摘要：
本文为个人学习Pytorch龙良曲版本时跟写的代码，碍于版本、环境等诸多原因，原视频中代码不能直接照搬。针对自己所遇到的问题进行了改动，与大家分享共勉。
目录
链接： B站-Pytorch龙良曲
课时4-简单回归问题
#利用numpy随机生成数据
import numpy as np
import pandas as pd
# 生成200个随机数
data = np.random.uniform(low=0, high=100, size=(100, 2))
# 将数据存放到DataFrame中
df = pd.DataFrame(data=data)
# 将DataFrame输出到CSV文件中
df.to_csv('data.csv', index=False)
# 输出DataFrame为表格
print(df.to_string(index=False))
import numpy as np
def computer_error_line(b,w,points):
totalError = 0
for i in range(0,len(points)):
x = points[i,0]
y = points[i,1]
totalError += (y - (w*x+b))**2
return totalError / float(len(points))
def step_gradient(b_current,w_current,points,learningRate):
b_gradient = 0
w_gradient = 0
N = float(len(points))
for i in range(0,len(points)):
x = points[i,0]
y = points[i,1]
b_gradient += -(2/N) * (y -((w_current * x) + b_current))
w_gradient += -(2/N) * x * (y - ((w_current * x) + b_current))
new_b = b_current - (learningRate * b_gradient)
new_m = w_current - (learningRate * w_gradient)
return [new_b,new_m]
def gradient_descent_runner(points,starting_b,starting_m,learning_rate,num_iterations):
b = starting_b
m = starting_m
for i in range(num_iterations):
b,m = step_gradient(b,m,np.array(points),learning_rate)
return [b,m]
def run():
points = np.genfromtxt("data.csv",delimiter=",")
learning_rate = 0.0001
initial_b = 0
initial_m =0
num_iterations = 1000
print("Starting gradient descent at b = {0},m = {1},error = {2}".format(initial_b,
initial_m,computer_error_line(initial_b,initial_m,points)))
print("Running..")
[b,m] = gradient_descent_runner(points,initial_b,initial_m,learning_rate,
num_iterations)
print("After {0} iteartions b = {1},m = {2},error = {3}".format(num_iterations,b,m,
computer_error_line(b,m,points)))
run()
课时9-手写数字初体验
#utils.py
import torch
from matplotlib import pyplot as plt
def plot_curve(data):
fig = plt.figure()
plt.plot(range(len(data)),data,color='blue')
plt.legend(['value'],loc='upper right')
plt.xlabel('step')
plt.ylabel('value')
plt.show()
def plot_img(img,label,name):
fig = plt.figure()
for i in range(6):
plt.subplot(2,3,i+1)
plt.tight_layout()
plt.imshow(img[i][0]*0.3081+0.1307,cmap='gray',interpolation='none')
plt.title("{}: {}".format(name,label[i].item()))
plt.xticks([])
plt.yticks([])
plt.show()
def one_hot(label,depth=10):
out = torch.zeros(label.size(0),depth)
idx = torch.LongTensor(label).view(-1,1)
out.scatter_(dim=1, index=idx, value=1)
return out
'''
手写数字识别初体验
'''
import torch
from torch import nn
from torch.nn import functional as F
from torch import optim
import torchvision
from matplotlib import pyplot as plt
from utils import plot_img, plot_curve,one_hot
batch_size = 512
train_loader = torch.utils.data.DataLoader(
torchvision.datasets.MNIST('mnist_data', train=True, download=True,
transform=torchvision.transforms.Compose([
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize(
(0.1307,),(0.3081,))
])),
batch_size = batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(
torchvision.datasets.MNIST('mnist_data/',train=False,download=True,
transform=torchvision.transforms.Compose([
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize(
(0.1307,),(0.3081,))
])),
batch_size=batch_size, shuffle = False)
x, y = next(iter(train_loader))
print(x.shape, y.shape,x.min(),x.max())
#plot_img(x, y, 'image simple')
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.fc1 = nn.Linear(28*28,256)
self.fc2 = nn.Linear(256,64)
self.fc3 = nn.Linear(64,10)
def forward(self,x):
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()
optimizier = optim.SGD(net.parameters(),lr=0.01,momentum=0.9)
train_loss = []
for epoch in range(3):
for batch_idx,(x,y) in enumerate(train_loader):
x = x.view(x.size(0),28*28)
out = net(x)
y_onehot = one_hot(y)
loss = F.mse_loss(out,y_onehot)
optimizier.zero_grad()
loss.backward()
optimizier.step()
train_loss.append(loss.item())
if batch_idx % 10 ==0:
print(epoch,batch_idx,loss.item())
#plot_curve(train_loss)
total_correct = 0
for x,y in test_loader:
x = x.view(x.size(0),28*28)
out = net(x)
pred = out.argmax(dim = 1)
