Pytorch RuntimeError: expected scalar type Double but found Float
Pytorch RuntimeError: expected scalar type Double but found Float
我刚开始学习 Pytorch 并创建了我的第一个 LSTM。数据集是时间序列数据。下面是训练代码。
使用 .double() 不能修复错误。
在 Windows 11 环境中是 运行。
import torch
import torch.nn as nn
from torch.optim import SGD
import math
import numpy as np
class Predictor(nn.Module):
def __init__(self, inputDim, hiddenDim, outputDim):
super(Predictor, self).__init__()
self.rnn = nn.LSTM(input_size = inputDim,
hidden_size = hiddenDim,
batch_first = True)
self.output_layer = nn.Linear(hiddenDim, outputDim)
def forward(self, inputs, hidden0=None):
output, (hidden, cell) = self.rnn(inputs, hidden0)
output = self.output_layer(output[:, -1, :])
return output
def mkDataSet(train_x, train_y=None):
t_train_x = []
t_train_y = []
sequence_length = 50
data_length = train_x.shape[0]
for offset in range(data_length-sequence_length):
t_train_x.append([train_x.iloc[offset + i] for i in range(sequence_length)])
try:
t_train_y.append([train_y.iloc[offset + i] for i in range(sequence_length)])
except:
pass
return t_train_x, t_train_y
def mkRandomBatch(train_x, train_t, batch_size=10):
batch_x = []
batch_t = []
for _ in range(batch_size):
idx = np.random.randint(0, len(train_x) - 1)
batch_x.append(train_x[idx])
try:
batch_t.append(train_t[idx])
except:
pass
return torch.tensor(batch_x), torch.tensor(batch_t)
def main(train_x=train_x, train_y=train_y, test_x=test_x):
training_size = 10000
test_size = 1000
epochs_num = 1000
hidden_size = 5
batch_size = 100
train_x_origin, train_y_origin, test_x_origin = train_x.copy(), train_y.copy(), test_x.copy()
train_x, train_t = mkDataSet(train_x, train_y)
test_x = mkDataSet(test_x)
model = Predictor(train_x_origin.shape[1], hidden_size, 1)
criterion = nn.MSELoss()
optimizer = SGD(model.parameters(), lr=0.01)
for epoch in range(epochs_num):
# training
running_loss = 0.0
training_accuracy = 0.0
for i in range(int(training_size / batch_size)):
optimizer.zero_grad()
data, label = mkRandomBatch(train_x, train_t, batch_size)
output = model(data)
loss = criterion(output, label)
loss.backward()
optimizer.step()
running_loss += loss.data[0]
training_accuracy += np.sum(np.abs((output.data - label.data).numpy()) < 0.1)
#test
test_accuracy = 0.0
for i in range(int(test_size / batch_size)):
offset = i * batch_size
data, label = torch.tensor(test_x[offset:offset+batch_size])
output = model(data, None)
training_accuracy /= training_size
print('%d loss: %.3f, training_accuracy: %.5f, test_accuracy: %.5f' % (
epoch + 1, running_loss, training_accuracy))
if __name__ == '__main__':
main(train_x, train_y, test_x)
然后我有这个错误：
RuntimeError Traceback (most recent call last)
.ipynb Cell 26' in <cell line: 113>()
109 print('%d loss: %.3f, training_accuracy: %.5f, test_accuracy: %.5f' % (
110 epoch + 1, running_loss, training_accuracy))
113 if __name__ == '__main__':
--> 114 main(train_x, train_y, test_x)
.ipynb Cell 26' in main(train_x, train_y, test_x)
87 optimizer.zero_grad()
89 data, label = mkRandomBatch(train_x, train_t, batch_size)
---> 91 output = model(data)
93 loss = criterion(output, label)
94 loss.backward()
File ~\Documents\lib\site-packages\torch\nn\modules\module.py:1110, in Module._call_impl(self, *input, **kwargs)
1106 # If we don't have any hooks, we want to skip the rest of the logic in
1107 # this function, and just call forward.
