原创目标检测算法——YOLOv7改进|增加小目标检测层

Nuyoah阅读量 1654

![图片]:(https://img-blog.csdnimg.cn/efc93113f9514e53ad9a557995d8404c.png)

>>>深度学习Tricks，第一时间送达<<<

小目标检测一直以来是计算机CV领域的难点之一，那么，刚出炉的YOLOv7该如何增加小目标检测层呢？

![图片]:(https://img-blog.csdnimg.cn/32e363e639614949adf6439c8e214ccd.jpeg)

目录

1.YOLOv7算法简介

2.原始YOLOv7模型

3.增加小目标检测层

>>>>一起交流！互相学习！共同进步！<<<<

1.YOLOv7算法简介

官方版的YOLOv7相同体量下比YOLOv5精度更高，速度快120%（FPS），比 YOLOX 快180%（FPS），比 Dual-Swin-T 快1200%（FPS），比 ConvNext 快550%（FPS），比 SWIN-L快500%（FPS）。在5FPS到160FPS的范围内，无论是速度或是精度，YOLOv7都超过了目前已知的检测器，并且在GPU V100上进行测试， 精度为56.8% AP的模型可达到30 FPS（batch=1）以上的检测速率，与此同时，这是目前唯一一款在如此高精度下仍能超过30FPS的检测器。

YOLOV7主要的贡献在于：

1.模型重参数化

YOLOV7将模型重参数化引入到网络架构中，重参数化这一思想最早出现于REPVGG中；

2.标签分配策略

YOLOV7的标签分配策略采用的是YOLOV5的跨网格搜索，以及YOLOX的匹配策略。

3.ELAN高效网络架构

YOLOV7中提出的一个新的网络架构，以高效为主。

4.带辅助头的训练

YOLOV7提出了辅助头的一个训练方法，主要目的是通过增加训练成本，提升精度，同时不影响推理的时间，因为辅助头只会出现在训练过程中。

![图片]:(https://img-blog.csdnimg.cn/4f79ccb05ae0414b88fd2f334ff6a6b0.png)

基于深度学习的目标检测算法大多针对于具有一定尺寸或比例的中大型目标，难以适应复杂背景下的小目标检测。对于小目标的定义主要有2种：

**第1种是绝对小物体：**COCO数据集中指明，当物体的像素点数小于32×32时，此物体即可被看作是小物体；

**第2种是相对小物体：**当目标尺寸小于原图尺寸的0.1时可认为是相对小物体。

2.原始YOLOv7模型

复制代码 
# parameters
nc: 1  # number of classes
depth_multiple: 1.0  # model depth multiple
width_multiple: 1.0  # layer channel multiple

# anchors
anchors:
  - [12,16, 19,36, 40,28]  # P3/8
  - [36,75, 76,55, 72,146]  # P4/16
  - [142,110, 192,243, 459,401]  # P5/32

# yolov7 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [32, 3, 1]],  # 0
  
   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2      
   [-1, 1, Conv, [64, 3, 1]],
   
   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4  
   [-1, 1, Conv, [64, 1, 1]],
   [-2, 1, Conv, [64, 1, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]],  # 11
         
   [-1, 1, MP, []],
   [-1, 1, Conv, [128, 1, 1]],
   [-3, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 16-P3/8  
   [-1, 1, Conv, [128, 1, 1]],
   [-2, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [512, 1, 1]],  # 24
         
   [-1, 1, MP, []],
   [-1, 1, Conv, [256, 1, 1]],
   [-3, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 29-P4/16  
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [1024, 1, 1]],  # 37
         
   [-1, 1, MP, []],
   [-1, 1, Conv, [512, 1, 1]],
   [-3, 1, Conv, [512, 1, 1]],
   [-1, 1, Conv, [512, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 42-P5/32  
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [1024, 1, 1]],  # 50
  ]

# yolov7 head
head:
  [[-1, 1, SPPCSPC, [512]], # 51
  
   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [37, 1, Conv, [256, 1, 1]], # route backbone P4
   [[-1, -2], 1, Concat, [1]],
   
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]], # 63
   
   [-1, 1, Conv, [128, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [24, 1, Conv, [128, 1, 1]], # route backbone P3
   [[-1, -2], 1, Concat, [1]],
   
   [-1, 1, Conv, [128, 1, 1]],
   [-2, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [128, 1, 1]], # 75
      