correct = pred.eq(y).sum().float().item()
total_correct += correct
total_num = len(test_loader.dataset)
acc = total_correct / total_num
print('test acc:',acc)
x,y = next(iter(test_loader))
out = net(x.view(x.size(0),28*28))
pred = out.argmax(dim = 1)
plot_img(x,pred,'test')
课时46-优化问题实战
报错：1、projection不识别2、用Axes3D运行成功但没有生成模型
import numpy as np
from matplotlib import pyplot as plt
import torch
from mpl_toolkits.mplot3d import Axes3D
def himmelblau(x):
return (x[0] ** 2 + x[1] - 11) ** 2 + (x[0] + x[1] ** 2 - 7) ** 2
x = np.arange(-6, 6, 0.1)
y = np.arange(-6, 6, 0.1)
print('x,y range:', x.shape, y.shape)
X, Y = np.meshgrid(x, y)
print('X,Y maps:', X.shape, Y.shape)
Z =himmelblau([X, Y])
fig = plt.figure('himmelblau')
# ax = fig.gca(projection='3d')
# ax = Axes3D(fig)
ax = fig.add_subplot(111, projection='3d')
ax.plot_surface(X, Y, Z)
ax.view_init(60, -30)
ax.set_xlabel('x')
ax.set_ylabel('y')
plt.show()
'''
当你使用`fig.gca(projection='3d')`时，`gca`代表"Get Current Axes"，它会尝试获取当前的Axes对象。
然而，在你的代码中，因为`fig`是通过`fig = plt.figure('himmelblau')`创建的，它是一个新创建
的Figure对象，并没有任何Axes对象。因此，尝试调用`gca()`方法时会报错。
而使用`fig.add_subplot(111, projection='3d')`方法，你创建了一个具有指定投影类型（3D）
的Axes对象，并将其添加到Figure中。`111`参数表示将Figure分割为1行1列的子图网格，
并选择第一个子图（也是唯一的一个子图）。这种方法可以成功创建带有3D投影的Axes对象,使用
`fig.add_subplot(111, projection='3d')`的方式更直接地创建了一个具有指定投影类型的Axes对象，
并将其添加到Figure中，从而避免了使用`gca()`方法时的报错。
'''
x = torch.tensor([0., 0],requires_grad=True)
optimizer = torch.optim.Adam([x], lr=1e-3)
for step in range(20000):
pred = himmelblau(x)
optimizer.zero_grad()
pred.backward()
optimizer.step()
if step % 2000 == 0:
print('step {}:x = {}, f(x) = {}'
.format(step,x.tolist(),pred.item()))
课时50-多分类问题实战及visdom
碍于缺少课时51 这里对y轴做了更改 主要让visdom跑起来为主
import torch
from torch import nn
from torch.nn import functional as F
from torchvision import datasets,transforms
from visdom import Visdom
batch_size=200
learning_rate=0.01
epochs=10
train_loader = torch.utils.data.DataLoader(
datasets.MNIST('../data', train=True, download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=batch_size, shuffle=True
)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('../data', train=False,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=batch_size, shuffle=True
)
w1, b1 = torch.randn(200, 784, requires_grad=True),\
torch.zeros(200, requires_grad=True)
w2, b2 = torch.randn(200, 200, requires_grad=True),\
torch.zeros(200, requires_grad=True)
w3, b3 = torch.randn(10, 200, requires_grad=True),\
torch.zeros(10, requires_grad=True)
torch.nn.init.kaiming_normal_(w1)
torch.nn.init.kaiming_normal_(w2)
torch.nn.init.kaiming_normal_(w3)
def forward(x):
x = x@w1.t() + b1
x = F.relu(x)
x = x @ w2.t() + b2
x = F.relu(x)
x = x @ w3.t() + b3
x = F.relu(x)
return x
optimizer = torch.optim.SGD([w1, b1, w2, b2, w3, b3], lr=learning_rate)
criteon = nn.CrossEntropyLoss()
for epoch in range(epochs):
for batch_idx, (data, target) in enumerate(train_loader):
data = data.view(-1, 28*28)
logits = forward(data)
loss = criteon(logits, target)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if batch_idx % 100 == 0:
print('Train Epoch:{} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()
))
test_loss = 0
correct = 0
for data, target in test_loader:
data = data.view(-1, 28*28)
logits = forward(data)
test_loss += criteon(logits, target).item()
pred = logits.data.max(1)[1]
correct += pred.eq(target.data).sum()
test_loss /= len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)
))
# python -m visdom.server
viz = Visdom()
viz.line([0.], [0.], win='train_loss', opts=dict(title='train loss'))
viz.line([loss.item()], [epoch], win='train_loss', update='append')
课时57-交叉运算 gpu运算
报错： Torch not compiled with CUDA enabled
主要为Pytorch和cuda版本的兼容问题，起初我的pytorch是下载anaconda时一起下载的所以之前没注意，做到这里才报错
我下载是官方最新版本pytorch2.0.1+cuda11.8
方法参考
Torch not compiled with CUDA enabled看这一篇就足够了
而且windows系统的cuda版本和程序运行环境中的cuda版本可以不同，已在两台电脑中这样
import torch
from torch import nn
from torch.nn import functional as F
from torchvision import datasets,transforms
# from visdom import Visdom
batch_size=200
