Pytorch學習筆記【18】：使用GPU加速

之前我寫過一篇CNN識別手寫數字的博客，我這一篇的介紹將基於那一篇的代碼做出相關改進

 

1. 改過的代碼

2. 原本的代碼

import os

# third-party library
import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt


# 定義一些參數
EPOCH = 1               # 訓練數據的次數，我們這裏假定訓練一次
BATCH_SIZE = 50         # 每次訓練的數據量，這個會產生每一次訓練分多少次進行，或者多少批進行
LR = 0.001              # 學習率
DOWNLOAD_MNIST = False


# 下載並且加載數據集
if not(os.path.exists('./mnist/')) or not os.listdir('./mnist/'):
    # not mnist dir or mnist is empyt dir
    DOWNLOAD_MNIST = True

train_data = torchvision.datasets.MNIST(
    root='./mnist/',
    train=True,                                     # 表示訓練數據
    transform=torchvision.transforms.ToTensor(),    # 將數據轉換成tensor
                                                    # torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
    download=DOWNLOAD_MNIST,
)

# plot one example
print(train_data.train_data.size())                 # (60000, 28, 28)
print(train_data.train_labels.size())               # (60000)
plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
plt.title('%i' % train_data.train_labels[0])
plt.show()

# Data Loader for easy mini-batch return in training, 每一批的數據形狀是 (50, 1, 28, 28)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True) # 加載數據

# pick 2000 samples to speed up testing
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)
test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:2000]/255.   # shape from (2000, 28, 28) to (2000, 1, 28, 28), value in range(0,1)
test_y = test_data.test_labels[:2000]


class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential(         # 輸入圖形的形式 (1, 28, 28) 定義第一個卷積層
            nn.Conv2d(
                in_channels=1,              # 輸入的通道數，也就是高度
                out_channels=16,            # n_filters，16個過濾器  之後圖形成了（16,28,28）
                kernel_size=5,              # 卷積核是5*5的
                stride=1,                   # filter 過濾器的步長
                padding=2,                  # if want same width and length of this image after Conv2d, padding=(kernel_size-1)/2 if stride=1
            ),                              # output shape (16, 28, 28)
            nn.ReLU(),                      # activation 激活函數
            nn.MaxPool2d(kernel_size=2),    # 選擇 2x2 area,進行池化層操作， 輸出形狀 (16, 14, 14)
        )
        self.conv2 = nn.Sequential(         # 輸入形狀 (16, 14, 14)
            nn.Conv2d(16, 32, 5, 1, 2),     # 輸出形狀 (32, 14, 14)
            nn.ReLU(),                      # 激活函數
            nn.MaxPool2d(2),                # 池化層之後的形狀 (32, 7, 7)
        )
        self.out = nn.Linear(32 * 7 * 7, 10)   # 全連接層, 輸出10個數字，因爲分類嘛，總共有10個類。

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)           # 將數據由（32,7,7)這樣的空間數據拉成一個列向量，也就是32*7*7
        output = self.out(x)
        return output, x    # return x for visualization


cnn = CNN()
print(cnn)  # net architecture

optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)   # 在優化器中傳入參數
loss_func = nn.CrossEntropyLoss()                       # 專門用來做分類的損失函數

# following function (plot_with_labels) is for visualization, can be ignored if not interested
# from matplotlib import cm
# try: from sklearn.manifold import TSNE; HAS_SK = True
# except: HAS_SK = False; print('Please install sklearn for layer visualization')
# def plot_with_labels(lowDWeights, labels):
#     plt.cla()
#     X, Y = lowDWeights[:, 0], lowDWeights[:, 1]
#     for x, y, s in zip(X, Y, labels):
#         c = cm.rainbow(int(255 * s / 9)); plt.text(x, y, s, backgroundcolor=c, fontsize=9)
#     plt.xlim(X.min(), X.max()); plt.ylim(Y.min(), Y.max()); plt.title('Visualize last layer'); plt.show(); plt.pause(0.01)
#
# plt.ion()
# training and testing
for epoch in range(EPOCH):
    for step, (b_x, b_y) in enumerate(train_loader):   # 數據總量/每批訓練量=最終step的值
        print('b_x: ',b_x)
        output = cnn(b_x)[0]            # cnn output
        loss = loss_func(output, b_y)   # cross entropy loss
        optimizer.zero_grad()           # clear gradients for this training step
        loss.backward()                 # 神經網絡反向傳播
        optimizer.step()                # 更新梯度，或者更新參數

