Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
Bw-bestperf
ResNet-CBAM
Commits
06aa0793
Commit
06aa0793
authored
Feb 04, 2026
by
maming
Browse files
Delete README.md
parent
a41fb568
Pipeline
#3363
canceled with stages
Changes
1
Pipelines
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
0 additions
and
119 deletions
+0
-119
README.md
README.md
+0
-119
No files found.
README.md
deleted
100755 → 0
View file @
a41fb568
# https://github.com/zhangzhengde0225/binary_distinguish_GRB_by_DL
## 论文
Application of Deep Learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM TTE Data
-
https://arxiv.org/abs/2303.00370
## 模型结构
卷积神经网络(CNN)架构的示意图如下。每个卷积块顶部和底部的数字分别表示卷积步幅(默认值为1)和卷积核的数量。图底部的数字描述了特征图的长度和宽度的变化。
<div
align=
left
>
<img
src=
"./assets/architectures.png"
/>
</div>
## 环境配置
### Docker(方法一)
docker pull image.sourcefind.cn:5000/dcu/admin/base/tensorflow:2.13.1-ubuntu20.04-dtk24.04.1-py3.10
docker run --shm-size 50g --network=host --name=binary_distinguish_GRB_by_DL --privileged --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v 项目地址(绝对路径):/home/ -v /opt/hyhal:/opt/hyhal:ro -it <your IMAGE ID> bash
pip install matplotlib -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
### Dockerfile(方法二)
docker build -t <IMAGE_NAME>:<TAG> .
docker run --shm-size 50g --network=host --name=binary_distinguish_GRB_by_DL --privileged --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v 项目地址(绝对路径):/home/ -v /opt/hyhal:/opt/hyhal:ro -it <your IMAGE ID> bash
pip install matplotlib -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
## 数据集
```
Binary_Distinguish_GRB_Datasetv1/data/
└── dataset_256ms/
├── test_count_map_256ms.npy
├── test_info.npy
├── train_count_map_256ms.npy
├── train_info.npy
├── validate_count_map_256ms.npy
└── validate_info.npy
└── ......
```
## 训练
```
bash
#jupter文件参考train_model.ipynb
cd
/path/your_code_data/code
python train.py
```
注意:请根据您的需求修改choonse_time_bin、 choose_model="plain-CNN-、data_set_dir等参数
## 推理
```
bash
#jupter文件参考test_model.ipynb
cd
/path/your_code_data/code
python test.py
```
## result
### 精度
模型信息:
-
Epoch :20
-
choose_model :ResNet-CBAM
-
choonse_time_bin :256 ms
硬件:
-
DCU :K100 AI
-
GPU :A800
| | accu | precision | recall | f1_score |
|:-------:|:------------:|:----------:|:--------:|:----------:|
| k100 ai | 93.718257%| 97.597977% |88.684664% | 92.9281% |
| A800 | 93.611334%| 98.514212% |87.593337% | 92.7334% |
### 性能
模型信息:
-
Epoch :20
-
choose_model :ResNet-CBAM
-
choonse_time_bin :256 ms
硬件:
-
DCU :K100 AI
-
GPU :A800
| | train | test |
|:-------:|:----------:|:---------:|
| k100 ai | 140ms/step | 39ms/step |
| A800 | 66ms/step | 20ms/step |
## 应用场景
### 算法类别
`AI for science`
### 热点应用行业
`科研,教育`
## 源码仓库及问题反馈
无
## 参考资料
*
https://github.com/zhangzhengde0225/binary_distinguish_GRB_by_DL
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment