测试出我们训练的模型是否准确
这里,我们使用CIFAR10这个数据集来训练与测试
首先,先debug下,查看这个数据集中有哪些target
我们以一个小狗的图片为例,测试我们的模型是否能识别正确
这里用到一个函数Rezie(),因为我们的模型需要32x32的图片,然后我们的图片print一下一看,是size=631x440 的。将我们的图片由PIL类型转化成totensor类型后进行测试
import torch
import torchvision
from PIL import Image
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear
image_path = "img.png"
image = Image.open(image_path)
image = image.convert("RGB")
transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32,32)),
torchvision.transforms.ToTensor()])
image = transform(image)
class Star(nn.Module):
def __init__(self):
super(Star, self).__init__()
self.conv1 = Conv2d(3,32,5,padding=2)
self.maxpool1 = MaxPool2d(kernel_size=2)
self.conv2 = Conv2d(32,32,5,padding=2)
self.maxpool2 = MaxPool2d(2)
self.conv3 = Conv2d(32,64,5,padding=2)
self.maxpool3 = MaxPool2d(kernel_size=2)
self.flatten = Flatten()
self.linear1 = Linear(1024,64)
self.linear2 = Linear(64,10)
def forward(self,x):
x = self.conv1(x)
x = self.maxpool1(x)
x = self.conv2(x)
x = self.maxpool2(x)
x = self.conv3(x)
x = self.maxpool3(x)
x = self.flatten(x)
x = self.linear1(x)
x = self.linear2(x)
return x;
model = torch.load("star_9.pth")
image = torch.reshape(image,(1,3,32,32))
image = image.cuda()
model.eval()
with torch.no_grad():
output = model(image)
print(output)
print(output.argmax(1))
输出:
tensor([[-0.4542, -7.7979, 2.0277, 4.0805, 1.7858, 4.6912, 1.4061, 4.3938,
-6.4003, -4.6274]], device='cuda:0')
tensor([5], device='cuda:0')
结果为5,对应上方target,结果为dog,测试正确
注意:
1.image = image.convert("RGB")
在导入图片后要加上,这是因为适应png,jpg各种格式的图片,png格式的图片为四通道,除了"RGB"三通道外,还有一个透明度通道,利用这个函数,可以都转化成RGB格式
2.为了养成一个良好的习惯,当然,这也是必须的,在测试模型前,要加上
model.eval()
with torch.no_grad():
3.有的时候可别忘了reshape
入门结束,撒花