Доброе утро, я новичок в машинном обучении и нейронных сетях. Я пытаюсь построить полностью подключенную нейронную сеть для решения проблемы регрессии. Набор данных состоит из 18 объектов и 1 метки, и все они являются физическими величинами.
Вы можете найти код ниже. Я загружаю рисунок эволюции функции потерь по эпохам (вы можете найти ее ниже). Я не уверен, есть ли переоснащение. Кто-то может объяснить мне, почему есть или нет переоснащение?
import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestRegressor
from sklearn.feature_selection import SelectFromModel
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
from matplotlib import pyplot as plt
import keras
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, BatchNormalization
from tensorflow.keras.callbacks import EarlyStopping
from keras import optimizers
from sklearn.metrics import r2_score
from keras import regularizers
from keras import backend
from tensorflow.keras import regularizers
from keras.regularizers import l2
# =============================================================================
# Scelgo il test size
# =============================================================================
test_size = 0.2
dataset = pd.read_csv('DataSet.csv', decimal=',', delimiter = ";")
label = dataset.iloc[:,-1]
features = dataset.drop(columns = ['Label'])
y_max_pre_normalize = max(label)
y_min_pre_normalize = min(label)
def denormalize(y):
final_value = y*(y_max_pre_normalize-y_min_pre_normalize)+y_min_pre_normalize
return final_value
# =============================================================================
# Split
# =============================================================================
X_train1, X_test1, y_train1, y_test1 = train_test_split(features, label, test_size = test_size, shuffle = True)
y_test2 = y_test1.to_frame()
y_train2 = y_train1.to_frame()
# =============================================================================
# Normalizzo
# =============================================================================
scaler1 = preprocessing.MinMaxScaler()
scaler2 = preprocessing.MinMaxScaler()
X_train = scaler1.fit_transform(X_train1)
X_test = scaler2.fit_transform(X_test1)
scaler3 = preprocessing.MinMaxScaler()
scaler4 = preprocessing.MinMaxScaler()
y_train = scaler3.fit_transform(y_train2)
y_test = scaler4.fit_transform(y_test2)
# =============================================================================
# Creo la rete
# =============================================================================
optimizer = tf.keras.optimizers.Adam(lr=0.001)
model = Sequential()
model.add(Dense(60, input_shape = (X_train.shape[1],), activation = 'relu',kernel_initializer='glorot_uniform'))
model.add(Dropout(0.2))
model.add(Dense(60, activation = 'relu',kernel_initializer='glorot_uniform'))
model.add(Dropout(0.2))
model.add(Dense(60, activation = 'relu',kernel_initializer='glorot_uniform'))
model.add(Dense(1,activation = 'linear',kernel_initializer='glorot_uniform'))
model.compile(loss = 'mse', optimizer = optimizer, metrics = ['mse'])
history = model.fit(X_train, y_train, epochs = 100,
validation_split = 0.1, shuffle=True, batch_size=250
)
history_dict = history.history
loss_values = history_dict['loss']
val_loss_values = history_dict['val_loss']
y_train_pred = model.predict(X_train)
y_test_pred = model.predict(X_test)
y_train_pred = denormalize(y_train_pred)
y_test_pred = denormalize(y_test_pred)
plt.figure()
plt.plot((y_test1),(y_test_pred),'.', color='darkviolet', alpha=1, marker='o', markersize = 2, markeredgecolor = 'black', markeredgewidth = 0.1)
plt.plot((np.array((-0.1,7))),(np.array((-0.1,7))),'-', color='magenta')
plt.xlabel('True')
plt.ylabel('Predicted')
plt.title('Test')
plt.figure()
plt.plot((y_train1),(y_train_pred),'.', color='darkviolet', alpha=1, marker='o', markersize = 2, markeredgecolor = 'black', markeredgewidth = 0.1)
plt.plot((np.array((-0.1,7))),(np.array((-0.1,7))),'-', color='magenta')
plt.xlabel('True')
plt.ylabel('Predicted')
plt.title('Train')
plt.figure()
plt.plot(loss_values,'b',label = 'training loss')
plt.plot(val_loss_values,'r',label = 'val training loss')
plt.xlabel('Epochs')
plt.ylabel('Loss Function')
plt.legend()
print("\n\nThe R2 score on the test set is:\t{:0.3f}".format(r2_score(y_test_pred, y_test1)))
print("The R2 score on the train set is:\t{:0.3f}".format(r2_score(y_train_pred, y_train1)))
from sklearn import metrics
# Measure MSE error.
score = metrics.mean_squared_error(y_test_pred,y_test1)
print("\n\nFinal score test (MSE): %0.4f" %(score))
score1 = metrics.mean_squared_error(y_train_pred,y_train1)
print("Final score train (MSE): %0.4f" %(score1))
score2 = np.sqrt(metrics.mean_squared_error(y_test_pred,y_test1))
print(f"Final score test (RMSE): %0.4f" %(score2))
score3 = np.sqrt(metrics.mean_squared_error(y_train_pred,y_train1))
print(f"Final score train (RMSE): %0.4f" %(score3))
РЕДАКТИРОВАТЬ:
I пробовал также сделать важные функции и вызвать n_epochs, вот результаты:
Важность функции:
Нет импорта функций:
