python深度学习简单实例_Github项目推荐 | Deepy - 基于 Numpy 的小巧优雅简单的(Python)深度学习库...

原标题：Github项目推荐 | Deepy - 基于 Numpy 的小巧优雅简单的(Python)深度学习库

只是为了好玩，就用python编写了一个深度学习库。

它使用numpy进行计算。 API类似于PyTorch的API。

Github项目地址：https://github.com/kaszperro/deepy

示例

在示例目录中有一个线性分类器，其准确率超过96%。

顺序模型的创建：

fromdeepy.moduleimportLinear, Sequentialfrom deepy.autograd.activations importSoftmax, ReLU

my_model = Sequential(

Linear(28* 28, 300),

ReLU(),

Linear(300, 300),

ReLU(),

Linear(300, 10),

Softmax()

)

损失：

fromdeepy.moduleimportLinear

fromdeepy.autograd.losses importCrossEntropyLoss, MSELoss

fromdeepy.variable importVariable

importnumpy asnp

my_model = Linear(10, 10)

loss1 = CrossEntropyLoss()

loss2 = MSELoss()

good_output = Variable(np.zeros((10,10)))

model_input = Variable(np.ones((10,10)))

model_output = my_model(model_input)

error = loss1(good_output, model_output)# now you can propagate error backwards:error.backward()

优化：

fromdeepy.moduleimportLinear

fromdeepy.autograd.losses importCrossEntropyLoss, MSELoss

fromdeepy.variable importVariable

fromdeepy.autograd.optimizers importSGD

importnumpy asnp

my_model = Linear(10, 10)

loss1 = CrossEntropyLoss()

loss2 = MSELoss()

optimizer1 = SGD(my_model.get_variables_list())

good_output = Variable(np.zeros((10,10)))

model_input = Variable(np.ones((10,10)))

model_output = my_model(model_input)

error = loss1(good_output, model_output)

# now you can propagate error backwards:

error.backward()

# and then optimizer can update variables:

optimizer1.zero_grad()

optimizer1.step()

项目地址：https://github.com/kaszperro/deepy

点击公众号菜单栏【每日一题】→【每日一题】或在公众号回复“0129”即可答题获取！返回搜狐，查看更多

责任编辑：