learning_rate=0.01
epochs=10
train_db = datasets.MNIST('../data', train=True, download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
]))
train_loader = torch.utils.data.DataLoader(
train_db,
batch_size=batch_size, shuffle=True)
test_db = datasets.MNIST('../data', train=False, transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,),(0.3081,))
]))
test_loader = torch.utils.data.DataLoader(test_db,
batch_size=batch_size, shuffle=True)
print('train:', len(train_db), 'test:', len(test_db))
train_db, val_db = torch.utils.data.random_split(train_db, [50000, 10000])
print('db1:', len(train_db), 'db2:', len(val_db))
train_loader = torch.utils.data.DataLoader(
train_db,
batch_size=batch_size, shuffle=True)
val_loader = torch.utils.data.DataLoader(
val_db,
batch_size=batch_size, shuffle=True)
class MLP(nn.Module):
def __init__(self):
super(MLP, self).__init__()
self.model = nn.Sequential(
nn.Linear(784,200),
nn.LeakyReLU(inplace=True),
nn.Linear(200, 200),
nn.LeakyReLU(inplace=True),
nn.Linear(200, 10),
nn.LeakyReLU(inplace=True),
)
def forward(self, x):
x = self.model(x)
return x
device = torch.device('cuda:0')
#Torch not compiled with CUDA enabled
net = MLP().to(device)
optimizer = torch.optim.SGD(net.parameters(), lr=learning_rate)
criteon = nn.CrossEntropyLoss().to(device)
for epoch in range(epochs):
for batch_idx, (data, target) in enumerate(train_loader):
data = data.view(-1, 28*28)
data, target = data.to(device), target.cuda()
logits = net(data)
loss = criteon(logits, target)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if batch_idx % 100 == 0:
print('Train Epoch:{} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()
))
test_loss = 0
correct = 0
for data, target in val_loader:
data = data.view(-1, 28 * 28)
data, target = data.to(device), target.cuda()
logits = net(data)
test_loss += criteon(logits, target).item()
pred = logits.data.max(1)[1]
correct += pred.eq(target.data).sum()
test_loss /= len(val_loader.dataset)
print('\nVal set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(val_loader.dataset),
100. * correct / len(val_loader.dataset)))
test_loss = 0
correct = 0
for data, target in test_loader:
data = data.view(-1, 28 * 28)
data, target = data.to(device), target.cuda()
logits = net(data)
test_loss += criteon(logits, target).item()
pred = logits.data.max(1)[1]
correct += pred.eq(target.data).sum()
test_loss /= len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
课时76-卷积网络实战 Lenet5
报错： AttributeError: ‘_SingleProcessDataLoaderIter’ object has no attribute ‘next’
小问题 代码改动如下
# wrong: x, label = iter(cifar_train).next()
x, label = iter(cifar_train).__next__()
完整代码 mian()
import torch
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision import transforms
from torch import nn, optim
from lenet5 import Lenet5
def main():
batchsz = 32
cifar_train = datasets.CIFAR10('cifar', True, transform=transforms.Compose([
transforms.Resize((32, 32)),
transforms.ToTensor()
]), download=True)
cifar_train = DataLoader(cifar_train, batch_size=batchsz, shuffle=True)
cifar_test = datasets.CIFAR10('cifar', False, transform=transforms.Compose([
transforms.Resize((32, 32)),
transforms.ToTensor()
]), download=True)
cifar_test = DataLoader(cifar_test, batch_size=batchsz, shuffle=True)
# AttributeError: '_SingleProcessDataLoaderIter' object has no attribute 'next'
# wrong: x, label = iter(cifar_train).next()
x, label = iter(cifar_train).__next__()
print('x:', x.shape, 'label:', label.shape)
device = torch.device('cuda')
model = Lenet5().to(device)
criteon = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=1e-3)
print(model)
for epoch in range(1000):
model.train()
for batchidx, (x, label) in enumerate(cifar_train):
# [b, 3, 32, 32]
# [b]
x, label = x.to(device), label.to(device)
# pred = logits经过softmax
logits = model(x)
# logits [b, 10]
# label [b]
# loss: tensor scalar
loss = criteon(logits, label)
#backprop
optimizer.zero_grad()
loss.backward()
optimizer.step()
#
print(epoch, loss.item())
model.eval()
with torch.no_grad():
# test
total_correct = 0
total_num = 0
