حول تطبيق مكتبة التعلم العميق في Python

معلومات عامة

ators عوامل التشغيل

ptمحسنات (محسنات)

functions وظائف الخسارة

▍ مبدئي

▍ المنظمون

التمايز التلقائي

التنفيذ

class  Function(object):
    def forward(self): 
        raise NotImplementedError
    
    def backward(self): 
        raise NotImplementedError
    
    def getParams(self): 
        return []

class Linear(Function):
    def __init__(self,in_nodes,out_nodes):
        self.weights = Tensor((in_nodes,out_nodes))
        self.bias    = Tensor((1,out_nodes))
        self.type = 'linear'

    def forward(self,x):
        output = np.dot(x,self.weights.data)+self.bias.data
        self.input = x 
        return output

    def backward(self,d_y):
        self.weights.grad += np.dot(self.input.T,d_y)
        self.bias.grad    += np.sum(d_y,axis=0,keepdims=True)
        grad_input         = np.dot(d_y,self.weights.data.T)
        return grad_input

    def getParams(self):
        return [self.weights,self.bias]

class Optimizer(object):
    def __init__(self,parameters):
        self.parameters = parameters
    
    def step(self): 
        raise NotImplementedError

    def zeroGrad(self):
        for p in self.parameters:
            p.grad = 0.

class SGD(Optimizer):
    def __init__(self,parameters,lr=.001,weight_decay=0.0,momentum = .9):
        super().__init__(parameters)
        self.lr           = lr
        self.weight_decay = weight_decay
        self.momentum     = momentum
        self.velocity     = []
        for p in parameters:
            self.velocity.append(np.zeros_like(p.grad))

    def step(self):
        for p,v in zip(self.parameters,self.velocity):
            v = self.momentum*v+p.grad+self.weight_decay*p.data
            p.data=p.data-self.lr*v

حل المشكلة الحقيقية

• نموذج: الرسم البياني للحساب.
• البيانات والقيمة المستهدفة: بيانات للتدريب على الشبكة.
• وظيفة الخسارة: بديل لهدف التحسين.
• مُحسِّن: آلية لتحديث معلمات النموذج.

model # 
data,target # 
loss_fn # 
optim #,         
Repeat:#   ,    ,     
   optim.zeroGrad() #    
   output = model.forward(data) #   
   loss   = loss_fn(output,target) # 
   grad   = loss.backward() #      
   model.backward(grad) #    
   optim.step() #  

class Model():
    def __init__(self):
        self.computation_graph = []
        self.parameters        = []

    def add(self,layer):
        self.computation_graph.append(layer)
        self.parameters+=layer.getParams()

    def __innitializeNetwork(self):
        for f in self.computation_graph:
            if f.type=='linear':
                weights,bias = f.getParams()
                weights.data = .01*np.random.randn(weights.data.shape[0],weights.data.shape[1])
                bias.data    = 0.

    def fit(self,data,target,batch_size,num_epochs,optimizer,loss_fn):
        loss_history = []
        self.__innitializeNetwork()
        data_gen = DataGenerator(data,target,batch_size)
        itr = 0
        for epoch in range(num_epochs):
            for X,Y in data_gen:
                optimizer.zeroGrad()
                for f in self.computation_graph: X=f.forward(X)
                loss = loss_fn.forward(X,Y)
                grad = loss_fn.backward()
                for f in self.computation_graph[::-1]: grad = f.backward(grad) 
                loss_history+=[loss]
                print("Loss at epoch = {} and iteration = {}: {}".format(epoch,itr,loss_history[-1]))
                itr+=1
                optimizer.step()
        
        return loss_history
    
    def predict(self,data):
        X = data
        for f in self.computation_graph: X = f.forward(X)
        return X

• : add() , . computation_graph.
• : , , , .
• : fit() . , .
• : predict() , , .

تدريب نموذجي

import dl_numpy as DL
import utilities

batch_size        = 20
num_epochs        = 200
samples_per_class = 100
num_classes       = 3
hidden_units      = 100
data,target       = utilities.genSpiralData(samples_per_class,num_classes)
model             = utilities.Model()
model.add(DL.Linear(2,hidden_units))
model.add(DL.ReLU())
model.add(DL.Linear(hidden_units,num_classes))
optim   = DL.SGD(model.parameters,lr=1.0,weight_decay=0.001,momentum=.9)
loss_fn = DL.SoftmaxWithLoss()
model.fit(data,target,batch_size,num_epochs,optim,loss_fn)
predicted_labels = np.argmax(model.predict(data),axis=1)
accuracy         = np.sum(predicted_labels==target)/len(target)
print("Model Accuracy = {}".format(accuracy))
utilities.plot2DDataWithDecisionBoundary(data,target,model)

ملخص

• عوامل التشغيل: الالتفاف ، الاختزال الجزئي.
• محسنات: آدم ، RMSProp.
• المنظمون: BatchNorm ، DropOut.