weixin_48645204的博客

原创 决策树推理

原创 强化学习-Actor

import gym, os from itertools import count import paddle import paddle.nn as nn import paddle.optimizer as optim import paddle.nn.functional as F from paddle.distribution import Categorical device = paddle.get_device() env = gym.make("CartPole-v0") sta

原创 手写字体识别

class MNIST(paddle.nn.Layer): def __init__(self): super(MNIST, self).__init__() # 定义一层全连接层，输出维度是1 self.fc = paddle.nn.Linear(in_features=784, out_features=1) # 定义网络结构的前向计算过程 def forward(self, inputs):

原创 卷积神经网络进行图像分类

import paddle import paddle.nn.functional as F from paddle.vision.transforms import ToTensor import numpy as np import matplotlib.pyplot as plt transform = ToTensor() cifar10_train = paddle.vision.datasets.Cifar10(mode='train',

原创 Euler公式2

import matplotlib.pyplot as plt import numpy as np x1 = np.zeros(100) y1 = np.ones(100) for i in range(1, 100): y1[i] = 1.1*y1[i-1]-0.2*x1[i-1]/y1[i-1] x1[i] = x1[i-1] + 0.1 y1[i] = y1[i-1] + 0.5 * 0.1 * (y1[i-1] - 2 * x1[i-1] / y1[i-1] + y1[.

原创 9.17作业

原创 感知器算法

from __future__ import print_function from functools import reduce class VectorOp(object): def dot(x, y): return reduce(lambda a, b: a + b, VectorOp.element_multiply(x, y), 0.0) def element_multiply(x, y): return list(map(lamb

原创 监督学习python

import numpy as np import matplotlib.pyplot as plt import random x=np.array([[2140,3],[1600,3],[2400,3],[1416,2],[3000,4]]) t=np.array([400,330,369,232,540]) alpha=0.0000001 k0=np.random.random() k1=np.random.random() k2=np.random.random() k=np.array([k1,k

原创 numpy

import numpy as np matrix=[ [1,2,3,4], [5,6,7,8], [9,10,11,12], ] q1=np.insert(matrix,1,[1,1,1,1],0) print('>>>>q1>>>>\n',q1) q2=np.insert(matrix,0,[1,1,1],1) print('>>>>q2>>>>\n',q2) q3=np.insert