for x, label in cifar_test:
# [b, 3, 32, 32]
# [b]
x, label = x.to(device), label.to(device)
# [b, 10]
logits = model(x)
# [b]
pred = logits.argmax(dim=1)
# [b] vs [b] => scalar tensor
total_correct += torch.eq(pred, label).float().sum().item()
total_num += x.size(0)
acc = total_correct / total_num
print(epoch, acc)
if __name__ == '__main__':
main()
lenet5():
import torch
from torch import nn
from torch.nn import functional as F
class Lenet5(nn.Module):
'''
for cifar10 dataset
'''
def __init__(self):
super(Lenet5, self).__init__()
self.conv_unit = nn.Sequential(
#x = [b, 3, 32, 32]→ [b, 6,
#kernel_size 一次关注的像素点
#stride 一次移动的像素点
#padding 类似于扩展矩阵，给周围像素增添0，这样原图像26*26就能移动传值26次
nn.Conv2d(3, 6, kernel_size=5, stride=1, padding=0),
nn.AvgPool2d(kernel_size=2, stride=2, padding=0),
#
nn.Conv2d(6, 16, kernel_size=5, stride=1, padding=0),
nn.AvgPool2d(kernel_size=2, stride=2, padding=0),
#
)
# flatten
# fc unit
self.fc_unit = nn.Sequential(
nn.Linear(16*5*5, 120),
nn.ReLU(),
nn.Linear(120, 84),
nn.ReLU(),
nn.Linear(84, 10),
)
# [b, 3, 32, 32]
tmp = torch.randn(2, 3, 32, 32)
out = self.conv_unit(tmp)
#[2, 16, 5, 5]
print('conv_out:', out.shape)
# use Cross Entropy Loss
# self.criteon = nn.CrossEntropyLoss()
def forward(self, x):
'''
:param x:[b, 3, 32, 32]
:return:
'''
batchsz = x.size(0)
# [b, 3, 32, 32] => [b, 16, 5, 5]
x = self.conv_unit(x)
# [b, 16, 5, 5] => [b, 16*5*5]
x = x.view(batchsz, 16*5*5)
# [b, 16*5*5] =>[b, 10]
logits = self.fc_unit(x)
# loss = self.criteon(logits, y)
return logits
def main():
net = Lenet5()
tmp = torch.randn(2, 3, 32, 32)
out = net(tmp)
# [2, 16, 5, 5]
print('lennt out:', out.shape)
if __name__ == '__main__':
main()
80-Resnet
import torch
from torch import nn
from torch.nn import functional as F
class ResBlk(nn.Module):
'''
resnet block
'''
def __init__(self, ch_in, ch_out, stride=1):
'''
:param ch_in:
:param ch_out:
'''
super(ResBlk, self).__init__()
self.conv1 = nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=stride, padding=1)
self.bn1 = nn.BatchNorm2d(ch_out)
self.conv2 = nn.Conv2d(ch_out, ch_out, kernel_size=3, stride=1, padding=1)
self.bn2 = nn.BatchNorm2d(ch_out)
self.extra = nn.Sequential()
if ch_out != ch_in:
self.extra = nn.Sequential(
nn.Conv2d(ch_in, ch_out, kernel_size=1, stride=stride),
nn.BatchNorm2d(ch_out)
)
def forward(self, x):
'''
:param x:
:return:
'''
out = F.relu(self.bn1(self.conv1(x)))
out = self.bn2(self.conv2(out))
# short cut,
# extra module: [b,ch_in, h, w] => [b, ch_out, h, w]
# element-wise add :
out = self.extra(x) + out
out = F.relu(out)
return out
class ResNet18(nn.Module):
def __init__(self):
super(ResNet18, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2d(3, 64, kernel_size=3, stride=3, padding=0),
nn.BatchNorm2d(64)
)
# followed 4 blocks
self.blk1 = ResBlk(64, 128, stride=2)
self.blk2 = ResBlk(128, 256, stride=2)
self.blk3 = ResBlk(256, 512, stride=2)
self.blk4 = ResBlk(512, 1024, stride=2)
self.outlayer = nn.Linear(512*1*1, 10)
def forward(self, x):
'''
:param x:
:return:
'''
x = F.relu(self.conv1(x))
x = self.blk1(x)
x = self.blk2(x)
x = self.blk3(x)
x = self.blk4(x)
x = self.outlayer(x)
return x
def main():
# blk = ResBlk(64, 128, stride=2)
blk = ResBlk(64, 128, stride=4)
tmp = torch.randn(2, 64, 32, 32)
out = blk(tmp)
print('block:', out.shape)
main()
96-Pokemon数据集
百度网盘链接： https://pan.baidu.com/s/1V_ZJ7ufjUUFZwD2NHSNMFw
网盘里文件夹是pokeman 输入路径的时候注意一下
utils
import torch
from torch import nn
from matplotlib import pyplot as plt
class Flatten(nn.Module):
def __init__(self):
super(Flatten, self).__init__()
def forward(self, x):
shape = torch.prod(torch.tensor(x.shape[1:])).item()
return x.view(-1, shape)
def plot_image(img, label, name):
fig = plt.figure()
for i in range(6):
plt.subplot(2, 3, i+1)
plt.tight_layout()
plt.imshow(img[i][0]*0.3081+0.1307, cmap='gray', interpolation='none')
plt.title("{}: {}".format(name, label[i].item()))
plt.xticks([])
plt.yticks([])
plt.show()
resnet
import torch
from torch import nn
from torch.nn import functional as F
class ResBlk(nn.Module):
'''
resnet block
'''