1108 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1109 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1110 return forward_call(*input, **kwargs)
1111 # Do not call functions when jit is used
1112 full_backward_hooks, non_full_backward_hooks = [], []
.ipynb Cell 26' in Predictor.forward(self, inputs, hidden0)
16 def forward(self, inputs, hidden0=None):
---> 17 output, (hidden, cell) = self.rnn(inputs, hidden0)
18 output = self.output_layer(output[:, -1, :])
20 return output
File ~\Documents\lib\site-packages\torch\nn\modules\module.py:1110, in Module._call_impl(self, *input, **kwargs)
1106 # If we don't have any hooks, we want to skip the rest of the logic in
1107 # this function, and just call forward.
1108 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1109 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1110 return forward_call(*input, **kwargs)
1111 # Do not call functions when jit is used
1112 full_backward_hooks, non_full_backward_hooks = [], []
File ~\Documents\lib\site-packages\torch\nn\modules\rnn.py:761, in LSTM.forward(self, input, hx)
759 self.check_forward_args(input, hx, batch_sizes)
760 if batch_sizes is None:
--> 761 result = _VF.lstm(input, hx, self._flat_weights, self.bias, self.num_layers,
762 self.dropout, self.training, self.bidirectional, self.batch_first)
763 else:
764 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights, self.bias,
765 self.num_layers, self.dropout, self.training, self.bidirectional)
RuntimeError: expected scalar type Double but found Float
我认为 'data' 有问题，我通过 print(type(data)):
打印它的类型
torch.Tensor
这是浮点数而不是双精度数。你知道哪里出了问题吗？感谢您的帮助！
您输入模型的数据是 Double 类型的张量，而模型需要一个浮点型张量。在 mkRandomBatch() 函数的最后一行执行此操作：
return torch.tensor(batch_x).float(), torch.tensor(batch_t)
在损失计算过程中，标签张量可能会也可能不会出现类似的错误，在这种情况下，也请尝试将标签张量转换为浮点数。
我刚开始学习 Pytorch 并创建了我的第一个 LSTM。数据集是时间序列数据。下面是训练代码。 使用 .double() 不能修复错误。 在 Windows 11 环境中是 运行。
import torch
import torch.nn as nn
from torch.optim import SGD
import math
import numpy as np
class Predictor(nn.Module):
def __init__(self, inputDim, hiddenDim, outputDim):
super(Predictor, self).__init__()
self.rnn = nn.LSTM(input_size = inputDim,
hidden_size = hiddenDim,
batch_first = True)
self.output_layer = nn.Linear(hiddenDim, outputDim)
def forward(self, inputs, hidden0=None):
output, (hidden, cell) = self.rnn(inputs, hidden0)
output = self.output_layer(output[:, -1, :])
return output
def mkDataSet(train_x, train_y=None):
t_train_x = []
t_train_y = []
sequence_length = 50
data_length = train_x.shape[0]
for offset in range(data_length-sequence_length):
t_train_x.append([train_x.iloc[offset + i] for i in range(sequence_length)])
try:
t_train_y.append([train_y.iloc[offset + i] for i in range(sequence_length)])
except:
pass
return t_train_x, t_train_y
def mkRandomBatch(train_x, train_t, batch_size=10):
batch_x = []
batch_t = []
for _ in range(batch_size):
idx = np.random.randint(0, len(train_x) - 1)
batch_x.append(train_x[idx])
try:
batch_t.append(train_t[idx])
except:
pass
return torch.tensor(batch_x), torch.tensor(batch_t)
def main(train_x=train_x, train_y=train_y, test_x=test_x):
training_size = 10000
test_size = 1000
epochs_num = 1000
hidden_size = 5
batch_size = 100
train_x_origin, train_y_origin, test_x_origin = train_x.copy(), train_y.copy(), test_x.copy()
train_x, train_t = mkDataSet(train_x, train_y)
test_x = mkDataSet(test_x)
model = Predictor(train_x_origin.shape[1], hidden_size, 1)
