Python YOLOv3 查看神经网络结构

最新推荐文章于 2024-04-22 19:45:20 发布
最新推荐文章于 2024-04-22 19:45:20 发布
阅读量1.5k 收藏 1
点赞数 1
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/wukai0909/article/details/99225953
版权

下载地址 https://github.com/wizyoung/YOLOv3_TensorFlow

Python  YOLOv3 查看神经网络架构

import tensorflow as tf
import numpy as np
reader = tf.train.NewCheckpointReader('./yolov3.ckpt')
 #tf.train.NewCheckpointReader
var_to_shape_map = reader.get_variable_to_shape_map()
for key in var_to_shape_map:
  print("tensor_name: ", key,len(reader.get_tensor(key)),reader.get_tensor(key).shape)
  #print(reader.get_tensor(key))

下载别人的预训练的神经网络，训练完自己的神经网络，需要加载自己的网络模型和对应自己的data.names或coco.names不修改自己的代码会导致：Assign requires shapes of both tensors to match. lhs shape= [255] rhs shape= [45]

下载别人的预训练的神经网络的网络结构：80个classes

wu@wu-X555LF:~/YOLOv3_TensorFlow-master/data/darknet_weights$ python test.py 
('yolov3/darknet53_body/Conv_10/BatchNorm/beta', 128, (128,))
('yolov3/darknet53_body/Conv_30/BatchNorm/moving_mean', 512, (512,))
('yolov3/yolov3_head/Conv_17/BatchNorm/moving_variance', 256, (256,))
('yolov3/yolov3_head/Conv_21/BatchNorm/beta', 256, (256,))
('yolov3/darknet53_body/Conv_31/BatchNorm/gamma', 256, (256,))
('yolov3/darknet53_body/Conv_39/BatchNorm/beta', 256, (256,))
('yolov3/darknet53_body/Conv_5/BatchNorm/moving_mean', 64, (64,))
('yolov3/darknet53_body/Conv_49/BatchNorm/gamma', 1024, (1024,))
('yolov3/darknet53_body/Conv_33/BatchNorm/gamma', 256, (256,))
('yolov3/yolov3_head/Conv/BatchNorm/moving_variance', 512, (512,))
('yolov3/yolov3_head/Conv_18/BatchNorm/moving_mean', 128, (128,))
('yolov3/darknet53_body/Conv_3/BatchNorm/gamma', 64, (64,))
('yolov3/darknet53_body/Conv_27/weights', 1, (1, 1, 512, 256))
('yolov3/darknet53_body/Conv_20/BatchNorm/gamma', 128, (128,))
('yolov3/darknet53_body/Conv_47/BatchNorm/moving_variance', 1024, (1024,))
('yolov3/yolov3_head/Conv_4/weights', 1, (1, 1, 1024, 512))
('yolov3/yolov3_head/Conv_19/BatchNorm/gamma', 256, (256,))
('yolov3/darknet53_body/Conv_12/BatchNorm/moving_mean', 128, (128,))
('yolov3/darknet53_body/Conv_42/BatchNorm/gamma', 512, (512,))
('yolov3/yolov3_head/Conv_11/BatchNorm/gamma', 512, (512,))
('yolov3/yolov3_head/Conv_11/BatchNorm/beta', 512, (512,))
('yolov3/darknet53_body/Conv_12/weights', 1, (1, 1, 256, 128))
('yolov3/yolov3_head/Conv_10/BatchNorm/gamma', 256, (256,))
('yolov3/darknet53_body/Conv_15/BatchNorm/moving_variance', 256, (256,))
('yolov3/yolov3_head/Conv_5/BatchNorm/moving_variance', 1024, (1024,))