def __init__(self, ch_in, ch_out, stride=1):
'''
:param ch_in:
:param ch_out:
'''
super(ResBlk, self).__init__()
self.conv1 = nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=stride, padding=1)
self.bn1 = nn.BatchNorm2d(ch_out)
self.conv2 = nn.Conv2d(ch_out, ch_out, kernel_size=3, stride=1, padding=1)
self.bn2 = nn.BatchNorm2d(ch_out)
self.extra = nn.Sequential()
if ch_out != ch_in:
self.extra = nn.Sequential(
nn.Conv2d(ch_in, ch_out, kernel_size=1, stride=stride),
nn.BatchNorm2d(ch_out)
)
def forward(self, x):
'''
:param x:
:return:
'''
out = F.relu(self.bn1(self.conv1(x)))
out = self.bn2(self.conv2(out))
# short cut,
# extra module: [b,ch_in, h, w] => [b, ch_out, h, w]
# element-wise add :
out = self.extra(x) + out
out = F.relu(out)
return out
class ResNet18(nn.Module):
def __init__(self, num_class):
super(ResNet18, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2d(3, 16, kernel_size=3, stride=3, padding=0),
nn.BatchNorm2d(16)
)
# followed 4 blocks
self.blk1 = ResBlk(16, 32, stride=3)
self.blk2 = ResBlk(32, 64, stride=3)
self.blk3 = ResBlk(64, 128, stride=2)
self.blk4 = ResBlk(128, 256, stride=2)
self.outlayer = nn.Linear(256*3*3, num_class)
def forward(self, x):
'''
:param x:
:return:
'''
x = F.relu(self.conv1(x))
x = self.blk1(x)
x = self.blk2(x)
x = self.blk3(x)
x = self.blk4(x)
# print(x.shape)
x = x.view(x.size(0), -1)
x = self.outlayer(x)
return x
def main():
# blk = ResBlk(64, 128, stride=2)
blk = ResBlk(64, 128)
tmp = torch.randn(2, 64, 224, 224)
out = blk(tmp)
print('block:', out.shape)
model = ResNet18(5)
tmp = torch.randn(2, 3, 244, 244)
out = model(tmp)
print('resnet:', out.shape)
p = sum(map(lambda p:p.numel(), model.parameters()))
print('parameters size:', p)
if __name__ == '__main__':
main()
pokemon
import torch
import os, glob
import random, csv
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms
from PIL import Image
class Pokemon(Dataset):
def __init__(self, root, resize, mode):
super(Pokemon, self).__init__()
self.root = root
self.resize = resize
self.name2label = {}
for name in sorted(os.listdir(os.path.join(root))):
if not os.path.isdir(os.path.join(root, name)):
continue
self.name2label[name] = len(self.name2label.keys())
# print(self.name2label)
self.images, self.labels = self.load_csv('images.csv')
if mode =='train':#60%
self.images = self.images[:int(0.6*len(self.images))]
self.labels = self.labels[:int(0.6*len(self.labels))]
elif mode=='val':
self.images = self.images[int(0.6 * len(self.images)):int(0.8 * len(self.images))]
self.labels = self.labels[int(0.6 * len(self.labels)):int(0.8 * len(self.labels))]
else:
self.images = self.images[int(0.8 * len(self.images)):]
self.labels = self.labels[int(0.8 * len(self.labels)):]
def load_csv(self, filename):
if not os.path.exists(os.path.join(self.root, filename)):
images = []
for name in self.name2label.keys():
images += glob.glob(os.path.join(self.root, name, '*.png'))
images += glob.glob(os.path.join(self.root, name, '*.jpg'))
images += glob.glob(os.path.join(self.root, name, '*.jpeg'))
# pokeman\\bulbasaur\\00000000.png
print(len(images), images)
random.shuffle(images)
with open(os.path.join(self.root, filename), mode='w', newline='') as f:
writer = csv.writer(f)
for img in images:
name = img.split(os.sep)[-2]
label = self.name2label[name]
writer.writerow([img, label])
print('writen into csv file:', filename)
# read form csv file
images, labels = [], []
with open(os.path.join(self.root, filename)) as f:
reader = csv.reader(f)
for row in reader:
img, label = row
label = int(label)
images.append(img)
labels.append(label)
assert len(images) == len(labels)
return images, labels
def __len__(self):
return len(self.images)
def denormalize(self, x_hat):
mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.255]
# x_hat = (x-mean)/ std
# x = x_hat*std = mean
# x:[c,h,w]
# mean:[3] => [3, 1, 1]
mean = torch.tensor(mean).unsqueeze(1).unsqueeze(1)
std = torch.tensor(std).unsqueeze(1).unsqueeze(1)
# print(mean.shape, std.shape)
x = x_hat * std +mean
return x
def __getitem__(self, idx):
