imclef_dataset's Introduction
The name of the file is X_Y.csv, which means: X is the labeled source domain, Y is the unlabeled target domain. First, we split X as training and validation set (8:2). Then, we run ImageNet pretrained ResNet-50 on training and validation set to acquire the best model (save it, call it model Z). Finally, we use model Z to extract features on Y (just one feedforward, no bp). Then we can get feature file X_Y.csv. The shape of the data in the file is [n_sample, feature_dim + 1], n_sample is the total number of sample in that domain, feature_dim is feature dimensionality (in ResNet-50, it's 2048). The last column denotes the label. How to use: If we want to perform transfer from X to Y, we can use the features X_X.csv and X_Y.csv as source and target domain, respectively. You are free to finetune other networks (VGG, Inception...) in this way.
imclef_dataset's People
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.