def esmm_model_fn(features, labels, mode, params):
wt = tf.feature_column.input_layer(features, params['weight_columns'])
mmoe_scope = 'mmoe'
multi_inputs, weights_shared = build_mmoe(features, params, mmoe_scope)
hidden_units = params['hidden_units']
linear_parent_scope = 'linear'
dnn_parent_scope = 'dnn'
is_dynamic = params['dynamic']
print("is_dynamic:", is_dynamic)
reg = 1e-4
dnn_scope = 'dnn'
with tf.variable_scope(dnn_scope):
ctr_logits = build_deep_layers(multi_inputs[0], hidden_units, mode, 'CTR', reg)
cvr_logits = build_deep_layers(multi_inputs[1], hidden_units, mode, 'CVR', reg)
ctr_preds = tf.nn.sigmoid(ctr_logits)
cvr_preds = tf.nn.sigmoid(cvr_logits)
ctcvr_preds = ctr_preds * cvr_preds
tf.summary.histogram("esmm/ctr_preds", ctr_preds)
tf.summary.histogram("esmm/cvr_preds", cvr_preds)
tf.summary.histogram("esmm/ctcvr_preds", ctcvr_preds)
if mode == tf.estimator.ModeKeys.PREDICT:
#redundant_items = ctr_preds
predictions = {
'prob': tf.concat([cvr_preds, ctr_preds], 1)
}
export_outputs = {
tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY: tf.estimator.export.PredictOutput(predictions) #线上预测需要的
}
return tf.estimator.EstimatorSpec(mode, predictions=predictions, export_outputs=export_outputs)
else:
ctr_labels = labels['ctr']
ctcvr_labels = labels['ctcvr']
linear_optimizer = tf.train.FtrlOptimizer(0.01, l1_regularization_strength=0.001, l2_regularization_strength=0.001)
dnn_optimizer = optimizers.get_optimizer_instance('Adam', params['learning_rate'])
loss_optimizer = optimizers.get_optimizer_instance('Adam', 0.001)
ctr_loss = tf.losses.log_loss(ctr_labels, ctr_preds, reduction=tf.losses.Reduction.SUM_OVER_BATCH_SIZE, weights=wt)
ctcvr_loss = tf.losses.log_loss(ctcvr_labels, ctcvr_preds, reduction=tf.losses.Reduction.SUM_OVER_BATCH_SIZE)
#reg_loss = tf.reduce_sum(ops.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES))
ctr_auc = tf.metrics.auc(labels=ctr_labels, predictions=ctr_preds, weights=wt)
ctcvr_auc = tf.metrics.auc(labels=ctcvr_labels, predictions=ctcvr_preds)
mask = tf.map_fn(lambda x:tf.cond(tf.equal(x, 1), lambda: True, lambda: False), tf.squeeze(labels['ctr']), dtype=tf.bool)
cvr_preds = tf.boolean_mask(cvr_preds, mask)
cvr_labels = tf.boolean_mask(labels['ctcvr'], mask)
cvr_auc = tf.metrics.auc(labels=cvr_labels, predictions=cvr_preds)
cvr_loss = tf.losses.log_loss(cvr_labels, cvr_preds, reduction=tf.losses.Reduction.SUM_OVER_NONZERO_WEIGHTS)
tf.summary.scalar("cvr_auc", cvr_auc[1])
tf.summary.scalar("cvr_loss", cvr_loss)
tf.summary.scalar('ctr_loss', ctr_loss)
tf.summary.scalar('ctcvr_loss', ctcvr_loss)
tf.summary.scalar('ctr_auc', ctr_auc[1])
tf.summary.scalar('ctcvr_auc', ctcvr_auc[1])
weight_loss, update_list, w_list, loss_gradnorm = get_weight_loss([ctr_loss, ctcvr_loss], is_dynamic, weights_shared)
#loss = tf.add_n(weight_loss + [reg_loss])
loss = tf.add_n(weight_loss)
#loss = weight_loss
#w_list = ops.get_collection(ops.GraphKeys.TRAINABLE_VARIABLES, scope='grad_weight')
def _train_op_fn(loss):
train_ops = []
global_step = tf.train.get_global_step()
if params['model'] in ('dnn'):
fm_var_list = ops.get_collection(ops.GraphKeys.TRAINABLE_VARIABLES, scope='fm')
dnn_var_list = ops.get_collection(ops.GraphKeys.TRAINABLE_VARIABLES, scope=dnn_scope) + ops.get_collection(ops.GraphKeys.TRAINABLE_VARIABLES, scope='dnn_embed') + ops.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope=mmoe_scope)
train_ops.append(
dnn_optimizer.minimize(
loss,
var_list=dnn_var_list))
train_ops.append(
linear_optimizer.minimize(
loss,
var_list=fm_var_list))
if w_list is not None and loss_gradnorm is not None:
train_ops.append(
loss_optimizer.minimize(
loss_gradnorm,
var_list=w_list))
if update_list is not None:
train_ops.append(update_list)
train_op = control_flow_ops.group(*train_ops)
with ops.control_dependencies([train_op]):
return state_ops.assign_add(global_step, 1).op
