深度学习模型是针对非常少的数据进行训练

Question

我正在使用100％行训练深度学习模型，其中80％的训练数据和20％的测试数据。数据正在拆分，但是我的模型显示了2242的训练输出。下面是提供了模型和输出的训练代码。任何帮助将不胜感激。

培训代码：

import time
start_time = time.time()

from sklearn.feature_extraction.text import TfidfVectorizer

tweet_table = cleaning_table(tweet_table)

def tokenization_tweets(dataset, features):
    tokenization = TfidfVectorizer(max_features=features)
    tokenization.fit(dataset)
    dataset_transformed = tokenization.transform(dataset).toarray()
    return dataset_transformed
    
 
def splitting(table):
    X_train, X_test, y_train, y_test = train_test_split(table.tweet, table.test, test_size=0.2, shuffle=True)
    return X_train, X_test, y_train, y_test

if __name__ == "__main__":
    tweet_table['test'] = tweet_table['Overall_Sentiment'].apply(lambda x: 1 if x == 'Positive' else (0 if x == 'Negative' else 2))


if __name__ == "__main__":
    X_train, X_test, y_train, y_test = splitting(tweet_table)

#print(tweet_table["test"].value_counts())
#print(tweet_table["Overall_Sentiment"].value_counts())
#print(list(set(y_train)))
#print(list(set(y_test)))


#Create a Neural Network
#Create the model
def train(X_train_mod, y_train, features, shuffle, drop, layer1, layer2, epoch, lr, epsilon, validation):
    model_nn = Sequential()
    model_nn.add(Dense(layer1, input_shape=(features,), activation='relu'))
    model_nn.add(Dropout(drop))
    model_nn.add(Dense(layer2, activation='sigmoid'))
    model_nn.add(Dropout(drop))
    model_nn.add(Dense(3, activation='softmax'))
    
    optimizer = keras.optimizers.Adam(lr=lr, beta_1=0.9, beta_2=0.999, epsilon=epsilon, decay=0.0, amsgrad=False)
    model_nn.compile(loss='sparse_categorical_crossentropy',
                 optimizer=optimizer,
                 metrics=['accuracy'])
    model_nn.fit(np.array(X_train_mod), y_train,
                 batch_size=32,
                 epochs=epoch,
                 verbose=1,
                 validation_split=validation,
                 shuffle=shuffle)
    return model_nn


def test(X_test, model_nn):
    prediction = model_nn.predict(X_test)
    return prediction


def model1(X_train, y_train):   
    features = 3500
    shuffle = True
    drop = 0.5
    layer1 = 512
    layer2 = 256
    epoch = 5
    lr = 0.001
    epsilon = None
    validation = 0.1
    X_train_mod = tokenization_tweets(X_train, features)
    model = train(X_train_mod, y_train, features, shuffle, drop, layer1, layer2, epoch, lr, epsilon, validation)
    return model;

#model1(X_train, y_train)

#model11(X_train, y_train)

def save_model(model):
        # lets assume `model` is main model 
        model_json = model.to_json()
        with open("model.json", "w") as json_file:
            json.dump(model_json, json_file)

        model.save_weights("model_weights.h5")

#print(len(X_train))
#print(len(y_train))
model_final = model1(X_train, y_train)

输出：

Epoch 1/5
2242/2242 [==============================] - 6s 3ms/step - loss: 0.3426 - accuracy: 0.8476 - val_loss: 0.2690 - val_accuracy: 0.8857
Epoch 2/5
2242/2242 [==============================] - 6s 3ms/step - loss: 0.2399 - accuracy: 0.9015 - val_loss: 0.2471 - val_accuracy: 0.8991
Epoch 3/5
2242/2242 [==============================] - 6s 3ms/step - loss: 0.1912 - accuracy: 0.9205 - val_loss: 0.2447 - val_accuracy: 0.9028
Epoch 4/5
2242/2242 [==============================] - 6s 3ms/step - loss: 0.1454 - accuracy: 0.9399 - val_loss: 0.2547 - val_accuracy: 0.9083
Epoch 5/5
2242/2242 [==============================] - 6s 3ms/step - loss: 0.1046 - accuracy: 0.9552 - val_loss: 0.2874 - val_accuracy: 0.9084
--- 192.1562056541443 seconds ---

非常感谢