Python Classifier Decision Boundary Code
Python Classifier Decision Boundary Code
Here is my code:
I'd like to see a decision boundary where my model predicts the six points in Python code please.
import numpy as np
import torch
import torch.nn as nn
import matplotlib.pyplot as plt
X = torch.from_numpy(np.array([[-1,0.5],[-1.2,0.3],[1,1],[0.9,1.2],[0.1,-1],[0.2,-0.5]])).float()
Y = torch.from_numpy(np.array(([0,0,1,1,2,2])))
train_data = torch.utils.data.TensorDataset(X, Y)
test_data = torch.utils.data.TensorDataset(X, Y)
train_loader = torch.utils.data.DataLoader(train_data, batch_size=6, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_data, batch_size=6, shuffle=True)
myModel0 = nn.Sequential(*[nn.Linear(2,2), nn.ReLU(), nn.Linear(2,3)])
myLoss = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(myModel0.parameters(), lr=0.01)
epoch_loss = []
step_loss = []
sum(p.numel() for p in myModel0.parameters() if p.requires_grad)
for epoch in range(1000):
running_loss = 0.0
miniBatch = 0
for x,y in train_loader:
optimizer.zero_grad()
score = myModel0(x)
loss = myLoss(score, y.type(torch.LongTensor))
loss.backward()
optimizer.step()
running_loss += loss.detach().numpy()
miniBatch += 1
step_loss.append(loss.detach().item())
epoch_loss.append(running_loss/len(train_loader))
Step by step
Solved in 2 steps
