import numpy as np
import torch
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
class DiabetesDataset(Dataset):
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]])
def __getitem__(self, index):
return self.x_data[index],self.y_data[index]
def __len__(self):
return self.len
dataset = DiabetesDataset('diabetes.csv.gz')
train_loader = DataLoader(dataset=dataset,batch_size=32,shuffle=True,num_workers=2)
# 模型构造
class Model(torch.nn.Module):
def __init__(self):
super(Model, self).__init__()#必要步骤，调用弗雷构造
self.linear1 = torch.nn.Linear(8,6)
self.linear2 = torch.nn.Linear(6,4)
self.linear3 = torch.nn.Linear(4,1)
self.sigmoid = torch.nn.Sigmoid()
def forward(self,x):
#这一步的输出作为下一步的输入
x = self.sigmoid(self.linear1(x))
x = self.sigmoid(self.linear2(x))
x = self.sigmoid(self.linear3(x))
return x
model = Model() #实例化
# 损失函数与优化器
criterion = torch.nn.BCELoss(size_average=True)
optimizer = torch.optim.SGD(model.parameters(),lr=0.01)
# Using DataLoader
for epoch in range(100):
for i, data in enumerate(train_loader,0):
# 1.Prepare data
# 从data中提取数据和标签
inputs, labels = data
# 2.forward,计算预测值和损失值
y_pred = model(inputs)
loss = criterion(y_pred,labels)
print(epoch,i,loss.item())
# 3. Backward
optimizer.zero_grad()
loss.backward()
#4.update
optimizer.step()
真的出现了，runtimeerror
import numpy as np
import torch
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
class DiabetesDataset(Dataset):
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]])
def __getitem__(self, index):
return self.x_data[index],self.y_data[index]
def __len__(self):
return self.len
dataset = DiabetesDataset('diabetes.csv.gz')
train_loader = DataLoader(dataset=dataset,batch_size=32,shuffle=True,num_workers=2)
# 模型构造
class Model(torch.nn.Module):
def __init__(self):
super(Model, self).__init__()#必要步骤，调用弗雷构造
self.linear1 = torch.nn.Linear(8,6)
self.linear2 = torch.nn.Linear(6,4)
self.linear3 = torch.nn.Linear(4,1)
self.sigmoid = torch.nn.Sigmoid()
def forward(self,x):
#这一步的输出作为下一步的输入
x = self.sigmoid(self.linear1(x))
x = self.sigmoid(self.linear2(x))
x = self.sigmoid(self.linear3(x))
return x
model = Model() #实例化
# 损失函数与优化器
criterion = torch.nn.BCELoss(size_average=True)
optimizer = torch.optim.SGD(model.parameters(),lr=0.01)
if __name__ == '__main__':
# Using DataLoader
for epoch in range(100):
for i, data in enumerate(train_loader,0):
# 1.Prepare data
# 从data中提取数据和标签
inputs, labels = data
# 2.forward,计算预测值和损失值
y_pred = model(inputs)
loss = criterion(y_pred,labels)
print(epoch,i,loss.item())
# 3. Backward
optimizer.zero_grad()
loss.backward()
#4.update
optimizer.step()
import torch
criterion = torch.nn.CrossEntropyLoss()
Y = torch.LongTensor([2,0,1])
Y_pred1 = torch.Tensor([[0.1,0.2,0.9],
[1.1,0.1,0.2],
[0.2,2.1,0.1]])
Y_pred2 = torch.Tensor([[0.8,0.2,0.3],
[0.2,0.3,0.5],
[0.2,0.2,0.5]])
l1 = criterion(Y_pred1,Y)
l2 = criterion(Y_pred2,Y)
print("Batch Loss1 = ",l1.data,"\nBatch Loss2=",l2.data)
和预测的结果一样，LOSS1是比较小的，因为算出来的比较吻合，损失较小
Y是预测值，Y_PRE是初始值
import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim
batch_size = 64
# Convert the PIL Image to Tensor
# totensor，把输入的图像转换为张量
# normalize: mean 均值 std标准差，就是0.1307，0.3081
transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.1307,),(0.3081,))])
train_dataset = datasets.MNIST(root='../dataset/mnist/',train=True,download=True,transform=transform)
