classifier¶
Classifier Context.
Classes
|
-
class
ashpy.contexts.classifier.
ClassifierContext
(classifier_model=None, loss=None, dataset=None, metrics=None, log_eval_mode=<LogEvalMode.TEST: 1>, global_step=<tf.Variable 'global_step:0' shape=() dtype=int64, numpy=0>, checkpoint=None)[source]¶ Bases:
ashpy.contexts.context.Context
ashpy.ClassifierContext
provide the standard functions to test a classifier.-
__init__
(classifier_model=None, loss=None, dataset=None, metrics=None, log_eval_mode=<LogEvalMode.TEST: 1>, global_step=<tf.Variable 'global_step:0' shape=() dtype=int64, numpy=0>, checkpoint=None)[source]¶ Instantiate the
ashpy.contexts.classifier.ClassifierContext
context.- Parameters
classifier_model (
tf.keras.Model
) – Atf.keras.Model
model.loss (
ashpy.losses.executor.Executor
) – Loss function, format f(y_true, y_pred).dataset (
tf.data.Dataset
) – The test dataset.metrics (
list
of [ashpy.metrics.metric.Metric
]) – List ofashpy.metrics.metric.Metric
with which to measure training and validation data performances.log_eval_mode (
ashpy.modes.LogEvalMode
) – Models’ mode to use when evaluating and logging.global_step (
tf.Variable
) – tf.Variable that keeps track of the training steps.checkpoint (
tf.train.Checkpoint
) – checkpoint to use to keep track of models status.
- Return type
-
property
classifier_model
¶ Retrieve the Model Object.
- Return type
Model
- Returns
tf.keras.Model
– The classifier model.
-
property
training_set
¶ Return the training set.
- Return type
DatasetV2
- Returns
tf.data.Dataset
– The training set.
-
property
validation_set
¶ Return the validation set.
- Return type
Optional
[DatasetV2
]- Returns
tf.data.Dataset
– The validation set.
-