Comments (2)
Hi,
we did not release the architecture code for resnet-cifar. You can check tensorflow models or tensorpack resnet for references. You could simply modify the network architecture by replace the conv2d op with our conv2dquant op.
from lq-nets.
ok, thanks very much
from lq-nets.
Related Issues (20)
- how this code works on a single GPU. HOT 1
- NotImplementedError HOT 4
- what is the size needed for LQ-Nets vgg model to run HOT 2
- why naive way wouldn`t get bitwise
- about tf version HOT 5
- loss=0 HOT 4
- could you release the code using BP instead of QEM HOT 1
- Lq nets traning hardware setup.
- Does it has pytorch version? HOT 2
- Is it possible the BTxB is not invertible? HOT 5
- Version of tensorpack and tensorflow HOT 3
- How to quantize weights only on Imagenet? HOT 2
- Extream Case (a=1bit/w=1bit) HOT 1
- How to train the full-precision model? HOT 1
- Lower quantized values set to 0 instead of levels[0] HOT 3
- Basis vectors tend to depend on initialized value
- update deprecated APIs HOT 1
- Frequent `Segmentation Fault (Core dumped)` HOT 6
- Question about implementation (not bug) HOT 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 lq-nets.