# self.images, self.labels
# img: 'pokemon\\bu...\\...
# label:0, 1, 2...
img , label = self.images[idx], self.labels[idx]
tf = transforms.Compose([
lambda x:Image.open(x).convert('RGB'), # path => data
transforms.Resize((int(self.resize*1.25), int(self.resize*1.25))),
transforms.RandomRotation(15),# 数据增强 随机旋转15°
transforms.CenterCrop(self.resize),# 中心裁剪 取消黑边
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.255])
])
img = tf(img)
label = torch.tensor(label)
return img, label
def main():
import visdom
import time
viz = visdom.Visdom()
db = Pokemon('pokeman', 64, 'train')
x, y = next(iter(db))
print('sample:', x.shape, y.shape)
viz.image(db.denormalize(x), win='sample_x', opts=dict(title='sample_x'))
loader = DataLoader(db, batch_size=32, shuffle=True, num_workers=8)
for x,y in loader:
viz.images(db.denormalize(x), nrow=8, win='batch', opts=dict(title='batch'))
viz.text(str(y.numpy()), win='lavel', opts=dict(title='batch-y'))
time.sleep(15)
if __name__ == '__main__':
main()
train_scratch
import torch
from torch import optim, nn
import visdom
import torchvision
from torch.utils.data import DataLoader
from pokemon import Pokemon
from resnet import ResNet18
batchsz = 32
lr = 1e-3
epochs = 10
device = torch.device('cuda')
torch.manual_seed(1234)
train_db = Pokemon('pokeman', 224, mode='train')
val_db = Pokemon('pokeman', 224, mode='val')
test_db = Pokemon('pokeman', 224, mode='test')
train_loader = DataLoader(train_db, batch_size=batchsz, shuffle=True,
num_workers=4)
val_loader = DataLoader(val_db, batch_size=batchsz, num_workers=2)
test_loader = DataLoader(test_db, batch_size=batchsz, num_workers=2)
viz = visdom.Visdom()
def evalute(model, loader):
correct = 0
total = len(loader.dataset)
for x,y in loader:
x,y = x.to(device), y.to(device)
with torch.no_grad():
logits = model(x)
pred = logits.argmax(dim=1)
correct += torch.eq(pred, y).sum().float().item()
return correct / total
def main():
model = ResNet18(5).to(device)
optimizer = optim.Adam(model.parameters(), lr=lr)
criteon = nn.CrossEntropyLoss()
best_acc, best_epoch = 0, 0
global_step = 0
viz.line([0], [-1], win='loss', opts=dict(title='loss'))
viz.line([0], [-1], win='val_acc', opts=dict(title='val_acc'))
for epoch in range(epochs):
for step, (x,y) in enumerate(train_loader):
x, y = x.to(device), y.to(device)
logits = model(x)
loss = criteon(logits, y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
viz.line([loss.item()], [global_step], win='loss', update='append')
global_step += 1
if epoch % 1 ==0:
val_acc = evalute(model, val_loader)
if val_acc > best_acc:
best_epoch = epoch
best_acc = val_acc
torch.save(model.state_dict(), 'best_mdl')
viz.line([val_acc], [global_step], win='val_acc', update='append')
print('best acc:', best_acc, 'best epoch:', best_epoch)
model.load_state_dict(torch.load('best.mdl'))
print('loaded from ckpt!')
test_acc = evalute(model, test_loader)
print('test acc:', test_acc)
if __name__ == '__main__':
main()
train_transfer
import torch
from torch import optim, nn
import visdom
import torchvision
from torch.utils.data import DataLoader
from pokemon import Pokemon
# from resnet import ResNet18
from torchvision.models import resnet18
from utils import Flatten
batchsz = 32
lr = 1e-3
epochs = 10
device = torch.device('cuda')
torch.manual_seed(1234)
train_db = Pokemon('pokeman', 224, mode='train')
val_db = Pokemon('pokeman', 224, mode='val')
test_db = Pokemon('pokeman', 224, mode='test')
train_loader = DataLoader(train_db, batch_size=batchsz, shuffle=True,
num_workers=4)
val_loader = DataLoader(val_db, batch_size=batchsz, num_workers=2)
test_loader = DataLoader(test_db, batch_size=batchsz, num_workers=2)
viz = visdom.Visdom()
def evalute(model, loader):
correct = 0
total = len(loader.dataset)
for x,y in loader:
x,y = x.to(device), y.to(device)
with torch.no_grad():
logits = model(x)
pred = logits.argmax(dim=1)
correct += torch.eq(pred, y).sum().float().item()
return correct / total
def main():
# model = ResNet18(5).to(device)
trained_model = resnet18(pretrained=True)
model = nn.Sequential(*list(trained_model.children())[:-1],
Flatten(),
nn.Linear(512, 5)).to(device)
# x = torch.randn(2, 3, 224, 224)
# print(model(x).shape)
optimizer = optim.Adam(model.parameters(), lr=lr)
criteon = nn.CrossEntropyLoss()
best_acc, best_epoch = 0, 0
global_step = 0
viz.line([0], [-1], win='loss', opts=dict(title='loss'))
viz.line([0], [-1], win='val_acc', opts=dict(title='val_acc'))
for epoch in range(epochs):
for step, (x,y) in enumerate(train_loader):
x, y = x.to(device), y.to(device)
logits = model(x)
loss = criteon(logits, y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
viz.line([loss.item()], [global_step], win='loss', update='append')
global_step += 1
if epoch % 1 ==0:
val_acc = evalute(model, val_loader)
if val_acc > best_acc:
best_epoch = epoch
best_acc = val_acc
torch.save(model.state_dict(), 'best_mdl')
viz.line([val_acc], [global_step], win='val_acc', update='append')
print('best acc:', best_acc, 'best epoch:', best_epoch)
model.load_state_dict(torch.load('best.mdl'))
print('loaded from ckpt!')
