Numpy and Torch对比
import torchimport numpy as npnp_data =np.arange(6).reshape((2,3))torch_data =torch.from_numpy(np_data)print( '\nnumpy',np_data, '\ntorch',torch_data)D:\Test>python test.pynumpy [[0 1 2] [3 4 5]]torch tensor([[0, 1, 2], [3, 4, 5]], dtype=torch.int32)
import torchimport numpy as npnp_data =np.arange(6).reshape((2,3))torch_data =torch.from_numpy(np_data)tensor2array =torch_data.numpy()print( '\nnumpy',np_data, '\ntorch',torch_data, '\ntensor2array',tensor2array,)D:\Test>python test.pynumpy [[0 1 2] [3 4 5]]torch tensor([[0, 1, 2], [3, 4, 5]], dtype=torch.int32)tensor2array [[0 1 2] [3 4 5]]
import torchimport numpy as npdata =[-1,-2,1,2]tensor =torch.FloatTensor(data)print( '\nabs:', '\ntorch:',np.abs(data), '\ntorch:',torch.abs(tensor))D:\Test>python test.pyabs:torch: [1 2 1 2]torch: tensor([1., 2., 1., 2.])
import torchimport numpy as npdata =[-1,-2,1,2]tensor =torch.FloatTensor(data)print( '\ntorch:',np.sin(data), '\ntorch:',torch.sin(tensor))D:\Test>python test.pytorch: [-0.84147098 -0.90929743 0.84147098 0.90929743]torch: tensor([-0.8415, -0.9093, 0.8415, 0.9093])
import torchimport numpy as npdata =[[1,2],[3,4]]tensor =torch.FloatTensor(data)print( '\nnumpy:',np.matmul(data,data), '\ntorch:',torch.mm(tensor,tensor))D:\Test>python test.pynumpy: [[ 7 10] [15 22]]torch: tensor([[ 7., 10.], [15., 22.]])
import torchimport numpy as npdata =[[1,2],[3,4]]tensor =torch.FloatTensor(data)data =np.array(data)print( '\nnumpy:',data.dot(data), '\ntorch:',tensor.dot(tensor))D:\Test>python test.pyTraceback (most recent call last): File "test.py", line 10, in'\ntorch:',tensor.dot(tensor))RuntimeError: dot: Expected 1-D argument self, but got 2-D
Variable变量
import torchfrom torch.autograd import Variabledata =([1,2],[3,4])tensor =torch.FloatTensor(data)variable =Variable(tensor, requires_grad=True)print('\ntensor:',tensor)print('\nvariable:',variable) 比较import torchfrom torch.autograd import Variabletensor =torch.FloatTensor([1,2],[3,4])variable =Variable(tensor, requires_grad=True)print('\ntensor:',tensor)print('\nvariable:',variable)D:\Test>python test.pyTraceback (most recent call last): File "test.py", line 4, in tensor =torch.FloatTensor([1,2],[3,4])TypeError: new() received an invalid combination of arguments - got (list, list), but expected one of: * (torch.device device) * (torch.Storage storage) * (Tensor other) * (tuple of ints size, torch.device device) didn't match because some of the arguments have invalid types: ([31;1mlist[0m, [31;1mlist[0m) * (object data, torch.device device) didn't match because some of the arguments have invalid types: ([31;1mlist[0m, [31;1mlist[0m) import torchfrom torch.autograd import Variabledata =([1,2],[3,4])tensor =torch.FloatTensor(data)variable =Variable(tensor, requires_grad=True)t_out =torch.mean(tensor *tensor)v_out =torch.mean(variable *variable)print('\ntensor:',t_out)print('\nvariable:',v_out)D:\Test>python test.pytensor: tensor(7.5000)variable: tensor(7.5000, grad_fn= ) 注:torch在0.4版本后将Tensor与Variable合并
反向求解梯度:*.backward()
