paddlepaddle卷积神经网络作业

最新推荐文章于 2024-04-22 15:14:54 发布

wry010504

最新推荐文章于 2024-04-22 15:14:54 发布

阅读量289

点赞数

文章标签：神经网络 paddlepaddle pytorch

本文链接：https://blog.csdn.net/wryshj/article/details/120791106

版权

该博客展示了如何使用PaddlePaddle库构建并训练一个简单的卷积神经网络（CNN）模型，以解决CIFAR-10数据集的图像分类任务。在训练过程中，模型逐渐提高验证集上的准确率，损失逐渐减小。最终，模型在验证集上达到了约71%的准确率。

摘要由CSDN通过智能技术生成

import paddle
import paddle.nn.functional as F
from paddle.vision.transforms import ToTensor
import numpy as np
import matplotlib.pyplot as plt

print(paddle.__version__)
transform = ToTensor()
cifar10_train = paddle.vision.datasets.Cifar10(mode='train',transform=transform)
cifar10_test = paddle.vision.datasets.Cifar10(mode='test',transform=transform)


class MyNet(paddle.nn.Layer):
    def __init__(self, num_classes=1):
        super(MyNet, self).__init__()

        self.conv1 = paddle.nn.Conv2D(in_channels=3, out_channels=32, kernel_size=(3, 3))
        self.pool1 = paddle.nn.MaxPool2D(kernel_size=2, stride=2)

        self.conv2 = paddle.nn.Conv2D(in_channels=32, out_channels=64, kernel_size=(3,3))
        self.pool2 = paddle.nn.MaxPool2D(kernel_size=2, stride=2)

        self.conv3 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=(3,3))

        self.flatten = paddle.nn.Flatten()

        self.linear1 = paddle.nn.Linear(in_features=1024, out_features=64)
        self.linear2 = paddle.nn.Linear(in_features=64, out_features=num_classes)

    def forward(self, x):
        x = self.conv1(x)
        x = F.relu(x)
        x = self.pool1(x)

        x = self.conv2(x)
        x = F.relu(x)
        x = self.pool2(x)

        x = self.conv3(x)
        x = F.relu(x)

        x = self.flatten(x)
        x = self.linear1(x)
        x = F.relu(x)
        x = self.linear2(x)
        return x
epoch_num = 10
batch_size = 32
learning_rate = 0.001
val_acc_history = []
val_loss_history = []

def train(model):
    print('start training ... ')
    # turn into training mode
    model.train()

    opt = paddle.optimizer.Adam(learning_rate=learning_rate,
                                parameters=model.parameters())

    train_loader = paddle.io.DataLoader(cifar10_train,
                                        shuffle=True,
                                        batch_size=batch_size)

    valid_loader = paddle.io.DataLoader(cifar10_test, batch_size=batch_size)
    
    for epoch in range(epoch_num):
        for batch_id, data in enumerate(train_loader()):
            x_data = data[0]
            y_data = paddle.to_tensor(data[1])
            y_data = paddle.unsqueeze(y_data, 1)

            logits = model(x_data)
            loss = F.cross_entropy(logits, y_data)

            if batch_id % 1000 == 0:
                print("epoch: {}, batch_id: {}, loss is: {}".format(epoch, batch_id, loss.numpy()))
            loss.backward()
            opt.step()
            opt.clear_grad()

        # evaluate model after one epoch
        model.eval()
        accuracies = []
        losses = []
        for batch_id, data in enumerate(valid_loader()):
            x_data = data[0]
            y_data = paddle.to_tensor(data[1])
            y_data = paddle.unsqueeze(y_data, 1)

            logits = model(x_data)
            loss = F.cross_entropy(logits, y_data)
            acc = paddle.metric.accuracy(logits, y_data)
            accuracies.append(acc.numpy())
            losses.append(loss.numpy())

        avg_acc, avg_loss = np.mean(accuracies), np.mean(losses)
        print("[validation] accuracy/loss: {}/{}".format(avg_acc, avg_loss))
        val_acc_history.append(avg_acc)
        val_loss_history.append(avg_loss)
        model.train()

model = MyNet(num_classes=10)
train(model)

plt.plot(val_acc_history, label = 'validation accuracy')

plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.ylim([0.5, 0.8])
plt.legend(loc='lower right')

运行结果如下

2.0.2
start training ... 
epoch: 0, batch_id: 0, loss is: [2.5867429]
epoch: 0, batch_id: 1000, loss is: [1.4291399]
[validation] accuracy/loss: 0.5660942196846008/1.192248821258545
epoch: 1, batch_id: 0, loss is: [1.4453502]
epoch: 1, batch_id: 1000, loss is: [0.9542478]
[validation] accuracy/loss: 0.6403753757476807/1.0135371685028076
epoch: 2, batch_id: 0, loss is: [0.7726191]
epoch: 2, batch_id: 1000, loss is: [0.6877733]
[validation] accuracy/loss: 0.6546525359153748/0.9844738841056824
epoch: 3, batch_id: 0, loss is: [0.9387559]
epoch: 3, batch_id: 1000, loss is: [0.6351695]
[validation] accuracy/loss: 0.6799121499061584/0.921659529209137
epoch: 4, batch_id: 0, loss is: [0.85253346]
epoch: 4, batch_id: 1000, loss is: [1.2389075]
[validation] accuracy/loss: 0.6968849897384644/0.8811760544776917
epoch: 5, batch_id: 0, loss is: [0.57655555]
epoch: 5, batch_id: 1000, loss is: [0.5159716]
[validation] accuracy/loss: 0.7062699794769287/0.8671459555625916
epoch: 6, batch_id: 0, loss is: [0.5851355]
epoch: 6, batch_id: 1000, loss is: [0.8208879]
[validation] accuracy/loss: 0.7045726776123047/0.8722187280654907
epoch: 7, batch_id: 0, loss is: [0.5359383]
epoch: 7, batch_id: 1000, loss is: [0.6991255]
[validation] accuracy/loss: 0.6884983777999878/0.9462959170341492
epoch: 8, batch_id: 0, loss is: [0.67292917]
epoch: 8, batch_id: 1000, loss is: [0.7463263]
[validation] accuracy/loss: 0.6968849897384644/0.9279959797859192
epoch: 9, batch_id: 0, loss is: [0.44502622]
epoch: 9, batch_id: 1000, loss is: [0.36299592]
[validation] accuracy/loss: 0.7103634476661682/0.9326649904251099
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/cbook/__init__.py:2349: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  if isinstance(obj, collections.Iterator):
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/cbook/__init__.py:2366: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  return list(data) if isinstance(data, collections.MappingView) else data
<matplotlib.legend.Legend at 0x7f763fe00250>