<?xml version="1.0"?>
<net name="torch_jit" version="11">
<layers>
<layer id="0" name="images" type="Parameter" version="opset1">
<data shape="1,3,640,640" element_type="f32" />
<output>
<port id="0" precision="FP32" names="images">
<dim>1</dim>
<dim>3</dim>
<dim>640</dim>
<dim>640</dim>
</port>
</output>
</layer>
<layer id="1" name="/model.22/Constant_9" type="Const" version="opset1">
<data element_type="f32" shape="1, 2, 8400" offset="0" size="67200" />
<output>
<port id="0" precision="FP32" names="/model.22/Constant_9_output_0">
<dim>1</dim>
<dim>2</dim>
<dim>8400</dim>
</port>
</output>
</layer>
<layer id="2" name="model.0.conv.weight" type="Const" version="opset1">
<data element_type="f32" shape="32, 3, 3, 3" offset="67200" size="3456" />
<output>
<port id="0" precision="FP32" names="model.0.conv.weight">
<dim>32</dim>
<dim>3</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="3" name="/model.0/conv/Conv/WithoutBiases" type="Convolution" version="opset1">
<data strides="2, 2" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>3</dim>
<dim>640</dim>
<dim>640</dim>
</port>
<port id="1" precision="FP32">
<dim>32</dim>
<dim>3</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>320</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="4" name="Reshape_14930" type="Const" version="opset1">
<data element_type="f32" shape="1, 32, 1, 1" offset="70656" size="128" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="5" name="/model.0/conv/Conv" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>320</dim>
<dim>320</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="/model.0/conv/Conv_output_0">
<dim>1</dim>
<dim>32</dim>
<dim>320</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="6" name="/model.0/act/Mul" type="Swish" version="opset4">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>320</dim>
<dim>320</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="/model.0/act/Mul_output_0">
<dim>1</dim>
<dim>32</dim>
<dim>320</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="7" name="model.1.conv.weight" type="Const" version="opset1">
<data element_type="f32" shape="64, 32, 3, 3" offset="70784" size="73728" />
<output>
<port id="0" precision="FP32" names="model.1.conv.weight">
<dim>64</dim>
<dim>32</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="8" name="/model.1/conv/Conv/WithoutBiases" type="Convolution" version="opset1">
<data strides="2, 2" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>320</dim>
<dim>320</dim>
</port>
<port id="1" precision="FP32">
<dim>64</dim>
<dim>32</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>160</dim>
<dim>160</dim>
</port>
</output>
</layer>
<layer id="9" name="Reshape_14947" type="Const" version="opset1">
<data element_type="f32" shape="1, 64, 1, 1" offset="144512" size="256" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="10" name="/model.1/conv/Conv" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>160</dim>
<dim>160</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="/model.1/conv/Conv_output_0">
<dim>1</dim>
<dim>64</dim>
<dim>160</dim>
<dim>160</dim>
</port>
</output>
</layer>
<layer id="11" name="/model.1/act/Mul" type="Swish" version="opset4">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>160</dim>
<dim>160</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="/model.1/act/Mul_output_0">
<dim>1</dim>
<dim>64</dim>
<dim>160</dim>
<dim>160</dim>
</port>
</output>
</layer>
<layer id="12" name="model.2.cv1.conv.weight" type="Const" version="opset1">
<data element_type="f32" shape="64, 64, 1, 1" offset="144768" size="16384" />
<output>
<port id="0" precision="FP32" names="model.2.cv1.conv.weight">
<dim>64</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="13" name="/model.2/cv1/conv/Conv/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>160</dim>
<dim>160</dim>
</port>
<port id="1" precision="FP32">
<dim>64</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>160</dim>
<dim>160</dim>
</port>
</output>
</layer>
<layer id="14" name="Reshape_14964" type="Const" version="opset1">
<data element_type="f32" shape="1, 64, 1, 1" offset="161152" size="256" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="15" name="/model.2/cv1/conv/Conv" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>160</dim>
<dim>160</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="/model.2/cv1/conv/Conv_output_0">
<dim>1</dim>
<dim>64</dim>
<dim>160</dim>
<dim>160</dim>
</port>
</output>
</layer>
<layer id="16" name="/model.2/cv1/act/Mul" type="Swish" version="opset4">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>160</dim>
<dim>160</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="/model.2/cv1/act/Mul_output_0">
<dim>1</dim>
<dim>64</dim>
<dim>160</dim>
<dim>160</dim>
</port>
</output>
</layer>
<layer id="17" name="Constant_14970" type="Const" version="opset1">
<data element_type="i64" shape="" offset="161408" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="18" name="Constant_14971" type="Const" vers
yolov8s-detect-openvino-model.rar
需积分: 5 24 浏览量
2023-10-25
08:28:46
上传
评论
收藏 35.23MB RAR 举报
乱蜂朝王
- 粉丝: 2606
- 资源: 362
最新资源
- RAG技术知识图谱概览
- VMware Workstation功能强大的桌面虚拟计算机软件
- 中文命名实体识别,采用bilstm+crf模型基于Pytorch实现
- PowerGREP V5.3.3 Retail
- 美赛数学建模算法-使用Matlab实现灰色系统建模GreySystem-国赛-题解.zip
- 基于albert-bilstm-crf架构利用keras框架实现NER
- RegexMagic V2.13.1 Retail
- python-3.6.5-macosx 安装包
- 美赛数学建模算法-使用Matlab实现图论GraphTheory-包括求最短路径-国赛-题解.zip
- RegexBuddy v4.14.1 Retail
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