import torchfrom torch.autograd import Variabledata =([1,2],[3,4])tensor =torch.FloatTensor(data)variable =Variable(tensor, requires_grad=True)t_out =torch.mean(tensor *tensor)v_out =torch.mean(variable *variable)v_out.backward()print('\nvariable:',variable.grad)D:\Test>python test.pyvariable: tensor([[0.5000, 1.0000], [1.5000, 2.0000]]) v_out =1 /4 *sum(variable *variable)d(v_out) /d(variable) =1 /4 *2 *variable =variable /2
v_out =1 /4 *sum(var *var)d(v_out) /d(var) =1 /4 *2 *variable =variable /2
import torchfrom torch.autograd import Variabledata =([1,2],[3,4])tensor =torch.FloatTensor(data)variable =Variable(tensor, requires_grad=True)t_out =torch.mean(tensor *tensor)v_out =torch.mean(variable *variable)v_out.backward()print('\nvariable:',variable.grad)print('\nvariable.data:',variable.data)print('\nvariable.data.numpy:',variable.data.numpy())D:\ptest>python test.pyvariable: tensor([[0.5000, 1.0000], [1.5000, 2.0000]])variable.data: tensor([[1., 2.], [3., 4.]])variable.data.numpy: [[1. 2.] [3. 4.]] Activation Fundtion激励函数
import torchimport torch.nn.functional as Ffrom torch.autograd import Variableimport matplotlib.pyplot as pltx =torch.linspace(-5,5,200)x =Variable(x)x_np =x.data.numpy()y_relu =F.relu(x).data.numpy()y_sigmoid =F.sigmoid(x).data.numpy()y_tanh =F.tanh(x).data.numpy()y_softplus =F.softplus(x).data.numpy()plt.figure(1,figsize =(8,6))plt.subplot(221)plt.plot(x_np,y_relu,c ='red',label ='relu')plt.ylim((-1,5))plt.legend(loc ='best')plt.subplot(222)plt.plot(x_np,y_sigmoid,c ='red',label ='sigmoid')plt.ylim((-0.2,1.2))plt.legend(loc ='best')plt.subplot(223)plt.plot(x_np,y_tanh,c ='red',label ='tanh')plt.ylim((-1.2,1.2))plt.legend(loc ='best')plt.subplot(224)plt.plot(x_np,y_softplus,c ='red',label ='softplus')plt.ylim((-0.2,6))plt.legend(loc ='best')plt.show()D:\ptest>python test.pyD:\Python\Python36\lib\site-packages\torch\nn\functional.py:1006: UserWarning: nn.functional.sigmoid is deprecated. Use torch.sigmoid instead. warnings.warn("nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.")D:\Python\Python36\lib\site-packages\torch\nn\functional.py:995: UserWarning: nn.functional.tanh is deprecated. Use torch.tanh instead. warnings.warn("nn.functional.tanh is deprecated. Use torch.tanh instead.") import torchimport torch.nn.functional as Ffrom torch.autograd import Variableimport matplotlib.pyplot as pltx =torch.linspace(-5,5,200)x =Variable(x)x_np =x.data.numpy()y_relu =torch.relu(x).data.numpy()y_sigmoid =torch.sigmoid(x).data.numpy()y_tanh =torch.tanh(x).data.numpy()y_softplus =F.softplus(x).data.numpy()plt.figure(1,figsize =(8,6))plt.subplot(221)plt.plot(x_np,y_relu,c ='red',label ='relu')plt.ylim((-1,5))plt.legend(loc ='best')plt.subplot(222)plt.plot(x_np,y_sigmoid,c ='red',label ='sigmoid')plt.ylim((-0.2,1.2))plt.legend(loc ='best')plt.subplot(223)plt.plot(x_np,y_tanh,c ='red',label ='tanh')plt.ylim((-1.2,1.2))plt.legend(loc ='best')plt.subplot(224)plt.plot(x_np,y_softplus,c ='red',label ='softplus')plt.ylim((-0.2,6))plt.legend(loc ='best')plt.show()
Regression回归(关系拟合)