train_loader = DataLoader(train_dataset,shuffle=True,batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist/',train=False,download=True,transform=transform)
test_loader = DataLoader(test_dataset,shuffle=False,batch_size=batch_size)
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.l1 = torch.nn.Linear(784,512)
self.l2 = torch.nn.Linear(512,256)
self.l3 = torch.nn.Linear(256,128)
self.l4 = torch.nn.Linear(128, 64)
self.l5 = torch.nn.Linear(64, 10)
def forward(self,x):
x = x.view(-1,784)
x = F.relu(self.l1(x))
x = F.relu(self.l2(x))
x = F.relu(self.l3(x))
x = F.relu(self.l4(x))
return self.l5(x)
model = Net()
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(),lr=0.01,momentum=0.5)
def train(epoch):
running_loss = 0.0
for batch_idx, data in enumerate(train_loader,0):
inputs,target = data
optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs,target)
loss.backward()
optimizer.step()
# 累计的loss拿出来，取loss的时候要用item
running_loss += loss.item()
# 如果300次迭代就拿出来
if batch_idx %300 == 299:
print('[%d,%5d] loss: %.3f' % (epoch+1,batch_idx+1,running_loss/300))
running_loss = 0.0
# test
def test():
correct = 0
total = 0
# torch.no_grad这里面不会计算梯度
with torch.no_grad():
for data in test_loader:
images, labels = data
# 拿完数据做预测，拿下标
outputs = model(images)
# 沿着横去找最大值的下标
_, predicted = torch.max(outputs.data,dim=1)
# 加上总数，total就是batch_size
total += labels.size(0)
# 求和拿出来，我们猜对了多少个
correct += (predicted == labels).sum().item()
print('Accuray on test set: "%d %%' % (100*correct/total))
if __name__ == '__main__':
for epoch in range(10):
train(epoch)
if epoch%10 == 9:
test()
import torch
in_channels,out_channels = 5,10
width ,height = 100,100
kernel_size = 3 #卷积核的大小
batch_size = 1
# 在pytorch里面，所以输入的数据必须是小批量的数据
input = torch.randn(batch_size,in_channels,width,height)
# 大小，尺寸 3*3 或者5*3 都可以，一般来说是正方形
conv_layer = torch.nn.Conv2d(in_channels,out_channels,kernel_size=kernel_size)
#创建的卷积对象 conv_layer 把input送给他
output = conv_layer(input)
print(input.shape)
print(output.shape)
print(conv_layer.weight.shape)
输入的图像5个通道，100*100
输出10个通道，98，98
10 输出的通道
import torch
# 输入的矩阵
input = [3,4,6,5,7,
2,4,6,8,2,
1,6,7,8,4,
9,7,4,6,2,
3,7,5,4,1]
# 输入=这个输入转化为1维的5，5
input = torch.Tensor(input).view(1,1,5,5)
conv_layer = torch.nn.Conv2d(1,1,kernel_size=3,padding=1,bias=False)
kernel = torch.Tensor([1,2,3,4,5,6,7,8,9]).view(1,1,3,3)
conv_layer.weight.data = kernel.data
output = conv_layer(input)
print(output)
D:\soft\pycharm\pro\venv\Scripts\python.exe D:/soft/pycharm/pro/op/f6.py
tensor([[[[ 91., 168., 224., 215., 127.],
[114., 211., 295., 262., 149.],
[192., 259., 282., 214., 122.],
[194., 251., 253., 169., 86.],
[ 96., 112., 110., 68., 31.]]]], grad_fn=<ConvolutionBackward0>)
进程已结束,退出代码0
stride
import torch
# 输入的矩阵
input = [3,4,6,5,7,
2,4,6,8,2,
1,6,7,8,4,
9,7,4,6,2,
3,7,5,4,1]
# 输入=这个输入转化为1维的5，5
input = torch.Tensor(input).view(1,1,5,5)
conv_layer = torch.nn.Conv2d(1,1,kernel_size=3,stride=2,bias=False)
kernel = torch.Tensor([1,2,3,4,5,6,7,8,9]).view(1,1,3,3)
conv_layer.weight.data = kernel.data
output = conv_layer(input)
print(output)
MaxPooling
import torch
input = [3,4,6,5,
2,3,6,8,
1,6,7,8,
9,7,4,6]
input = torch.Tensor(input).view(1,1,4,4)
maxpooling_layer = torch.nn.MaxPool2d(kernel_size=2)
output = maxpooling_layer(input)
print(output)
D:\soft\pycharm\pro\venv\Scripts\python.exe D:/soft/pycharm/pro/op/f8.py
tensor([[[[4., 8.],
[9., 8.]]]])
进程已结束,退出代码0
扫一扫
447
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