('yolov3/darknet53_body/Conv_10/weights', 1, (1, 1, 256, 128))
('yolov3/darknet53_body/Conv_25/weights', 3, (3, 3, 128, 256))
('yolov3/yolov3_head/Conv_13/BatchNorm/moving_variance', 512, (512,))
('yolov3/darknet53_body/Conv_32/BatchNorm/moving_variance', 512, (512,))
('yolov3/darknet53_body/Conv_13/BatchNorm/moving_variance', 256, (256,))
('yolov3/darknet53_body/Conv_19/BatchNorm/beta', 256, (256,))
('yolov3/darknet53_body/Conv_13/BatchNorm/beta', 256, (256,))
('yolov3/darknet53_body/Conv_13/BatchNorm/gamma', 256, (256,))
('yolov3/darknet53_body/Conv_2/BatchNorm/beta', 32, (32,))
('yolov3/darknet53_body/Conv_37/weights', 1, (1, 1, 512, 256))
('yolov3/darknet53_body/Conv_7/BatchNorm/gamma', 64, (64,))
('yolov3/yolov3_head/Conv_4/BatchNorm/moving_mean', 512, (512,))
('yolov3/darknet53_body/Conv_31/weights', 1, (1, 1, 512, 256))
('yolov3/yolov3_head/Conv_5/BatchNorm/gamma', 1024, (1024,))
('yolov3/darknet53_body/Conv_21/BatchNorm/moving_variance', 256, (256,))
('yolov3/yolov3_head/Conv_9/BatchNorm/moving_mean', 512, (512,))
('yolov3/yolov3_head/Conv_18/weights', 1, (1, 1, 256, 128))
('yolov3/darknet53_body/Conv_18/BatchNorm/moving_mean', 128, (128,))
('yolov3/darknet53_body/Conv_21/BatchNorm/gamma', 256, (256,))
('yolov3/darknet53_body/Conv_2/BatchNorm/gamma', 32, (32,))
('yolov3/yolov3_head/Conv_3/BatchNorm/beta', 1024, (1024,))
('yolov3/darknet53_body/Conv_42/weights', 3, (3, 3, 256, 512))
('yolov3/yolov3_head/Conv_15/BatchNorm/moving_mean', 128, (128,))
('yolov3/darknet53_body/Conv_44/BatchNorm/gamma', 512, (512,))
('yolov3/darknet53_body/Conv_25/BatchNorm/moving_mean', 256, (256,))
('yolov3/darknet53_body/Conv_18/BatchNorm/beta', 128, (128,))
('yolov3/darknet53_body/Conv_30/weights', 3, (3, 3, 256, 512))
('yolov3/yolov3_head/Conv_21/BatchNorm/gamma', 256, (256,))
('yolov3/darknet53_body/Conv_41/BatchNorm/gamma', 256, (256,))
('yolov3/darknet53_body/Conv_5/weights', 1, (1, 1, 128, 64))
('yolov3/darknet53_body/Conv_6/BatchNorm/moving_mean', 128, (128,))
('yolov3/darknet53_body/Conv_45/BatchNorm/beta', 1024, (1024,))
('yolov3/yolov3_head/Conv_6/weights', 1, (1, 1, 1024, 255))
('yolov3/darknet53_body/Conv_34/BatchNorm/moving_mean', 512, (512,))
('yolov3/darknet53_body/Conv_51/BatchNorm/gamma', 1024, (1024,))
('yolov3/yolov3_head/Conv_10/BatchNorm/moving_mean', 256, (256,))
('yolov3/yolov3_head/Conv_1/BatchNorm/beta', 1024, (1024,))
('yolov3/darknet53_body/Conv_34/BatchNorm/beta', 512, (512,))
('yolov3/yolov3_head/Conv_5/weights', 3, (3, 3, 512, 1024))
