keras:how训练前获取初始损失函数值
keras:how to get initial loss function value before training
在Keras中，我检查了回调机制。
但是它在training.Like开始之前不提供任何信息输出总是在epoch=1.I之后想检查第一次feedforward.How的损失函数值可以吗实现这个？
谢谢
此答案无效。
'setting model.trainable = False and then train the model'.
我在编译模型前设置了model.trainable = False，但是模型还是输出不同的loss functions.This是weird.It应该是输出一个常量loss，也就是当a时的loss执行前馈。
The code is in the following:
from keras import backend as K
from keras.models import Model
from keras.layers import Dense, Input
from keras.models import Sequential
import numpy as np
import random
from keras.layers import Input, Dense
from keras.models import Model
from keras.layers.core import Dropout,Activation,Flatten,Lambda
from keras.layers.normalization import BatchNormalization
import keras
import time
from sklearn.preprocessing import StandardScaler
import tensorflow as tf
from ann_visualizer.visualize import ann_viz;
def gen_x(n,p,rho):
if abs(rho) < 1 :
beta=np.sqrt(rho/(1-rho))
x0=np.random.normal(size=(n,p))
z=np.random.normal(size=(n,1))
x=beta*np.repeat(z,repeats=p,axis=1)+x0
if abs(rho)==1:
x=np.repeat(z,repeats=p,axis=1)
return x
## This function creates true survival times as described in section 3 of the paper. In all simulations we set snr (signal to noise ratio) to 3.
def genecoef(p):
#return list( map(lambda x : np.power(-1,x)*np.exp(-0.1*(x-1)), np.arange(1,p+1,1)) )
return list( np.random.rand(p) )
def gen_times(x,snr):
n,p=x.shape
coef=genecoef(p)
f=np.matmul(np.matrix(x),np.matrix(coef).T)
e=np.random.normal(size=(n,1))
k=np.sqrt(np.var(f)/(snr*np.var(e)))
y=np.exp(f+k*e)
return(y)
## This function creates true survival times as described in section 3 of the paper. In all simulations we set snr (signal to noise ratio) to 3.
def gen_times_censor(x,snr):
n,p=x.shape
coef=genecoef(p)
f=np.matmul(np.matrix(x),np.matrix(coef).T)
e=np.random.normal(size=(n,1))
k=np.sqrt(np.var(f)/(snr*np.var(e)))
y=np.exp(k*e)
return(y)
def nltr(x):
y1 = x[:,0]*x[:,1]
y2 = x[:,2]*x[:,3]
y3 = x[:,4]**2
y4 = x[:,5]* (x[:,6]**2)
y5 = x[:,7]*x[:,8]* x[:,9]
y6 = 0.5 *np.exp(x[:,8]* x[:,9])
newx = np.column_stack((y1,y2,y3,y4,y5,y6))
return newx
def survdata(n,p,snr,rho):
x = gen_x(n,p,rho)
time = gen_times(x,snr)
censortime = gen_times_censor(x,snr)
y = np.apply_along_axis(np.min,1,np.column_stack((time,censortime)))
y = np.array(y)
#b==0 censored b ==1 uncensored
b = np.apply_along_axis(np.argmax,1,np.column_stack((time,censortime)))
b = np.array(b)
a = x
ordery=np.argsort(y)
a=a[ordery]
y=y[ordery]
b=b[ordery]
Rlist=[]
event_index=np.argwhere(b==1).ravel().astype(np.int32)
nsample=len(b)
nevent=sum(b)
Rlist=[]
for j in range(nevent):
Rlist+=[ list(range(np.argwhere(b==1).ravel()[j],nsample) )]
bmask = b.astype(bool)
cumlist=list(reversed(np.append(event_index,n)))
slarr=np.vectorize(lambda x:(len(x)-1))
nctrue = np.sum(slarr(Rlist))
#a:n(#samples)*p(#features) matrix,survival time from short to high
#y:survival time
#b censored(0) or not(1)
#bmask bool(b)
#nevent #uncensored
return a,y,b,bmask,nsample,nevent,event_index,Rlist,cumlist,nctrue
n=50
p=10
snr=1
rho=0.1
a,y,b,bmask,nsample,nevent,event_index,Rlist,cumlist,nctrue= survdata(n,p,snr,rho)
sc=StandardScaler()
a=nltr(a)
a=sc.fit_transform(a)
def ploss(y_true,y_pred):
#y_pred for sample x_i is the value of np.dot(x_i,beta) in the linear cox case