hooks = tf.train.LoggingTensorHook({'ctr_loss':ctr_loss, 'ctcvr_loss':ctcvr_loss, 'cvr_loss':cvr_loss}, every_n_iter=10000)
train_op = _train_op_fn(loss)
train_op = head_v1._append_update_ops(train_op)
metrics = {'ctr_auc': ctr_auc, 'ctcvr_auc': ctcvr_auc, 'cvr_auc': cvr_auc}
#return _TPUEstimatorSpec(mode, loss=loss, train_op=train_op).as_estimator_spec()
return tf.estimator.EstimatorSpec(mode, loss=loss, train_op=train_op, eval_metric_ops=metrics)
def _create_tpu_estimator_spec(self,
features,
mode,
logits,
labels=None,
optimizer=None,
train_op_fn=None,
regularization_losses=None):
"""Returns an `model_fn._TPUEstimatorSpec`.
Args:
features: Input `dict` of `Tensor` or `SparseTensor` objects.
mode: Estimator's `ModeKeys`.
logits: logits `Tensor` with shape `[D0, D1, ... DN, n_classes]`.
For many applications, the shape is `[batch_size, n_classes]`.
labels: Labels with shape matching `logits`. Can be multi-hot `Tensor`
with shape `[D0, D1, ... DN, n_classes]` or `SparseTensor` with
`dense_shape` `[D0, D1, ... DN, ?]`. `labels` is required argument when
`mode` equals `TRAIN` or `EVAL`.
optimizer: `Optimizer` instance to optimize the loss in TRAIN mode.
Namely, sets `train_op = optimizer.minimize(loss, global_step)`, which
updates variables and increments `global_step`.
train_op_fn: Function that takes a scalar loss `Tensor` and returns
`train_op`. Used if `optimizer` is `None`.
regularization_losses: A list of additional scalar losses to be added to
the training loss, such as regularization losses. These losses are
usually expressed as a batch average, so for best results users need to
set `loss_reduction=SUM_OVER_BATCH_SIZE` or
`loss_reduction=SUM_OVER_NONZERO_WEIGHTS` when creating the head to
avoid scaling errors.
Returns:
`model_fn._TPUEstimatorSpec`.
Raises:
ValueError: If both `train_op_fn` and `optimizer` are `None` in TRAIN
mode, or if both are set.
"""
with ops.name_scope(self._name, 'head'):
logits = head_lib._check_logits_final_dim(logits,
self.logits_dimension) # pylint:disable=protected-access
# Predict.
pred_keys = prediction_keys.PredictionKeys
with ops.name_scope(None, 'predictions', (logits, )):
probabilities = math_ops.sigmoid(logits,
name=pred_keys.PROBABILITIES)
predictions = {
pred_keys.LOGITS: logits,
pred_keys.PROBABILITIES: probabilities,
}
if mode == model_fn.ModeKeys.PREDICT:
classifier_output = head_lib._classification_output( # pylint:disable=protected-access
scores=probabilities,
n_classes=self._n_classes,
label_vocabulary=self._label_vocabulary)
return model_fn._TPUEstimatorSpec( # pylint:disable=protected-access
mode=model_fn.ModeKeys.PREDICT,
predictions=predictions,
export_outputs={
_DEFAULT_SERVING_KEY: classifier_output,
head_lib._CLASSIFY_SERVING_KEY: classifier_output, # pylint:disable=protected-access
head_lib._PREDICT_SERVING_KEY: ( # pylint:disable=protected-access
export_output.PredictOutput(predictions))
})
(training_loss, unreduced_loss, weights,
processed_labels) = self.create_loss(features=features,
mode=mode,
logits=logits,
labels=labels)
if regularization_losses:
regularization_loss = math_ops.add_n(regularization_losses)
regularized_training_loss = math_ops.add_n(
[training_loss, regularization_loss])
else:
regularization_loss = None
regularized_training_loss = training_loss
# Eval.
if mode == model_fn.ModeKeys.EVAL:
return model_fn._TPUEstimatorSpec( # pylint:disable=protected-access
mode=model_fn.ModeKeys.EVAL,
predictions=predictions,
loss=regularized_training_loss,
eval_metrics=head_lib._create_eval_metrics_tuple( # pylint:disable=protected-access
self._eval_metric_ops, {
'labels': processed_labels,
'probabilities': probabilities,
'weights': weights,
'unreduced_loss': unreduced_loss,
'regularization_loss': regularization_loss,
}))
# Train.
if optimizer is not None:
if train_op_fn is not None:
raise ValueError(
'train_op_fn and optimizer cannot both be set.')
