Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
Peanut17
pytorch-yolov4
提交
4ccef0ec
P
pytorch-yolov4
项目概览
Peanut17
/
pytorch-yolov4
与 Fork 源项目一致
从无法访问的项目Fork
通知
6
Star
0
Fork
2
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
pytorch-yolov4
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
前往新版Gitcode,体验更适合开发者的 AI 搜索 >>
未验证
提交
4ccef0ec
编写于
9月 02, 2020
作者:
E
Eric Sheng
提交者:
GitHub
9月 02, 2020
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Remove "evolving"
上级
b444b155
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
4 addition
and
4 deletion
+4
-4
README.md
README.md
+4
-4
未找到文件。
README.md
浏览文件 @
4ccef0ec
...
...
@@ -76,7 +76,7 @@ you can use darknet2pytorch to convert it yourself, or download my converted mod
python train.py -g [GPU_ID] -dir [Dataset direction] ...
```
# 2. Inference
(Evolving)
# 2. Inference
## 2.1 Performance on MS COCO dataset (using pretrained DarknetWeights from <https://github.com/AlexeyAB/darknet>)
...
...
@@ -140,7 +140,7 @@ There are 2 inference outputs.
Until now, still a small piece of post-processing including NMS is required. We are trying to minimize time and complexity of post-processing.
# 3. Darknet2ONNX
(Evolving)
# 3. Darknet2ONNX
-
**This script is to convert the official pretrained darknet model into ONNX**
...
...
@@ -167,7 +167,7 @@ Until now, still a small piece of post-processing including NMS is required. We
-
Dynamic batch size will generate only one ONNX model
-
Static batch size will generate 2 ONNX models, one is for running the demo (batch_size=1)
# 4. Pytorch2ONNX
(Evolving)
# 4. Pytorch2ONNX
-
**You can convert your trained pytorch model into ONNX using this script**
...
...
@@ -201,7 +201,7 @@ Until now, still a small piece of post-processing including NMS is required. We
-
Static batch size will generate 2 ONNX models, one is for running the demo (batch_size=1)
# 5. ONNX2TensorRT
(Evolving)
# 5. ONNX2TensorRT
-
**TensorRT version Recommended: 7.0, 7.1**
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录