   [-1, 1, MP, []],
   [-1, 1, Conv, [128, 1, 1]],
   [-3, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 2]],
   [[-1, -3, 63], 1, Concat, [1]],
   
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]], # 88
      
   [-1, 1, MP, []],
   [-1, 1, Conv, [256, 1, 1]],
   [-3, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, -3, 51], 1, Concat, [1]],
   
   [-1, 1, Conv, [512, 1, 1]],
   [-2, 1, Conv, [512, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [512, 1, 1]], # 101
   
   [75, 1, RepConv, [256, 3, 1]],
   [88, 1, RepConv, [512, 3, 1]],
   [101, 1, RepConv, [1024, 3, 1]],

   [[102,103,104], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
  ]

3.增加小目标检测层

复制代码 
# parameters
nc: 80  # number of classes
depth_multiple: 1.0  # model depth multiple
width_multiple: 1.0  # layer channel multiple

# anchors
anchors:
  - [12,15, 30,15, 15,30]
  - [56,19, 28,43, 93,30]
  - [46,95, 167,48, 110,155]
  - [383,136, 286,354, 609,255]

# yolov7 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [32, 3, 1]],  # 0

   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
   [-1, 1, Conv, [64, 3, 1]],

   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
   [-1, 1, Conv, [64, 1, 1]],
   [-2, 1, Conv, [64, 1, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]],  # 11

   [-1, 1, MP, []],
   [-1, 1, Conv, [128, 1, 1]],
   [-3, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 16-P3/8
   [-1, 1, Conv, [128, 1, 1]],
   [-2, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [512, 1, 1]],  # 24

   [-1, 1, MP, []],
   [-1, 1, Conv, [256, 1, 1]],
   [-3, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 29-P4/16
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [1024, 1, 1]],  # 37

   [-1, 1, MP, []],
   [-1, 1, Conv, [512, 1, 1]],
   [-3, 1, Conv, [512, 1, 1]],
   [-1, 1, Conv, [512, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 42-P5/32
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [1024, 1, 1]],  # 50
  ]

# yolov7 head
head:
  [[-1, 1, SPPCSPC, [512]], # 51

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [37, 1, Conv, [256, 1, 1]], # route backbone P4
   [[-1, -2], 1, Concat, [1]],

   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]], # 63

   [-1, 1, Conv, [128, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [24, 1, Conv, [128, 1, 1]], # route backbone P3
   [[-1, -2], 1, Concat, [1]],

   [-1, 1, Conv, [128, 1, 1]],
   [-2, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [128, 1, 1]], # 75

  # ------------------------------------------------#
   [-1, 1, Conv, [64, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [11, 1, Conv, [64, 1, 1]], # route backbone P2
   [[-1, -2], 1, Concat, [1]],

   [-1, 1, Conv, [64, 1, 1]],
   [-2, 1, Conv, [64, 1, 1]],
   [-1, 1, Conv, [32, 3, 1]],
   [-1, 1, Conv, [32, 3, 1]],
   [-1, 1, Conv, [32, 3, 1]],
   [-1, 1, Conv, [32, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [64, 1, 1]], # 87
  # ------------------------------------------------#
   [-1, 1, MP, []],
   [-1, 1, Conv, [64, 1, 1]],
   [-3, 1, Conv, [64, 1, 1]],
   [-1, 1, Conv, [64, 3, 2]],
   [[-1, -3, 75], 1, Concat, [1]],

   [-1, 1, Conv, [128, 1, 1]],
   [-2, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [128, 1, 1]], # 100
  # ------------------------------------------------#
   [-1, 1, MP, []],
   [-1, 1, Conv, [128, 1, 1]],
   [-3, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 2]],
   [[-1, -3, 63], 1, Concat, [1]],

   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]], # 113

   [-1, 1, MP, []],
   [-1, 1, Conv, [256, 1, 1]],
   [-3, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, -3, 51], 1, Concat, [1]],

   [-1, 1, Conv, [512, 1, 1]],
   [-2, 1, Conv, [512, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [512, 1, 1]], # 126

   [87, 1, RepConv, [128, 3, 1]],
   [100, 1, RepConv, [256, 3, 1]],
   [113, 1, RepConv, [512, 3, 1]],
   [126, 1, RepConv, [1024, 3, 1]],

   [[127,128,129,130], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
  ]

🚀🏆🍀【算法创新&算法训练&论文投稿】相关链接👇👇👇

✨【YOLO创新算法尝新系列】✨

🏂 美团出品 | YOLOv6 v3.0 is Coming（超越YOLOv7、v8）

🏂 官方正品 | Ultralytics YOLOv8算法来啦（尖端SOTA模型）

------------------------------🌴【重磅干货来袭】🎄------------------------------

🚀一、主干网络改进（持续更新中）🎄🎈

1.目标检测算法------YOLOv5/YOLOv7改进之结合ConvNeXt结构（纯卷积|超越Swin）****

2.目标检测算法------YOLOv5/YOLOv7改进之结合MobileOne结构（高性能骨干|仅需1ms）****

3.目标检测算法------YOLOv5/YOLOv7改进之结合Swin Transformer V2（涨点神器）****

4.目标检测算法------YOLOv5/YOLOv7改进结合BotNet（Transformer）****

5.目标检测算法------YOLOv5/YOLOv7改进之GSConv+Slim Neck（优化成本）****

6.目标检测算法------YOLOv5/YOLOv7改进结合新神经网络算子Involution（CVPR 2021）****

7.目标检测算法------YOLOv7改进|增加小目标检测层****

8.目标检测算法------YOLOv5改进|增加小目标检测层****

🌴 持续更新中......

🚀二、轻量化网络（持续更新中）🎄🎈

1.目标检测算法------YOLOv5/YOLOv7改进之结合​RepVGG（速度飙升）****

2.目标检测算法------YOLOv5/YOLOv7改进之结合​PP-LCNet（轻量级CPU网络）****

3.目标检测算法------YOLOv5/YOLOv7改进之结合轻量化网络MobileNetV3（降参提速）****

4.目标检测算法------YOLOv5/YOLOv7改进|结合轻量型网络ShuffleNetV2****

5.目标检测算法------YOLOv5/YOLOv7改进结合轻量型Ghost模块****

🌴 持续更新中......

🚀三、注意力机制（持续更新中）🎄🎈

1.目标检测算法------YOLOv5改进之结合CBAM注意力机制****

2.目标检测算法------YOLOv7改进之结合CBAM注意力机制****

3.目标检测算法------YOLOv5/YOLOv7之结合CA注意力机制****

4.目标检测算法------YOLOv5/YOLOv7改进之结合ECA注意力机制****

5.目标检测算法------YOLOv5/YOLOv7改进之结合NAMAttention（提升涨点）****

6.目标检测算法------YOLOv5/YOLOv7改进之结合GAMAttention****

7.目标检测算法------YOLOv5/YOLOv7改进之结合无参注意力SimAM（涨点神器）****

8.目标检测算法------YOLOv5/YOLOv7改进之结合Criss-Cross Attention****

9.​目标检测算法------YOLOv5/YOLOv7改进之结合​SOCA（单幅图像超分辨率）****

🌴 持续更新中......

🚀四、检测头部改进（持续更新中）🎄🎈

1.魔改YOLOv5/v7高阶版（魔法搭配+创新组合）------改进之结合解耦头Decoupled_Detect****

2.目标检测算法------YOLOv5/YOLOv7改进结合涨点Trick之ASFF（自适应空间特征融合）****

🌴 持续更新中......

🚀五、空间金字塔池化（持续更新中）🎄🎈

1.目标检测算法------YOLOv5/YOLOv7改进之结合​ASPP（空洞空间卷积池化金字塔）****

2.目标检测算法------YOLOv5/YOLOv7改进之结合特征提取网络RFBNet（涨点明显）****

🌴 持续更新中......

🚀六、损失函数及NMS改进（持续更新中）🎄🎈

1.目标检测算法------YOLOv5/YOLOv7改进|将IOU Loss替换为EIOU Loss****

2.目标检测算法------助力涨点 | YOLOv5改进结合Alpha-IoU****

3.目标检测算法------YOLOv5/YOLOv7改进之结合SIoU****

4.目标检测算法------YOLOv5将NMS替换为DIoU-NMS****

🌴 持续更新中......