        if step % 50 == 0:
            test_output, last_layer = cnn(test_x)
            pred_y = torch.max(test_output, 1)[1].data.numpy()
            accuracy = float((pred_y == test_y.data.numpy()).astype(int).sum()) / float(test_y.size(0)) # 計算正確率
            print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy(), '| test accuracy: %.2f' % accuracy)
            # if HAS_SK:
            #     # Visualization of trained flatten layer (T-SNE)
            #     tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000)
            #     plot_only = 500
            #     low_dim_embs = tsne.fit_transform(last_layer.data.numpy()[:plot_only, :])
            #     labels = test_y.numpy()[:plot_only]
            #     plot_with_labels(low_dim_embs, labels)
# plt.ioff()

# print 10 predictions from test data
test_output, _ = cnn(test_x[:10])
pred_y = torch.max(test_output, 1)[1].data.numpy()
print('pred_y_1: ',test_output)
print('pred_y_2: ',torch.max(test_output,1))
print('pred_y_3: ',torch.max(test_output,1)[1])
print(pred_y, 'prediction number')
print(test_y[:10].numpy(), 'real number')

3. 改過之後的代碼

import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision

# torch.manual_seed(1)

EPOCH = 1
BATCH_SIZE = 50
LR = 0.001
DOWNLOAD_MNIST = False

train_data = torchvision.datasets.MNIST(root='./mnist/', train=True, transform=torchvision.transforms.ToTensor(), download=DOWNLOAD_MNIST,)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)

# !!!!!!!! 改變這裏 !!!!!!!!! #
test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:2000].cuda()/255.   # Tensor on GPU
test_y = test_data.test_labels[:2000].cuda()


class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential(nn.Conv2d(in_channels=1, out_channels=16, kernel_size=5, stride=1, padding=2,),
                                   nn.ReLU(), nn.MaxPool2d(kernel_size=2),)
        self.conv2 = nn.Sequential(nn.Conv2d(16, 32, 5, 1, 2), nn.ReLU(), nn.MaxPool2d(2),)
        self.out = nn.Linear(32 * 7 * 7, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)
        output = self.out(x)
        return output

cnn = CNN()

# !!!!!!!! 改變這裏 !!!!!!!!! #
cnn.cuda()      # Moves all model parameters and buffers to the GPU.

optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)
loss_func = nn.CrossEntropyLoss()

for epoch in range(EPOCH):
    for step, (x, y) in enumerate(train_loader):

        # !!!!!!!! 改變這裏 !!!!!!!!! #
        b_x = x.cuda()    # Tensor on GPU
        b_y = y.cuda()    # Tensor on GPU

        output = cnn(b_x)
        loss = loss_func(output, b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if step % 50 == 0:
            test_output = cnn(test_x)

            # !!!!!!!! 改變這裏 !!!!!!!!! #
            pred_y = torch.max(test_output, 1)[1].cuda().data  # move the computation in GPU

            accuracy = torch.sum(pred_y == test_y).type(torch.FloatTensor) / test_y.size(0)
            print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.cpu().numpy(), '| test accuracy: %.2f' % accuracy)


test_output = cnn(test_x[:10])

# !!!!!!!! 改變這裏 !!!!!!!!! #
pred_y = torch.max(test_output, 1)[1].cuda().data # move the computation in GPU

print(pred_y, 'prediction number')
print(test_y[:10], 'real number')