def train():
x_train, y_train = process_file(train_dir, word_to_id, cat_to_id,
600) #获取训练数据每个字的id和对应标签的oe-hot形式
x_val, y_val = process_file(val_dir, word_to_id, cat_to_id, 600)
#使用LSTM或者CNN
model = TextRNN()
model.train()
# model = TextCNN()
#选择损失函数
Loss = nn.MultiLabelSoftMarginLoss()
# Loss = nn.BCELoss()
# Loss = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)
best_val_acc = 0
for epoch in range(100):
i = 0
print('epoch:{}'.format(epoch))
batch_train = batch_iter(x_train, y_train, 64)
for x_batch, y_batch in batch_train:
i += 1
# print(i)
x = np.array(x_batch)
y = np.array(y_batch)
x = torch.LongTensor(x)
y = torch.Tensor(y)
# y = torch.LongTensor(y)
# x = Variable(x)
# y = Variable(y)
out = model(x)
loss = Loss(out, y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 对模型进行验证
if i % 90 == 0:
los, accracy = evaluate(model, Loss, x_val,
y_val) # 此处不需要优化器参数
print('loss:{},accracy:{}'.format(los, accracy))
if accracy > best_val_acc:
torch.save(model.state_dict(), 'model_params.pkl')
best_val_acc = accracy
def test():
print("Loading test data...")
start_time = time.time()
x_test, y_test = process_file(test_dir, word_to_id, cat_to_id, config.seq_length)
session = tf.Session()
session.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess=session, save_path=save_path)
# 在保存和恢复模型时都需要首先运行这一行：tf.train.Saver()，而不是只有保存时需要。
print('Testing...')
loss_test, acc_test = evaluate(session, x_test, y_test)
# 返回了10000个总测试样本的平均交叉熵损失和平均准率。
msg = 'Test Loss: {0:>6.2}, Test Acc: {1:>7.2%}'
print(msg.format(loss_test, acc_test))
batch_size = 128
data_len = len(x_test)
num_batch = int((data_len - 1) / batch_size) + 1
y_test_cls = np.argmax(y_test, 1)
y_pred_cls = np.zeros(shape=len(x_test), dtype=np.int32)
for i in range(num_batch):
start_id = i * batch_size
end_id = min((i + 1) * batch_size, data_len)
feed_dict = {
model.input_x: x_test[start_id:end_id],
model.keep_prob: 1.0
}
y_pred_cls[start_id:end_id] = session.run(model.y_pred_cls, feed_dict=feed_dict)
# 测试的时候不需要dropout神经元。
print("Precision, Recall and F1-Score...")
print(metrics.classification_report(y_test_cls, y_pred_cls, target_names=categories))
# 可以得到准确率 、召回率和F1_score
# 混淆矩阵
print("Confusion Matrix...")
cm = metrics.confusion_matrix(y_test_cls, y_pred_cls)
print(cm)
time_dif = get_time_dif(start_time)
print("Time usage:", time_dif)
def test():
print("Loading test data...")
start_time = time.time()
x_test, y_test = process_file(test_dir, word_to_id, cat_to_id,
args.SEQ_LENGTH)
session = tf.Session()
session.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess=session, save_path=save_path) # 读取保存的模型
print('Testing...')
loss_test, acc_test = evaluate(session, x_test, y_test)
msg = 'Test Loss: {0:>6.2}, Test Acc: {1:>7.2%}'
print(msg.format(loss_test, acc_test))
batch_size = 128
data_len = len(x_test)
num_batch = int((data_len - 1) / batch_size) + 1
y_test_cls = np.argmax(y_test, 1)
y_pred_cls = np.zeros(shape=len(x_test), dtype=np.int32) # 保存预测结果
for i in range(num_batch): # 逐批次处理
start_id = i * batch_size
end_id = min((i + 1) * batch_size, data_len)
feed_dict = {
model.input_x: x_test[start_id:end_id],
model.keep_prob: 1.0
}
y_pred_cls[start_id:end_id] = session.run(model.y_pred_cls,
feed_dict=feed_dict)
# 评估
print("Precision, Recall and F1-Score...")