import torchimport torchfrom torch.autograd import Variableimport torch.nn.functional as Fimport matplotlib.pyplot as pltx =torch.unsqueeze(torch.linspace(-1,1,100),dim =1)y =x.pow(2) +0.2 *torch.rand(x.size())x,y =Variable(x),Variable(y)#plt.scatter(x.data.numpy(),y.data.numpy())#plt.show()class Net(torch.nn.Module): def __init__(self,n_feature,n_hidden,n_output): super(Net,self).__init__() self.hidden =torch.nn.Linear(n_feature,n_hidden) self.predict =torch.nn.Linear(n_hidden,n_output) def forward(self,x): x =torch.relu(self.hidden(x)) x =self.predict(x) return xnet =Net(n_feature =1,n_hidden =10,n_output =1)print(net)optimizer =torch.optim.SGD(net.parameters(),lr =0.2)loss_func =torch.nn.MSELoss()plt.ion()plt.show()for t in range(200): prediction =net(x) loss =loss_func(prediction,y) optimizer.zero_grad() loss.backward() optimizer.step() if t %5 ==0: plt.cla() plt.scatter(x.data.numpy(),y.data.numpy()) plt.plot(x.data.numpy(),prediction.data.numpy(),'r-',lw =5) plt.text(0.5,0,'loss =%.4f' % loss.data.numpy(),fontdict ={'size':20,'color':'red'}) plt.pause(0.1)plt.ioff()plt.show() Classification分类(区分类型)
import torchfrom torch.autograd import Variableimport torch.nn.functional as Fimport matplotlib.pyplot as pltn_data =torch.ones(100,2)x0 =torch.normal(2 *n_data,1)y0 =torch.zeros(100)x1 =torch.normal(-2 *n_data,1)y1 =torch.ones(100)x =torch.cat((x0,x1),0).type(torch.FloatTensor)y =torch.cat((y0,y1),).type(torch.LongTensor)x,y =Variable(x),Variable(y)#plt.scatter(x.data.numpy(),y.data.numpy())#plt.show()class Net(torch.nn.Module): def __init__(self,n_feature,n_hidden,n_output): super(Net,self).__init__() self.hidden =torch.nn.Linear(n_feature,n_hidden) self.predict =torch.nn.Linear(n_hidden,n_output) def forward(self,x): x =torch.relu(self.hidden(x)) x =self.predict(x) return xnet =Net(n_feature =2,n_hidden =10,n_output =2)print(net)optimizer =torch.optim.SGD(net.parameters(),lr =0.02)loss_func =torch.nn.CrossEntropyLoss()plt.ion()plt.show()for t in range(100): out =net(x) loss =loss_func(out,y) optimizer.zero_grad() loss.backward() optimizer.step() if t %2 ==0: plt.cla() prediction =torch.max(out,1)[1] pred_y =prediction.data.numpy() target_y =y.data.numpy() plt.scatter(x.data.numpy()[:,0],x.data.numpy()[:,1],c =pred_y,s =100,lw =0,cmap ='RdYlGn') accuracy =float((pred_y ==target_y).astype(int).sum()) /float(target_y.size) plt.text(1.5,-4,'Accuracy =%.2f' % accuracy,fontdict ={'size':20,'color':'red'}) plt.pause(0.1)plt.ioff()plt.show() 快速搭建法
import torchfrom torch.autograd import Variableimport torch.nn.functional as Fimport matplotlib.pyplot as pltn_data =torch.ones(100,2)x0 =torch.normal(2 *n_data,1)y0 =torch.zeros(100)x1 =torch.normal(-2 *n_data,1)y1 =torch.ones(100)x =torch.cat((x0,x1),0).type(torch.FloatTensor)y =torch.cat((y0,y1),).type(torch.LongTensor)x,y =Variable(x),Variable(y)#plt.scatter(x.data.numpy(),y.data.numpy())#plt.show()class Net(torch.nn.Module): def __init__(self,n_feature,n_hidden,n_output): super(Net,self).__init__() self.hidden =torch.nn.Linear(n_feature,n_hidden) self.predict =torch.nn.Linear(n_hidden,n_output) def forward(self,x): x =torch.relu(self.hidden(x)) x =self.predict(x) return xnet1 =Net(n_feature =2,n_hidden =10,n_output =2)print(net1)net2 =torch.nn.Sequential( torch.nn.Linear(2,10), torch.nn.ReLU(), torch.nn.Linear(10,2),)print(net2)D:\ptest>python test.pyNet( (hidden): Linear(in_features=2, out_features=10, bias=True) (predict): Linear(in_features=10, out_features=2, bias=True))Sequential( (0): Linear(in_features=2, out_features=10, bias=True) (1): ReLU() (2): Linear(in_features=10, out_features=2, bias=True))
