Light

zjost / blog_code Goto Github PK

View Code? Open in Web Editor NEW

142.0 142.0 74.0 7.75 MB

A repo for holding example code

License: Apache License 2.0

Jupyter Notebook 100.00%

blog_code's People

Contributors

Stargazers

Watchers

Forkers

naveedafzal adbmd tonylv bucaixiaosheng christianadriano o7s8r6 ashish96puri tobiasweede gombessa1938 victordaniel charlie-42 qianyaoyy sts-sadr asr-engineering-consulting mausam3407 shankal17 virajlimbasiya hilbert-qyw jimmygjean sprite0153 goolewoo tristanoprofetto abybordi urvashikhanna leonardtd shiernee tiagoventura omidtarkhaneh elnaaz vazagal-s chandrima91 raisony jackdgolding mirjunaid26 ksoumya sundaravelpandian temitope-benson hli8nova harishgovardhandamodar oesmanhk madhug30 emc000 rubenszimbres zsoftwarerepository shounakjoshi07 abdullahmuaad9 gokcenkvz qqfox sorinmol terrisgo foobar41 iankfc maddurup ghudeihed fti130 dylanloader poldanampa tlinjordet gaybro8777 abamidele wontae-lee mbayraktar12 keshavs05 melaku51 muhammadibrahimnejadian vargeus web-logs2 dave2z0 nswarumys melihozlem vishnusaikarthikgindi utksi dmitry-lesnik

blog_code's Issues

Why is there no bias in the output of GCN layer and why there is linear layer before softmax implementation?

Hi,

I was reading the Thomas N. Kipf pytorch implementation of GCN [https://github.com/tkipf/pygcn/blob/master/pygcn/layers.py]. If I understand correctly, he adds bias to every GCN layer output [line 35].
Why is it so? Is it required to be done in Numpy implementation, too?
Also, there is no linear layer before the softmax layer. Why does the numpy implementation have a linear layer before the softmax implementation in the softmax_layer function?

Please help
Thank you

i have an error in 'Jp = xent(predp, labels).mean() + wd_term'. (IndexError Traceback (most recent call last) Cell In[52], line 1 ----> 1 dW_approx = get_grads((gcn1_out,), sm1, "W", labels, eps=1e-4, wd=opt.wd) 2 db_approx = get_grads((gcn1_out,), sm1, "b", labels, eps=1e-4, wd=opt.wd) Cell In[50], line 16 14 wd_term = wd/2*(cp_flat**2).sum() / labels.shape[0] 15 #print(wd_term) ---> 16 Jp = xent(predp, labels).mean() + wd_term 18 # J(theta - eps) 19 cp_flat[i] = theta - eps Cell In[47], line 8 7 def xent(pred, labels): #fonction de perte d'entropie croisée ----> 8 return -np.log(pred)[np.arange(pred.shape[0]), np.argmax(labels, axis=1)] IndexError: shape mismatch: indexing arrays could not be broadcast together with shapes (34,) (5,) )

Difficulty in understanding xent function

Hi,
Thank you so much for the detailed code.
I would highly appreciate your explaining the xent function with np.arange and np.argmax. What is it actually doing?

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.