def evaluate(self, seq_data, head_i=0, loss='poisson'):
""" Evaluate model on SeqDataset. """
# choose model
if self.ensemble is None:
model = self.models[head_i]
else:
model = self.ensemble
# compile with dense metrics
num_targets = self.model.output_shape[-1]
if loss == 'bce':
model.compile(optimizer=tf.keras.optimizers.SGD(),
loss=loss,
metrics=[
metrics.SeqAUC(curve='ROC', summarize=False),
metrics.SeqAUC(curve='PR', summarize=False)
])
else:
model.compile(optimizer=tf.keras.optimizers.SGD(),
loss=loss,
metrics=[
metrics.PearsonR(num_targets, summarize=False),
metrics.R2(num_targets, summarize=False)
])
# evaluate
return model.evaluate(seq_data.dataset)
def compile(self, seqnn_model):
for model in seqnn_model.models:
if self.loss == 'bce':
model_metrics = [metrics.SeqAUC(curve='ROC'), metrics.SeqAUC(curve='PR')]
else:
num_targets = model.output_shape[-1]
model_metrics = [metrics.PearsonR(num_targets), metrics.R2(num_targets)]
model.compile(loss=self.loss_fn,
optimizer=self.optimizer,
metrics=model_metrics)
self.compiled = True