Comments (2)
@abhigoku10
hello,
- I used some method like: prune weights < threshold; give every 3*3 weights a mask, and skip the compute when mask ==0; use L1 regula to delete some feature maps in cfg file; use openmp to realize threads compute in cpu
- because the pruned weights is also float 32, so weights file is same big as before, but you can use hoffman convert to compress weights file
- natuerlich, in convolutional.c files, the author has some functions to plot the weights map, you can find them :)
from yolov3_lite.
@ArtyZe thanks for response ,
- thanks , openmp shall be used onlyin the case of cpu
- since the weight size before and after pruning are the same but the performance(fps) is improved right??have you used huffman to compress the weights
3.thanks for the pointers
4.after performing pruning did you re-train the model i.e iterative pruning and training , if so what is the loss value and iteration u have reached
Thanks in advance
from yolov3_lite.
Related Issues (10)
- prune weights for support yolo-v3 HOT 5
- can the model file after training (just use google quantization) be correctly parsed by original darknet
- L1 scales regularization HOT 2
- Weights File for yolov2 HOT 10
- Predictions are not drawing after testing trained model HOT 8
- Is this implementation for YOLOV2 or YOLOV3? HOT 7
- `Hash Compress` `Google Quantization` `Huffman Compress`
- AVX Problem HOT 6
- how to get output_scale and output_zero_point in the cfg file.
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 yolov3_lite.