('yolov3/darknet53_body/Conv_51/weights', 3, (3, 3, 512, 1024))
('yolov3/darknet53_body/Conv_50/BatchNorm/gamma', 512, (512,))
('yolov3/darknet53_body/Conv_36/BatchNorm/gamma', 512, (512,))
('yolov3/darknet53_body/Conv_29/BatchNorm/moving_variance', 256, (256,))
('yolov3/darknet53_body/Conv_15/BatchNorm/gamma', 256, (256,))
('yolov3/darknet53_body/Conv_50/BatchNorm/beta', 512, (512,))
('yolov3/yolov3_head/Conv_7/BatchNorm/gamma', 256, (256,))
('yolov3/darknet53_body/Conv_47/weights', 3, (3, 3, 512, 1024))
('yolov3/yolov3_head/Conv_2/BatchNorm/gamma', 512, (512,))
('yolov3/darknet53_body/Conv_43/BatchNorm/moving_variance', 1024, (1024,))
('yolov3/darknet53_body/Conv_45/BatchNorm/gamma', 1024, (1024,))
('yolov3/yolov3_head/Conv_20/BatchNorm/gamma', 128, (128,))
('yolov3/darknet53_body/Conv_37/BatchNorm/gamma', 256, (256,))
('yolov3/yolov3_head/Conv_12/weights', 1, (1, 1, 512, 256))
('yolov3/darknet53_body/Conv_45/BatchNorm/moving_variance', 1024, (1024,))
('yolov3/yolov3_head/Conv_5/BatchNorm/moving_mean', 1024, (1024,))
('yolov3/darknet53_body/Conv_6/BatchNorm/beta', 128, (128,))
('yolov3/darknet53_body/Conv_19/BatchNorm/moving_mean', 256, (256,))
('yolov3/yolov3_head/Conv_8/BatchNorm/beta', 256, (256,))
('yolov3/darknet53_body/Conv_11/BatchNorm/moving_variance', 256, (256,))
('yolov3/darknet53_body/Conv_41/BatchNorm/moving_mean', 256, (256,))
('yolov3/darknet53_body/Conv_50/weights', 1, (1, 1, 1024, 512))
('yolov3/darknet53_body/Conv_8/BatchNorm/gamma', 128, (128,))
('yolov3/yolov3_head/Conv/weights', 1, (1, 1, 1024, 512))
('yolov3/darknet53_body/Conv_17/BatchNorm/moving_mean', 256, (256,))
('yolov3/darknet53_body/Conv_11/BatchNorm/beta', 256, (256,))
('yolov3/yolov3_head/Conv_9/BatchNorm/gamma', 512, (512,))
('yolov3/darknet53_body/Conv_42/BatchNorm/moving_variance', 512, (512,))
('yolov3/darknet53_body/Conv_17/BatchNorm/moving_variance', 256, (256,))
('yolov3/darknet53_body/Conv_51/BatchNorm/beta', 1024, (1024,))
('yolov3/darknet53_body/Conv_4/BatchNorm/gamma', 128, (128,))
('yolov3/darknet53_body/Conv_25/BatchNorm/moving_variance', 256, (256,))
('yolov3/darknet53_body/Conv_32/BatchNorm/moving_mean', 512, (512,))
('yolov3/darknet53_body/Conv_19/BatchNorm/moving_variance', 256, (256,))
('yolov3/darknet53_body/Conv_40/BatchNorm/gamma', 512, (512,))
('yolov3/darknet53_body/Conv_41/BatchNorm/beta', 256, (256,))
('yolov3/darknet53_body/Conv_23/BatchNorm/moving_variance', 256, (256,))
('yolov3/yolov3_head/Conv_2/BatchNorm/moving_variance', 512, (512,))
('yolov3/darknet53_body/Conv_9/BatchNorm/beta', 256, (256,))
