Comments (3)
Hi,
In this work, the output (activation) of LayerNorm is quantized, while retaining the floating-point computation of LayerNorm itself.
from repq-vit.
Thank you! And I have another question. In FQ-ViT, both the softmax and LayerNorm layers are computed in integer form. So, would it be unfair to compare the accuracy of the method in this paper with FQ-ViT?
from repq-vit.
Our method follows the settings of the previous PTQ4ViT and APQ-ViT, so comparisons with the PTQ4ViT and APQ-ViT are exactly fair.
from repq-vit.
Related Issues (10)
- reproduced performance is poor in swin-base HOT 1
- Hello! Here's another question about the log sqrt2 quantization.
- AttributeError: 'Attention' object has no attribute 'reduction' HOT 1
- How to save and load the quantized model? HOT 1
- Discrepancy between reported and tested mAP for `mask_rcnn_swin_small`
- How to understand the concept of channel before layernorm? HOT 4
- I'm sorry, why did I run the example and still get a quantitative model of float32?
- What does reconstruction mean in quantization. HOT 2
- Unable to run the code
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 repq-vit.