def _valid_step(model: tf.keras.Model, dataset: tf.data.Dataset, progress_bar: ProgressBar,
loss_metric: tf.keras.metrics.Mean, max_train_steps: Any = -1) -> Dict:
""" 验证步
:param model: 验证模型
:param dataset: 验证数据集
:param progress_bar: 进度管理器
:param loss_metric: 损失计算器
:param max_train_steps: 验证步数
:return: 验证指标
"""
print("验证轮次")
start_time = time.time()
loss_metric.reset_states()
result, targets = tf.convert_to_tensor([], dtype=tf.float32), tf.convert_to_tensor([], dtype=tf.int32)
for (batch, (first_queries, second_queries, labels)) in enumerate(dataset.take(max_train_steps)):
outputs = model(inputs=[first_queries, second_queries])
loss = tf.keras.losses.SparseCategoricalCrossentropy()(labels, outputs)
loss_metric(loss)
result = tf.concat([result, outputs[:, 1]], axis=0)
targets = tf.concat([targets, labels], axis=0)
progress_bar(current=batch + 1, metrics=get_dict_string(data={"valid_loss": loss_metric.result()}))
auc_score = roc_auc_score(y_true=targets, y_score=result)
progress_bar(current=progress_bar.total, metrics=get_dict_string(
data={"valid_loss": loss_metric.result(), "valid_auc": auc_score}
))
progress_bar.done(step_time=time.time() - start_time)
return {"valid_loss": loss_metric.result(), "valid_auc": auc_score}
def _validate_step(self,
inputs: tf.Tensor,
labels: tf.Tensor,
masks: tf.Tensor,
loss_tensor: tf.keras.metrics.Mean,
training: bool = False) -> float:
predictions = self.call(inputs, training=training)
loss = self.loss_fn(predictions, labels, masks)
loss_tensor.update_state(loss)
return loss
def __validation_step(X: tf.Tensor, y: tf.Tensor, model: tf.keras.Model,
loss_fn: tf.keras.losses.Loss,
loss: tf.keras.metrics.Mean,
metrics: List[tf.keras.metrics.Metric]) -> None:
logits = model(X, training=False)
loss_value = loss_fn(y, logits)
loss.update_state(loss_value)
for metric in metrics:
metric.update_state(y, logits)
def _valid_step(model: tf.keras.Model,
dataset: tf.data.Dataset,
progress_bar: ProgressBar,
batch_size: Any,
loss_metric: tf.keras.metrics.Mean,
max_train_steps: Any = -1) -> Dict:
""" 验证步
:param model: 验证模型
:param dataset: 验证数据集
:param progress_bar: 进度管理器
:param batch_size: batch大小
:param loss_metric: 损失计算器
:param max_train_steps: 验证步数
:return: 验证指标
"""
print("验证轮次")
start_time = time.time()
loss_metric.reset_states()
result, targets = tf.convert_to_tensor(
[], dtype=tf.float32), tf.convert_to_tensor([], dtype=tf.int32)
for (batch, (queries, _, true_outputs,
labels)) in enumerate(dataset.take(max_train_steps)):
outputs = model(inputs=queries)
loss = tf.keras.losses.SparseCategoricalCrossentropy(
reduction=tf.keras.losses.Reduction.NONE)(true_outputs, outputs)
mask = tf.cast(x=tf.math.not_equal(true_outputs, 0), dtype=tf.float32)
batch_loss = tf.reduce_sum(mask * loss) / batch_size
loss_metric(batch_loss)
result = tf.concat(
[result,
tf.nn.softmax(logits=outputs[:, 0, 5:7], axis=-1)[:, 1]],
axis=0)
targets = tf.concat([targets, labels], axis=0)
progress_bar(
current=batch + 1,
metrics=get_dict_string(data={"valid_loss": loss_metric.result()}))
auc_score = roc_auc_score(y_true=targets, y_score=result)
progress_bar(current=progress_bar.total,
metrics=get_dict_string(data={
"valid_loss": loss_metric.result(),
"valid_auc": auc_score
}))
progress_bar.done(step_time=time.time() - start_time)
return {"valid_loss": loss_metric.result(), "valid_auc": auc_score}
def _train_step(model: tf.keras.Model, optimizer: tf.keras.optimizers.Adam,
loss_metric: tf.keras.metrics.Mean, train_enc: Any,
train_dec: Any, month_enc: Any, month_dec: Any,
labels: Any) -> Tuple:
""" 单个训练步
:param model: 训练模型
:param optimizer: 优化器
:param loss_metric: 损失计算器
:param train_enc: enc输入
:param train_dec: dec输入
:param month_enc: enc月份输入
:param month_dec: dec月份输入
:param labels: 标签
:return: 训练指标
"""
with tf.GradientTape() as tape:
train_enc = tf.squeeze(train_enc, axis=0)
train_dec = tf.squeeze(train_dec, axis=0)
outputs = model(inputs=[train_enc, train_dec, month_enc, month_dec])
treat_outputs = tf.squeeze(input=outputs[:, -24:, :], axis=-1)
loss = tf.keras.losses.mean_squared_error(labels, treat_outputs)
