我对PyTorch和神经网络非常陌生,尤其在创建一个通过姓名分类性别的神经网络方面遇到了一些问题。
我参考了PyTorch教程中按国籍分类姓名的RNN,但我决定不采用循环的方法...如果这个想法不正确,请立即停止我!
然而,每当我试图通过网络运行输入时,它告诉我:
RuntimeError: matrices expected, got 3D, 2D tensors at /py/conda-bld/pytorch_1493681908901/work/torch/lib/TH/generic/THTensorMath.c:1232
我知道这与PyTorch始终期望有批量大小有关,而我已经按照这种方式设置了我的张量,但你可能可以从这一点看出来,我不知道我在说什么。
这是我的代码:
from future import unicode_literals, print_function, division
from io import open
import glob
import unicodedata
import string
import torch
import torchvision
import torch.nn as nn
import torch.optim as optim
import random
from torch.autograd import Variable
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker
"""------GLOBAL VARIABLES------"""
all_letters = string.ascii_letters + " .,;'"
num_letters = len(all_letters)
all_names = {}
genders = ["Female", "Male"]
"""-------DATA EXTRACTION------"""
def findFiles(path):
return glob.glob(path)
def unicodeToAscii(s):
return ''.join(
c for c in unicodedata.normalize('NFD', s)
if unicodedata.category(c) != 'Mn'
and c in all_letters
)
# Read a file and split into lines
def readLines(filename):
lines = open(filename, encoding='utf-8').read().strip().split('\n')
return [unicodeToAscii(line) for line in lines]
for file in findFiles("/home/andrew/PyCharm/PycharmProjects/CantStop/data/names/*.txt"):
gender = file.split("/")[-1].split(".")[0]
names = readLines(file)
all_names[gender] = names
"""-----DATA INTERPRETATION-----"""
def nameToTensor(name):
tensor = torch.zeros(len(name), 1, num_letters)
for index, letter in enumerate(name):
tensor[index][0][all_letters.find(letter)] = 1
return tensor
def outputToGender(output):
gender, gender_index = output.data.topk(1)
if gender_index[0][0] == 0:
return "Female"
return "Male"
"""------NETWORK SETUP------"""
class Net(nn.Module):
def __init__(self, input_size, output_size):
super(Net, self).__init__()
#Layer 1
self.Lin1 = nn.Linear(input_size, int(input_size/2))
self.ReLu1 = nn.ReLU()
self.Batch1 = nn.BatchNorm1d(int(input_size/2))
#Layer 2
self.Lin2 = nn.Linear(int(input_size/2), output_size)
self.ReLu2 = nn.ReLU()
self.Batch2 = nn.BatchNorm1d(output_size)
self.softMax = nn.LogSoftmax()
def forward(self, input):
output1 = self.Batch1(self.ReLu1(self.Lin1(input)))
output2 = self.softMax(self.Batch2(self.ReLu2(self.Lin2(output1))))
return output2
NN = Net(num_letters, 2)
"""------TRAINING------"""
def getRandomTrainingEx():
gender = genders[random.randint(0, 1)]
name = all_names[gender][random.randint(0, len(all_names[gender])-1)]
gender_tensor = Variable(torch.LongTensor([genders.index(gender)]))
name_tensor = Variable(nameToTensor(name))
return gender_tensor, name_tensor, gender
def train(input, target):
loss_func = nn.NLLLoss()
optimizer = optim.SGD(NN.parameters(), lr=0.0001, momentum=0.9)
optimizer.zero_grad()
output = NN(input)
loss = loss_func(output, target)
loss.backward()
optimizer.step()
return output, loss
all_losses = []
current_loss = 0
for i in range(100000):
gender_tensor, name_tensor, gender = getRandomTrainingEx()
output, loss = train(name_tensor, gender_tensor)
current_loss += loss
if i%1000 == 0:
print("Guess: %s, Correct: %s, Loss: %s" % (outputToGender(output), gender, loss.data[0]))
if i%100 == 0:
all_losses.append(current_loss/10)
current_loss = 0
# plt.figure()
# plt.plot(all_losses)
# plt.show()
请帮助一个初学者!
word2vec
。 - finbarr