Question

我正在尝试为数据集设置自定义损失函数。我将常量初始参数作为输入层的一部分传递，并且我想在损失函数中切片y_true张量以仅返回系统中的动态变量。即

def modified_mse(y_true,y_pred):
    return losses.mse(y_true[:,10:], y_pred)

但是，此损失函数所产生的损失与Keras女士所带来的损失截然不同。为什么损失如此不同？我希望他们是一样的。最小工作示例：

import pandas as pd
import numpy as np
from sklearn import metrics
import math, glob
import matplotlib.pyplot as plt
from collections import defaultdict
from functools import partial
from itertools import repeat
from sklearn.utils import shuffle
from sklearn.model_selection import train_test_split
from sklearn.model_selection import StratifiedKFold
from sklearn.metrics import roc_curve, auc
from keras.utils import to_categorical
from keras import models
from keras import layers
from keras.callbacks import EarlyStopping, ModelCheckpoint
from keras.layers import Dense, Dropout, Activation, Input
import keras.backend as K
import tensorflow as tf
from keras import losses
from keras.models import Model
from numpy.random import seed

df = pd.read_csv("julia_batch5_1.csv")

dfShuffle = shuffle(df,random_state=42)

i_col = ["m1","m2", "m3","x1", "x2", "x3", "y1", "y2", "y3", "tEnd"]
o_col = ["x1tEnd", "x2tEnd", "x3tEnd", "y1tEnd", "y2tEnd", "y3tEnd", "dx1tEnd", "dx2tEnd", "dx3tEnd", "dy1tEnd", "dy2tEnd", "dy3tEnd","eventID"]

X1 = dfShuffle[i_col].values
y1 = dfShuffle[o_col+i_col].values

X_train,X_test,y_train,y_test = train_test_split(X1,y1, test_size=0.2, random_state=42)


id_list_train = y_train[:,len(o_col+icol)-1]
id_list_test = y_test[:,len(o_col+icol)-1]
y_train = np.delete(y_train,len(o_col+icol)-1,1)
y_test = np.delete(y_test,len(o_col+icol)-1,1)

X_train = X_train.astype('float64')
X_test = X_test.astype('float64')
y_train = y_train.astype('float64')
y_test = y_test.astype('float64')

network = models.Sequential()
network.add(layers.Dense(128,activation='relu',input_dim=len(i_col)))
for i in range(9):
    network.add(layers.Dense(128,activation='relu'))
network.add(layers.Dense(12,activation='linear'))
network.compile(optimizer='adam', loss=modified_mse, metrics=['accuracy'])
network.save_weights('model_init.h5')

history = network.fit(X_train,y_train,
                              epochs=30,
                              batch_size=128,
                              validation_data=(X_test,y_test),
                              verbose = 1)

数据文件位于https://drive.google.com/open?id=1Jy5U3pjhNEoJUXSuyabzM_LMUNAOQJ3f

自定义损失函数不同于常规的mse

0 个答案: