**我的完整代码在这里：我正在按照github代码完成任务。我收到尺寸不匹配错误。该代码给我尺寸不匹配错误。我收到以下错误：ValueError：预期输入batch_size（1）匹配目标batch_size（64）。我很困惑，我不知道我应该在此代码中更改什么。请帮助我解决此问题。 **
def windowz(data, size):
start = 0
while start < len(data):
yield start, start + size
start += (size // 2)
def segment_pa2(x_train,y_train,window_size):
segments = np.zeros(((len(x_train)//(window_size//2))-1,window_size,52))
labels = np.zeros(((len(y_train)//(window_size//2))-1))
i_segment = 0
i_label = 0
for (start,end) in windowz(x_train,window_size):
if(len(x_train[start:end]) == window_size):
m = stats.mode(y_train[start:end])
segments[i_segment] = x_train[start:end]
labels[i_label] = m[0]
i_label+=1
i_segment+=1
return segments, labels
print ('starting...')
start_time = time.time()
dataset = sys.argv[1]
path = '/Users/tehreem/Desktop/PAMAP2/PAMAP2_Dataset/pamap2.h5'
f = h5py.File(path, 'r')
print(f)
x_train = f.get('train').get('inputs')[()]
y_train = f.get('train').get('targets')[()]
x_test = f.get('test').get('inputs')[()]
y_test = f.get('test').get('targets')[()]
print ("x_train shape =",x_train.shape)
print ("y_train shape =",y_train.shape)
print ("x_test shape =" ,x_test.shape)
print ("y_test shape =",y_test.shape)
x_train = x_train[::3,:]
y_train = y_train[::3]
x_test = x_test[::3,:]
y_test = y_test[::3]
print ("x_train shape(downsampled) = ", x_train.shape)
print ("y_train shape(downsampled) =",y_train.shape)
print ("x_test shape(downsampled) =" ,x_test.shape)
print ("y_test shape(downsampled) =",y_test.shape)
print (np.unique(y_train))
print (np.unique(y_test))
unq = np.unique(y_test)
input_width = 52
print("segmenting signal...")
train_x, train_y = segment_pa2(x_train,y_train,input_width)
test_x, test_y = segment_pa2(x_test,y_test,input_width)
print ("signal segmented.")
train = pd.get_dummies(train_y)
test = pd.get_dummies(test_y)
train, test = train.align(test, join='inner', axis=1)
train_y = np.asarray(train)
test_y = np.asarray(test)
input_height = 1
input_width = input_width
num_labels = 11
num_channels = 52
batch_size = 64
stride_size = 2
kernel_size_1 = 7
kernel_size_2 = 3
kernel_size_3 = 1
depth_1 = 128
depth_2 = 128
depth_3 = 128
num_hidden = 512
dropout_1 = 0.1 #0.1
dropout_2 = 0.25 #0.25
dropout_3 = 0.5 #0.5
learning_rate = 0.0005
training_epochs = 50
total_batches = train_x.shape[0] // batch_size
train_x = train_x.reshape(len(train_x),1,input_width,num_channels)
test_x = test_x.reshape(len(test_x),1,input_width,num_channels)
print ("test_x_reshaped = " , test_x.shape)
print ("train_x shape =",train_x.shape)
print ("train_y shape =",train_y.shape)
print ("test_x shape =",test_x.shape)
print ("test_y shape =",test_y.shape)
train_x = train_x.reshape(-1,input_width,num_channels)
test_x = test_x.reshape(-1,input_width,num_channels)
def init_weights(m):
if type(m) == nn.LSTM:
for name, param in m.named_parameters():
if 'weight_ih' in name:
torch.nn.init.orthogonal_(param.data)
elif 'weight_hh' in name:
torch.nn.init.orthogonal_(param.data)
elif 'bias' in name:
param.data.fill_(0)
elif type(m) == nn.Conv1d or type(m) == nn.Linear:
torch.nn.init.orthogonal_(m.weight)
m.bias.data.fill_(0)
model.apply(init_weights)
import torch
import torch.nn as nn
import torch.nn.functional as F
class CharCNN(nn.Module):
def __init__(self):
super(CharCNN, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv1d(num_channels, depth_1, kernel_size=kernel_size_1, stride=stride_size),
nn.ReLU(),
nn.MaxPool1d(kernel_size=kernel_size_1, stride=stride_size),
nn.Dropout(0.1),
)
self.conv2 = nn.Sequential(
nn.Conv1d(depth_1, depth_2, kernel_size=kernel_size_2, stride=stride_size),
nn.ReLU(),
nn.MaxPool1d(kernel_size=kernel_size_2, stride=stride_size),
nn.Dropout(0.25)
)
self.fc1 = nn.Sequential(
nn.Linear(128*64, num_hidden),
nn.ReLU(),
nn.Dropout(0.5)
)
self.fc2 = nn.Sequential(
nn.Linear(num_hidden, 11),
nn.ReLU(),
nn.Dropout(0.5)
)
def forward(self, x):
out = self.conv1(x)
out = self.conv2(out)
# collapse
out = out.reshape(-1,128*64)
#out = out.view(out.size(0), -1)
# linear layer
out = self.fc1(out)
# output layer
out = self.fc2(out)
#out = self.log_softmax(x,dim=1)
return out
model = CharCNN()
print(model)
def iterate_minibatches(inputs, targets, batch_size, shuffle=True):
assert len(inputs) == len(targets)
if shuffle:
indices = np.arange(len(inputs))
np.random.shuffle(indices)
for start_idx in range(0, len(inputs) - batch_size + 1, batch_size):
if shuffle:
excerpt = indices[start_idx:start_idx + batch_size]
else:
excerpt = slice(start_idx, start_idx + batch_size)
yield inputs[excerpt], targets[excerpt]
criterion = nn.CrossEntropyLoss()
opt = torch.optim.Adam(model.parameters(),lr=learning_rate)
for e in range(training_epochs):
if(train_on_gpu):
net.cuda()
train_losses = []
for batch in iterate_minibatches(train_x, train_y, batch_size):
x, y = batch
inputs, targets = torch.from_numpy(x), torch.from_numpy(y)
if(train_on_gpu):
inputs, targets = inputs.cuda(), targets.cuda()
#inputs= inputs.view(batch_size, 128*64)
#targets = targets.view(batch_size)
opt.zero_grad()
output = model(inputs)
loss = criterion(output, targets.long())
train_losses.append(loss.item())
loss.backward()
opt.step()
val_losses = []
accuracy=0
f1score=0
print("Epoch: {}/{}...".format(e+1, training_epochs),
"Train Loss: {:.4f}...".format(np.mean(train_losses)))
我收到以下错误：
<ipython-input-468-7a508893b28d> in <module>
21 output = model(inputs)
22
---> 23 loss = criterion(output, targets.long())
24 train_losses.append(loss.item())
25 loss.backward()
~\AppData\Local\Continuum\anaconda3\lib\site-packages\torch\nn\modules\module.py in __call__(self, *input, **kwargs)
530 result = self._slow_forward(*input, **kwargs)
531 else:
--> 532 result = self.forward(*input, **kwargs)
533 for hook in self._forward_hooks.values():
534 hook_result = hook(self, input, result)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\torch\nn\modules\loss.py in forward(self, input, target)
914 def forward(self, input, target):
915 return F.cross_entropy(input, target, weight=self.weight,
--> 916 ignore_index=self.ignore_index, reduction=self.reduction)
917
918
~\AppData\Local\Continuum\anaconda3\lib\site-packages\torch\nn\functional.py in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction)
2019 if size_average is not None or reduce is not None:
2020 reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 2021 return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
2022
2023
~\AppData\Local\Continuum\anaconda3\lib\site-packages\torch\nn\functional.py in nll_loss(input, target, weight, size_average, ignore_index, reduce, reduction)
1834 if input.size(0) != target.size(0):
1835 raise ValueError('Expected input batch_size ({}) to match target batch_size ({}).'
-> 1836 .format(input.size(0), target.size(0)))
1837 if dim == 2:
1838 ret = torch._C._nn.nll_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
ValueError: Expected input batch_size (1) to match target batch_size (64).```
答案 0 :(得分：0)
您发布的代码没有正确粘贴正确的缩进（代码的每个部分都不相同），因此很难遍历代码。
但是据我从您的错误消息中了解到的，问题出在“输出”张量的大小上。对于64的批量大小，“输出”张量应具有尺寸（64，num_classes）。但是根据错误消息，“输出”张量的第一维为1。我怀疑您的张量中会增加一个额外的维度。
我建议使用output.size()打印出“输出”张量的大小，这应该使您知道错误的根源。如果我的直觉是正确的并且确实是（1，64，num_classes），那么简单的output = output.squeeze(0)就可以解决问题。