save保存提取
import torchfrom torch.autograd import Variableimport matplotlib.pyplot as plt#torch.manual_seed(1)x =torch.unsqueeze(torch.linspace(-1,1,100),dim =1)y =x.pow(2) +0.2 *torch.rand(x.size())x,y =Variable(x,requires_grad =False),Variable(y,requires_grad =False)def save(): net1 =torch.nn.Sequential( torch.nn.Linear(1,10), torch.nn.ReLU(), torch.nn.Linear(10,1),) print('\nnet1:',net1) optimizer =torch.optim.SGD(net1.parameters(),lr =0.5) loss_func =torch.nn.MSELoss() for t in range(100): prediction =net1(x) loss =loss_func(prediction,y) optimizer.zero_grad() loss.backward() optimizer.step() plt.figure(1,figsize =(10,3)) plt.subplot(131) plt.title('Net1') plt.scatter(x.data.numpy(),y.data.numpy()) plt.plot(x.data.numpy(),prediction.data.numpy(),'r-',lw =5) torch.save(net1,'net.pkl') torch.save(net1.state_dict(),'net_params.pkl')def restore_net(): net2 =torch.load('net.pkl') prediction =net2(x) print('\nnet2:',net2) plt.subplot(132) plt.title('Net2') plt.scatter(x.data.numpy(),y.data.numpy()) plt.plot(x.data.numpy(),prediction.data.numpy(),'r-',lw =5)def restore_params(): net3 =torch.nn.Sequential( torch.nn.Linear(1,10), torch.nn.ReLU(), torch.nn.Linear(10,1),) print('\nnet3:',net3) net3.load_state_dict(torch.load('net_params.pkl')) prediction =net3(x) plt.subplot(133) plt.title('Net3') plt.scatter(x.data.numpy(),y.data.numpy()) plt.plot(x.data.numpy(),prediction.data.numpy(),'r-',lw =5) plt.show()save()restore_net()restore_params() 批数据训练
import torchimport torch.utils.data as DataBATCH_SIZE =5x =torch.linspace(1,10,10)y =torch.linspace(10,1,10)torch_dataset =Data.TensorDataset(x,y)#(data_tensor =x,target_tensor =y)loader =Data.DataLoader( dataset =torch_dataset, batch_size =BATCH_SIZE, shuffle =True, num_workers =2,)def show_batch(): for epoch in range(3): for step,(batch_x,batch_y) in enumerate(loader): print('Epoch:',epoch,'| Step:',step,'| batch x:', batch_x.numpy(),'| batch y:',batch_y.numpy())if __name__ =='__main__': show_batch()D:\ptest>python test.pyEpoch: 0 | Step: 0 | batch x: [ 3. 5. 6. 10. 8.] | batch y: [8. 6. 5. 1. 3.]Epoch: 0 | Step: 1 | batch x: [1. 2. 7. 9. 4.] | batch y: [10. 9. 4. 2. 7.]Epoch: 1 | Step: 0 | batch x: [2. 5. 1. 3. 8.] | batch y: [ 9. 6. 10. 8. 3.]Epoch: 1 | Step: 1 | batch x: [ 6. 7. 4. 10. 9.] | batch y: [5. 4. 7. 1. 2.]Epoch: 2 | Step: 0 | batch x: [10. 5. 9. 7. 4.] | batch y: [1. 6. 2. 4. 7.]Epoch: 2 | Step: 1 | batch x: [1. 6. 2. 3. 8.] | batch y: [10. 5. 9. 8. 3.] import torchimport torch.utils.data as DataBATCH_SIZE =8x =torch.linspace(1,10,10)y =torch.linspace(10,1,10)torch_dataset =Data.TensorDataset(x,y)#(data_tensor =x,target_tensor =y)loader =Data.DataLoader( dataset =torch_dataset, batch_size =BATCH_SIZE, shuffle =True, num_workers =2,)def show_batch(): for epoch in range(3): for step,(batch_x,batch_y) in enumerate(loader): print('Epoch:',epoch,'| Step:',step,'| batch x:', batch_x.numpy(),'| batch y:',batch_y.numpy())if __name__ =='__main__': show_batch()D:\ptest>python test.pyEpoch: 0 | Step: 0 | batch x: [ 2. 7. 8. 4. 1. 3. 10. 5.] | batch y: [ 9. 4. 3. 7. 10. 8. 1. 6.]Epoch: 0 | Step: 1 | batch x: [9. 6.] | batch y: [2. 5.]Epoch: 1 | Step: 0 | batch x: [6. 5. 7. 3. 8. 9. 4. 1.] | batch y: [ 5. 6. 4. 8. 3. 2. 7. 10.]Epoch: 1 | Step: 1 | batch x: [ 2. 10.] | batch y: [9. 1.]Epoch: 2 | Step: 0 | batch x: [ 3. 7. 6. 5. 10. 1. 8. 4.] | batch y: [ 8. 4. 5. 6. 1. 10. 3. 7.]Epoch: 2 | Step: 1 | batch x: [2. 9.] | batch y: [9. 2.] Optimizer优化器
