How to use BCELoss, MSELoss (pytorch)

TOP MENU

Python

library
・pip

・MeCab

numpy
・digitize

・mgrid

・pad

・polyfit

・prod

・shape

matplotlib
・figure

・pcolormesh

・scatter

pytorch
・BCELoss, MSELoss

・device

・Embedding

・TensorDataset, Dataloader

・RNN, LSTM

scikit-learn
・SVC

scipy
・interpolate

tkinter
・postscript

・image display

・frame, grid

other
・linear interpolation

OpenAI gym
・CartPole-v0

Release date:2022/2/28　　　　　　　　　

・In Japanese

■Description of BCELoss, MSELoss

Calculates the error function used in machine learning.

■Specific example using BCELoss, MSELoss

＜Binary Cross Entropy Loss＞

import torch
import torch.nn as nn

loss = nn.BCELoss()
estimate = torch.tensor([0.7,0.2,0.1]) # estimate value
real = torch.tensor([1.0, 0, 0]) # true value or target value

print(loss(estimate , real))

　⇒ tensor(0.2284)

The calculation is below

＜MSE:Mean Square Error＞
The format is the same as above, changing the "BCE Loss" part to "MSE Loss".

import torch
import torch.nn as nn

loss = nn.MSELoss()
estimate = torch.tensor([0.7,0.2,0.1]) # estimate value
real = torch.tensor([1.0, 0, 0]) # true value or target value

print(loss(estimate , real))

　⇒ tensor(0.0467)

The calculation is below

List of related articles