Comments (2)
I uploaded training dataset(4000 images) and test dataset(1000 images).
Each dataset consists of 3 gz files(image, label-digit, label-color) and has the same format as the ordinary MNIST dataset.
When you use the dataset
- Unzip the datasets.
- Each file is a byte code. So you have to change it to integer. Here is an example of decoding the datasets.
import numpy as np
from struct import *
images = open('test-images-ubyte', 'rb')
digits = open('test-label-digit-ubyte', 'rb')
colors = open('test-label-color-ubyte', 'rb')
for i in range(4000):
image_byte = images.read(28 * 28 * 3)
digit_byte = digits.read(1)
color_byte = colors.read(3)
image = np.reshape(unpack(len(image_byte) * 'B', image_byte), [28, 28, 3])
digit = unpack(len(digit_byte) * 'B', digit_byte)
color = unpack(len(color_byte) * 'B', color_byte)
Then, you can get an image and the corresponding digit and color,
Note that digit is not a one-hot vector, but a scalar value.
If there is any problem with the datasets, feel free to contact me.
Thanks.
from conditional-similarity-network-mnist.
@drillermoon I try it!! thanks :) I appreciate the code you have also released.
from conditional-similarity-network-mnist.
Related Issues (1)
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 conditional-similarity-network-mnist.