[TIL] 2023-02-27

어제 ADSP를 봤고,  오늘은 코칭스터디 인공지능 기초 다지기 5주차 복습으로

• logistic regression 리마인드 및 code 작성

을 진행했다. 오늘은 조금 쉬어가는 시간을 가져야 할 듯.

 

logistic regression

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

class BinaryClassifier(nn.Module):
  def __init__(self):
    super().__init__()
    self.linear = nn.Linear(2, 1)
    self.sigmoid = nn.Sigmoid()

  def forward(self, x):
    return self.sigmoid(self.linear(x))

# 전체 코드
#imports

if __name__ == "__main__":

  # Training Data
  x_data = [[1, 2], [2, 3], [3, 1], [4, 3], [5, 3], [6, 2]] # 6, 2
  y_data = [[0],[0],[0],[1],[1],[1]]

  x_train = torch.FloatTensor(x_data)
  y_train = torch.FloatTensor(y_data)

  model = BinaryClassifier()

  n_epochs = 1000

  optimizer = optim.SGD(model.parameters(), lr=1)

  for epoch in range(n_epochs+1):
    hypothesis = model(x_train)

    #cost
    cost = F.binary_cross_entropy(hypothesis, y_train)

    optimizer.zero_grad()
    cost.backward()
    optimizer.step()

    if epoch % 10 == 0:
      prediction = hypothesis >= torch.FloatTensor([0.5])
      correct_prediction = prediction.float() == y_train
      accuracy = correct_prediction.sum().item() / len(correct_prediction)
      print("Epoch {:4d}/{} Cost: {:.6f}, Accuracy: {:2.2f}%".format(
          epoch, n_epochs, cost, accuracy * 100
      ))