Я разрабатываю автокодер в стеке, пытаясь настроить мою нейронную сеть по рейтингу фильма, если пользователь не оценил какой-либо фильм, который он не будет считать
Мой тренировочный набор работает отлично, но когда я запускаю тестовый набор, он показывает мне эту ошибку
RuntimeError: Форма маски [1682] с индексом 0 не соответствует форме индексированного тензора [1, 1682] с индексом 0
Я получил ошибку в конце тестового блока, который я там прокомментировал
КОД: -
# Auto Encoder
import numpy as np
import pandas as pd
import torch
import torch.nn as nn
import torch.nn as nn
import torch.nn.parallel
import torch.optim as optim
import torch.utils.data
from torch.autograd import Variable
# Importing dataset
movies= pd.read_csv('ml-1m/movies.dat',sep ='::', header= None,engine ='python', encoding= 'latin-1')
users= pd.read_csv('ml-1m/users.dat',sep ='::', header= None,engine ='python', encoding= 'latin-1')
ratings = pd.read_csv('ml-1m/ratings.dat',sep ='::', header= None,engine ='python', encoding= 'latin-1')
# preparing the training set and the dataset
training_set =pd.read_csv('ml-100k/u1.base',delimiter ='\t')
training_set =np.array(training_set, dtype= 'int')
test_set =pd.read_csv('ml-100k/u1.test',delimiter ='\t')
test_set =np.array(test_set, dtype= 'int')
# Getting the number of users and movies
# we are taking the maximum no of values from training set and test set
nb_users = int(max(max(training_set[:,0]), max(test_set[:,0])))
nb_movies = int(max(max(training_set[:,1]), max(test_set[:,1])))
# converting the data into an array within users in lines and movies in columns
def convert(data):
new_data = []
for id_users in range(1, nb_users +1):
id_movies = data[:,1][data[:,0]==id_users]#movies id from data
id_ratings = data[:,2][data[:,0]==id_users] #ratings
ratings= np.zeros(nb_movies)
ratings[id_movies-1] = id_ratings # -1 for making it start from 1
new_data.append(list(ratings))
return new_data
training_set =convert(training_set)
test_set =convert(test_set)
# Converting the data into Torch tensor
training_set = torch.FloatTensor(training_set)
test_set = torch.FloatTensor(test_set)
# creating the architecture of the neural network
class SAE(nn.Module):
def __init__(self, ): # after comma it will consider parameters of module ie parent class
super(SAE,self).__init__()#parent class inheritence
self.fc1 = nn.Linear(nb_movies, 20) #20 nodes in hidden layer
self.fc2= nn.Linear(20,10)
self.fc3 = nn.Linear(10,20) #decoding
self.fc4= nn.Linear(20, nb_movies) #decoding
self.activation= nn.Sigmoid()
#self.myparameters= nn.ParameterList(self.fc1,self.fc2,self.fc3,self.fc4,self.activation)
def forward(self, x):
x=self.activation(self.fc1(x))#encoding
x=self.activation(self.fc2(x))#encoding
x=self.activation(self.fc3(x)) #decoding
x=self.fc4(x) #last layer machine understand automaically
return x
sae= SAE()
criterion = nn.MSELoss()
optimizer= optim.RMSprop(sae.parameters(), lr= 0.01 , weight_decay =0.5)
# Training the SAE
nb_epoch = 200
for epoch in range(1, nb_epoch + 1):
train_loss = 0
s = 0.
for id_user in range(nb_users):
input = Variable(training_set[id_user]).unsqueeze(0)
target = input.clone()
if torch.sum(target.data > 0) > 0:
output = sae(input)
target.require_grad = False
output[target == 0] = 0
loss = criterion(output, target)
mean_corrector = nb_movies/float(torch.sum(target.data > 0) + 1e-10)
loss.backward()
train_loss += np.sqrt(loss.data.item()*mean_corrector)
s += 1.
optimizer.step()
print('epoch: '+str(epoch)+' loss: '+str(train_loss/s))
# Testing the SAE
test_loss = 0
s = 0.
for id_user in range(nb_users):
input = Variable(training_set[id_user]).unsqueeze(0)
target = Variable(test_set[id_user])
if torch.sum(target.data > 0) > 0:
output = sae(input)
target.require_grad = False
output[target == 0] = 0 # I get error at this line
loss = criterion(output, target)
mean_corrector = nb_movies/float(torch.sum(target.data > 0) + 1e-10)
test_loss += np.sqrt(loss.data.item()*mean_corrector)
s += 1.
print('test loss: '+str(test_loss/s))