# acikill_metrics = eval_score(preds=outputs, label=labels)
loss_metric(loss)
variables = model.trainable_variables
gradients = tape.gradient(target=loss, sources=variables)
optimizer.apply_gradients(zip(gradients, variables))
return {"train_loss": loss_metric.result()}, treat_outputs
def __train_step(X: tf.Tensor, y: tf.Tensor, model: tf.keras.Model,
optimizer: tf.keras.optimizers.Optimizer,
loss_fn: tf.keras.losses.Loss, loss: tf.keras.metrics.Mean,
metrics: List[tf.keras.metrics.Metric]) -> None:
with tf.GradientTape() as tape:
logits = model(X, training=True)
loss_value = loss_fn(y, logits)
optimizer.apply_gradients(
zip(tape.gradient(loss_value, model.trainable_variables),
model.trainable_variables))
loss.update_state(loss_value)
for metric in metrics:
metric.update_state(y, logits)
def _train_step(model: tf.keras.Model, optimizer: tf.keras.optimizers.Adam,
batch_size: Any, loss_metric: tf.keras.metrics.Mean,
queries: Any, targets: Any) -> Tuple:
""" 单个训练步
:param model: 训练模型
:param optimizer: 优化器
:param batch_size: batch大小
:param loss_metric: 损失计算器
:param queries: 第一个查询句子
:param targets: 第二个查询句子
:return: 训练指标
"""
with tf.GradientTape() as tape:
outputs = model(inputs=queries)
loss = tf.keras.losses.SparseCategoricalCrossentropy(
reduction=tf.keras.losses.Reduction.NONE)(targets, outputs)
mask = tf.cast(x=tf.math.not_equal(targets, 0), dtype=tf.float32)
batch_loss = tf.reduce_sum(mask * loss) / batch_size
loss_metric(batch_loss)
variables = model.trainable_variables
gradients = tape.gradient(target=batch_loss, sources=variables)
optimizer.apply_gradients(zip(gradients, variables))
return {
"train_loss": loss_metric.result()
}, tf.nn.softmax(logits=outputs[:, 0, 5:7], axis=-1)
def _valid_step(model: tf.keras.Model,
dataset: tf.data.Dataset,
progress_bar: ProgressBar,
loss_metric: tf.keras.metrics.Mean,
max_train_steps: Any = -1) -> Dict:
""" 验证步
:param model: 验证模型
:param dataset: 验证数据集
:param progress_bar: 进度管理器
:param loss_metric: 损失计算器
:param max_train_steps: 验证步数
:return: 验证指标
"""
print("验证轮次")
start_time = time.time()
loss_metric.reset_states()
for (batch, (train_enc, train_dec, month_enc, month_dec,
labels)) in enumerate(dataset.take(max_train_steps)):
train_enc = tf.squeeze(train_enc, axis=0)
train_dec = tf.squeeze(train_dec, axis=0)
outputs = model(inputs=[train_enc, train_dec, month_enc, month_dec])
treat_outputs = tf.squeeze(input=outputs[:, -24:, :], axis=-1)
loss = tf.keras.losses.MSE(labels, treat_outputs)
loss_metric(loss)
progress_bar(
current=batch + 1,
metrics=get_dict_string(data={"valid_loss": loss_metric.result()}))
progress_bar(
current=progress_bar.total,
metrics=get_dict_string(data={"valid_loss": loss_metric.result()}))
progress_bar.done(step_time=time.time() - start_time)
return {"valid_loss": loss_metric.result()}
def _train_step(model: tf.keras.Model, optimizer: Any, segments: Any,
loss_metric: tf.keras.metrics.Mean, queries: Any, targets: Any) -> Any:
""" 单个训练步
:param model: 训练模型
:param optimizer: 优化器
:param loss_metric: 损失计算器
:param queries: 第一个查询句子
:param targets: 第二个查询句子
:return: 训练指标
"""
with tf.GradientTape() as tape:
outputs = model(inputs=[queries, segments])
loss = loss_function(pred=outputs, targets=targets)
loss_metric(loss)
variables = model.trainable_variables
gradients = tape.gradient(target=loss, sources=variables)
optimizer.apply_gradients(zip(gradients, variables))
return {"train_loss": loss_metric.result()}
def _train_step(model: tf.keras.Model, optimizer: tf.keras.optimizers.Adam,
loss_metric: tf.keras.metrics.Mean, first_queries: Any, second_queries: Any, labels: Any) -> Tuple:
""" 单个训练步
:param model: 训练模型
:param optimizer: 优化器
:param loss_metric: 损失计算器
:param first_queries: 第一个查询句子
:param second_queries: 第二个查询句子
:param labels: 标签
:return: 训练指标
"""
with tf.GradientTape() as tape:
outputs = model(inputs=[first_queries, second_queries])
loss = tf.keras.losses.SparseCategoricalCrossentropy()(labels, outputs)
loss_metric(loss)
variables = model.trainable_variables
gradients = tape.gradient(target=loss, sources=variables)
optimizer.apply_gradients(zip(gradients, variables))
return {"train_loss": loss_metric.result()}, outputs