test_acc = evalute(model, test_loader)
print('test acc:', test_acc)
if __name__ == '__main__':
main()
115-Auto Encoder
记得开visdom
ae
import torch
from torch import nn
class AE(nn.Module):
def __init__(self):
super(AE, self).__init__()
# [b, 784] => [b, 20]
self.encoder = nn.Sequential(
nn.Linear(784, 256),
nn.ReLU(),
nn.Linear(256, 64),
nn.ReLU(),
nn.Linear(64, 20),
nn.ReLU()
)
# [b, 20] => [b, 784]
self.decoder = nn.Sequential(
nn.Linear(20, 64),
nn.ReLU(),
nn.Linear(64, 256),
nn.ReLU(),
nn.Linear(256, 784),
nn.Sigmoid()
)
def forward(self, x):
'''
:param x:
:return:
'''
batchsz = x.size(0)
x = x.view(batchsz,784)
x = self.encoder(x)
x = self.decoder(x)
x = x.view(batchsz, 1, 28, 28)
return x
ae_main
import torch
from torch.utils.data import DataLoader
from torch import nn, optim
from torchvision import transforms, datasets
from ae import AE
import visdom
def main():
mnist_train = datasets.MNIST('mnist', True, transform=transforms.Compose([
transforms.ToTensor()
]), download=True)
mnist_train = DataLoader(mnist_train, batch_size=32, shuffle=True)
mnist_test = datasets.MNIST('mnist', False, transform=transforms.Compose([
transforms.ToTensor()
]), download=True)
mnist_test = DataLoader(mnist_test, batch_size=32, shuffle=True)
x, _ = iter(mnist_train).__next__()
print('x:', x.shape)
device = torch.device('cuda')
model = AE().to(device)
criteon = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=1e-3)
print(model)
viz = visdom.Visdom()
for epoch in range(1000):
for batchidx, (x, _) in enumerate(mnist_train):
x = x.to(device)
x_hat = model(x)
loss = criteon(x_hat, x)
optimizer.zero_grad()
loss.backward()
optimizer.step()
print(epoch, 'loss', loss.item())
x, _ = iter(mnist_test).__next__()
x = x.to(device)
with torch.no_grad():
x_hat = model(x)
viz.images(x, nrow=8, win='x', opts=dict(title='x'))
viz.images(x_hat, nrow=8, win='x_hat', opts=dict(title='x_hat'))
if __name__ == '__main__':
main()
117-VAE
vae
import numpy as np
import torch
from torch import nn
class VAE(nn.Module):
def __init__(self):
super(VAE, self).__init__()
# [b, 784] => [b, 20]
self.encoder = nn.Sequential(
nn.Linear(784, 256),
nn.ReLU(),
nn.Linear(256, 64),
nn.ReLU(),
nn.Linear(64, 20),
nn.ReLU()
)
# [b, 10] => [b, 784]
self.decoder = nn.Sequential(
nn.Linear(10, 64),
nn.ReLU(),
nn.Linear(64, 256),
nn.ReLU(),
nn.Linear(256, 784),
nn.Sigmoid()
)
def forward(self, x):
'''
:param x:
:return:
'''
batchsz = x.size(0)
x = x.view(batchsz, 784)
h_ = self.encoder(x)
mu, sigma = h_.chunk(2, dim=1)
h = mu + sigma * torch.rand_like(sigma)
x_hat = self.decoder(h)
x_hat = x.view(batchsz, 1, 28, 28)
kld = 0.5 * torch.sum(
torch.pow(mu, 2) +
torch.pow(sigma, 2) -
torch.log(1e-8 + torch.pow(sigma, 2)) -1
) / (batchsz*28*28)
return x_hat, kld
vae_main
import torch
from torch.utils.data import DataLoader
from torch import nn, optim
from torchvision import transforms, datasets
from vae import VAE
import visdom
def main():
mnist_train = datasets.MNIST('mnist', True, transform=transforms.Compose([
transforms.ToTensor()
]), download=True)
mnist_train = DataLoader(mnist_train, batch_size=32, shuffle=True)
mnist_test = datasets.MNIST('mnist', False, transform=transforms.Compose([
transforms.ToTensor()
]), download=True)
mnist_test = DataLoader(mnist_test, batch_size=32, shuffle=True)
x, _ = iter(mnist_train).__next__()
print('x:', x.shape)
device = torch.device('cuda')
model = VAE().to(device)
criteon = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=1e-3)
print(model)
viz = visdom.Visdom()
for epoch in range(1000):
for batchidx, (x, _) in enumerate(mnist_train):
x = x.to(device)
x_hat, kld = model(x)
loss = criteon(x_hat, x)
if kld is not None:
elbo = - loss - 1.0 * kld
loss = -elbo
optimizer.zero_grad()
loss.backward()
optimizer.step()
print(epoch, 'loss', loss.item(), 'kld:', kld.item())
x, _ = iter(mnist_test).__next__()
x = x.to(device)
with torch.no_grad():
x_hat, kld= model(x)
viz.images(x, nrow=8, win='x', opts=dict(title='x'))
viz.images(x_hat, nrow=8, win='x_hat', opts=dict(title='x_hat'))
if __name__ == '__main__':
main()
127-GAN
import torch
from torch import nn, optim, autograd
import numpy as np
import visdom
import random
h_dim = 400
batchsz = 512
# viz = visdom.Visdom()
class Generator(nn.Module):
def __init__(self):
super(Generator, self).__init__()
self.net = nn.Sequential(
nn.Linear(2, h_dim),
nn.ReLU(True),
nn.Linear(h_dim, h_dim),
nn.ReLU(True),
nn.Linear(h_dim, h_dim),
nn.ReLU(True),
nn.Linear(h_dim, 2)
)
def forward(self, z):
output = self.net(z)
return output
class Discriminator(nn.Module):
def __init__(self):
super(Discriminator, self).__init__()
self.net = nn.Sequential(
nn.Linear(2, h_dim),
nn.ReLU(True),
nn.Linear(h_dim, h_dim),
nn.ReLU(True),
nn.Linear(h_dim, h_dim),
nn.ReLU(True),
nn.Linear(h_dim, 1),
nn.Sigmoid()
)
def forward(self, x):
output = self.net(x)
return output.view(-1)
def data_generator():
scale = 2.
