Comments (2)
Hi,
thank you for your comment, we will continue this work to further improve the performance, and also consider to compare with the fast convolution algorithm (maybe we could also take advantages
with it). In this implementation we actually paid more attention on how to reduce the model size and enable the application of complicated deep models on mobile devices; and how to make the binary components be used as easy as possible. Of course further speedup is also our next goal.
from bmxnet.
thank you for your reply.cheers~
from bmxnet.
Related Issues (20)
- Error while doing inference on binarized model. HOT 12
- What is the location of the implement of QActivation, QConvolution, and QFullyConneted? HOT 2
- encounter errors durring complie HOT 2
- cudnn_off=False has some problems with mx.mon.Monitor HOT 4
- Where do you implement XNOR networks? HOT 1
- Build failing
- How to integrate a trained binary model in iOS? HOT 3
- No difference in binarized and full-precision LeNet model size HOT 2
- Can an existing MXNet 1.0.0 installation be used to set up BMXNet ? HOT 10
- Order of QActivation, QConvolution layers HOT 1
- Quantization method HOT 3
- depth-wise convolution support HOT 2
- less forward speed-up when batch size is larger HOT 1
- mxnet error: redeclaration of 'kNone' when setting USE_CPP_PACKAGE = 1 HOT 1
- Any pre-built dynamic library or executable file for andriod? HOT 2
- No speedup or even slower on CPU with 1-bit QConvolution and QActivation HOT 4
- ImportError: cannot import name 'transforms' HOT 2
- How do I get the model-convertor executable file ?
- XNOR-Net implementation HOT 1
- Regarding pretrained binary models
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 bmxnet.