train_op = optimizer.minimize(
regularized_training_loss,
global_step=training_util.get_global_step())
elif train_op_fn is not None:
train_op = train_op_fn(regularized_training_loss)
else:
raise ValueError(
'train_op_fn and optimizer cannot both be None.')
train_op = head_lib._append_update_ops(train_op) # pylint:disable=protected-access
# Only summarize mean_loss for SUM reduction to preserve backwards
# compatibility. Otherwise skip it to avoid unnecessary computation.
if self._loss_reduction == losses.Reduction.SUM:
example_weight_sum = math_ops.reduce_sum(
weights * array_ops.ones_like(unreduced_loss))
mean_loss = training_loss / example_weight_sum
else:
mean_loss = None
with ops.name_scope(''):
keys = metric_keys.MetricKeys
summary.scalar(
head_lib._summary_key(self._name, keys.LOSS), # pylint:disable=protected-access
regularized_training_loss)
if mean_loss is not None:
summary.scalar(
head_lib._summary_key(self._name, keys.LOSS_MEAN), # pylint:disable=protected-access
mean_loss)
if regularization_loss is not None:
summary.scalar(
head_lib._summary_key(self._name,
keys.LOSS_REGULARIZATION), # pylint:disable=protected-access
regularization_loss)
return model_fn._TPUEstimatorSpec( # pylint:disable=protected-access
mode=model_fn.ModeKeys.TRAIN,
predictions=predictions,
loss=regularized_training_loss,
train_op=train_op)
def _create_tpu_estimator_spec(
self, features, mode, logits, labels=None, optimizer=None,
train_op_fn=None, regularization_losses=None):
"""Returns an `model_fn._TPUEstimatorSpec`.
Args:
features: Input `dict` of `Tensor` or `SparseTensor` objects.
mode: Estimator's `ModeKeys`.
logits: logits `Tensor` with shape `[D0, D1, ... DN, n_classes]`.
For many applications, the shape is `[batch_size, n_classes]`.
labels: Labels with shape matching `logits`. Can be multi-hot `Tensor`
with shape `[D0, D1, ... DN, n_classes]` or `SparseTensor` with
`dense_shape` `[D0, D1, ... DN, ?]`. `labels` is required argument when
`mode` equals `TRAIN` or `EVAL`.
optimizer: `Optimizer` instance to optimize the loss in TRAIN mode.
Namely, sets `train_op = optimizer.minimize(loss, global_step)`, which
updates variables and increments `global_step`.
train_op_fn: Function that takes a scalar loss `Tensor` and returns
`train_op`. Used if `optimizer` is `None`.
regularization_losses: A list of additional scalar losses to be added to
the training loss, such as regularization losses. These losses are
usually expressed as a batch average, so for best results users need to
set `loss_reduction=SUM_OVER_BATCH_SIZE` or
`loss_reduction=SUM_OVER_NONZERO_WEIGHTS` when creating the head to
avoid scaling errors.
Returns:
`model_fn._TPUEstimatorSpec`.
Raises:
ValueError: If both `train_op_fn` and `optimizer` are `None` in TRAIN
mode, or if both are set.
"""
with ops.name_scope(self._name, 'head'):
logits = head_lib._check_logits_final_dim(logits, self.logits_dimension) # pylint:disable=protected-access
# Predict.
pred_keys = prediction_keys.PredictionKeys
with ops.name_scope(None, 'predictions', (logits,)):
probabilities = math_ops.sigmoid(logits, name=pred_keys.PROBABILITIES)
predictions = {
pred_keys.LOGITS: logits,
pred_keys.PROBABILITIES: probabilities,
}
if mode == model_fn.ModeKeys.PREDICT:
classifier_output = head_lib._classification_output( # pylint:disable=protected-access
scores=probabilities, n_classes=self._n_classes,
label_vocabulary=self._label_vocabulary)
return model_fn._TPUEstimatorSpec( # pylint:disable=protected-access
mode=model_fn.ModeKeys.PREDICT,
predictions=predictions,
export_outputs={
_DEFAULT_SERVING_KEY: classifier_output,
head_lib._CLASSIFY_SERVING_KEY: classifier_output, # pylint:disable=protected-access
head_lib._PREDICT_SERVING_KEY: ( # pylint:disable=protected-access
export_output.PredictOutput(predictions))
})
(training_loss, unreduced_loss, weights,
processed_labels) = self.create_loss(
features=features, mode=mode, logits=logits, labels=labels)
if regularization_losses:
regularization_loss = math_ops.add_n(regularization_losses)
regularized_training_loss = math_ops.add_n(
[training_loss, regularization_loss])
else:
regularization_loss = None
regularized_training_loss = training_loss
# Eval.
if mode == model_fn.ModeKeys.EVAL:
return model_fn._TPUEstimatorSpec( # pylint:disable=protected-access
mode=model_fn.ModeKeys.EVAL,
predictions=predictions,
loss=regularized_training_loss,
eval_metrics=head_lib._create_eval_metrics_tuple( # pylint:disable=protected-access
self._eval_metric_ops, {
'labels': processed_labels,
'probabilities': probabilities,
'weights': weights,
'unreduced_loss': unreduced_loss,
'regularization_loss': regularization_loss,
}))
# Train.
if optimizer is not None:
if train_op_fn is not None:
raise ValueError('train_op_fn and optimizer cannot both be set.')
train_op = optimizer.minimize(
regularized_training_loss,
global_step=training_util.get_global_step())
elif train_op_fn is not None:
train_op = train_op_fn(regularized_training_loss)
else:
raise ValueError('train_op_fn and optimizer cannot both be None.')
train_op = head_lib._append_update_ops(train_op) # pylint:disable=protected-access
# Only summarize mean_loss for SUM reduction to preserve backwards
# compatibility. Otherwise skip it to avoid unnecessary computation.
if self._loss_reduction == losses.Reduction.SUM:
example_weight_sum = math_ops.reduce_sum(
weights * array_ops.ones_like(unreduced_loss))
mean_loss = training_loss / example_weight_sum
else:
mean_loss = None
with ops.name_scope(''):
keys = metric_keys.MetricKeys
summary.scalar(
head_lib._summary_key(self._name, keys.LOSS), # pylint:disable=protected-access
regularized_training_loss)
if mean_loss is not None:
summary.scalar(
head_lib._summary_key(self._name, keys.LOSS_MEAN), # pylint:disable=protected-access
mean_loss)
if regularization_loss is not None:
summary.scalar(
head_lib._summary_key(self._name, keys.LOSS_REGULARIZATION), # pylint:disable=protected-access
regularization_loss)
return model_fn._TPUEstimatorSpec( # pylint:disable=protected-access
mode=model_fn.ModeKeys.TRAIN,
predictions=predictions,
loss=regularized_training_loss,
train_op=train_op)
def esmm_model_fn(features, labels, mode, params):
batch_weight = tf.feature_column.input_layer(features,
params['weight_columns'])
inputs, shared_weights = build_input(features, params)
hidden_units = params['hidden_units']
linear_parent_scope = 'linear'
dnn_parent_scope = 'dnn'
is_dynamic = params['dynamic']
print("is_dynamic:", is_dynamic)
reg = 1e-4
if params['model'] == 'linear':
with tf.variable_scope(linear_parent_scope,
values=tuple(six.itervalues(features)),
reuse=tf.AUTO_REUSE):
with tf.variable_scope('linear_ctr'):
ctr_logit_fn = linear._linear_logit_fn_builder(
1, params['linear_columns'])
ctr_logits = ctr_logit_fn(features=features)
with tf.variable_scope('linear_cvr'):
cvr_logit_fn = linear._linear_logit_fn_builder(