#y_pred is the loss for sample i
z = 0
#for j in event_index:
#z = z + K.sum(y_pred[j,0])
#z = z + K.constant(y_pred[j,0])
#z = K.sum(tf.boolean_mask(y_pred,bmask) )
#iz = K.print_tensor(tf.boolean_mask(y_pred,bmask),'y_pred_mask is')
#gz = K.print_tensor(K.gather(y_pred,event_index),'y_pred_gather is')
z = K.sum(K.gather(y_pred,event_index))
currentsum = 0
for j in range(nevent):
currentsum = currentsum + K.sum(K.exp(K.gather(y_pred,\
np.array(range(cumlist[j+1],cumlist[j])))))
z = z - K.log(currentsum)
#tempz=0
#for i in j:
#tempz = tempz + K.exp(y_pred[i,0])
#z = z - K.log(tempz)
z = -z
return z
def c_index_func(y_true, y_pred):
#y_pred is the loss for sample i
c_hat = 0
for i in range(nevent-1):
c_hat = c_hat + K.sum(K.cast(y_pred[event_index[i]+1:,0]\
<y_pred[event_index[i],0],tf.float32))
#c_hat = c_hat + K.sum(K.cast(y_pred[event_index[i]+1:,0]\
#<y_pred[event_index[i],0],float32))
return c_hat/nctrue
model=Sequential()
model.add(Dense(1,activation='linear',kernel_initializer='one',\
batch_input_shape=(a.shape[0],a.shape[1])))
#model.add(Dropout(0.2))
#model.compile(loss=ploss,optimizer='newton-raphson')
#model.compile(loss=ploss,optimizer=keras.optimizers.Adam(lr=0, beta_1=0.9, beta_2=0.999, \
#epsilon=None, decay=0.0, amsgrad=False),metrics=[c_index_func])
model.trainable=False
model.compile(loss=ploss,optimizer=keras.optimizers.SGD(lr=0.001, momentum=0.0, \
decay=0.0, nesterov=False),metrics=[c_index_func])
model.fit(x=a,y=y,batch_size=len(a),epochs=3,verbose=2)
为此，您可以只使用 model.evaluate(x, y)，它将 return 一个包含损失和指标的数组。该数组的第一个元素是给定数据的损失。只要在训练前这样做，它就会给你初始损失。
非常简单，只需进行学习rate = 0并训练DNN，所有损失都是初始损失
在Keras中，我检查了回调机制。 但是它在training.Like开始之前不提供任何信息输出总是在epoch=1.I之后想检查第一次feedforward.How的损失函数值可以吗实现这个？ 谢谢
此答案无效。
'setting model.trainable = False and then train the model'.
我在编译模型前设置了model.trainable = False，但是模型还是输出不同的loss functions.This是weird.It应该是输出一个常量loss，也就是当a时的loss执行前馈。
The code is in the following:
from keras import backend as K
from keras.models import Model
from keras.layers import Dense, Input
from keras.models import Sequential
import numpy as np
import random
from keras.layers import Input, Dense
from keras.models import Model
from keras.layers.core import Dropout,Activation,Flatten,Lambda
from keras.layers.normalization import BatchNormalization
import keras
import time
from sklearn.preprocessing import StandardScaler
import tensorflow as tf
from ann_visualizer.visualize import ann_viz;
def gen_x(n,p,rho):
if abs(rho) < 1 :
beta=np.sqrt(rho/(1-rho))
x0=np.random.normal(size=(n,p))
z=np.random.normal(size=(n,1))
x=beta*np.repeat(z,repeats=p,axis=1)+x0
if abs(rho)==1:
x=np.repeat(z,repeats=p,axis=1)
return x
## This function creates true survival times as described in section 3 of the paper. In all simulations we set snr (signal to noise ratio) to 3.
def genecoef(p):
#return list( map(lambda x : np.power(-1,x)*np.exp(-0.1*(x-1)), np.arange(1,p+1,1)) )
return list( np.random.rand(p) )
def gen_times(x,snr):
n,p=x.shape
coef=genecoef(p)
f=np.matmul(np.matrix(x),np.matrix(coef).T)
e=np.random.normal(size=(n,1))
k=np.sqrt(np.var(f)/(snr*np.var(e)))
y=np.exp(f+k*e)
return(y)
## This function creates true survival times as described in section 3 of the paper. In all simulations we set snr (signal to noise ratio) to 3.