print(
metrics.classification_report(y_test_cls,
y_pred_cls,
target_names=categories))
# 混淆矩阵
print("Confusion Matrix...")
cm = metrics.confusion_matrix(y_test_cls, y_pred_cls)
print(cm)
time_dif = get_time_dif(start_time)
print("Time usage:", time_dif)
def test():
print("loading test data ...")
start_time=time.time()
x_test,y_test=process_file(test_dir,word_to_id,cat_to_id,config.seq_length)
session=tf.Session()
session.run(tf.global_variables_initializer())
saver=tf.train.Saver()
saver.restore(sess=session,save_path=save_path)
print("testing.. ")
loss_test,acc_test=evaluate(session,x_test,y_test)
msg="Test Loss: {0:>6.2}, Test Acc: {1:>7.2%}"
print(msg.format(loss_test,acc_test))
batch_size=128
data_len=len(x_test)
num_batch=int((data_len-1)/batch_size)+1
y_test_cls=np.argmax(y_test,1)#1指的是第一列数据
y_pred_cls=np.zeros(shape=len(x_test),dtype=np.int32)
for i in range(num_batch):
start_id=i*batch_size
end_id=min((i+1)*batch_size,data_len)
feed_dict={
model.input_x:x_test[start_id:end_id],
model.keep_prob:1.0
}
y_pred_cls[start_id:end_id]=session.run(model.y_pred_cls,feed_dict=feed_dict)
#评估
print('precision, recall and f1')
print(metrics.classification_report(y_test_cls,y_pred_cls,target_names=categories))
#混淆矩阵
print("confusion matrix")
cm=metrics.confusion_matrix(y_test_cls,y_pred_cls)
print(cm)
time_dif=get_time_dif(start_time)
print("time usage ",time_dif)
def train():
print("Configuring TensorBoard and Saver...")
# 配置 Tensorboard，重新训练时，请将tensorboard文件夹删除，不然图会覆盖
tensorboard_dir = 'tensorboard/textrnn'
if not os.path.exists(tensorboard_dir):
os.makedirs(tensorboard_dir)
tf.summary.scalar("loss", model.loss)
tf.summary.scalar("accuracy", model.acc)
merged_summary = tf.summary.merge_all()
writer = tf.summary.FileWriter(tensorboard_dir)
# 配置 Saver
saver = tf.train.Saver()
if not os.path.exists(save_dir):
os.makedirs(save_dir)
print("Loading training and validation data...")
# 载入训练集与验证集
start_time = time.time()
x_train, y_train = process_file(train_dir, word_to_id, cat_to_id, config.seq_length)
x_val, y_val = process_file(val_dir, word_to_id, cat_to_id, config.seq_length)
time_dif = get_time_dif(start_time)
print("Time usage:", time_dif)
# 创建session
session = tf.Session()
session.run(tf.global_variables_initializer())
writer.add_graph(session.graph)
print('Training and evaluating...')
start_time = time.time()
total_batch = 0 # 总批次
best_acc_val = 0.0 # 最佳验证集准确率
last_improved = 0 # 记录上一次提升批次
require_improvement = 1000 # 如果超过1000轮未提升，提前结束训练
flag = False
for epoch in range(config.num_epochs):
print('Epoch:', epoch + 1)
batch_train = batch_iter(x_train, y_train, config.batch_size)
for x_batch, y_batch in batch_train:
feed_dict = feed_data(x_batch, y_batch, config.dropout_keep_prob)
if total_batch % config.save_per_batch == 0:
# 每多少轮次将训练结果写入tensorboard scalar
s = session.run(merged_summary, feed_dict=feed_dict)
writer.add_summary(s, total_batch)
if total_batch % config.print_per_batch == 0:
# 每多少轮次输出在训练集和验证集上的性能
feed_dict[model.keep_prob] = 1.0
loss_train, acc_train = session.run([model.loss, model.acc], feed_dict=feed_dict)
loss_val, acc_val = evaluate(session, x_val, y_val) # todo
if acc_val > best_acc_val:
# 保存最好结果
best_acc_val = acc_val
last_improved = total_batch
saver.save(sess=session, save_path=save_path)
improved_str = '*'
else:
improved_str = ''
time_dif = get_time_dif(start_time)
msg = 'Iter: {0:>6}, Train Loss: {1:>6.2}, Train Acc: {2:>7.2%},' \
+ ' Val Loss: {3:>6.2}, Val Acc: {4:>7.2%}, Time: {5} {6}'
print(msg.format(total_batch, loss_train, acc_train, loss_val, acc_val, time_dif, improved_str))
session.run(model.optim, feed_dict=feed_dict) # 运行优化
total_batch += 1
if total_batch - last_improved > require_improvement:
# 验证集正确率长期不提升，提前结束训练
print("No optimization for a long time, auto-stopping...")