('yolov3/darknet53_body/Conv_27/BatchNorm/moving_mean', 256, (256,))
('yolov3/darknet53_body/Conv_28/BatchNorm/beta', 512, (512,))
('yolov3/darknet53_body/Conv_45/weights', 3, (3, 3, 512, 1024))
('yolov3/darknet53_body/Conv_46/BatchNorm/beta', 512, (512,))
('yolov3/darknet53_body/Conv_35/BatchNorm/moving_variance', 256, (256,))
('yolov3/darknet53_body/Conv_3/BatchNorm/moving_variance', 64, (64,))
('yolov3/darknet53_body/Conv_46/BatchNorm/moving_variance', 512, (512,))
('yolov3/darknet53_body/Conv_1/BatchNorm/moving_variance', 64, (64,))
('yolov3/darknet53_body/Conv_30/BatchNorm/beta', 512, (512,))
('yolov3/yolov3_head/Conv_18/BatchNorm/gamma', 128, (128,))
('yolov3/yolov3_head/Conv_9/BatchNorm/beta', 512, (512,))
('yolov3/yolov3_head/Conv_10/weights', 1, (1, 1, 512, 256))
('yolov3/yolov3_head/Conv_22/weights', 1, (1, 1, 256, 255))
('yolov3/darknet53_body/Conv_11/weights', 3, (3, 3, 128, 256))
('yolov3/darknet53_body/Conv_24/BatchNorm/moving_variance', 128, (128,))
('yolov3/yolov3_head/Conv_7/weights', 1, (1, 1, 512, 256))
('yolov3/darknet53_body/Conv/weights', 3, (3, 3, 3, 32))
('yolov3/darknet53_body/Conv_19/BatchNorm/gamma', 256, (256,))
('yolov3/yolov3_head/Conv_8/BatchNorm/moving_variance', 256, (256,))
('yolov3/darknet53_body/Conv_16/BatchNorm/gamma', 128, (128,))
('yolov3/darknet53_body/Conv_13/BatchNorm/moving_mean', 256, (256,))
('yolov3/darknet53_body/Conv_23/BatchNorm/beta', 256, (256,))
('yolov3/darknet53_body/Conv_28/weights', 3, (3, 3, 256, 512))
('yolov3/darknet53_body/Conv_25/BatchNorm/gamma', 256, (256,))
('yolov3/yolov3_head/Conv_10/BatchNorm/moving_variance', 256, (256,))
('yolov3/yolov3_head/Conv_3/BatchNorm/moving_variance', 1024, (1024,))
('yolov3/darknet53_body/Conv_33/weights', 1, (1, 1, 512, 256))
('yolov3/darknet53_body/Conv_16/weights', 1, (1, 1, 256, 128))
('yolov3/yolov3_head/Conv_22/biases', 255, (255,))
('yolov3/yolov3_head/Conv_16/BatchNorm/moving_variance', 128, (128,))
('yolov3/darknet53_body/Conv_46/BatchNorm/moving_mean', 512, (512,))
('yolov3/darknet53_body/Conv_30/BatchNorm/gamma', 512, (512,))
('yolov3/darknet53_body/Conv_20/BatchNorm/moving_variance', 128, (128,))
('yolov3/darknet53_body/Conv/BatchNorm/moving_mean', 32, (32,))
('yolov3/yolov3_head/Conv_1/BatchNorm/gamma', 1024, (1024,))
('yolov3/darknet53_body/Conv_48/weights', 1, (1, 1, 1024, 512))
('yolov3/yolov3_head/Conv_10/BatchNorm/beta', 256, (256,))
('yolov3/darknet53_body/Conv_44/weights', 1, (1, 1, 1024, 512))
