def evaluate(self,
dataset: torch.utils.data.Dataset) -> Dict[str, Any]:
"""
This model's evaluation function.
:param dataset:
A torch.utils.data.Dataset object representing the dataset you wish
to evaluate this model's performance on.
:return:
A Dict[str, Any] object mapping metric keys with values measured
by evaluating the model.
"""
dl = list(torch.utils.data.DataLoader(dataset=dataset,
batch_size=1,
shuffle=False,
collate_fn=pad_collate))
x, y = zip(*[(entry[0].squeeze(0), entry[1]) for entry in dl])
return evaluate(self, x, y, loss=self.loss)
data_test = encode_sentences([content[0] for content in test_data],
word_to_id)
label_test = to_categorical(
encode_cate([content[1] for content in test_data], cat_to_id))
data_train = sequence.pad_sequences(data_train, maxlen=args.max_len)
data_test = sequence.pad_sequences(data_test, maxlen=args.max_len)
model = TextRNN(args.max_len, args.max_features,
args.embedding_size).build_model()
model.compile('adam', 'categorical_crossentropy', metrics=['accuracy'])
logger.info('开始训练...')
callbacks = [
ModelCheckpoint('./model.h5', verbose=1),
EarlyStopping(monitor='val_accuracy', patience=2, mode='max')
]
history = model.fit(data_train,
label_train,
batch_size=args.batch_size,
epochs=args.epochs,
callbacks=callbacks,
validation_data=(data_test, label_test))
model.summary()
label_pre = model.predict(data_test)
pred_argmax = label_pre.argmax(-1)
label_test = label_test.argmax(-1)
print(evaluate(label_test, pred_argmax, categories))