.RunNetOnce(train_init_net)
workspace.RunNetOnce(train_net)
indices = workspace.FetchBlob(map_to_range_output())
np.testing.assert_array_equal(
np.array([1, 2, 3, 4, 5, 6, 2, 6], dtype=np.int32),
indices
)
schema.FeedRecord(
input_record,
[np.array([10, 3, 23, 35, 60, 15, 10, 15], dtype=np.int32)]
)
workspace.RunNetOnce(train_net)
indices = workspace.FetchBlob(map_to_range_output())
np.testing.assert_array_equal(
np.array([1, 2, 7, 8, 9, 5, 1, 5], dtype=np.int32),
indices
)
eval_net = self.get_eval_net()
schema.FeedRecord(
input_record,
[np.array([10, 3, 23, 35, 60, 15, 200], dtype=np.int32)]
)
workspace.RunNetOnce(eval_net)
indices = workspace.FetchBlob(map_to_range_output())
np.testing.assert_array_equal(
np.array([1, 2, 7, 8, 9, 5, 0], dtype=np.int32),
indices
)
schema.FeedRecord(
input_record,
[np.array([10, 3, 23, 15, 101, 115], dtype=np.int32)]
)
workspace.RunNetOnce(eval_net)
indices = workspace.FetchBlob(map_to_range_output())
np.testing.assert_array_equal(
np.array([1, 2, 7, 5, 0, 0], dtype=np.int32),
indices
)
predict_net = self.get_predict_net()
schema.FeedRecord(
input_record,
[np.array([3, 3, 20, 23, 151, 35, 60, 15, 200], dtype=np.int32)]
)
workspace.RunNetOnce(predict_net)
indices = workspace.FetchBlob(map_to_range_output())
np.testing.assert_array_equal(
np.array([2, 2, 3, 7, 0, 8, 9, 5, 0], dtype=np.int32),
indices
)
def testFromEmptyColumnList(self):
st = schema.Struct()
columns = st.field_names()
rec = schema.from_column_list(col_names=columns)
self.assertEqual(rec, schema.Struct())
def filter_metrics_schema(self, white_set):
logger.info("Filter metric schema with white_set {}".format(white_set))
field_names = self._metrics_schema.field_names()
for name in field_names:
if name not in white_set:
self._metrics_schema = self._metrics_schema - schema.Struct((name, schema.Scalar()))
def __init__(self, model, input_record, num_to_collect,
name='reservoir_sampling', **kwargs):
super(ReservoirSampling, self).__init__(
model, name, input_record, **kwargs)
assert num_to_collect > 0
self.num_to_collect = num_to_collect
self.reservoir = self.create_param(
param_name='reservoir',
shape=[0],
initializer=('ConstantFill',),
optimizer=model.NoOptim,
)
self.num_visited_blob = self.create_param(
param_name='num_visited',
shape=[],
initializer=('ConstantFill', {
'value': 0,
'dtype': core.DataType.INT64,
}),
optimizer=model.NoOptim,
)
self.mutex = self.create_param(
param_name='mutex',
shape=None,
initializer=('CreateMutex',),
optimizer=model.NoOptim,
)
self.extra_input_blobs = []
self.extra_output_blobs = []
if 'object_id' in input_record:
object_to_pos = self.create_param(
param_name='object_to_pos',
initializer=('CreateMap', {
'key_dtype': core.DataType.INT64,
'valued_dtype': core.DataType.INT32,
}),
optimizer=model.NoOptim,
)
pos_to_object = self.create_param(
param_name='pos_to_object',
shape=[0],
initializer=('ConstantFill', {
'value': 0,
'dtype': core.DataType.INT64,
}),
optimizer=model.NoOptim,
)
self.extra_input_blobs.append(input_record.object_id())
self.extra_input_blobs.extend([object_to_pos, pos_to_object])
self.extra_output_blobs.extend([object_to_pos, pos_to_object])
self.output_schema = schema.Struct(
(
'reservoir',
schema.from_blob_list(input_record.data, [self.reservoir])
),
('num_visited', schema.Scalar(blob=self.num_visited_blob)),
('mutex', schema.Scalar(blob=self.mutex)),
)
def __init__(
self,
model,
input_record,
output_dims,
s=1,
scale_random=1.0,
scale_learned=1.0,
weight_init_random=None,
bias_init_random=None,
weight_init_learned=None,
