Comments (1)
After adding a pre-processing step, the ACC can reach 0.457 for now. But there is still a gap between 0.627 which is reported in the paper. Could you please leave more details? It would be very helpful!
mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.225]
@torch.no_grad()
def CIFAR10_features():
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize(mean, std)])
cifar10 = torchvision.datasets.CIFAR10(root='/home/mxh/datasets/CIFAR10',train=True,download=False,transform=transform)
trainloader = torch.utils.data.DataLoader(cifar10, batch_size=2048, shuffle=True, num_workers=2)
model = torchvision.models.resnet50(weights='DEFAULT')
model.eval()
model.fc= torch.nn.Identity()
img_list = []
label_list = []
for img,label in trainloader:
img_list.append(model(img))
label_list.append(label)
cifar10 = torchvision.datasets.CIFAR10(root='/home/mxh/datasets/CIFAR10',train=False,download=False,transform=transform)
testloader = torch.utils.data.DataLoader(cifar10, batch_size=2048, shuffle=True, num_workers=2)
for img,label in testloader:
img_list.append(model(img))
label_list.append(label)
img_list = torch.cat(img_list, dim=0).numpy()
label_list = torch.cat(label_list, dim=0).numpy()
data = {'data':img_list, 'label':label_list}
np.save("/home/mxh/codes/EDESC-pytorch-master/data/CIFAR10/cifar.npy", data)
from edesc-pytorch.
Related Issues (3)
- About Data Loading HOT 3
- 关于代码的运行
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from edesc-pytorch.