('yolov3/darknet53_body/Conv_8/BatchNorm/moving_variance', 128, (128,))
('yolov3/darknet53_body/Conv_29/weights', 1, (1, 1, 512, 256))
('yolov3/darknet53_body/Conv_40/BatchNorm/moving_variance', 512, (512,))
('yolov3/darknet53_body/Conv_39/BatchNorm/gamma', 256, (256,))
('yolov3/darknet53_body/Conv_14/weights', 1, (1, 1, 256, 128))
('yolov3/darknet53_body/Conv_18/BatchNorm/gamma', 128, (128,))
('yolov3/darknet53_body/Conv_38/weights', 3, (3, 3, 256, 512))
('yolov3/darknet53_body/Conv_28/BatchNorm/moving_variance', 512, (512,))
('yolov3/yolov3_head/Conv_3/weights', 3, (3, 3, 512, 1024))
('yolov3/da
最低0.47元/天 解锁文章
Renaissance5K
关注
  • 1
    点赞
  • 踩
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
基于python的神经网络层级结构
07-13
基于python的神经网络层级结构基于python的神经网络层级结构
Python深度学习13——Keras模型的可视化(神经网络结构图)
weixin_46277779的博客
09-30 6136
keras画神经网络模型的结构图，plot_model()用法，和常见报错解决方法。
[神经网络与深度学习]算法估计，YOLO，语义分割，风格迁移
最新发布
weixin_56809732的博客
04-22 407
转置卷积：假设有一个2*2的输入张量和一个2*2的核张量，计算转置卷积就是将输入张量的每个张量乘以核张量，再将得到的结果相加。被正确地划分为正例的个数，FP为被错误地划分为正例的个数，FN为被错误地划分为负例的个数，TN为被正确地划分为负例的个数。（2）选择一个预训练的卷积神经网络来抽取图像的特征，其中的模型参数在训练中无须更新。类别均可确定对应的AP，在多类的检测中，取每个类AP的平均值，即为mAP。（4）模型训练结束时，输出风格迁移的模型参数，得到最终的合成图像。P（精确率）=TP/(TP+FP)
基于python的完整神经网络结构代码
09-24
基于python的完整神经网络结构代码，可用于猫狗大战等，具有较好的泛化性能，包含9个部分的代码，老手新手皆可上手
神经网络—yolov3的cfg和权重文件
10-04
yolov3的cfg配置文件以及weights文件，测试帧数达到40+，精度高
神经网络—yolov3Tiny的cfg和权重文件
10-04
yolov3Tiny的cfg配置文件以及weights文件，测试帧数达到40+，精度高
基于python与yolov3的物体检测算法实现
04-29
首先，YOLOv3的架构基于深度学习模型，尤其是Darknet框架，这是一个轻量级的神经网络框架，适用于实时应用。YOLOv3改进了YOLOv2的设计，引入了更细粒度的特征金字塔网络，可以检测不同尺度的物体，提高了小物体的...
YOLOv5网络结构包含SPPF结构.rar
04-15
1、资源内容：yolov5网络结构包含SPPF结构（完整版）.rar 2、代码特点：参数化编程、参数可方便更改、代码编程思路清晰、注释明细。 3、适用对象：计算机，电子信息工程、数学等专业的大学生课程设计和毕业设计。 4...
keras-yolo3-master_keras_python教程_yolov3_yolo3_自训练数据集_
09-30
【描述】提到的是在Windows操作系统环境下，使用Keras（一个高级神经网络API，基于TensorFlow、Theano或CNTK等后端）和Python语言进行实践。这通常涉及到以下步骤：安装必要的库，如Keras、TensorFlow、PIL等；...
keras-yolov3_keras_深度学习训练标签生成_yolov3_python_
09-30
Keras是一个高级神经网络API，用Python编写，可运行于TensorFlow、Microsoft Cognitive Toolkit (CNTK)或Theano之上。 描述中提到"pyhton 文件将标签与图片数据集匹配生成训练所用文件，在深度学习的训练中使用"，...
Python-YOLOv3的最小化PyTorch实现
08-11
在Python中实现YOLOv3，通常会利用PyTorch框架，因为PyTorch提供了灵活的神经网络构建工具和强大的GPU加速功能。这个"Python-YOLOv3的最小化PyTorch实现"项目，旨在提供一个简洁、易于理解的代码库，用于快速理解和...
【Pytorch】使用tensorwatch神经网络结构可视化
03-10 676
首先使用conda 创建一个python3.6的新环境。后面是jupyter里显示的核的名字。后面跟的是刚刚创建的环境名称，pip 安装ipykernel。，将其中第 13 行代码改为。，解决方法，找到文件。安装graphviz。
YOLO-V5 系列算法和代码解析（四）—— 网络结构
DAOCHI
12-28 2156
文章目录： 辅助工具， 网络配置文件， 网络构建， 网络推理， 绘制网络结构；
手把手教你用Python绘制神经网络图