criterion = nn.MSELoss()
optimizer = SGD(model.parameters(), lr=0.01)
for epoch in range(epochs_num):
# training
running_loss = 0.0
training_accuracy = 0.0
for i in range(int(training_size / batch_size)):
optimizer.zero_grad()
data, label = mkRandomBatch(train_x, train_t, batch_size)
output = model(data)
loss = criterion(output, label)
loss.backward()
optimizer.step()
running_loss += loss.data[0]
training_accuracy += np.sum(np.abs((output.data - label.data).numpy()) < 0.1)
#test
test_accuracy = 0.0
for i in range(int(test_size / batch_size)):
offset = i * batch_size
data, label = torch.tensor(test_x[offset:offset+batch_size])
output = model(data, None)
training_accuracy /= training_size
print('%d loss: %.3f, training_accuracy: %.5f, test_accuracy: %.5f' % (
epoch + 1, running_loss, training_accuracy))
if __name__ == '__main__':
main(train_x, train_y, test_x)
然后我有这个错误：
RuntimeError Traceback (most recent call last)
.ipynb Cell 26' in <cell line: 113>()
109 print('%d loss: %.3f, training_accuracy: %.5f, test_accuracy: %.5f' % (
110 epoch + 1, running_loss, training_accuracy))
113 if __name__ == '__main__':
--> 114 main(train_x, train_y, test_x)
.ipynb Cell 26' in main(train_x, train_y, test_x)
87 optimizer.zero_grad()
89 data, label = mkRandomBatch(train_x, train_t, batch_size)
---> 91 output = model(data)
93 loss = criterion(output, label)
94 loss.backward()
File ~\Documents\lib\site-packages\torch\nn\modules\module.py:1110, in Module._call_impl(self, *input, **kwargs)
1106 # If we don't have any hooks, we want to skip the rest of the logic in
1107 # this function, and just call forward.
1108 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1109 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1110 return forward_call(*input, **kwargs)
1111 # Do not call functions when jit is used
1112 full_backward_hooks, non_full_backward_hooks = [], []
.ipynb Cell 26' in Predictor.forward(self, inputs, hidden0)
16 def forward(self, inputs, hidden0=None):
---> 17 output, (hidden, cell) = self.rnn(inputs, hidden0)
18 output = self.output_layer(output[:, -1, :])
20 return output
File ~\Documents\lib\site-packages\torch\nn\modules\module.py:1110, in Module._call_impl(self, *input, **kwargs)
1106 # If we don't have any hooks, we want to skip the rest of the logic in
1107 # this function, and just call forward.
1108 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1109 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1110 return forward_call(*input, **kwargs)
1111 # Do not call functions when jit is used
1112 full_backward_hooks, non_full_backward_hooks = [], []
File ~\Documents\lib\site-packages\torch\nn\modules\rnn.py:761, in LSTM.forward(self, input, hx)
759 self.check_forward_args(input, hx, batch_sizes)
760 if batch_sizes is None:
--> 761 result = _VF.lstm(input, hx, self._flat_weights, self.bias, self.num_layers,
762 self.dropout, self.training, self.bidirectional, self.batch_first)
763 else:
764 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights, self.bias,
765 self.num_layers, self.dropout, self.training, self.bidirectional)
RuntimeError: expected scalar type Double but found Float
我认为 'data' 有问题，我通过 print(type(data)):
打印它的类型torch.Tensor
这是浮点数而不是双精度数。你知道哪里出了问题吗？感谢您的帮助！
您输入模型的数据是 Double 类型的张量，而模型需要一个浮点型张量。在 mkRandomBatch() 函数的最后一行执行此操作：
return torch.tensor(batch_x).float(), torch.tensor(batch_t)
在损失计算过程中，标签张量可能会也可能不会出现类似的错误，在这种情况下，也请尝试将标签张量转换为浮点数。