bias_init_learned=None,
weight_optim=None,
bias_optim=None,
set_weight_as_global_constant=False,
name='semi_random_features',
**kwargs):
if isinstance(input_record, schema.Struct):
schema.is_schema_subset(
schema.Struct(
('full', schema.Scalar()),
('random', schema.Scalar()),
),
input_record
)
self.input_record_full = input_record.full
self.input_record_random = input_record.random
elif isinstance(input_record, schema.Scalar):
self.input_record_full = input_record
self.input_record_random = input_record
super(SemiRandomFeatures, self).__init__(
model,
self.input_record_full,
output_dims,
s=s,
scale=scale_random, # To initialize the random parameters
weight_init=weight_init_random,
bias_init=bias_init_random,
weight_optim=None,
bias_optim=None,
set_weight_as_global_constant=set_weight_as_global_constant,
initialize_output_schema=False,
name=name,
**kwargs)
self.output_schema = schema.Struct(
('full', schema.Scalar(
(np.float32, output_dims),
model.net.NextScopedBlob(name + '_full_output')
),),
('random', schema.Scalar(
(np.float32, output_dims),
model.net.NextScopedBlob(name + '_random_output')
),),
)
# To initialize the learnable parameters
assert (scale_learned > 0.0), \
"Expected scale (learned) > 0, got %s" % scale_learned
self.stddev = scale_learned * np.sqrt(1.0 / self.input_dims)
# Learned Parameters
(self.learned_w, self.learned_b) = self._initialize_params(
'learned_w',
'learned_b',
w_init=weight_init_learned,
b_init=bias_init_learned,
w_optim=weight_optim,
b_optim=bias_optim
)
def testGatherRecord(self):
indices = np.array([1, 3, 4], dtype=np.int32)
dense = np.array(range(20), dtype=np.float32).reshape(10, 2)
lengths = np.array(range(10), dtype=np.int32)
items = np.array(range(lengths.sum()), dtype=np.int64)
items_lengths = np.array(range(lengths.sum()), dtype=np.int32)
items_items = np.array(range(items_lengths.sum()), dtype=np.int64)
record = self.new_record(
schema.Struct(
('dense', schema.Scalar(np.float32)),
('sparse',
schema.Struct(
('list', schema.List(np.int64)),
('list_of_list', schema.List(schema.List(np.int64))),
)), ('empty_struct', schema.Struct())))
indices_record = self.new_record(schema.Scalar(np.int32))
input_record = schema.Struct(
('indices', indices_record),
('record', record),
)
schema.FeedRecord(input_record, [
indices, dense, lengths, items, lengths, items_lengths, items_items
])
gathered_record = self.model.GatherRecord(input_record)
self.assertTrue(schema.equal_schemas(gathered_record, record))
self.run_train_net_forward_only()
gathered_dense = workspace.FetchBlob(gathered_record.dense())
np.testing.assert_array_equal(
np.concatenate([dense[i:i + 1] for i in indices]), gathered_dense)
gathered_lengths = workspace.FetchBlob(
gathered_record.sparse.list.lengths())
np.testing.assert_array_equal(
np.concatenate([lengths[i:i + 1] for i in indices]),
gathered_lengths)
gathered_items = workspace.FetchBlob(
gathered_record.sparse.list.items())
offsets = lengths.cumsum() - lengths
np.testing.assert_array_equal(
np.concatenate(
[items[offsets[i]:offsets[i] + lengths[i]] for i in indices]),
gathered_items)
gathered_items_lengths = workspace.FetchBlob(
gathered_record.sparse.list_of_list.items.lengths())
np.testing.assert_array_equal(
np.concatenate([
items_lengths[offsets[i]:offsets[i] + lengths[i]]
for i in indices
]), gathered_items_lengths)
nested_offsets = []
nested_lengths = []
nested_offset = 0
j = 0
for l in lengths:
nested_offsets.append(nested_offset)
nested_length = 0
for _i in range(l):
nested_offset += items_lengths[j]