def gen_times_censor(x,snr):
n,p=x.shape
coef=genecoef(p)
f=np.matmul(np.matrix(x),np.matrix(coef).T)
e=np.random.normal(size=(n,1))
k=np.sqrt(np.var(f)/(snr*np.var(e)))
y=np.exp(k*e)
return(y)
def nltr(x):
y1 = x[:,0]*x[:,1]
y2 = x[:,2]*x[:,3]
y3 = x[:,4]**2
y4 = x[:,5]* (x[:,6]**2)
y5 = x[:,7]*x[:,8]* x[:,9]
y6 = 0.5 *np.exp(x[:,8]* x[:,9])
newx = np.column_stack((y1,y2,y3,y4,y5,y6))
return newx
def survdata(n,p,snr,rho):
x = gen_x(n,p,rho)
time = gen_times(x,snr)
censortime = gen_times_censor(x,snr)
y = np.apply_along_axis(np.min,1,np.column_stack((time,censortime)))
y = np.array(y)
#b==0 censored b ==1 uncensored
b = np.apply_along_axis(np.argmax,1,np.column_stack((time,censortime)))
b = np.array(b)
a = x
ordery=np.argsort(y)
a=a[ordery]
y=y[ordery]
b=b[ordery]
Rlist=[]
event_index=np.argwhere(b==1).ravel().astype(np.int32)
nsample=len(b)
nevent=sum(b)
Rlist=[]
for j in range(nevent):
Rlist+=[ list(range(np.argwhere(b==1).ravel()[j],nsample) )]
bmask = b.astype(bool)
cumlist=list(reversed(np.append(event_index,n)))
slarr=np.vectorize(lambda x:(len(x)-1))
nctrue = np.sum(slarr(Rlist))
#a:n(#samples)*p(#features) matrix,survival time from short to high
#y:survival time
#b censored(0) or not(1)
#bmask bool(b)
#nevent #uncensored
return a,y,b,bmask,nsample,nevent,event_index,Rlist,cumlist,nctrue
n=50
p=10
snr=1
rho=0.1
a,y,b,bmask,nsample,nevent,event_index,Rlist,cumlist,nctrue= survdata(n,p,snr,rho)
sc=StandardScaler()
a=nltr(a)
a=sc.fit_transform(a)
def ploss(y_true,y_pred):
#y_pred for sample x_i is the value of np.dot(x_i,beta) in the linear cox case
#y_pred is the loss for sample i
z = 0
#for j in event_index:
#z = z + K.sum(y_pred[j,0])
#z = z + K.constant(y_pred[j,0])
#z = K.sum(tf.boolean_mask(y_pred,bmask) )
#iz = K.print_tensor(tf.boolean_mask(y_pred,bmask),'y_pred_mask is')
#gz = K.print_tensor(K.gather(y_pred,event_index),'y_pred_gather is')
z = K.sum(K.gather(y_pred,event_index))
currentsum = 0
for j in range(nevent):
currentsum = currentsum + K.sum(K.exp(K.gather(y_pred,\
np.array(range(cumlist[j+1],cumlist[j])))))
z = z - K.log(currentsum)
#tempz=0
#for i in j:
#tempz = tempz + K.exp(y_pred[i,0])
#z = z - K.log(tempz)
z = -z
return z
def c_index_func(y_true, y_pred):
#y_pred is the loss for sample i
c_hat = 0
for i in range(nevent-1):
c_hat = c_hat + K.sum(K.cast(y_pred[event_index[i]+1:,0]\
<y_pred[event_index[i],0],tf.float32))
#c_hat = c_hat + K.sum(K.cast(y_pred[event_index[i]+1:,0]\
#<y_pred[event_index[i],0],float32))
return c_hat/nctrue
model=Sequential()
model.add(Dense(1,activation='linear',kernel_initializer='one',\
batch_input_shape=(a.shape[0],a.shape[1])))
#model.add(Dropout(0.2))
#model.compile(loss=ploss,optimizer='newton-raphson')
#model.compile(loss=ploss,optimizer=keras.optimizers.Adam(lr=0, beta_1=0.9, beta_2=0.999, \
#epsilon=None, decay=0.0, amsgrad=False),metrics=[c_index_func])
model.trainable=False
model.compile(loss=ploss,optimizer=keras.optimizers.SGD(lr=0.001, momentum=0.0, \
decay=0.0, nesterov=False),metrics=[c_index_func])
model.fit(x=a,y=y,batch_size=len(a),epochs=3,verbose=2)
为此，您可以只使用 model.evaluate(x, y)，它将 return 一个包含损失和指标的数组。该数组的第一个元素是给定数据的损失。只要在训练前这样做，它就会给你初始损失。
非常简单，只需进行学习rate = 0并训练DNN，所有损失都是初始损失