Use Pytorch Medium order of API The linear regression model and DNN A dichotomous model .
Pytorch Medium order of API It mainly includes various model layers , Loss function , Optimizer , Data pipes and so on .
1, Prepare the data
import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
import torch
from torch import nn
import torch.nn.functional as F
from torch.utils.data import Dataset,DataLoader,TensorDataset
# Number of samples
n = 400
# Generate test data set
X = 10*torch.rand([n,2])-5.0 #torch.rand It's evenly distributed
w0 = torch.tensor([[2.0],[-3.0]])
b0 = torch.tensor([[10.0]])
Y = [email protected] + b0 + torch.normal( 0.0,2.0,size = [n,1]) # @ Representation matrix multiplication , Increase normal disturbance
# Data visualization
%matplotlib inline
%config InlineBackend.figure_format = 'svg'
plt.figure(figsize = (12,5))
ax1 = plt.subplot(121)
ax1.scatter(X[:,0],Y[:,0], c = "b",label = "samples")
ax1.legend()
plt.xlabel("x1")
plt.ylabel("y",rotation = 0)
ax2 = plt.subplot(122)
ax2.scatter(X[:,1],Y[:,0], c = "g",label = "samples")
ax2.legend()
plt.xlabel("x2")
plt.ylabel("y",rotation = 0)
plt.show()
# Building input data pipelines
ds = TensorDataset(X,Y)
dl = DataLoader(ds,batch_size = 10,shuffle=True,num_workers=2)
2, Defining models
model = nn.Linear(2,1) # Linear layer
model.loss_func = nn.MSELoss()
model.optimizer = torch.optim.SGD(model.parameters(),lr = 0.01)
3, Training models
def train_step(model, features, labels):
predictions = model(features)
loss = model.loss_func(predictions,labels)
loss.backward()
model.optimizer.step()
model.optimizer.zero_grad()
return loss.item()
# test train_step effect
features,labels = next(iter(dl))
train_step(model,features,labels)
139.59463500976562
def train_model(model,epochs):
for epoch in range(1,epochs+1):
for features, labels in dl:
loss = train_step(model,features,labels)
if epoch%50==0:
printbar()
w = model.state_dict()["weight"]
b = model.state_dict()["bias"]
print("epoch =",epoch,"loss = ",loss)
print("w =",w)
print("b =",b)
train_model(model,epochs = 200)
1, Prepare the data
import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
import torch
from torch import nn
import torch.nn.functional as F
from torch.utils.data import Dataset,DataLoader,TensorDataset
%matplotlib inline
%config InlineBackend.figure_format = 'svg'
# Number of positive and negative samples
n_positive,n_negative = 2000,2000
# Generate positive samples , Small circles
r_p = 5.0 + torch.normal(0.0,1.0,size = [n_positive,1])
theta_p = 2*np.pi*torch.rand([n_positive,1])
Xp = torch.cat([r_p*torch.cos(theta_p),r_p*torch.sin(theta_p)],axis = 1)
Yp = torch.ones_like(r_p)
# Generating negative samples , Big circle distribution
r_n = 8.0 + torch.normal(0.0,1.0,size = [n_negative,1])
theta_n = 2*np.pi*torch.rand([n_negative,1])
Xn = torch.cat([r_n*torch.cos(theta_n),r_n*torch.sin(theta_n)],axis = 1)
Yn = torch.zeros_like(r_n)
# Aggregate samples
X = torch.cat([Xp,Xn],axis = 0)
Y = torch.cat([Yp,Yn],axis = 0)
# visualization
plt.figure(figsize = (6,6))
plt.scatter(Xp[:,0],Xp[:,1],c = "r")
plt.scatter(Xn[:,0],Xn[:,1],c = "g")
plt.legend(["positive","negative"]);
# Building input data pipelines
ds = TensorDataset(X,Y)
dl = DataLoader(ds,batch_size = 10,shuffle=True,num_workers=2)
2, Defining models
class DNNModel(nn.Module):
def __init__(self):
super(DNNModel, self).__init__()
self.fc1 = nn.Linear(2,4)
self.fc2 = nn.Linear(4,8)
self.fc3 = nn.Linear(8,1)
# Positive communication
def forward(self,x):
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
y = nn.Sigmoid()(self.fc3(x))
return y
# Loss function
def loss_func(self,y_pred,y_true):
return nn.BCELoss()(y_pred,y_true)
# Evaluation function ( Accuracy rate )
def metric_func(self,y_pred,y_true):
y_pred = torch.where(y_pred>0.5,torch.ones_like(y_pred,dtype = torch.float32),
torch.zeros_like(y_pred,dtype = torch.float32))
acc = torch.mean(1-torch.abs(y_true-y_pred))
return acc
# Optimizer
@property
def optimizer(self):
return torch.optim.Adam(self.parameters(),lr = 0.001)
model = DNNModel()
# Test model structure
(features,labels) = next(iter(dl))
predictions = model(features)
loss = model.loss_func(predictions,labels)
metric = model.metric_func(predictions,labels)
print("init loss:",loss.item())
print("init metric:",metric.item())
init loss: 0.7503358125686646 init metric: 0.20000000298023224
3, Training models
def train_step(model, features, labels):
# Forward propagation for loss
predictions = model(features)
loss = model.loss_func(predictions,labels)
metric = model.metric_func(predictions,labels)
# Back propagation gradient
loss.backward()
# Update model parameters
model.optimizer.step()
model.optimizer.zero_grad()
return loss.item(),metric.item()
# test train_step effect
features,labels = next(iter(dl))
train_step(model,features,labels)
(0.7407774925231934, 0.4000000059604645)
def train_model(model,epochs):
for epoch in range(1,epochs+1):
loss_list,metric_list = [],[]
for features, labels in dl:
lossi,metrici = train_step(model,features,labels)
loss_list.append(lossi)
metric_list.append(metrici)
loss = np.mean(loss_list)
metric = np.mean(metric_list)
if epoch%100==0:
printbar()
print("epoch =",epoch,"loss = ",loss,"metric = ",metric)
train_model(model,epochs = 300)
# Result visualization
fig, (ax1,ax2) = plt.subplots(nrows=1,ncols=2,figsize = (12,5))
ax1.scatter(Xp[:,0],Xp[:,1], c="r")
ax1.scatter(Xn[:,0],Xn[:,1],c = "g")
ax1.legend(["positive","negative"]);
ax1.set_title("y_true");
Xp_pred = X[torch.squeeze(model.forward(X)>=0.5)]
Xn_pred = X[torch.squeeze(model.forward(X)<0.5)]
ax2.scatter(Xp_pred[:,0],Xp_pred[:,1],c = "r")
ax2.scatter(Xn_pred[:,0],Xn_pred[:,1],c = "g")
ax2.legend(["positive","negative"]);
ax2.set_title("y_pred");