Using SGD without using sklearn (LogLoss increasing with every epoch)

问题

def train(X_train,y_train,X_test,y_test,epochs,alpha,eta0):
    w,b = initialize_weights(X_train[0])
    loss_test=[]
    N=len(X_train)
    for i in range(0,epochs):
        print(i)
        for j in range(N-1):
            grad_dw=gradient_dw(X_train[j],y_train[j],w,b,alpha,N)
            grad_db=gradient_db(X_train[j],y_train[j],w,b)
            w=np.array(w)+(alpha*(np.array(grad_dw)))
            b=b+(alpha*(grad_db))                
               predict2 = []
    for m in range(len(y_test)):
        z=np.dot(w[0],X_test[m])+b
        if sigmoid(z) == 0: # sigmoid(w,x,b) returns 1/(1+exp(-(dot(x,w)+b)))
            predict2.append(0.000001)
        elif sigmoid(z) == 1:
            predict2.append(0.99999)
        else:
            predict2.append(sigmoid(z)) 
            
    loss_test.append(logloss(y_test,predict2))       
    return w,b,loss_test

my gradient dw function

def gradient_dw(x,y,w,b,alpha,N):
    dw=[]
    for i in range(len(x)):
        dw.append((x[i]*(y-1/(1+np.exp(abs(w.T[0][i]*x[i]+b)))))+(alpha/N)*(w.T[0][i]))
    return dw

My gradient db function:

 def gradient_db(x,y,w,b):
        db=0
        for i in range(len(x)):
            db=(y-1/(1+np.exp(abs(w.T[0][i]*x[i]+b))))
        return db

My loss function:

def logloss(y_true,y_pred):
    loss=0
    for i in range(len(y_true)):
        loss+=((y_true[i]*math.log10(y_pred[i]))+((1-y_true[i])*math.log10(1-y_pred[i])))
    loss=-1*(1/len(y_true))*loss
    return loss

My problem is after every epoch my loss is increasing. Why?

Any Help will be appreciated

Thank you

回答1:

1. The problem was of weight function

2. i was taking weight array as of dim(15,1)

3. but it should be (15)

4. So all the changes need to be done according with it in this code

5. Thank You

来源：https://stackoverflow.com/questions/63009169/using-sgd-without-using-sklearn-logloss-increasing-with-every-epoch