def add_ops(self, net):
prediction = net.Squeeze(self.input_record.prediction(),
net.NextScopedBlob('squeezed_prediction'),
dims=[1])
label = self.input_record.label.field_blobs()
if self.input_record.label.field_type().base != (
self.input_record.prediction.field_type().base):
label = net.Cast(label,
net.NextScopedBlob('cast_label'),
to=schema.data_type_for_dtype(
self.input_record.prediction.field_type()))
const_delta = net.ConstantFill(
label,
net.NextScopedBlob("delta"),
value=self._delta,
dtype=core.DataType.FLOAT,
)
label = net.StopGradient(label, net.NextScopedBlob('stopped_label'))
const_delta = net.StopGradient(const_delta,
net.NextScopedBlob('stopped_delta'))
# abs_error = np.abs(true - pred)
abs_error = net.L1Distance([label, prediction],
net.NextScopedBlob("abs_error"))
# quadratic = 0.5*min(abs_error, delta)^2, linear = delta*max(abs_error-delta, 0)
min_error = net.Min([abs_error, const_delta],
net.NextScopedBlob("min_error_delta"))
quadratic_term = net.Scale(net.Sqr(min_error), scale=float(0.5))
linear_term = net.Mul([
net.Sub([abs_error, min_error]),
const_delta,
], net.NextScopedBlob("huber_linear_term"))
# huber = 0.5 * min(abs_error, delta)^2 + delta * max(abs_error-delta, 0)
huber_dist = net.Add([quadratic_term, linear_term],
net.NextScopedBlob("huber_dist"))
if 'weight' in self.input_record.fields:
weight_blob = self.input_record.weight()
if self.input_record.weight.field_type().base != np.float32:
weight_blob = net.Cast(weight_blob,
weight_blob + '_float32',
to=core.DataType.FLOAT)
weight_blob = net.StopGradient(
[weight_blob],
[net.NextScopedBlob('weight_stop_gradient')],
)
huber_dist = net.Mul(
[huber_dist, weight_blob],
net.NextScopedBlob("weighted_huber_distance"),
)
net.AveragedLoss(huber_dist, self.output_schema.field_blobs())
def add_ops(self, net):
prediction = net.Squeeze(
self.input_record.prediction(),
net.NextScopedBlob('squeezed_prediction'),
dims=[1]
)
label = self.input_record.label.field_blobs()
if self.input_record.label.field_type().base != (
self.input_record.prediction.field_type().base):
label = net.Cast(
label,
net.NextScopedBlob('cast_label'),
to=schema.data_type_for_dtype(
self.input_record.prediction.field_type()
)
)
label = net.StopGradient(
label,
net.NextScopedBlob('stopped_label')
)
l2dist = net.SquaredL2Distance(
[label, prediction],
net.NextScopedBlob('l2')
)
net.AveragedLoss(l2dist, self.output_schema.field_blobs())
def add_ops(self, net):
prediction = net.Squeeze(
self.input_record.prediction(),
net.NextScopedBlob('squeezed_prediction'),
dims=[1]
)
label = self.input_record.label.field_blobs()
if self.input_record.label.field_type().base != (
self.input_record.prediction.field_type().base):
label = net.Cast(
label,
net.NextScopedBlob('cast_label'),
to=schema.data_type_for_dtype(
self.input_record.prediction.field_type()
)
)
label = net.StopGradient(
label,
net.NextScopedBlob('stopped_label')
)
l2dist = net.SquaredL2Distance(
[label, prediction],
net.NextScopedBlob('l2')
)
net.AveragedLoss(l2dist, self.output_schema.field_blobs())
def __init__(self, init_net, filename, schema, num_passes=1, batch_size=1):
"""
Create op for building a TextFileReader instance in the workspace.
Args:
init_net : Net that will be run only once at startup.
filename : Path to file to read from.
schema : schema.Struct representing the schema of the data.
Currently, only support Struct of strings.
num_passes : Number of passes over the data.
batch_size : Number of rows to read at a time.
"""
assert isinstance(schema, Struct), 'Schema must be a schema.Struct'
for name, child in schema.get_children():
assert isinstance(child, Scalar), (
'Only scalar fields are supported in TextFileReader.')