import torchimport torch.utils.data as Dataimport torch.nn.functional as Ffrom torch.autograd import Variableimport matplotlib.pyplot as pltLR =0.01BATCH_SIZE =32EPOCH =12x =torch.unsqueeze(torch.linspace(-1,1,10000),dim =1)y =x.pow(2) +0.1 *torch.normal(torch.zeros(*x.size()))torch_dataset =Data.TensorDataset(x,y)#(data_tensor =x,target_tensor =y)loader =Data.DataLoader(dataset =torch_dataset,batch_size =BATCH_SIZE,shuffle =True,num_workers =2,)class Net(torch.nn.Module): def __init__(self): super(Net,self).__init__() self.hidden =torch.nn.Linear(1,20) self.predict =torch.nn.Linear(20,1) def forward(self,x): x =F.relu(self.hidden(x)) x =self.predict(x) return xif __name__ == '__main__': net_SGD =Net() net_Momentum =Net() net_RMSprop =Net() net_Adam =Net() nets =[net_SGD,net_Momentum,net_RMSprop,net_Adam] opt_SGD =torch.optim.SGD(net_SGD.parameters(),lr =LR) opt_Momentum =torch.optim.SGD(net_Momentum.parameters(),lr =LR,momentum =0.8) opt_RMSprop =torch.optim.RMSprop(net_RMSprop.parameters(),lr =LR,alpha =0.9) opt_Adam =torch.optim.Adam(net_Adam.parameters(),lr =LR,betas =(0.9,0.99)) optimizers =[opt_SGD,opt_Momentum,opt_RMSprop,opt_Adam] loss_func =torch.nn.MSELoss() losses_his =[[],[],[],[]] for epoch in range(EPOCH): print(epoch) for step,(batch_x,batch_y) in enumerate(loader): b_x =Variable(batch_x) b_y =Variable(batch_y) for net,opt,l_his in zip(nets,optimizers,losses_his): output =net(b_x) loss =loss_func(output,b_y) opt.zero_grad() loss.backward() opt.step() l_his.append(loss.data[0]) labels =['SGD','Momentum','RMSprop','Adam'] for i,l_his in enumerate(losses_his): plt.plot(l_his,label =labels[i]) plt.legend(loc ='best') plt.xlabel('Steps') plt.ylabel('Loss') plt.ylim((0,0.2)) plt.show() CNN卷积神经网络
import torchimport torch.utils.data as Datafrom torch.autograd import Variableimport matplotlib.pyplot as pltimport torchvisionimport torch.nn as nnEPOCH =1BATCH_SIZE =50LR =0.001DOWNLOAD_MNIST =Truetrain_data =torchvision.datasets.MNIST( root ='./mnist', train =True, transform =torchvision.transforms.ToTensor(), download =DOWNLOAD_MNIST)print(train_data.train_data.size())print(train_data.train_labels.size())plt.imshow(train_data.train_data[0].numpy(),cmap ='gray')plt.title('%i' % train_data.train_labels[0])plt.show()D:\ptest>python test.pytorch.Size([60000, 28, 28])torch.Size([60000]) import torchimport torch.utils.data as Datafrom torch.autograd import Variableimport matplotlib.pyplot as pltimport torchvisionimport torch.nn as nnEPOCH =1BATCH_SIZE =50LR =0.001DOWNLOAD_MNIST =Truetrain_data =torchvision.datasets.MNIST( root ='./mnist', train =True, transform =torchvision.transforms.ToTensor(), download =DOWNLOAD_MNIST)train_loader =Data.DataLoader(dataset =train_data,batch_size =BATCH_SIZE,shuffle =True,num_workers =2)test_data =torchvision.datasets.MNIST(root ='./mnist/',train =False)test_x =Variable(torch.unsqueeze(test_data.test_data,dim =1),volatile =True).type(torch.FloatTensor)[:2000] /255.test_y =test_data.test_labels[:2000]class CNN(nn.Module): def __init__(self): super(CNN,self).