强大的PyTorch：10分钟让你了解深度学习领域新流行的框架

import torch # arrays on GPUimport torch.autograd as autograd #build a computational graphimport torch.nn as nn # neural net libraryimport torch.nn.functional as F # most non-linearities are hereimport torch.optim as optim # optimization package

# 2 matrices of size 2x3 into a 3d tensor 2x2x3d=[[[1., 2.,3.],[4.,5.,6.]],[[7.,8.,9.],[11.,12.,13.]]]d=torch.Tensor(d) # array from python listprint "shape of the tensor:",d.size()# the first index is the depthz=d[0]+d[1]print "adding up the two matrices of the 3d tensor:",zshape of the tensor: torch.Size([2, 2, 3])adding up the two matrices of the 3d tensor:   8  10  12 15  17  19[torch.FloatTensor of size 2x3]# a heavily used operation is reshaping of tensors using .view()print d.view(2,-1) #-1 makes torch infer the second dim  1   2   3   4   5   6  7   8   9  11  12  13[torch.FloatTensor of size 2x6]

# d is a tensor not a node, to create a node based on it:x= autograd.Variable(d, requires_grad=True)print "the node's data is the tensor:", x.data.size()print "the node's gradient is empty at creation:", x.grad # the grad is empty right nowthe node's data is the tensor: torch.Size([2, 2, 3])the node's gradient is empty at creation: None# do operation on the node to make a computational graphy= x+1z=x+ys=z.sum()print s.creator<torch.autograd._functions.reduce.Sum object at 0x7f1e59988790># calculate gradientss.backward()print "the variable now has gradients:",x.gradthe variable now has gradients: Variable containing:(0 ,.,.) =   2  2  2  2  2  2(1 ,.,.) =   2  2  2  2  2  2[torch.FloatTensor of size 2x2x3]

# linear transformation of a 2x5 matrix into a 2x3 matrixlinear_map=nn.Linear(5,3)print "using randomly initialized params:", linear_map.parametersusing randomly initialized params: <bound method Linear.parameters of Linear (5 -> 3)># data has 2 examples with 5 features and 3 targetdata=torch.randn(2,5) # trainingy=autograd.Variable(torch.randn(2,3)) # target# make a nodex=autograd.Variable(data, requires_grad=True)# apply transformation to a node creates a computational grapha=linear_map(x)z=F.relu(a)o=F.softmax(z)print "output of softmax as a probability distribution:", o.data.view(1,-1)# loss functionloss_func=nn.MSELoss() #instantiate loss functionL=loss_func(z,y) # calculateMSE loss between output and targetprint "Loss:", Loutput of softmax as a probability distribution:  0.2092  0.1979  0.5929  0.4343  0.3038  0.2619[torch.FloatTensor of size 1x6]Loss: Variable containing: 2.9838[torch.FloatTensor of size 1]

class Log_reg_classifier(nn.Module):    def __init__(self, in_size,out_size):        super(Log_reg_classifier,self).__init__() #always call parent's init         self.linear=nn.Linear(in_size, out_size) #layer parameters    def forward(self,vect):        return F.log_softmax(self.linear(vect)) # 

optimizer=optim.SGD(linear_map.parameters(),lr=1e-2) # instantiate optimizer with model params + learning rate# epoch loop: we run following until convergenceoptimizer.zero_grad() # make gradients zeroL.backward(retain_variables=True)optimizer.step()print LVariable containing: 2.9838[torch.FloatTensor of size 1]

# define modelmodel = Log_reg_classifier(10,2)# define loss functionloss_func=nn.MSELoss() # define optimizeroptimizer=optim.SGD(model.parameters(),lr=1e-1)# send data through model in minibatches for 10 epochsfor epoch in range(10):    for minibatch, target in data:        model.zero_grad() # pytorch accumulates gradients, making them zero for each minibatch        #forward pass        out=model(autograd.Variable(minibatch))        #backward pass         L=loss_func(out,target) #calculate loss        L.backward() # calculate gradients        optimizer.step() # make an update step