https://github.com/bestsongc/yolov5-distillation-5.0
yolov5 5.0 version distillation || yolov5 5.0版本知识蒸馏,yolov5l >> yolov5s
Science Score: 10.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
○codemeta.json file
-
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (4.6%) to scientific vocabulary
Last synced: 10 months ago
·
JSON representation
Repository
yolov5 5.0 version distillation || yolov5 5.0版本知识蒸馏,yolov5l >> yolov5s
Basic Info
- Host: GitHub
- Owner: Bestsongc
- License: gpl-3.0
- Default Branch: main
- Size: 903 KB
Statistics
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
- Releases: 0
Fork of Sharpiless/yolov5-distillation-5.0
Created almost 3 years ago
· Last pushed almost 5 years ago
https://github.com/Bestsongc/yolov5-distillation-5.0/blob/main/
# [https://github.com/Sharpiless/yolov5-distillation-5.0](https://github.com/Sharpiless/yolov5-distillation-5.0)# [https://pan.baidu.com/s/13gq5QwCrRNdRXWzSYUeJIw ](https://pan.baidu.com/s/13gq5QwCrRNdRXWzSYUeJIw ) 4ppv # ```bash python train.py --weights weights/yolov5s.pt \ --cfg models/yolov5s.yaml --data data/voc.yaml --epochs 50 \ --batch-size 8 --device 0 --hyp data/hyp.scratch.yaml \ --t_weights yolov5l_voc.pt --distill ``` # : > --weights > --t_weights > --distill > --dist_lossl2kl > --temperature [Object detection at 200 Frames Per Second](https://arxiv.org/pdf/1805.06361.pdf) teacher networkobjectness valuebounding boxclass probabilities   # data/voc.yaml VOC data/scripts/get_voc2007.sh yaml # VOC2007VOC2012 GPU2080Ti*1 Batch Size8 Epoches100 BaselineYolov5s Teacher modelYolov5lmAP 0.5:0.95 = 0.541 VOC20122k ||||P|R|mAP50| |:----|:----|:----|:----|:----|:----| ||||0.7756|0.7115|0.7609| |Yolov5l|output based|l2|0.7585|0.7198|0.7644| |Yolov5l|output based|KL|0.7417|0.7207|0.7536| |Yolov5m|output based|l2|0.7682|0.7436|0.7976| |Yolov5m|output based|KL|0.7731|0.7313|0.7931|  KLL2 logitsSigmoid ## 1.  ## 2. L2  #  # > B[https://space.bilibili.com/470550823](https://space.bilibili.com/470550823) > CSDN[https://blog.csdn.net/weixin_44936889](https://blog.csdn.net/weixin_44936889) > AI Studio[https://aistudio.baidu.com/aistudio/personalcenter/thirdview/67156](https://aistudio.baidu.com/aistudio/personalcenter/thirdview/67156) > Github[https://github.com/Sharpiless](https://github.com/Sharpiless)
Owner
- Name: Bestsongc
- Login: Bestsongc
- Kind: user
- Repositories: 1
- Profile: https://github.com/Bestsongc
#
[https://pan.baidu.com/s/13gq5QwCrRNdRXWzSYUeJIw ](https://pan.baidu.com/s/13gq5QwCrRNdRXWzSYUeJIw )
4ppv
#
```bash
python train.py --weights weights/yolov5s.pt \
--cfg models/yolov5s.yaml --data data/voc.yaml --epochs 50 \
--batch-size 8 --device 0 --hyp data/hyp.scratch.yaml \
--t_weights yolov5l_voc.pt --distill
```
# :
> --weights
> --t_weights
> --distill
> --dist_lossl2kl
> --temperature
[Object detection at 200 Frames Per Second](https://arxiv.org/pdf/1805.06361.pdf)
teacher networkobjectness valuebounding boxclass probabilities


#
data/voc.yaml VOC
data/scripts/get_voc2007.sh
yaml
#
VOC2007VOC2012
GPU2080Ti*1
Batch Size8
Epoches100
BaselineYolov5s
Teacher modelYolov5lmAP 0.5:0.95 = 0.541
VOC20122k
||||P|R|mAP50|
|:----|:----|:----|:----|:----|:----|
||||0.7756|0.7115|0.7609|
|Yolov5l|output based|l2|0.7585|0.7198|0.7644|
|Yolov5l|output based|KL|0.7417|0.7207|0.7536|
|Yolov5m|output based|l2|0.7682|0.7436|0.7976|
|Yolov5m|output based|KL|0.7731|0.7313|0.7931|

KLL2 logitsSigmoid
## 1.

## 2. L2

#

#
> B[https://space.bilibili.com/470550823](https://space.bilibili.com/470550823)
> CSDN[https://blog.csdn.net/weixin_44936889](https://blog.csdn.net/weixin_44936889)
> AI Studio[https://aistudio.baidu.com/aistudio/personalcenter/thirdview/67156](https://aistudio.baidu.com/aistudio/personalcenter/thirdview/67156)
> Github[https://github.com/Sharpiless](https://github.com/Sharpiless)