nested_length += items_lengths[j]
j += 1
nested_lengths.append(nested_length)
gathered_items_items = workspace.FetchBlob(
gathered_record.sparse.list_of_list.items.items())
np.testing.assert_array_equal(
np.concatenate([
items_items[nested_offsets[i]:nested_offsets[i] +
nested_lengths[i]] for i in indices
]), gathered_items_items)
def testSetInputRecordWithoutBlobs(self):
net = core.Net("test")
record = schema.Struct(("x", schema.Scalar(np.float)))
input_record = net.set_input_record(record)
self.assertTrue(net.BlobIsDefined(input_record.x()))
self.assertIn(input_record.x(), net.external_inputs)
def __init__(self,
model,
input_record,
input_specs,
name="feature_sparse_to_dense",
**kwargs):
"""
`input_specs` follows the format of FeatureSpec from schema. To be more
precise it's a namedtuple that should have:
'feature_type', 'feature_names', 'feature_ids'
"""
super(FeatureSparseToDense, self).__init__(model, name, input_record,
**kwargs)
self.input_specs = input_specs
outputs = []
for field, feature_specs in self.input_specs:
assert len(feature_specs.feature_names) == len(
feature_specs.feature_ids)
if feature_specs.feature_type == "FLOAT":
outputs.append((
field,
schema.Scalar(
(np.float32, (len(feature_specs.feature_ids), )),
self.get_next_blob_reference(field + "_output"),
),
))
elif feature_specs.feature_type == "ID_LIST":
outputs.append((
field,
schema.Struct(
(
"ranges",
schema.Scalar(
(np.int32,
(len(feature_specs.feature_ids), 2)),
self.get_next_blob_reference(field +
"_ranges"),
),
),
(
"values",
schema.Scalar(
np.int64,
self.get_next_blob_reference(field +
"_values"),
),
),
),
))
elif feature_specs.feature_type == "ID_SCORE_LIST":
outputs.append((
field,
schema.Struct(
(
"ranges",
schema.Scalar(
(np.int32,
(len(feature_specs.feature_ids), 2)),
self.get_next_blob_reference(field +
"_ranges"),
),
),
(
"ids",
schema.Scalar(
np.int64,
self.get_next_blob_reference(field + "_ids"),
),
),
(
"scores",
schema.Scalar(
np.float32,
self.get_next_blob_reference(field +
"_scores"),
),
),
),
))
elif feature_specs.feature_type == "EMBEDDING":
# We don't know dimensions of embeddings in input data.
# Even though they should match dimensions from feature config,
# we keep ranges blob to check input data later.
outputs.append((
field,
schema.Struct(
(
"ranges",
schema.Scalar(
(np.int32,
(len(feature_specs.feature_ids), 2)),
self.get_next_blob_reference(field +
"_ranges"),
),
),
(
"values",
schema.Scalar(
np.float32,
self.get_next_blob_reference(field +
"_values"),
),
),
),
))
elif feature_specs.feature_type == "GENERIC_FEATURE":
# We don't know dimensions of embeddings in input data.
# Even though they should match dimensions from feature config,
# we keep ranges blob to check input data later.
# Currently this schema with ranges and values is only for
# generic type enum 1. If new types are implemented, we need to
# modify the ParseGeneric operator, and this part accordinly
outputs.append((
field,
schema.Struct(
(
"ranges",
schema.Scalar(
(np.int32,
(len(feature_specs.feature_ids), 2)),
self.get_next_blob_reference(field +
"_ranges"),
),
),
(
"values",
schema.Scalar(
np.float32,
self.get_next_blob_reference(field +
"_values"),
),
),
),
))
else:
raise TypeError("Unsupported input type: {0}".format(
feature_specs.feature_type))
# TODO(amalevich): This schema is producing ranges. And thus if there is
# something using it it should support ranges as well. It might be
# confusing, if we don't add better support for ranges/have it as a
# first layer
self.output_schema = schema.Struct(*outputs)
