JustinSDK

package cc.openhome;

import java.util.Arrays;

interface List {
    default Integer head() { return null; }
    default List tail() { return null; }
    Integer sum();
    
    // 實現模式比對

JustinSDK

package cc.openhome;

import java.util.Arrays;

sealed interface List<T> permits Nil, Cons<T> {
    default T head() { return null; }
    default List<T> tail() { return null; }
}

final class Nil implements List {

JustinSDK

import torch

import cv2
import matplotlib.pyplot as plt

def training_loop(epochs, lr, params, x, y, verbose = False):
    mx = torch.unsqueeze(x, 1).float()
    my = torch.unsqueeze(y, 1).float()
    model = torch.nn.Linear(mx.size(1), my.size(1))
    mse_loss = torch.nn.MSELoss() 

JustinSDK

import torch

import cv2
import matplotlib.pyplot as plt

def model(x, w, b):
    return w * x + b
    
def mse_loss(p, y):
    return ((p - y) ** 2).mean()

JustinSDK

import torch

import cv2
import matplotlib.pyplot as plt

def model(x, w, b):
    return w * x + b
    
def mse_loss(p, y):
    return ((p - y) ** 2).mean()

JustinSDK

import torch

import cv2
import matplotlib.pyplot as plt

def model(x, w, b):
    return w * x + b
    
def mse_loss(p, y):
    return ((p - y) ** 2).mean()

JustinSDK

import numpy as np
import cv2
import matplotlib.pyplot as plt

def model(x, w, b):
    return w * x + b
    
def mse_loss(p, y):
    return ((p - y) ** 2).mean()
    

JustinSDK

import numpy as np
import cv2
import matplotlib.pyplot as plt

def model(x, w, b):
    return w * x + b
    
def mse_loss(p, y):
    return ((p - y) ** 2).mean()

JustinSDK

import numpy as np
import matplotlib.pyplot as plt

# 雙抛物面公式
def f(x, y):
    return x ** 2 / 4 - y ** 2 / 4

  # https://openhome.cc/Gossip/DCHardWay/ab.csv
data = np.loadtxt('ab.csv', delimiter=',')

JustinSDK

import numpy as np
import matplotlib.pyplot as plt

# https://openhome.cc/Gossip/DCHardWay/ab.csv
data = np.loadtxt('ab.csv', delimiter=',')

a = data[:,0]
b = data[:,1]
label = data[:,2]