flag = True
break # 跳出循环
if flag: # 同上
break
def train():
print("Configuring TensorBoard and Saver...")
tensorboard_dir = 'tensorboard/textcnn'
if not os.path.exists(tensorboard_dir):
os.makedirs(tensorboard_dir)
tf.summary.scalar("loss", model.loss)
tf.summary.scalar("accuracy", model.acc)
# 用到 tf.summary 中的方法保存日志数据，用于tensorboard可视化操作。
# 用 tf.summary.scalar 保存标量，一般用来保存loss，accuary，学习率等数据
merged_summary = tf.summary.merge_all()
writer = tf.summary.FileWriter(tensorboard_dir)
# 使用 tf.summaries.merge_all() 对所有的汇总操作进行合并
# 将数据写入本地磁盘: tf.summary.FileWriter
saver = tf.train.Saver()
if not os.path.exists(save_dir):
os.makedirs(save_dir)
print("Loading training and validation data...")
start_time = time.time()
x_train, y_train = process_file(train_dir, word_to_id, cat_to_id, config.seq_length)
x_val, y_val = process_file(val_dir, word_to_id, cat_to_id, config.seq_length)
time_dif = get_time_dif(start_time)
print("Time usage:", time_dif)
session = tf.Session()
session.run(tf.global_variables_initializer())
writer.add_graph(session.graph)
print('Training and evaluating...')
start_time = time.time()
total_batch = 0
best_acc_val = 0.0
last_improved = 0
require_improvement = 1000
# 如果超过1000轮未提升，提前结束训练，防止过拟合。
flag = False
for epoch in range(config.num_epochs):
print('Epoch:', epoch + 1)
batch_train = batch_iter(x_train, y_train, config.batch_size)
for x_batch, y_batch in batch_train:
feed_dict = feed_data(x_batch, y_batch, config.dropout_keep_prob)
if total_batch % config.save_per_batch == 0:
s = session.run(merged_summary, feed_dict=feed_dict)
writer.add_summary(s, total_batch)
if total_batch % config.print_per_batch == 0:
feed_dict[model.keep_prob] = 1.0
loss_train, acc_train = session.run([model.loss, model.acc], feed_dict=feed_dict)
loss_val, acc_val = evaluate(session, x_val, y_val) # todo
if acc_val > best_acc_val:
# 保存最好结果
best_acc_val = acc_val
last_improved = total_batch
saver.save(sess=session, save_path=save_path)
improved_str = '*'
else:
improved_str = ''
time_dif = get_time_dif(start_time)
msg = 'Iter: {0:>6}, Train Loss: {1:>6.2}, Train Acc: {2:>7.2%},' \
+ ' Val Loss: {3:>6.2}, Val Acc: {4:>7.2%}, Time: {5} {6}'
print(msg.format(total_batch, loss_train, acc_train, loss_val, acc_val, time_dif, improved_str))
session.run(model.optim, feed_dict=feed_dict) # 运行优化
total_batch += 1
if total_batch - last_improved > require_improvement:
# 验证集正确率长期不提升，提前结束训练
print("No optimization for a long time, auto-stopping...")
flag = True
break
if flag:
break
def train():
print("configuring tensorboard and saver")
tensorboard_dir="tensorboard/textcnn"
if not os.path.exists(tensorboard_dir):
os.makedirs(tensorboard_dir)
tf.summary.scalar("loss",model.loss)
tf.summary.scalar("accuracy",model.acc)
merged_summary=tf.summary.merge_all()
writer=tf.summary.FileWriter(tensorboard_dir)
saver=tf.train.Saver()
if not os.path.exists(save_dir):
os.makedirs(save_dir)
print("loading training and validation data..")
start_time=time.time()
x_train,y_train=process_file(train_dir,word_to_id,cat_to_id,config.seq_length)
x_val,y_val=process_file(val_dir,word_to_id,cat_to_id,config.seq_length)
time_dif=get_time_dif(start_time)
print("time usage: ",time_dif)
#创建session
session=tf.Session()
session.run(tf.global_variables_initializer())
writer.add_graph(session.graph)
print("training and evaluate...")
start_time=time.time()
total_batch=0
best_acc_val=0.0
last_improved=0
require_improvement=1000
flag=False
for epoch in range(config.num_epochs):
print("epoch: ",epoch+1)
batch_train=batch_iter(x_train,y_train,config.batch_size)
for x_batch,y_batch in batch_train:
feed_dict=feed_data(x_batch,y_batch,config.dropout_keep_prob)
if(total_batch%config.save_per_batch==0):
s=session.run(merged_summary,feed_dict=feed_dict)
writer.add_summary(s,total_batch)
if(total_batch%config.print_per_batch==0):
feed_dict[model.keep_prob]=1.0
loss_train,acc_train=session.run([model.loss,model.acc],feed_dict=feed_dict)
loss_val,acc_val=evaluate(
session,x_val,y_val
)
# 保存最好的结果
if acc_val>best_acc_val:
best_acc_val=acc_val
last_improved=0
saver.save(sess=session,save_path=save_path)
improved_str="*"
else:
improved_str=""
time_dif=get_time_dif(start_time)
#msg="iter: {0:>6}, train loss: {1:6.2},train acc:{2:7.2},"+"val loss: {3:>6.2},val acc: {4:>7.2%},time:{5},{6}"
msg = 'Iter: {0:>6}, Train Loss: {1:>6.2}, Train Acc: {2:>7.2%},' \
+ ' Val Loss: {3:>6.2}, Val Acc: {4:>7.2%}, Time: {5} {6}'
print(msg.format(total_batch, loss_train, acc_train, loss_val, acc_val, time_dif, improved_str))
session.run(model.optim,feed_dict=feed_dict)
total_batch+=1
if total_batch-last_improved>require_improvement:
print("no optimization for a long time, auto-stopping...")
flag=True
break
if flag:
break
num_classes = 10 #类别数
# Preparing data is usually the most time-consuming part of machine learning.
base_dir = r'C:\Users\weke\Desktop\语料搜集\cnews'
train_dir = os.path.join(base_dir, 'cnews.train.txt')
test_dir = os.path.join(base_dir, 'cnews.test.txt')
val_dir = os.path.join(base_dir, 'cnews.val.txt')
vocab_dir = os.path.join(base_dir, 'cnews.vocab.txt')
if not os.path.exists(vocab_dir): # 如果不存在词汇表，重建
build_vocab(train_dir, vocab_dir, config.vocab_size)
categories, cat_to_id = read_category()
words, word_to_id = read_vocab(vocab_dir)
vocab_size = len(words)
X_train, y_train = process_file(train_dir, word_to_id, cat_to_id, seq_length)
X_test, y_test = process_file(val_dir, word_to_id, cat_to_id, seq_length)
print(len(X_train), 'train sequences')
print(len(X_test), 'test sequences')