Lov1_BYS的博客
10-15 3136
使用Python快捷绘制神经网络结构图
使用Python和Numpy构建神经网络模型
班婕妤
06-11 3080
一：波士顿房价预测任务 上一节我们初步认识了神经网络的基本概念（如神经元、多层连接、前向计算、计算图）和模型结构三要素（模型假设、评价函数和优化算法）。本节将以“波士顿房价”任务为例，向读者介绍使用Python语言和Numpy库来构建神经网络模型的思考过程和操作方法。 波士顿房价预测是一个经典的机器学习任务，类似于程序员世界的“Hello World”。和大家对房价的普遍认知相同，波士顿地区的房价是由诸多因素影响的。该数据集统计了13种可能影响房价的因素和该类型房屋的均价，期望构建一个基于13个因素进行房价
卷积神经网络——YOLOv3论文翻译
itlilyer的博客
08-02 1155
论文链接：https://arxiv.org/abs/1804.02767 YOLOv3: An Incremental Improvement Abstract (摘要) 我们提出了一些对YOLO的升级！我们做了一些小的设计修改来使它更好。我们同样训练了该新网络，它的表现非常不错。它比上一个版本大一点但是精度更高。别担心，它仍然足够快。使用320x320的输入时YOLOv3的执行速度为22ms得到mAP为28.2，与SSD精度一样高但是速度快了三倍。如果看老的检测指标——0.5IOU的mAP，YOLOv3
目标检测系列讲解（三）之yolov3原理论文讲解
爱吃橘子的小翟
06-16 1153
论文题目：YOLOv3: An Incremental Improvement（翻译过来就是一个渐进式的改进）论文下载地址: https://arxiv.org/abs/1804.02767在学习yolov3的时候，我们先假设我们已经对神经网络有所了解，至少应该学过alexnet和vgg这些网络，这样的话，我们的讲解才能放清晰透彻。目标检测作为一个比图像识别更复杂的算法，我们要做的不仅仅是将图像识别出来，还要将目标的位置定位出来，也就是我们不仅要识别目标的种类，还有检测目标的位置，这也就是为啥目标检测相对复
yolov5 模型输出的格式解析
走错路的程序员
02-01 1万+
关键要看shape的最后一位，在这一步的时候，不是最终输出的格式，这里只是把它们合并起来了。后面还有个y.view进行了重新改变维度， 让这个组合的矩阵变的更加的直观， 改变维度后， 它的shape变成了。（我非常反感这种配置来配置去，搞脑子的写法， 因为非常的不方便代码理解， 不如直接在代码中硬编码, 最好的代码是一看就懂。从代码中可以看的出来，配置文件中的最后一列 arg参数， 并不是跟代码中class的参数一一对应的。剩下的应该都能看的懂。知道了存储的数据格式，后续的处理，实际上就很简单了。
yolov5源码解析(9)--输出
热门推荐
10-24 1万+
本文章基于yolov5-6.2版本。主要讲解的是yolov5是怎么在最终的特征图上得出物体边框、置信度、物体分类的。
Yolov5 v6.1网络结构
08-15
Yolov5 v6.1网络结构的配置文件可以在models文件夹下找到，其中包括yolov5n.yaml, yolov5s.yaml, yolov5m.yaml等等。尽管这些网络结构的实现稍有不同，但它们的核心思想和结构是相似的。通过调整depth_multiple和width_multiple参数，可以控制网络结构的深度和宽度。 如果你想要可视化Yolov5 v6.1网络结构，你可以使用GitHub上的lutzroeder/netron工具。这个工具可以帮助你可视化神经网络、深度学习和机器学习模型。 如果你想将Yolov5的.pt模型转换成onnx文件，你可以使用yolov5作者提供的方法: python path/to/export.py --weights yolov5s.pt --include onnx。这样就可以将模型转换成onnx格式。 关于网络结构具体的参数配置，可以参考目标检测YOLOv5的自定义网络结构文档。其中oup表示输出通道数，hidden_dim表示隐藏维度，kernel_size表示卷积核大小，stride表示步长，use_se表示是否使用SELayer，use_hs表示使用h_swish还是ReLU作为激活函数。<span class="em">1</span><span class="em">2</span><span class="em">3</span> #### 引用[.reference_title] - *1* *3* [Yolov5 网络结构](https://blog.csdn.net/windowsyun/article/details/123540894)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v92^chatsearchT0_1"}}] [.reference_item style="max-width: 50%"] - *2* [window系统下 利用netron将YOLOv5 v6.1 完整网络模型可视化（另附yolov5 v6.1中yolov5s.pt的网络结构图）](https://blog.csdn.net/m0_46093829/article/details/123500470)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v92^chatsearchT0_1"}}] [.reference_item style="max-width: 50%"] [ .reference_list ]

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值