IndexError: форма маски [1, 1682] с индексом 0 не соответствует форме индексированного тензора [100, 1682] с индексом 0. - PullRequest
Новая
       0

IndexError: форма маски [1, 1682] с индексом 0 не соответствует форме индексированного тензора [100, 1682] с индексом 0.

0 голосов
/ 28 мая 2020

Я сейчас прохожу курс DeepLearning в Удеми. В настоящее время я разрабатываю машину Больцмана с ограничениями, на которой мое обучение проходит идеально, но я получил эту ошибку при тестировании

IndexError: форма маски [1, 1682] с индексом 0 не соответствует форме индексированного тензора [100, 1682] с индексом 0 


import numpy as np
import pandas as pd
import torch
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 training and test set
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 no of users and movies
nb_users = int(max(max(training_set[:,0]),max(test_set[:,0]))) #max out of both
nb_movies = int(max(max(training_set[:,1]),max(test_set[:,1])))

#Array with 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]
        id_ratings = data[:,2][data[:,0]==id_users]
        ratings = np.zeros(nb_movies)
        ratings[id_movies-1]= id_ratings
        new_data.append(list(ratings))
    return new_data

training_set = convert(training_set)
test_set = convert(test_set)

# COnverting data to torcch tensors
training_set = torch.FloatTensor(training_set)
test_set = torch.FloatTensor(test_set)

# Converting the rating into binary ratings 1 (Liked) or 0 (Not liked)
training_set[training_set == 0] = -1 #taking all zero values in trainingset
training_set[training_set == 1] = 0
training_set[training_set == 2] = 0
training_set[training_set >= 3] = 1
test_set[test_set == 0] = -1 #taking all zero values in trainingset
test_set[test_set == 1] = 0
test_set[test_set == 2] = 0
test_set[test_set >= 3] = 1

# Creating the architecture of the Neural network
class RBM():
    def __init__(self, nv, nh):
        self.W = torch.randn(nh, nv)
        self.a = torch.randn(1, nh)
        self.b = torch.randn(1, nv)
    def sample_h(self, x):
        wx = torch.mm(x, self.W.t())
        activation = wx + self.a.expand_as(wx)
        p_h_given_v = torch.sigmoid(activation)
        return p_h_given_v, torch.bernoulli(p_h_given_v)
    def sample_v(self, y):
        wy = torch.mm(y, self.W)
        activation = wy + self.b.expand_as(wy)
        p_v_given_h = torch.sigmoid(activation)
        return p_v_given_h, torch.bernoulli(p_v_given_h)
    def train(self, v0, vk, ph0, phk):
        self.W += (torch.mm(v0.t(), ph0) - torch.mm(vk.t(), phk)).t()
        self.b += torch.sum((v0 - vk), 0)
        self.a += torch.sum((ph0 - phk), 0)
nv = len(training_set[0])
nh = 100
batch_size = 100
rbm = RBM(nv, nh)

#Training the RBM
nb_epoch = 10
for epoch in range(1, nb_epoch + 1):
    train_loss = 0
    s = 0.
    for id_user in range(0, nb_users - batch_size, batch_size):
        vk = training_set[id_user:id_user+batch_size]
        v0 = training_set[id_user:id_user+batch_size]
        ph0,_ = rbm.sample_h(v0)
        for k in range(10):
            _,hk = rbm.sample_h(vk)
            _,vk = rbm.sample_v(hk)
            vk[v0<0] = v0[v0<0]
        phk,_ = rbm.sample_h(vk)
        rbm.train(v0, vk, ph0, phk)
        train_loss += torch.mean(torch.abs(v0[v0>=0] - vk[v0>=0]))
        s += 1.
    print(f'epoch: {epoch} loss: {train_loss/s}')


# Testing the RBM
test_loss = 0
s = 0.
for id_user in range(nb_users):
    v = training_set[id_user:id_user+1]
    vt = training_set[id_user:id_user+1]
    if len(vt[vt>=0]) > 0:
        _,h = rbm.sample_h(v)
        _,v = rbm.sample_v(hk)
    test_loss += torch.mean(torch.abs(vt[vt>=0] - v[vt>=0]))
    s += 1.
print(f'test_loss: {test_loss/s}')

1 Ответ

0 голосов
/ 28 мая 2020

В тесте l oop вы повторно используете переменную фазы обучения, что, я думаю (вы не предоставили полную трассировку стека), является просто опечаткой: 

for id_user in range(nb_users):
    v = training_set[id_user:id_user+1]
    vt = training_set[id_user:id_user+1]
    if len(vt[vt>=0]) > 0:
        _,h = rbm.sample_h(v)
        _,v = rbm.sample_v(hk)  # hk should be h, shouldn't it?
...