## Padding input data
# Models in Keras (and elsewhere) usually take as input batches of sentences of the same length.
# Since sentences usually have different sizes, we "pad" sentences (we add a dummy "padding" token at the end of the
# sentences. The input thus has this size : (batchsize, maxseqlen) where maxseqlen is the maximum length of a sentence
# in the batch.
'''
maxlen = 80 # cut texts after this number of words (among top vocab_size most common words)
X_train = sequence.pad_sequences(X_train, maxlen=maxlen)
X_test = sequence.pad_sequences(X_test, maxlen=maxlen)
'''
test_file = 'cnews.test.txt'
val_file = 'cnews.val.txt'
# 获取文本的类别及其对应id的字典
categories, cat_to_id = read_category()
#print(categories)
# 获取训练文本中所有出现过的字及其所对应的id
words, word_to_id = read_vocab('cnews.vocab.txt')
#print(words)
#print(word_to_id)
#print(word_to_id)
#获取字数
vocab_size = len(words)
# 数据加载及分批
# 获取训练数据每个字的id和对应标签的one-hot形式
x_train, y_train = process_file('cnews.train1.txt', word_to_id, cat_to_id, 600)
#print('x_train=', x_train)
x_val, y_val = process_file('cnews.val.txt', word_to_id, cat_to_id, 600)
#设置GPU
cuda = torch.device('cuda')
x_train, y_train = torch.LongTensor(x_train), torch.Tensor(y_train)
x_val, y_val = torch.LongTensor(x_val), torch.Tensor(y_val)
train_dataset = Data.TensorDataset(x_train, y_train)
train_loader = Data.DataLoader(dataset=train_dataset,
batch_size=1280,
shuffle=True)
val_dataset = Data.TensorDataset(x_val, y_val)
val_loader = Data.DataLoader(dataset=val_dataset, batch_size=1280)
})
text = features["text"]
title = tf.cast(features["title"], tf.int32)
label = tf.cast(features["label"], tf.int32)
return text, title, label
if __name__ == "__main__":
# 数据格式转换
config = TCNNConfig()
if not os.path.exists(vocab_dir): # 如果不存在词汇表，重建
build_vocab(train_dir, vocab_dir, config.vocab_size)
categories, cat_to_id = read_category()
words, word_to_id = read_vocab(vocab_dir)
x_train, y_train = process_file(train_dir, word_to_id, cat_to_id,
config.seq_length)
text_test, x_test, y_test = process_file2(test_dir, word_to_id, cat_to_id,
config.seq_length)
convert_to_TFRecords([x_train, y_train], base_dir + "/train")
# convert_to_TFRecords_withText([text_test, x_test, y_test], base_dir+"/test")
# 读取测试
# read_TFRecords_test("sexText/train10.tfrecords")
# queue = tf.train.string_input_producer(["sexText/test.tfrecords"], num_epochs=10)
# text, title, label = read_example(queue)
#
# text_batch, title_batch, label_batch = tf.train.batch([text, title, label], batch_size=1, capacity=5000,
# num_threads=1)
# count = 0
# with tf.Session() as sess:
"""
words, word_to_id = read_vocab(vocab_dir)
categories, cat_to_id = read_category()
# vocab_size = len(words)
return words, word_to_id, categories, cat_to_id
if __name__ == "__main__":
test_dir = 'file/cnews/cnews.test.txt'
vocab_dir = 'file/cnews/vocab.txt'
train_dir = 'file/cnews/cnews.train.txt'
words, word_to_id, categories, cat_to_id = load_data(vocab_dir)
x_pad, y_pad = process_file(train_dir,
word_to_id,
cat_to_id,
max_length=5000)
x_test, y_test = process_file(test_dir,
word_to_id,
cat_to_id,
max_length=5000)
X = x_pad.T
Y = y_pad.T
x_test = x_test.T
y_test = y_test.T
learning_rate = 1e-3
num_interantion = 100
print("---------------start------------------------")
train_epochs = 1000
batch_size = 256
lr = 0.001
#########################################
# 获取文本的类别及其对应id的字典
categories, cat_to_id = read_category()
print(categories)
# 获取训练文本中所有出现过的字及其所对应的id
words, word_to_id = read_vocab('cnews.vocab.txt')
vocab_size = len(words)
# 数据加载及分批
# 获取训练数据每个字的id和对应标签的one-hot形式
x_train, y_train = process_file('cnews.train.txt', word_to_id, cat_to_id, 600)
x_test, y_test = process_file('cnews.val.txt', word_to_id, cat_to_id, 600)
cuda = torch.device('cuda')
x_train, y_train = torch.LongTensor(x_train), torch.LongTensor(y_train)
x_test, y_test = torch.LongTensor(x_test), torch.LongTensor(y_test)
train_dataset = Data.TensorDataset(x_train, y_train)
train_loader = Data.DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
test_dataset = Data.TensorDataset(x_test, y_test)
test_loader = Data.DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=True)
#################################################################################