# TODO(amalevich): Consider moving this data to schema, instead
# Structs doens't support attaching metadata to them and clonning
# will break things badly, but this is the most elegant way to pass
# this info around. Should we change it or it'll be too much work and
# not worse it?
for field, feature_specs in input_specs:
schema.attach_metadata_to_scalars(
self.output_schema[field],
schema.Metadata(feature_specs=feature_specs))
self.zero = model.global_constants["ZERO"]
self.zero_range = model.global_constants["ZERO_RANGE"]
def __init__(
self,
model,
input_record,
output_dims,
s=0,
scale=None,
weight_init=None,
bias_init=None,
weight_optim=None,
bias_optim=None,
set_weight_as_global_constant=False,
name='semi_random_features',
**kwargs):
if isinstance(input_record, schema.Struct):
schema.is_schema_subset(
schema.Struct(
('full', schema.Scalar()),
('random', schema.Scalar()),
),
input_record
)
self.input_record_full = input_record.full
self.input_record_random = input_record.random
elif isinstance(input_record, schema.Scalar):
self.input_record_full = input_record
self.input_record_random = input_record
super(SemiRandomFeatures, self).__init__(
model,
self.input_record_full,
output_dims,
s=s,
scale=scale,
weight_init=weight_init,
bias_init=bias_init,
weight_optim=None,
bias_optim=None,
set_weight_as_global_constant=set_weight_as_global_constant,
initialize_output_schema=False,
name=name,
**kwargs)
self.output_schema = schema.Struct(
('full', schema.Scalar(
(np.float32, output_dims),
model.net.NextScopedBlob(name + '_full_output')
),),
('random', schema.Scalar(
(np.float32, output_dims),
model.net.NextScopedBlob(name + '_random_output')
),),
)
# Learned Parameters
self.learned_w = self.model.net.NextScopedBlob(self.name + "_learned_w")
self.learned_b = self.model.net.NextScopedBlob(self.name + "_learned_b")
self.params += self._initialize_params(self.learned_w,
self.learned_b,
w_init=weight_init,
b_init=bias_init,
w_optim=weight_optim,
b_optim=bias_optim)
def create_net(self):
net = core.Net("feature_extractor")
init_net = core.Net("feature_extractor_init")
missing_scalar = self.create_const(init_net, "MISSING_SCALAR",
MISSING_VALUE)
action_schema = map_schema(
) if self.sorted_action_features else schema.Scalar()
input_schema = schema.Struct(
(InputColumn.STATE_FEATURES, map_schema()),
(InputColumn.NEXT_STATE_FEATURES, map_schema()),
(InputColumn.ACTION, action_schema),
(InputColumn.NEXT_ACTION, action_schema),
(InputColumn.NOT_TERMINAL, schema.Scalar()),
)
if self.include_possible_actions:
input_schema += schema.Struct(
(InputColumn.POSSIBLE_ACTIONS_MASK, schema.List(
schema.Scalar())),
(InputColumn.POSSIBLE_NEXT_ACTIONS_MASK,
schema.List(schema.Scalar())),
)
if self.sorted_action_features is not None:
input_schema += schema.Struct(
(InputColumn.POSSIBLE_ACTIONS, schema.List(map_schema())),
(InputColumn.POSSIBLE_NEXT_ACTIONS,
schema.List(map_schema())),
)
input_record = net.set_input_record(input_schema)
state = self.extract_float_features(
net,
"state",
input_record[InputColumn.STATE_FEATURES],
self.sorted_state_features,
missing_scalar,
)
next_state = self.extract_float_features(
net,
"next_state",
input_record[InputColumn.NEXT_STATE_FEATURES],
self.sorted_state_features,
missing_scalar,
)
if self.sorted_action_features:
action = self.extract_float_features(
net,
InputColumn.ACTION,
input_record[InputColumn.ACTION],
self.sorted_action_features,
missing_scalar,
)