field_types = [
data_type_for_dtype(dtype) for dtype in schema.field_types()]
Reader.__init__(self, schema)
self._reader = init_net.CreateTextFileReader(
[],
filename=filename,
num_passes=num_passes,
field_types=field_types)
self._batch_size = batch_size
def add_ops(self, net):
prediction = net.Squeeze(self.input_record.prediction(),
net.NextScopedBlob('squeezed_prediction'),
dims=[1])
label = self.input_record.label.field_blobs()
if self.input_record.label.field_type().base != (
self.input_record.prediction.field_type().base):
label = net.Cast(label,
net.NextScopedBlob('cast_label'),
to=schema.data_type_for_dtype(
self.input_record.prediction.field_type()))
label = net.StopGradient(label, net.NextScopedBlob('stopped_label'))
l2dist = net.SquaredL2Distance([label, prediction],
net.NextScopedBlob('l2'))
if 'weight' in self.input_record.fields:
weight_blob = self.input_record.weight()
if self.input_record.weight.field_type().base != np.float32:
weight_blob = net.Cast(weight_blob,
weight_blob + '_float32',
to=core.DataType.FLOAT)
weight_blob = net.StopGradient(
[weight_blob],
[net.NextScopedBlob('weight_stop_gradient')],
)
l2dist = net.Mul(
[l2dist, weight_blob],
net.NextScopedBlob('weighted_l2_distance'),
)
net.AveragedLoss(l2dist, self.output_schema.field_blobs())
def __init__(self, init_net, filename, schema, num_passes=1, batch_size=1):
"""
Create op for building a HiveReader instance in the workspace.
Args:
init_net : Net that will be run only once at startup.
filename : Path to file to read from.
schema : schema.Struct representing the schema of the data.
Currently, only support Struct of strings.
num_passes : Number of passes over the data.
batch_size : Number of rows to read at a time.
"""
assert isinstance(schema, Struct), 'Schema must be a schema.Struct'
for name, child in schema.get_children():
assert isinstance(child, Scalar), (
'Only scalar fields are supported in TextFileReader.')
field_types = [
data_type_for_dtype(dtype) for dtype in schema.field_types()]
Reader.__init__(self, schema)
self._reader = init_net.CreateTextFileReader(
[],
filename=filename,
num_passes=num_passes,
field_types=field_types)
self._batch_size = batch_size
def add_ops(self, net):
prediction = self.input_record.prediction()
label = self.input_record.label.field_blobs()
if self.input_record.label.field_type().base != (
self.input_record.prediction.field_type().base):
label = net.Cast(label,
net.NextScopedBlob('cast_label'),
to=schema.data_type_for_dtype(
self.input_record.prediction.field_type()))
label = net.StopGradient(label, net.NextScopedBlob('stopped_label'))
l1dist = net.L1Distance([label, prediction],
net.NextScopedBlob('l1_dist'))
net.AveragedLoss(l1dist, self.output_schema.l1_metric())
scaler, scaler_no_clip = net.ScaleWithClip(
[label],
[
net.NextScopedBlob('scaler'),
net.NextScopedBlob('scaler_no_clip')
],
max_scale=self.max_scale,
)
scaler = net.StopGradient(scaler, net.NextScopedBlob('stopped_scaler'))
scaler_no_clip = net.StopGradient(
scaler_no_clip, net.NextScopedBlob('stopped_scaler_no_clip'))
scaler = net.Squeeze(scaler,
net.NextScopedBlob('squeezed_scaler'),
dims=[1])
scaler_no_clip = net.Squeeze(
scaler_no_clip,
net.NextScopedBlob('squeezed_scaler_no_clip'),
dims=[1])
scaled_loss = net.Mul([l1dist, scaler],
net.NextScopedBlob('scaled_loss'))
scaled_loss_no_clip = net.Mul(
[l1dist, scaler_no_clip],
net.NextScopedBlob('scaled_loss_no_clip'))
net.AveragedLoss(scaled_loss, self.output_schema.loss())
net.AveragedLoss(scaled_loss_no_clip,
self.output_schema.scaled_l1_metric())
def _store_parameter(self, parameters, name, value):
c2_name = C2.NextBlob(name)
if C2.init_net():
C2.init_net().GivenTensorFill(
[],
c2_name,
shape=value.shape,
values=value.flatten(),
dtype=schema.data_type_for_dtype(value.dtype),
)
C2.init_net().AddExternalOutput(c2_name)
else:
workspace.FeedBlob(c2_name, value)
parameters.append(c2_name)
return c2_name
def add_ops(self, net):
prediction = net.Squeeze(
self.input_record.prediction(),
net.NextScopedBlob('squeezed_prediction'),
dims=[1]
)
label = self.input_record.label.field_blobs()
if self.input_record.label.field_type().base != (
self.input_record.prediction.field_type().base):
label = net.Cast(
label,
net.NextScopedBlob('cast_label'),
to=schema.data_type_for_dtype(
self.input_record.prediction.field_type()
)
)
label = net.StopGradient(
label,
net.NextScopedBlob('stopped_label')
)
l2dist = net.SquaredL2Distance(
[label, prediction],
net.NextScopedBlob('l2')
)
if 'weight' in self.input_record.fields:
weight_blob = self.input_record.weight()
if self.input_record.weight.field_type().base != np.float32:
weight_blob = net.Cast(
weight_blob,
weight_blob + '_float32',
to=core.DataType.FLOAT
)
weight_blob = net.StopGradient(
[weight_blob],
[net.NextScopedBlob('weight_stop_gradient')],
)
l2dist = net.Mul(
[l2dist, weight_blob],
net.NextScopedBlob('weighted_l2_distance'),
)
net.AveragedLoss(l2dist, self.output_schema.field_blobs())