Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

"descriptive statistics" der Zalando Bilddaten #1

Open
lborke opened this issue Dec 13, 2017 · 4 comments
Open

"descriptive statistics" der Zalando Bilddaten #1

lborke opened this issue Dec 13, 2017 · 4 comments

Comments

@lborke
Copy link
Member

lborke commented Dec 13, 2017

Auch zum Datensatz: was ist genau drin, etwas "descriptive statistics" und Hintergrundinfo zu den Daten, wie viele, welche Labels, etc.?

@lborke
Copy link
Member Author

lborke commented Dec 13, 2017

Du kannst dazu gerne eine neue Python-Datei mit notwendigen Funktionen etc. anlegen.
Ich bin sicher, dass
Numpy
Pandas
Sklearn
etc. sinnvoll sein werden.

@anastasia-stepanchenko
Copy link
Member

https://github.com/lborke/AI_DL_AWS/blob/master/MXNet/Fashion_MNIST_Data_Description.ipynb

Вот то, что пока в голову пришло.. Буду добавлять по мере поступления мыслей.

@lborke
Copy link
Member Author

lborke commented Dec 14, 2017

Hier ist meine Version, die deine korrigiert, verbessert, und "richtig" formatiert:
https://github.com/lborke/AI_DL_AWS/blob/master/MXNet/Fashion_MNIST_Data_Description_LB.py

@anastasia-stepanchenko
Copy link
Member

https://github.com/lborke/AI_DL_AWS/blob/master/MXNet/Fashion_MNIST_Data_Description.ipynb
внесла твои изменения

Wie kann man das noch kompakter und eleganter machen. De facto wird hier ein Loop gemacht.
[fashion_labels[i] for i in train_lbl[0:pict_number].tolist()]
заменила на
operator.itemgetter(*train_lbl[0:pict_number])(fashion_labels)
везде пишут, что она быстрее

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants