我有一个基本的PyTorch LSTM:
import torch.nn as nn
import torch.nn.functional as F
class BaselineLSTM(nn.Module):
def __init__(self):
super(BaselineLSTM, self).__init__()
self.lstm = nn.LSTM(input_size=13, hidden_size=13)
def forward(self, x):
x = self.lstm(x)
return x
对于我的数据,我有:
train_set = CorruptedAudioDataset(corrupted_path, train_set=True)
train_loader = torch.utils.data.DataLoader(train_set, batch_size=128, shuffle=True, **kwargs)
我CorruptedAudioDataset
有:
def __getitem__(self, index):
corrupted_sound_file = SoundFile(self.file_paths[index])
corrupted_samplerate = corrupted_sound_file.samplerate
corrupted_signal_audio_array = corrupted_sound_file.read()
clean_path = self.file_paths[index].split('/')
# print(self.file_paths[index], clean_path)
clean_sound_file = SoundFile(self.file_paths[index])
clean_samplerate = clean_sound_file.samplerate
clean_signal_audio_array = clean_sound_file.read()
corrupted_mfcc = mfcc(corrupted_signal_audio_array, samplerate=corrupted_samplerate)
clean_mfcc = mfcc(clean_signal_audio_array, samplerate=clean_samplerate)
print('return', corrupted_mfcc.shape, clean_mfcc.shape)
return corrupted_mfcc, clean_mfcc
我的训练循环如下:
model = BaselineLSTM()
for epoch in range(300):
for inputs, outputs in train_loader:
print('inputs', inputs)
这就是我得到错误的那一行:
File "train_lstm_baseline.py", line 47, in train
for inputs, outputs in train_loader:
...
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 1219 and 440 in dimension 1 at ../aten/src/TH/generic/THTensor.cpp:612
不知道我在做什么错。任何帮助,将不胜感激。谢谢!
基本上会引发此异常,因为您正在加载具有不同形状的批次。由于它们存储在同一张量中,因此所有样本都必须具有相同的形状。在这种情况下,您将无法输入尺寸为0的1219和440。例如,您有以下内容:
torch.Size([1, 1219])
torch.Size([1, 440])
torch.Size([1, 550])
...
你必须有:
torch.Size([1, n])
torch.Size([1, n])
torch.Size([1, n])
...
解决此问题的最简单方法是设置batch_size=1
。但是,这可能会延迟您的代码。
最好的方法是将数据设置为相同的形状。在这种情况下,您需要评估您的问题以检查是否可能。
希望对您有所帮助。
本文收集自互联网,转载请注明来源。
如有侵权,请联系[email protected] 删除。
我来说两句