CuPy显卡加速工具包

Chainer是由日本PreferredNetworks公司推出的一套深度学习框架，支持各领域深度学习研究和应用开发的高性能实现。内部提供了与Numpy类似的API，通过CuPy来调用GPUs的运算能力，支持通用和动态图模型，并提供了计算机视觉和分布式训练的强大功能包。

# copy from:https://docs.chainer.org/en/stable/examples/cnn.html
import chainer.links as L
import chainer.functions as F

class LeNet5(Chain):  #继成Chain类
    def __init__(self):
        super(LeNet5, self).__init__()
        with self.init_scope():
            self.conv1 = L.Convolution2D(
                in_channels=1, out_channels=6, ksize=5, stride=1)
            self.conv2 = L.Convolution2D(
                in_channels=6, out_channels=16, ksize=5, stride=1)
            self.conv3 = L.Convolution2D(
                in_channels=16, out_channels=120, ksize=4, stride=1)
            self.fc4 = L.Linear(None, 84)
            self.fc5 = L.Linear(84, 10)  #定义各种操作函数

    def forward(self, x):   #定义序列模型，前向传播函数
        h = F.sigmoid(self.conv1(x))
        h = F.max_pooling_2d(h, 2, 2)
        h = F.sigmoid(self.conv2(h))
        h = F.max_pooling_2d(h, 2, 2)
        h = F.sigmoid(self.conv3(h))
        h = F.sigmoid(self.fc4(h))
        if chainer.config.train:
            return self.fc5(h)
        return F.softmax(self.fc5(h))


##-----------也可以直接调用Chain的API来使用----------##
import chainer.links as L
from functools import partial

class LeNet5(Chain):
    def __init__(self):
        super(LeNet5, self).__init__()
        net = [('conv1', L.Convolution2D(1, 6, 5, 1))]
        net += [('_sigm1', F.sigmoid)]
        net += [('_mpool1', partial(F.max_pooling_2d, ksize=2, stride=2))]
        net += [('conv2', L.Convolution2D(6, 16, 5, 1))]
        net += [('_sigm2', F.sigmoid)]
        net += [('_mpool2', partial(F.max_pooling_2d, ksize=2, stride=2))]
        net += [('conv3', L.Convolution2D(16, 120, 4, 1))]
        net += [('_sigm3', F.sigmoid)]
        net += [('_mpool3', partial(F.max_pooling_2d, ksize=2, stride=2))]
        net += [('fc4', L.Linear(None, 84))]
        net += [('_sigm4', F.sigmoid)]
        net += [('fc5', L.Linear(84, 10))]
        net += [('_sigm5', F.sigmoid)]
        with self.init_scope():
            for n in net:
                if not n[0].startswith('_'):
                    setattr(self, n[0], n[1])
        self.layers = net   #直接定义前传的操作序列
## 注,定义模型也可以使用Sequential的形式：https://docs.chainer.org/en/stable/reference/generated/chainer.Sequential.html#chainer.Sequential

    def forward(self, x):   #前向传播函数
        for n, f in self.layers:
            if not n.startswith('_'):
                x = getattr(self, n)(x)
            else:
                x = f(x)
        if chainer.config.train:
            return x
        return F.softmax(x)

损失函数的定义方法

model = LeNet5()

# Input data and label
x = np.random.rand(32, 1, 28, 28).astype(np.float32)
t = np.random.randint(0, 10, size=(32,)).astype(np.int32)

# Forward computation
y = model(x)    #预测结果

# Loss calculation
loss = F.softmax_cross_entropy(y, t)    #交叉熵结果

参考网站 Docs:https://docs.chainer.org/en/stable/
Website:https://chainer.org/
论文地址：https://arxiv.org/pdf/1908.00213.pdf