centers = [
(1, 0),
(-1, 0),
(0, 1),
(0, -1),
(1. / np.sqrt(2), 1. / np.sqrt(2)),
(1. / np.sqrt(2), -1. / np.sqrt(2)),
(-1. / np.sqrt(2), 1. / np.sqrt(2)),
(-1. / np.sqrt(2), -1. / np.sqrt(2)),
]
centers = [(scale * x, scale * y) for x,y in centers]
while True:
dataset = []
for i in range(batchsz):
point = np.random.randn(2) * 0.02
center = random.choice(centers)
point[0] += center[0]
point[1] += center[1]
dataset.append(point)
dataset = np.array(dataset).astype(np.float32)
dataset /= 1.414
yield dataset
def main():
torch.manual_seed(23)
np.random.seed(23)
data_iter = data_generator()
x = next(data_iter)
# print(x.shape)
G = Generator().cuda()
D = Discriminator().cuda()
# print(G)
# print(D)
optim_G = optim.Adam(G.parameters(), lr=5e-4, betas=(0.5, 0.9))
optim_D = optim.Adam(D.parameters(), lr=5e-4, betas=(0.5, 0.9))
for epoch in range(50000):
for _ in range(5):
x = next(data_iter)
x = torch.from_numpy(x).cuda()
predr = D(x)
lossr = -predr.mean()
z = torch.randn(batchsz, 2).cuda()
xf = G(z).detach()
predf = D(xf)
lossf = predf.mean()
loss_D =lossr + lossf
optim_D.zero_grad()
loss_D.backward()
optim_D.step()
z = torch.randn(batchsz, 2).cuda()
xf = G(z)
predf = D(xf)
loss_G = -predf.mean()
optim_G.zero_grad()
loss_G.backward()
optim_G.step()
if epoch % 100 ==0:
print(loss_D.item(), loss_G.item())
if __name__ == '__main__':
main()
144-numpy实现神经网络
import numpy as np
import random
def sigmoid(z):
return 1.0 / (1.0 + np.exp(-z))
def sigmoid_prime(z):
return sigmoid(z)(1-sigmoid(z))
class MIP_np:
def __init__(self, sizes):
'''
:param sizes:[784, 30, 10]
'''
self.sizes = sizes
self.num_layers = len(sizes) - 1
self.weights = [np.random.randn(ch2, ch1) for ch1,ch2 in zip(sizes[:-1], sizes[1:])]
self.biases = [np.random.randn(ch, 1) for ch in sizes[1:]]
def forward(self, x):
'''
:param x:[784, 1]
:return: [10, 1]
'''
for b,w in zip(self.biases, self.weights):
z = np.dot(w, x) + b
x = sigmoid(z)
return x
def backprop(self, x, y):
'''
:param x: 784 1
:param y: 10 1
:return:
'''
nabla_w = [np.zeros(w.shape) for w in self.weights]
nabla_b = [np.zeros(b.shape) for b in self.biases]
activations = [x]
zs = []
activation = x
for b,w in zip(self.biases, self.weights):
z = np.dot(w, activation) + b
activation = sigmoid(z)
zs.append(z)
activations.append(activation)
delta = activations[-1] * (1 - activations[-1]) * (activations[-1] -y)
nabla_b[-1] = delta
nabla_w[-1] = np.dot(delta, activations[-2].T)
for l in range(2, self.num_layers+1):
l = -1
z = zs[l]
a = activations[l]
delta = np.dot(self.weights[l + 1].T, delta) * a * (1-a)
nabla_b[l] = delta
nabla_w[l] = np.dot(delta, activations[l-1].T)
return nabla_w, nabla_w
def train(self, training_data, epochs, batchsz, lr , test_data):
'''
:param training_data: list
:param epochs: 1000
:param batchsz: 10
:param lr: 0.01
:param test_data:
:return:
'''
if test_data:
n_test = len(test_data)
n = len(training_data)
for j in range(epochs):
random.shuffle(training_data)
mini_batches = [
training_data[k:k+batchsz]
for k in range(0, n ,batchsz)
]
for mini_batch in mini_batches:
self.update_mini_batch(mini_batch, lr)
if test_data:
print('Epoch {0}: {1} / {2}'.format(
j, self.evaluate(test_data), n_test
))
else:
print('Epoch {0} complete'.format(j))
def update_mini_batch(self, batch, lr):
'''
:param batch:
:param lr:
:return:
'''
nabla_w = [np.zeros(w.shape) for w in self.weights]
nabla_b = [np.zeros(b.shape) for b in self.biases]
for x,y in batch:
nabla_w, nabla_b = self.backprop(x, y)
nabla_w = [accu+cur for accu,cur in zip(nabla_w, nabla_w)]
nabla_b = [accu+cur for accu,cur in zip(nabla_b, nabla_b)]
nabla_w = [w/len(batch) for w in nabla_w]
nabla_b = [b/len(batch) for b in nabla_b]
self.weights = [w - lr * nabla for w, nabla in zip(self.weights, nabla_w)]
self.biases = [b - lr * nabla for b, nabla in zip(self.biases, nabla_b)]
def evaluate(self, test_data):
'''
:param test_data:
:return:
'''
result = [(np.argmax(self.forward(x)), y) for x,y in test_data]
correct = sum(int(pred == y) for pred,y in result)
return correct
def main():
pass
if __name__ == '__main__':
main()
1518
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