next_action = self.extract_float_features(
net,
InputColumn.NEXT_ACTION,
input_record[InputColumn.NEXT_ACTION],
self.sorted_action_features,
missing_scalar,
)
if self.include_possible_actions:
possible_action_features = self.extract_float_features(
net,
InputColumn.POSSIBLE_ACTIONS,
input_record[InputColumn.POSSIBLE_ACTIONS]["values"],
self.sorted_action_features,
missing_scalar,
)
possible_next_action_features = self.extract_float_features(
net,
InputColumn.POSSIBLE_NEXT_ACTIONS,
input_record[InputColumn.POSSIBLE_NEXT_ACTIONS]["values"],
self.sorted_action_features,
missing_scalar,
)
else:
action = input_record[InputColumn.ACTION]
next_action = input_record[InputColumn.NEXT_ACTION]
if self.normalize:
C2.set_net_and_init_net(net, init_net)
state, _ = PreprocessorNet().normalize_dense_matrix(
state,
self.sorted_state_features,
self.state_normalization_parameters,
blobname_prefix="state",
split_expensive_feature_groups=True,
)
next_state, _ = PreprocessorNet().normalize_dense_matrix(
next_state,
self.sorted_state_features,
self.state_normalization_parameters,
blobname_prefix="next_state",
split_expensive_feature_groups=True,
)
if self.sorted_action_features is not None:
action, _ = PreprocessorNet().normalize_dense_matrix(
action,
self.sorted_action_features,
self.action_normalization_parameters,
blobname_prefix="action",
split_expensive_feature_groups=True,
)
next_action, _ = PreprocessorNet().normalize_dense_matrix(
next_action,
self.sorted_action_features,
self.action_normalization_parameters,
blobname_prefix="next_action",
split_expensive_feature_groups=True,
)
if self.include_possible_actions:
possible_action_features, _ = PreprocessorNet(
).normalize_dense_matrix(
possible_action_features,
self.sorted_action_features,
self.action_normalization_parameters,
blobname_prefix="possible_action",
split_expensive_feature_groups=True,
)
possible_next_action_features, _ = PreprocessorNet(
).normalize_dense_matrix(
possible_next_action_features,
self.sorted_action_features,
self.action_normalization_parameters,
blobname_prefix="possible_next_action",
split_expensive_feature_groups=True,
)
C2.set_net_and_init_net(None, None)
output_schema = schema.Struct(
(InputColumn.STATE_FEATURES, state),
(InputColumn.NEXT_STATE_FEATURES, next_state),
(InputColumn.ACTION, action),
(InputColumn.NEXT_ACTION, next_action),
(InputColumn.NOT_TERMINAL, input_record[InputColumn.NOT_TERMINAL]),
)
if self.include_possible_actions:
# Drop the "lengths" blob from possible_actions_mask since we know
# it's just a list of [max_num_actions, max_num_actions, ...]
output_schema += schema.Struct(
(
InputColumn.POSSIBLE_ACTIONS_MASK,
input_record[InputColumn.POSSIBLE_ACTIONS_MASK]["values"],
),
(
InputColumn.POSSIBLE_NEXT_ACTIONS_MASK,
input_record[InputColumn.POSSIBLE_NEXT_ACTIONS_MASK]
["values"],
),
)
if self.sorted_action_features is not None:
output_schema += schema.Struct(
(InputColumn.POSSIBLE_ACTIONS, possible_action_features),
(InputColumn.POSSIBLE_NEXT_ACTIONS,
possible_next_action_features),
)
net.set_output_record(output_schema)
return FeatureExtractorNet(net, init_net)
def __init__(self,
name,
input_feature_schema,
trainer_extra_schema,
keep_blobs=False,
use_attribution=True):
''' TODO(amalevich): more documnetation on input args
use_attribution:
if True, will generate the atrribution net for feature importance
calculation; Need to turn it to false when FC is quantized as FP16
This attribute access will be consistent with MTML model.
