def main():
seq_id, seq_O, seq_P, id_to_label, id_to_term = encode_seq(
df_label=df_label, maxlen=MAX_LEN)
class Evaluation(Callback):
def __init__(self, val_data, interval=1):
self.val_data = val_data
self.interval = interval
self.best_f1 = 0.
self.true_vp_val = [
(row["id"], row["OpinionTerms"], row["Polarities"],
row['O_start'], row['O_end']) for rowid, row in df_label[
df_label['id'].isin(self.val_data[0])].iterrows()
]
def on_epoch_end(self, epoch, log={}):
if epoch % self.interval == 0:
o_out, p_out = pred_model.predict(
self.val_data[1:4], batch_size=BATCH_SIZE) # CRF概率
o_pred = np.argmax(o_out, axis=2)
p_pred = np.argmax(p_out, axis=2)
texts = [
df_review[df_review['id'] == i]["Reviews"].values[0]
for i in self.val_data[0]
]
pred_vp_val = decode_seq(self.val_data[0], o_pred, p_pred,
id_to_label, texts)
precision, recall, f1 = cal_opinion_metrics(
pred_vp_val, self.true_vp_val)
if f1 > self.best_f1:
self.best_f1 = f1
self.model.save_weights(
f'./model_op/op_model_0924_viteb.weights')
print(f'best = {f1}')
tokenizer = BertTokenizer(token_dict)
seq_input, seq_seg = bert_text_to_seq(list(df_review["Reviews"]),
tokenizer,
maxlen=MAX_LEN)
true_vp = [(row["id"], row["OpinionTerms"], row["Polarities"],
row['O_start'], row['O_end'])
for rowid, row in df_label.iterrows()]
pred_vp = decode_seq(seq_id, seq_O, seq_P, id_to_label,
list(df_review["Reviews"]))
cal_opinion_metrics(pred_vp, true_vp)
seq_O = to_categorical(seq_O)
seq_P = to_categorical(seq_P)
df_review['pos_tag'] = df_review['Reviews'].progress_apply(pos_tag)
with open('./data/postag2id_0922_laptop_make_up.pkl', 'rb') as f:
postag2id = pickle.load(f)
df_review['pos_tag'] = df_review['pos_tag'].progress_apply(
lambda postag: [postag2id[x] for x in postag])
seq_postag = np.array(df_review['pos_tag'].values.tolist())
view_train, view_val = split_viewpoints(seq_id, seq_input, seq_seg, seq_O,
seq_P, seq_postag)
print(view_val[0])
print('------------------- 保存验证集的id ---------------------')
print('保存final 验证集的val ids')
# np.save('./data/final_makeup_laptop_val_ids', view_val[0])
print('------------------- 保存完毕 ---------------------------')
# exit()
bert_model = load_trained_model_from_checkpoint(config_path,
checkpoint_path,
seq_len=None)
for l in bert_model.layers:
l.trainable = True
x1_in = Input(shape=(MAX_LEN, ), name='x1_in')
x2_in = Input(shape=(MAX_LEN, ), name='x2_in')
o_in = Input(shape=(
MAX_LEN,
len(id_to_term) + 1,
), name='o_in')
p_in = Input(shape=(
MAX_LEN,
len(id_to_label) + 1,
), name='p_in')
pos_tag_in = Input(shape=(MAX_LEN, ), name='pos_tag_in')
pos_tag_emb = Embedding(len(postag2id), POS_TAG_DIM,
trainable=True)(pos_tag_in)
x = bert_model([x1_in, x2_in])
x = Concatenate()([x, pos_tag_emb])
p_out = Dense(len(id_to_label) + 1,
activation='softmax')(x) # p_out 是极性的输出
crf = CRF(len(id_to_term) + 1)
o_out = crf(x)
loss_seq_O = crf.loss_function(o_in, o_out) # 直接加入 Lambda层后 计算图会出错
loss_seq_O = Lambda(lambda x: K.mean(x))(loss_seq_O)
# loss_seq_O = Lambda(lambda x: K.mean(categorical_crossentropy(x[0], x[1])), name='loss_seq_O')([o_in, o_out])
loss_p = Lambda(lambda x: K.mean(categorical_crossentropy(x[0], x[1])),
name='loss_c')([p_in, p_out])
train_model = Model([x1_in, x2_in, pos_tag_in, o_in, p_in], [o_out, p_out])
pred_model = Model([x1_in, x2_in, pos_tag_in], [o_out, p_out])
train_model._losses = []
train_model._per_input_losses = {}
train_model.add_loss(loss_seq_O)
train_model.add_loss(loss_p)
print(view_train[0].shape[0])
total_steps, warmup_steps = calc_train_steps(
num_example=view_train[0].shape[0],
batch_size=BATCH_SIZE,
epochs=EPOCHS,
warmup_proportion=0.1,
)
# optimizer = Adam(lr=1e-5)
optimizer = AdamWarmup(total_steps, warmup_steps, lr=5e-5, min_lr=1e-6)
train_model.compile(optimizer=optimizer)
train_model.metrics_tensors.append(loss_seq_O)
train_model.metrics_names.append('loss_seq_O')
train_model.metrics_tensors.append(loss_p)
train_model.metrics_names.append('loss_p')
train_model.summary()
eval_callback = Evaluation(val_data=view_val)
train_model.fit(view_train[1:],
epochs=EPOCHS,
shuffle=True,
batch_size=BATCH_SIZE,
callbacks=[eval_callback])