1, params['linear_columns'])
cvr_logits = cvr_logit_fn(features=features)
if params['model'] == 'dnn':
with tf.variable_scope(dnn_parent_scope):
with tf.variable_scope('dnn_ctr'):
ctr_logits = build_deep_layers(inputs, hidden_units, mode,
params['ctr_reg'])
#ctr_logit_fn = dnn._dnn_logit_fn_builder(1, hidden_units, params['dnn_columns'], tf.nn.relu, None, None, True)
#ctr_logits = ctr_logit_fn(features=features, mode=mode)
with tf.variable_scope('dnn_cvr'):
cvr_logits = build_deep_layers(inputs, hidden_units, mode,
params['cvr_reg'])
#cvr_logit_fn = dnn._dnn_logit_fn_builder(1, hidden_units, params['dnn_columns'], tf.nn.relu, None, None, True)
#cvr_logits = cvr_logit_fn(features=features, mode=mode)
ctr_preds = tf.nn.sigmoid(ctr_logits)
cvr_preds = tf.nn.sigmoid(cvr_logits)
#ctcvr_preds = tf.stop_gradient(ctr_preds) * cvr_preds
ctcvr_preds = ctr_preds * cvr_preds
tf.summary.histogram("esmm/ctr_preds", ctr_preds)
tf.summary.histogram("esmm/ctcvr_preds", ctcvr_preds)
if mode == tf.estimator.ModeKeys.PREDICT:
#redundant_items = ctr_preds
predictions = {'prob': tf.concat([ctcvr_preds, ctr_preds], 1)}
export_outputs = {
tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY:
tf.estimator.export.PredictOutput(predictions) #线上预测需要的
}
return tf.estimator.EstimatorSpec(mode,
predictions=predictions,
export_outputs=export_outputs)
else:
ctr_labels = labels['ctr']
ctcvr_labels = labels['ctcvr']
linear_optimizer = tf.train.FtrlOptimizer(
0.01,
l1_regularization_strength=0.001,
l2_regularization_strength=0.001)
dnn_optimizer = optimizers.get_optimizer_instance(
'Adam', params['learning_rate'])
loss_optimizer = optimizers.get_optimizer_instance('Adam', 0.001)
ctr_loss = tf.losses.log_loss(
ctr_labels,
ctr_preds,
reduction=tf.losses.Reduction.SUM_OVER_BATCH_SIZE,
weights=batch_weight)
ctcvr_loss = tf.losses.log_loss(
ctcvr_labels,
ctcvr_preds,
reduction=tf.losses.Reduction.SUM_OVER_BATCH_SIZE)
#reg_loss = tf.reduce_sum(ops.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES))
ctr_auc = tf.metrics.auc(labels=ctr_labels,
predictions=ctr_preds,
weights=batch_weight)
ctcvr_auc = tf.metrics.auc(labels=ctcvr_labels,
predictions=ctcvr_preds)
tf.summary.scalar('ctr_loss', ctr_loss)
tf.summary.scalar('ctcvr_loss', ctcvr_loss)
tf.summary.scalar('ctr_auc', ctr_auc[1])
tf.summary.scalar('ctcvr_auc', ctcvr_auc[1])
weight_loss, update_list, w_list, loss_gradnorm = get_weight_loss(
[ctr_loss, ctcvr_loss], is_dynamic, shared_weights)
#loss = tf.add_n(weight_loss + [reg_loss])
loss = tf.add_n(weight_loss)
#loss = weight_loss
#w_list = ops.get_collection(ops.GraphKeys.TRAINABLE_VARIABLES, scope='grad_weight')
def _train_op_fn(loss):
train_ops = []
global_step = tf.train.get_global_step()
if params['model'] in ('dnn'):
fm_var_list = ops.get_collection(
ops.GraphKeys.TRAINABLE_VARIABLES, scope='fm')
dnn_var_list = ops.get_collection(
ops.GraphKeys.TRAINABLE_VARIABLES,
scope=dnn_parent_scope) + ops.get_collection(
ops.GraphKeys.TRAINABLE_VARIABLES, scope='dnn_embed')
train_ops.append(
dnn_optimizer.minimize(loss, var_list=dnn_var_list))
train_ops.append(
linear_optimizer.minimize(loss, var_list=fm_var_list))
if params['model'] in ('linear'):
train_ops.append(
linear_optimizer.minimize(
loss,
var_list=ops.get_collection(
ops.GraphKeys.TRAINABLE_VARIABLES,
scope=linear_parent_scope)))
if w_list is not None and loss_gradnorm is not None:
train_ops.append(
loss_optimizer.minimize(loss_gradnorm, var_list=w_list))
if update_list is not None:
train_ops.append(update_list)
train_op = control_flow_ops.group(*train_ops)
with ops.control_dependencies([train_op]):
return state_ops.assign_add(global_step, 1).op
train_op = _train_op_fn(loss)
train_op = head_v1._append_update_ops(train_op)
metrics = {'ctr_auc': ctr_auc, 'ctcvr_auc': ctcvr_auc}
#return _TPUEstimatorSpec(mode, loss=loss, train_op=train_op).as_estimator_spec()
return tf.estimator.EstimatorSpec(mode,
loss=loss,
train_op=train_op,
eval_metric_ops=metrics)