'''
super(LayerModelHelper, self).__init__(name=name)
self._layer_names = set()
self._layers = []
self._param_to_shape = {}
# seed default
self._seed = None
self._sequence_seed = True
# optimizer bookkeeping
self.param_to_optim = {}
self.param_to_reg = {}
self._default_optimizer = None
self._loss = None
self._prediction = []
self._output_schema = None
self._post_grad_net_modifiers = []
self._final_net_modifiers = []
# breakdown map; breakdown features are categorical (like dense) but not
# necessarily used to represent data for training
self._breakdown_map = None
# Connect Schema to self.net. That particular instance of schmea will be
# use for generation of the Layers across the network and would be used
# for connection with Readers.
self._input_feature_schema = schema.NewRecord(
self.net, input_feature_schema
) if not keep_blobs else input_feature_schema.clone()
self._trainer_extra_schema = schema.NewRecord(
self.net, trainer_extra_schema
) if not keep_blobs else trainer_extra_schema.clone()
self._metrics_schema = schema.Struct()
self._preproc_output_schema = None
self._init_global_constants()
self.param_init_net = self.create_init_net('param_init_net')
self._initialize_params = True
self._transfer_learning_blob_name_mappings = None
# additional (hard-coded) diagnose_options to report based on the model
# TODO(xlwang): it's hack!
self.ad_hoc_diagnose_blobs_and_operations = []
self.ad_hoc_plot_blobs = []
self.use_attribution = use_attribution
def add_metric_field(self, name, value):
assert name not in self._metrics_schema.fields, (
"Try to add metric field twice: {}".format(name))
self._metrics_schema = self._metrics_schema + schema.Struct(
(name, value))
def testDupField(self):
with self.assertRaises(ValueError):
schema.Struct(
('a', schema.Scalar()),
('a', schema.Scalar()))
def testSamplingTrain(self):
output_dims = 1000
indices = self.new_record(schema.Scalar((np.int32, (10,))))
sampling_prob = self.new_record(schema.Scalar((np.float32, (10, ))))
sampled_fc = self.model.SamplingTrain(
schema.Struct(
('input', self.model.input_feature_schema.float_features),
('indices', indices),
('sampling_prob', sampling_prob),
),
"FC",
output_dims,
)
self.model.output_schema = sampled_fc
# Check that we don't add prediction layer into the model
self.assertEqual(1, len(self.model.layers))
self.assertEqual(
schema.Scalar((np.float32, (output_dims, ))),
sampled_fc
)
train_init_net, train_net = self.get_training_nets()
init_ops = self.assertNetContainOps(
train_init_net,
[
OpSpec("UniformFill", None, None),
OpSpec("UniformFill", None, None),
]
)
sampled_fc_layer = self.model.layers[0]
gather_w_spec = OpSpec(
"Gather",
[
init_ops[0].output[0],
indices(),
],
[
sampled_fc_layer._prediction_layer.train_param_blobs[0]
]
)
gather_b_spec = OpSpec(
"Gather",
[
init_ops[1].output[0],
indices(),
],
[
sampled_fc_layer._prediction_layer.train_param_blobs[1]
]
)
train_fc_spec = OpSpec(
"FC",
[
self.model.input_feature_schema.float_features(),
] + sampled_fc_layer._prediction_layer.train_param_blobs,
sampled_fc.field_blobs()
)
log_spec = OpSpec("Log", [sampling_prob()], [None])
sub_spec = OpSpec(
"Sub",
[sampled_fc.field_blobs()[0], None],
sampled_fc.field_blobs()
)
train_ops = self.assertNetContainOps(
train_net,
[gather_w_spec, gather_b_spec, train_fc_spec, log_spec, sub_spec])
self.assertEqual(train_ops[3].output[0], train_ops[4].input[1])
predict_net = self.get_predict_net()
self.assertNetContainOps(
predict_net,
[
OpSpec(
"FC",
[
self.model.input_feature_schema.float_features(),
init_ops[0].output[0],
init_ops[1].output[0],
],
sampled_fc.field_blobs()
)
]
)
def testNormalizeField(self):
s = schema.Struct(('field1', np.int32), ('field2', str))
self.assertEquals(
s,
schema.Struct(('field1', schema.Scalar(dtype=np.int32)),
('field2', schema.Scalar(dtype=str))))
