def train():
train_args, model_args = ConfigSection(), ConfigSection()
ConfigLoader.load_config(config_dir, {"text_class": train_args})
# load dataset
print("Loading data...")
data = TextClassifyDataSet(load_func=ClassDataSetLoader.load)
data.load(train_data_dir)
print("vocabulary size:", len(data.word_vocab))
print("number of classes:", len(data.label_vocab))
save_pickle(data.word_vocab, save_dir, "word2id.pkl")
save_pickle(data.label_vocab, save_dir, "label2id.pkl")
model_args["num_classes"] = len(data.label_vocab)
model_args["vocab_size"] = len(data.word_vocab)
# construct model
print("Building model...")
model = CNNText(model_args)
# train
print("Training...")
trainer = ClassificationTrainer(epochs=train_args["epochs"],
batch_size=train_args["batch_size"],
validate=train_args["validate"],
use_cuda=train_args["use_cuda"],
pickle_path=save_dir,
save_best_dev=train_args["save_best_dev"],
model_name=model_name,
loss=Loss("cross_entropy"),
optimizer=Optimizer("SGD", lr=0.001, momentum=0.9))
trainer.train(model, data)
print("Training finished!")
saver = ModelSaver(os.path.join(save_dir, model_name))
saver.save_pytorch(model)
print("Model saved!")
# construct model
model_args = {
'num_classes': n_classes,
'vocab_size': vocab_size
}
model = ClassificationModel(num_classes=n_classes, vocab_size=vocab_size)
# construct trainer
train_args = {
"epochs": 3,
"batch_size": 16,
"pickle_path": data_dir,
"validate": False,
"save_best_dev": False,
"model_saved_path": None,
"use_cuda": True,
"loss": Loss("cross_entropy"),
"optimizer": Optimizer("Adam", lr=0.001)
}
trainer = ClassificationTrainer(**train_args)
# start training
trainer.train(model, train_data=train_set, dev_data=dev_set)
# predict using model
data_infer = [x[0] for x in data]
infer = ClassificationInfer(data_dir)
labels_pred = infer.predict(model.cpu(), data_infer)
print(labels_pred)
dim=attention_unit,
num_vec=attention_hops)
self.mlp = MLP(
size_layer=[lstm_hidden_size * 2 * attention_hops, nfc, class_num])
def forward(self, x):
x_emb = self.embedding(x)
output = self.lstm(x_emb)
after_attention, penalty = self.attention(output, x)
after_attention = after_attention.view(after_attention.size(0), -1)
output = self.mlp(after_attention)
return output
def loss(self, predict, ground_truth):
print("predict:%s; g:%s" %
(str(predict.size()), str(ground_truth.size())))
print(ground_truth)
return F.cross_entropy(predict, ground_truth)
train_args = ConfigSection()
ConfigLoader("good path").load_config('config.cfg', {"train": train_args})
train_args['vocab'] = len(word2index)
trainer = ClassificationTrainer(**train_args.data)
# for k in train_args.__dict__.keys():
# print(k, train_args[k])
model = SELF_ATTENTION_YELP_CLASSIFICATION(train_args)
trainer.train(model, train_data, dev_data)