PyTorch 教程-PyTorch中图像识别模型的测试
P
点击关注 👉约 7 分钟
点击关注 👉约 7 分钟在看到这个图片后，我们将意识到它是数字5。现在，我们将尝试让我们的网络进行预测。
我们有以下步骤来预测数字图像：
步骤1：
import requests
url='https://images.homedepot-static.com/productImages/007164ea-d47e-4f66-8d8c-fd9f621984a2/svn/architectural-mailboxes-house-letters-numbers-3585b-5-64_1000.jpg'
步骤2：
response=requests.get(url,stream=True)
👉点击领取：最全Python资料合集
步骤3：
from PIL import Image
img=Image.open(response.raw)
plt.imshow(img)plt.show()
当运行它时，它会生成一个错误，因为PIL。我们必须首先安装Pillow才能运行此代码。我们必须在Anaconda命令提示符上运行conda install -c anaconda pillow命令来安装pillow。
当您运行代码时，它将给出预期的输出。
步骤4：
我们需要确保图像与神经网络训练要学习的内容相对应。我们的图像大小为1000 * 1000像素，因此我们需要将其变成28 * 28的灰度图像，就像训练数据中的图像一样。在我们的训练图像数据集中，图像具有黑色背景和白色前景，在上面的图像中有白色背景和黑色前景。现在，我们的第一个任务是对此图像进行预处理。
img=PIL.ImageOps.invert(img)
img=img.convert('1')
transform1=transforms.Compose([transforms.Resize((28,28)),transforms.ToTensor(),transforms.Normalize((0.5,),(0.5,))])img=transform1(img)
import PIL.ImageOpsplt.imshow(im_convert(img))
步骤5：
img=img.view(img.shape[0],-1)output=model(img)_,pred=torch.max(output,1)print(pred.item())
步骤6：
dataiter=iter(validation_loader)images,labels=dataiter.next()
images_=images.view(images.shape[0],-1)output=model(images_)_,preds=torch.max(output,1)
步骤7：
fig=plt.figure(figsize=(25,4))
ax=fig.add_subplot(2,10,idx+1)
plt.imshow(im_convert(images[idx]))ax.set_title("{}({})".format(str(preds[idx].item()),str(labels[idx].item())),color=("green" if preds[idx]==labels[idx] else "red"))
完整代码：
import torchimport matplotlib.pyplot as pltimport numpy as npimport torch.nn.functional as funcimport PIL.ImageOpsfrom torch import nnfrom torchvision import datasets,transformsimport requestsfrom PIL import Imagetransform1=transforms.Compose([transforms.Resize((28,28)),transforms.ToTensor(),transforms.Normalize((0.5,),(0.5,))])training_dataset=datasets.MNIST(root='./data',train=True,download=True,transform=transform1)validation_dataset=datasets.MNIST(root='./data',train=False,download=True,transform=transform1)training_loader=torch.utils.data.DataLoader(dataset=training_dataset,batch_size=100,shuffle=True)validation_loader=torch.utils.data.DataLoader(dataset=validation_dataset,batch_size=100,shuffle=False)def im_convert(tensor):image=tensor.clone().detach().numpy()image=image.transpose(1,2,0)print(image.shape)image=image*(np.array((0.5,0.5,0.5))+np.array((0.5,0.5,0.5)))image=image.clip(0,1)return imagedataiter=iter(training_loader)images,labels=dataiter.next()fig=plt.figure(figsize=(25,4))for idx in np.arange(20):ax=fig.add_subplot(2,10,idx+1)plt.imshow(im_convert(images[idx]))ax.set_title([labels[idx].item()])class classification1(nn.Module):def __init__(self,input_layer,hidden_layer1,hidden_layer2,output_layer):super().__init__()self.linear1=nn.Linear(input_layer,hidden_layer1)self.linear2=nn.Linear(hidden_layer1,hidden_layer2)self.linear3=nn.Linear(hidden_layer2,output_layer)def forward(self,x):x=func.relu(self.linear1(x))x=func.relu(self.linear2(x))x=self.linear3(x)return xmodel=classification1(784,125,65,10)criteron=nn.CrossEntropyLoss()optimizer=torch.optim.Adam(model.parameters(),lr=0.0001)epochs=12loss_history=[]correct_history=[]val_loss_history=[]val_correct_history=[]for e in range(epochs):loss=0.0correct=0.0val_loss=0.0val_correct=0.0for input,labels in training_loader:inputs=input.view(input.shape[0],-1)outputs=model(inputs)loss1=criteron(outputs,labels)optimizer.zero_grad()loss1.backward()optimizer.step()_,preds=torch.max(outputs,1)loss+=loss1.item()correct+=torch.sum(preds==labels.data)else:with torch.no_grad():for val_input,val_labels in validation_loader:val_inputs=val_input.view(val_input.shape[0],-1)val_outputs=model(val_inputs)val_loss1=criteron(val_outputs,val_labels)_,val_preds=torch.max(val_outputs,1)val_loss+=val_loss1.item()val_correct+=torch.sum(val_preds==val_labels.data)epoch_loss=loss/len(training_loader.dataset)epoch_acc=correct.float()/len(training_dataset)loss_history.append(epoch_loss)correct_history.append(epoch_acc)val_epoch_loss=val_loss/len(validation_loader.dataset)val_epoch_acc=val_correct.float()/len(validation_dataset)val_loss_history.append(val_epoch_loss)val_correct_history.append(val_epoch_acc)print('training_loss:{:.4f},{:.4f}'.format(epoch_loss,epoch_acc.item()))print('validation_loss:{:.4f},{:.4f}'.format(val_epoch_loss,val_epoch_acc.item()))url='https://images.homedepot-static.com/productImages/007164ea-d47e-4f66-8d8c-fd9f621984a2/svn/architectural-mailboxes-house-letters-numbers-3585b-5-64_1000.jpg'response=requests.get(url,stream=True)img=Image.open(response.raw)img=PIL.ImageOps.invert(img)img=img.convert('1')img=transform1(img)plt.imshow(im_convert(img))img=img.view(img.shape[0],-1)output=model(img)_,pred=torch.max(output,1)print(pred.item())dataiter=iter(validation_loader)images,labels=dataiter.next()images_=images.view(images.shape[0],-1)output=model(images_)_,preds=torch.max(output,1)fig=plt.figure(figsize=(25,4))for idx in np.arange(20):ax=fig.add_subplot(2,10,idx+1,xticks=[],yticks=[])plt.imshow(im_convert(images[idx]))ax.set_title("{}({})".format(str(preds[idx].item()),str(labels[idx].item())),color=("green" if preds[idx]==labels[idx] else "red"))plt.show()
热门推荐