刚刚接触深度学习，希望同学们能指点一下
做一个一维数据的分类模型，一共有9类，一类样本有1024个样本，一个样本有1024个数据。（样本在csv中是一行一个）
下面是模型代码
import torch
import numpy as np
import pandas as pd
import torch.nn as nn
import torch.nn.functional as F
import matplotlib.pyplot as plt
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
class CNN(nn.Module):
def __init__(self):
super(CNN, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv1d(
in_channels=1,
out_channels=16,
kernel_size=5,
stride=1,
padding=2
),
nn.ReLU(),
nn.MaxPool1d(kernel_size=1)
)
self.conv2 = nn.Sequential(
nn.Conv1d(
in_channels=16,
out_channels=64,
kernel_size=5,
stride=1,
padding=2
),
nn.ReLU(),
nn.MaxPool1d(kernel_size=1)
)
self.out = nn.Linear(128, 9)
def forward(self, x):
# x = torch.Tensor(x).view(-1, 1, 1024)
# x = torch.unsqueeze(x, dim=0)
print(x.shape)
x = self.conv1(x),
x = self.conv2(x),
output = self.out(x)
return output
# 转tensor
# transform = transforms.Compose([
# transforms.ToTensor(),
# transforms.Normalize((0.1307,), (0.3081,))
# ])
# 数据导入
class MyDataset:
def __init__(self, filepath):
xy = np.loadtxt(filepath, delimiter=',', dtype=np.float32)
self.len = xy.shape[0]
self.x_data = torch.from_numpy(xy[:, :-1])
self.y_data = torch.from_numpy(xy[:, [-1]])
print('--------数据已载入--------')
def __getitem__(self, index):
return self.x_data[index], self.y_data[index]
def __len__(self):
return self.len
file = 'F:/PyCharm 项目/dataset/多分类/多分类—CNN .csv'
mydataset = MyDataset(file)
train_loader = DataLoader(dataset=mydataset,
batch_size=16,
shuffle=True)
# 实例化模型
model = CNN()
# 损失函数：交叉熵
criterion = nn.CrossEntropyLoss()
# 带动量的随机梯度下降
optimizer = torch.optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
# 储存损失
loss_list = []
for epoch in range(5):
for batch, (X, y) in enumerate(train_loader):
# 正向传播
y_pred = model(X)
# 计算损失
loss = criterion(y_pred, y)
# 梯度归零
optimizer.zero_grad()
# 反向传播
loss.backward()
# 更新参数
optimizer.step()
# 每100次查看损失
if batch % 100 == 0:
loss_list.append(loss.data.item())
print('loss-------------:', loss.data.item())
# 显示损失下降的图像
plt.plot(np.linspace(0, 1000, len(loss_list)), loss_list)
plt.show()
# 检验测试集的正确率
rets = []
total = 0
correct = 0
# 不需要计算梯度
with torch.no_grad():
for data in test_loader:
X, y = data
y_pred = model(X)
# 返回值有两个，第一个是最大的值，第二个是最大值的索引
_, predicted = torch.max(y_pred.data, dim=1)
total += y.size(0)
correct += (predicted == y).sum().item()
print('Accuracy on test set: %.2f %% ' % (100.0 * (correct / total)))
运行之后出这个bug
```python
"F:\PyCharm 2020.1\Anadonda 3\python.exe" "F:/PyCharm 项目/练习/1D-CNN/CNN.py"
--------数据已载入--------
torch.Size([16, 1024])
Traceback (most recent call last):
File "F:/PyCharm 项目/练习/1D-CNN/CNN.py", line 93, in <module>
y_pred = model(X)
File "F:\PyCharm 2020.1\Anadonda 3\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "F:/PyCharm 项目/练习/1D-CNN/CNN.py", line 42, in forward
x = self.conv1(x),
File "F:\PyCharm 2020.1\Anadonda 3\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "F:\PyCharm 2020.1\Anadonda 3\lib\site-packages\torch\nn\modules\container.py", line 141, in forward
input = module(input)
File "F:\PyCharm 2020.1\Anadonda 3\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "F:\PyCharm 2020.1\Anadonda 3\lib\site-packages\torch\nn\modules\conv.py", line 302, in forward
return self._conv_forward(input, self.weight, self.bias)
File "F:\PyCharm 2020.1\Anadonda 3\lib\site-packages\torch\nn\modules\conv.py", line 298, in _conv_forward
return F.conv1d(input, weight, bias, self.stride,
RuntimeError: Given groups=1, weight of size [16, 1, 5], expected input[1, 16, 1024] to have 1 channels, but got 16 channels instead
```
RuntimeError: Given groups=1, weight of size [16, 1, 5], expected input[1, 16, 1024] to have 1 channels, but got 16 channels instead
数据集的维度不匹配
你的标签不对，要用独热码编辑