DAY 39 图像数据与显存
目录
-
-
- DAY 39 图像数据与显存
-
- 1.图像数据的格式：灰度和彩色数据
- 2.模型的定义
- 3.显存占用的4种地方
-
- a.模型参数+梯度参数
- b.优化器参数
- c.数据批量所占显存
- d.神经元输出中间状态
- 4.batchisize和训练的关系
- 作业：今日代码较少，理解内容即可
-
DAY 39 图像数据与显存
1.图像数据的格式：灰度和彩色数据
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader , Dataset
from torchvision import datasets, transforms
import matplotlib.pyplot as plt
torch.manual_seed(42)
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])
train_dataset = datasets.MNIST(
root='./data',
train=True,
download=True,
transform=transform
)
test_dataset = datasets.MNIST(
root='./data',
train=False,
transform=transform
)
Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz
Failed to download (trying next):
HTTP Error 404: Not Found
Downloading https://ossci-datasets.s3.amazonaws.com/mnist/train-images-idx3-ubyte.gz
Downloading https://ossci-datasets.s3.amazonaws.com/mnist/train-images-idx3-ubyte.gz to ./data\MNIST\raw\train-images-idx3-ubyte.gz
100%|██████████| 9912422/9912422 [00:04<00:00, 2238688.48it/s]
Extracting ./data\MNIST\raw\train-images-idx3-ubyte.gz to ./data\MNIST\raw
Downloading http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz
Failed to download (trying next):
HTTP Error 404: Not Found
Downloading https://ossci-datasets.s3.amazonaws.com/mnist/train-labels-idx1-ubyte.gz
Downloading https://ossci-datasets.s3.amazonaws.com/mnist/train-labels-idx1-ubyte.gz to ./data\MNIST\raw\train-labels-idx1-ubyte.gz
100%|██████████| 28881/28881 [00:00<00:00, 58196.21it/s]
Extracting ./data\MNIST\raw\train-labels-idx1-ubyte.gz to ./data\MNIST\raw
Downloading http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz
Failed to download (trying next):
HTTP Error 404: Not Found
Downloading https://ossci-datasets.s3.amazonaws.com/mnist/t10k-images-idx3-ubyte.gz
Downloading https://ossci-datasets.s3.amazonaws.com/mnist/t10k-images-idx3-ubyte.gz to ./data\MNIST\raw\t10k-images-idx3-ubyte.gz
100%|██████████| 1648877/1648877 [00:03<00:00, 512805.54it/s]
Extracting ./data\MNIST\raw\t10k-images-idx3-ubyte.gz to ./data\MNIST\raw
Downloading http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz
Failed to download (trying next):
HTTP Error 404: Not Found
Downloading https://ossci-datasets.s3.amazonaws.com/mnist/t10k-labels-idx1-ubyte.gz
Downloading https://ossci-datasets.s3.amazonaws.com/mnist/t10k-labels-idx1-ubyte.gz to ./data\MNIST\raw\t10k-labels-idx1-ubyte.gz
100%|██████████| 4542/4542 [00:00<00:00, 2709504.87it/s]
Extracting ./data\MNIST\raw\t10k-labels-idx1-ubyte.gz to ./data\MNIST\raw
sample_idx = torch.randint(0, len(train_dataset), size=(1,)).item()
image, label = train_dataset[sample_idx]
def imshow(img):
img = img * 0.3081 + 0.1307
npimg = img.numpy()
plt.imshow(npimg[0], cmap='gray')
plt.show()
print(f'Label: {label}')
imshow(image)
Label: 6
image.shape
torch.Size([1, 28, 28])
import torch
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np
torch.manual_seed(42)
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
trainset = torchvision.datasets.CIFAR10(
root='./data',
train=True,
download=True,
transform=transform
)
trainloader = torch.utils.data.DataLoader(
trainset,
batch_size=4,
shuffle=True
)
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
sample_idx = torch.randint(0, len(trainset), size=(1,)).item()
image, label = trainset[sample_idx]
print(f'图像形状: {image.shape}')
print(f'图像类别: {classes[label]}')
def imshow(img):
img = img / 2 + 0.5
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
plt.axis('off')
plt.show()
imshow(image)
Downloading https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to ./data\cifar-10-python.tar.gz
100%|██████████| 170498071/170498071 [17:26<00:00, 162858.21it/s]
Extracting ./data\cifar-10-python.tar.gz to ./data
图像形状: torch.Size([3, 32, 32])
图像类别: frog
2.模型的定义
import matplotlib.pyplot as plt
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])
train_dataset = datasets.MNIST(
root='./data',
train=True,
download=True,
transform=transform
)
test_dataset = datasets.MNIST(
root='./data',
train=False,
transform=transform
)
from torchsummary import summary
class MLP(nn.Module):
def __init__(self):
super(MLP, self).__init__()
self.flatten = nn.Flatten()
self.layer1 = nn.Linear(784, 128)
self.relu = nn.ReLU()
self.layer2 = nn.Linear(128, 10)
def forward(self, x):
x = self.flatten(x)
x = self.layer1(x)
x = self.relu(x)
x = self.layer2(x)
return x
model = MLP()
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = model.to(device)
print('\n模型结构信息:')
summary(model, input_size=(1, 28, 28))
模型结构信息:
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Flatten-1 [-1, 784] 0
Linear-2 [-1, 128] 100,480
ReLU-3 [-1, 128] 0
Linear-4 [-1, 10] 1,290
================================================================
Total params: 101,770
Trainable params: 101,770
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.00
Forward/backward pass size (MB): 0.01
Params size (MB): 0.39
Estimated Total Size (MB): 0.40
----------------------------------------------------------------
from torchsummary import summary
class MLP(nn.Module):
def __init__(self, input_size=3072, hidden_size=128, num_classes=10):
super(MLP, self).__init__()
self.flatten = nn.Flatten()
self.fc1 = nn.Linear(input_size, hidden_size)
self.relu = nn.ReLU()
self.fc2 = nn.Linear(hidden_size, num_classes)
def forward(self, x):
x = self.flatten(x)
x = self.fc1(x)
x = self.relu(x)
x = self.fc2(x)
return x
model = MLP()
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = model.to(device)
print('\n模型结构信息:')
summary(model, input_size=(3, 32, 32))
模型结构信息:
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Flatten-1 [-1, 3072] 0
Linear-2 [-1, 128] 393,344
ReLU-3 [-1, 128] 0
Linear-4 [-1, 10] 1,290
================================================================
Total params: 394,634
Trainable params: 394,634
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.01
Forward/backward pass size (MB): 0.03
Params size (MB): 1.51
Estimated Total Size (MB): 1.54
----------------------------------------------------------------
class MLP(nn.Module):
def __init__(self):
super().__init__()
self.flatten = nn.Flatten()
self.layer1 = nn.Linear(784, 128)
self.relu = nn.ReLU()
self.layer2 = nn.Linear(128, 10)
def forward(self, x):
x = self.flatten(x)
x = self.layer1(x)
x = self.relu(x)
x = self.layer2(x)
return x
3.显存占用的4种地方
from torch.utils.data import DataLoader
train_loader = DataLoader(
dataset=train_dataset,
batch_size=64,
shuffle=True
)
test_loader = DataLoader(
dataset=test_dataset,
batch_size=1000,
shuffle=False
)
a.模型参数+梯度参数
b.优化器参数
c.数据批量所占显存
d.神经元输出中间状态
4.batchisize和训练的关系
作业：今日代码较少，理解内容即可
@浙大疏锦行