__init__() self.conv1 =nn.Sequential( nn.Conv2d( #（1，28，28） in_channels =1, out_channels =16, kernel_size =5, stride =1, padding =2,),#if stride =1,padding =(kernel_size -1) /2 =(5 -1) /2 # ->(16,28,28) nn.ReLU(), # ->(16,14,14) nn.MaxPool2d(kernel_size =2),) self.conv2 =nn.Sequential( #(16,14,14) nn.Conv2d(16,32,5,1,2), # ->(32,14,14) nn.ReLU(), # ->(32,14,14) nn.MaxPool2d(2)) # ->(32,7,7) self.out =nn.Linear(32 *7 *7,10) def forward(self,x): x =self.conv1(x) x =self.conv2(x) x =x.view(x.size(0),-1) output =self.out(x) return outputcnn =CNN()print(cnn)D:\ptest>python test.pytest.py:22: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead. test_x =Variable(torch.unsqueeze(test_data.test_data,dim =1),volatile =True).type(torch.FloatTensor)[:2000] /255.CNN( (conv1): Sequential( (0): Conv2d(1, 16, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2)) (1): ReLU() (2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) ) (conv2): Sequential( (0): Conv2d(16, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2)) (1): ReLU() (2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) ) (out): Linear(in_features=1568, out_features=10, bias=True))
错误import torchimport torch.utils.data as Datafrom torch.autograd import Variableimport matplotlib.pyplot as pltimport torchvisionimport torch.nn as nnEPOCH =1BATCH_SIZE =50LR =0.001DOWNLOAD_MNIST =Truetrain_data =torchvision.datasets.MNIST( root ='./mnist', train =True, transform =torchvision.transforms.ToTensor(), download =DOWNLOAD_MNIST)train_loader =Data.DataLoader(dataset =train_data,batch_size =BATCH_SIZE,shuffle =True,num_workers =2)test_data =torchvision.datasets.MNIST(root ='./mnist/',train =False)test_x =Variable(torch.unsqueeze(test_data.test_data,dim =1),volatile =True).type(torch.FloatTensor)[:2000] /255.test_y =test_data.test_labels[:2000]class CNN(nn.Module): def __init__(self): super(CNN,self).__init__() self.conv1 =nn.Sequential( nn.Conv2d( #（1，28，28） in_channels =1, out_channels =16, kernel_size =5, stride =1, padding =2,),#if stride =1,padding =(kernel_size -1) /2 =(5 -1) /2 # ->(16,28,28) nn.ReLU(), # ->(16,14,14) nn.MaxPool2d(kernel_size =2),) self.conv2 =nn.Sequential( #(16,14,14) nn.Conv2d(16,32,5,1,2), # ->(32,14,14) nn.ReLU(), # ->(32,14,14) nn.MaxPool2d(2)) # ->(32,7,7) self.out =nn.Linear(32 *7 *7,10) def forward(self,x): x =self.conv1(x) x =self.conv2(x) x =x.view(x.size(0),-1) output =self.out(x) return outputcnn =CNN()print(cnn)for epoch in range(EPOCH): for step,(x,y) in enumerate(train_loader): b_x =Variable(x) b_y =Variable(y) output =cnn(b_x) loss =loss_func(output,b_y) optimizer.zero_grad() loss.backward() optimizer.step() if step % 50 ==0: test_output =cnn(test_x) pred_y =torch.max(test_output,1)[1].data.squeeze() accuracy =sum(pred_y ==test_y) /test_y.size(0) print('Epoch: ',epoch,'| train loss %.4f' % loss.data.numpy(),'| test accuracy: %.2f' % accuracy)test_output =cnn(test_x[:10])pred_y =torch.max(test_output,1)[1].data.numpy().squeeze()print(pred_y,'prediction number')print(test_y[:10].numpy(),'real numpy')