Python Pytorch上的1D CNN:mat1和mat2形状不能相乘(10x3和10x2)
我有一个样本大小为500的时间序列和两种类型的标签,我想构建一个带有pytorch的1D CNN:Python Pytorch上的1D CNN:mat1和mat2形状不能相乘(10x3和10x2),python,neural-network,pytorch,torch,Python,Neural Network,Pytorch,Torch,我有一个样本大小为500的时间序列和两种类型的标签,我想构建一个带有pytorch的1D CNN: class Simple1DCNN(torch.nn.Module): def __init__(self): super(Simple1DCNN, self).__init__() self.layer1 = torch.nn.Conv1d(in_channels=50, out
class Simple1DCNN(torch.nn.Module):
def __init__(self):
super(Simple1DCNN, self).__init__()
self.layer1 = torch.nn.Conv1d(in_channels=50,
out_channels=20,
kernel_size=5,
stride=2)
self.act1 = torch.nn.ReLU()
self.layer2 = torch.nn.Conv1d(in_channels=20,
out_channels=10,
kernel_size=1)
self.fc1 = nn.Linear(10* 1 * 1, 2)
def forward(self, x):
x = x.view(1, 50,-1)
x = self.layer1(x)
x = self.act1(x)
x = self.layer2(x)
x = self.fc1(x)
return x
model = Simple1DCNN()
model(torch.tensor(np.random.uniform(-10, 10, 500)).float())
但收到了以下错误消息:
Traceback (most recent call last):
File "so_pytorch.py", line 28, in <module>
model(torch.tensor(np.random.uniform(-10, 10, 500)).float())
File "/Users/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "so_pytorch.py", line 23, in forward
x = self.fc1(x)
File "/Users/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/Users/lib/python3.8/site-packages/torch/nn/modules/linear.py", line 93, in forward
return F.linear(input, self.weight, self.bias)
File "/Users/lib/python3.8/site-packages/torch/nn/functional.py", line 1692, in linear
output = input.matmul(weight.t())
RuntimeError: mat1 and mat2 shapes cannot be multiplied (10x3 and 10x2)
回溯(最近一次呼叫最后一次):
文件“so_pytorch.py”,第28行,在
模型(torch.tensor(np.random.uniform(-10,10500)).float())
文件“/Users/lib/python3.8/site packages/torch/nn/modules/module.py”,第727行,在
结果=自我转发(*输入,**kwargs)
文件“so_pytorch.py”,第23行,向前
x=自身.fc1(x)
文件“/Users/lib/python3.8/site packages/torch/nn/modules/module.py”,第727行,在
结果=自我转发(*输入,**kwargs)
文件“/Users/lib/python3.8/site packages/torch/nn/modules/linear.py”,第93行,向前
返回F.linear(输入、自重、自偏压)
文件“/Users/lib/python3.8/site packages/torch/nn/functional.py”,第1692行,线性
输出=输入.matmul(weight.t())
运行时错误:mat1和mat2形状不能相乘(10x3和10x2)
我做错了什么?行
x=self.layer2(x)
(也是下一行x=self.fc1(x)
的输入)的输出形状是torch.Size([1,10,3])
现在从self.fc1
的定义来看,它期望其输入的最后一个维度是10*1*1
,即10
,而您的输入有3
,因此出现错误
我不知道你想做什么,但假设你想做的是
500
大小序列标记为两个标签中的一个,然后执行此操作10
timesteps分别标记为两个标签中的一个,然后执行此操作# replace self.fc1 = nn.Linear(10* 1 * 1, 2) with
self.fc1 = nn.Linear(10 * 3, 2)
# replace x = self.fc1(x) with
x = x.view(1, -1)
x = self.fc1(x)
# replace self.fc1 = nn.Linear(10* 1 * 1, 2) with
self.fc1 = nn.Linear(2, 2)