🚀七、其他创新改进项目（持续更新中）🎄🎈

1.手把手教你搭建属于自己的PyQt5-YOLOv5目标检测平台（保姆级教程）****

2.YOLO算法改进之结合GradCAM可视化热力图（附详细教程）****

3.目标检测算法------YOLOv5/YOLOv7改进之结合SPD-Conv（低分辨率图像和小目标涨点明显）****

4.目标检测算法------YOLOv5/YOLOv7改进之更换FReLU激活函数****

5.目标检测算法------YOLOv5/YOLOv7改进之结合BiFPN****

🌴 持续更新中......

🚀八、算法训练相关项目（持续更新中）🎄🎈

1.目标检测算法------YOLOv7训练自己的数据集（保姆级教程）****

2.人工智能前沿------玩转OpenAI语音机器人ChatGPT（中文版）****

3.深度学习之语义分割算法（入门学习）****

4.知识经验分享------YOLOv5-6.0训练出错及解决方法（RuntimeError）****

5.目标检测算法------将xml格式转换为YOLOv5格式txt****

6.目标检测算法------YOLOv5/YOLOv7如何改变bbox检测框的粗细大小****

7.人工智能前沿------6款AI绘画生成工具****

8.YOLOv5结合人体姿态估计****

9.超越YOLOv5，0.7M超轻量，又好又快（PP-YOLOE&PP-PicoDet）****

10.目标检测算法------收藏|小目标检测的定义（一）****

11.目标检测算法------收藏|小目标检测难点分析（二）****

12.目标检测算法------收藏|小目标检测解决方案（三）****

🌴 持续更新中......

🚀九、数据资源相关项目（持续更新中）🎄🎈

1.目标检测算法------小目标检测相关数据集（附下载链接）****

2.目标检测算法------3D公共数据集汇总（附下载链接）****

3.目标检测算法------3D公共数据集汇总 2（附下载链接）****

4.目标检测算法------行人检测&人群计数数据集汇总(附下载链接)****

5.目标检测算法------遥感影像数据集资源汇总（附下载链接）****

6.目标检测算法------自动驾驶开源数据集汇总（附下载链接）****

7.目标检测算法------自动驾驶开源数据集汇总 2（附下载链接）****

8.目标检测算法------图像分类开源数据集汇总（附下载链接）****

9.目标检测算法------医学图像开源数据集汇总（附下载链接）****

10.目标检测算法------工业缺陷数据集汇总1（附下载链接）****

11.目标检测算法------工业缺陷数据集汇总2（附下载链接）****

12.目标检测算法------垃圾分类数据集汇总（附下载链接）****

13.目标检测算法------人脸识别数据集汇总（附下载链接）****

14.目标检测算法------安全帽识别数据集（附下载链接）****

15.目标检测算法------人体姿态估计数据集汇总（附下载链接）****

16.目标检测算法------人体姿态估计数据集汇总 2（附下载链接）****

17.目标检测算法------车辆牌照识别数据集汇总（附下载链接）****

18.目标检测算法------车辆牌照识别数据集汇总 2（附下载链接）****

19.收藏 | 机器学习公共数据集集锦（附下载链接）****

20.目标检测算法------图像分割数据集汇总（附下载链接）****

21.目标检测算法------图像分割数据集汇总 2（附下载链接）****

22.收藏 | 自然语言处理（NLP）数据集汇总（附下载链接）****

23.自然语言处理（NLP）数据集汇总 2（附下载链接）****

24.自然语言处理（NLP）数据集汇总 3（附下载链接）****

25.自然语言处理（NLP）数据集汇总 4（附下载链接）****

🌴 持续更新中......

🚀十、论文投稿相关项目（持续更新中）🎄🎈

1.论文投稿指南------收藏|SCI论文投稿注意事项（提高命中率）****

2.论文投稿指南------收藏|SCI论文怎么投？（Accepted）****

3.论文投稿指南------收藏|SCI写作投稿发表全流程****

4.论文投稿指南------收藏|如何选择SCI期刊（含选刊必备神器）****

5.论文投稿指南------SCI选刊****

6.论文投稿指南------SCI投稿各阶段邮件模板****

7.人工智能前沿------深度学习热门领域（确定选题及研究方向）****

8.人工智能前沿------2022年最流行的十大AI技术****

9.人工智能前沿------未来AI技术的五大应用领域****

10.人工智能前沿------无人自动驾驶技术****

11.人工智能前沿------AI技术在医疗领域的应用****

12.人工智能前沿------随需应变的未来大脑****

13.目标检测算法------深度学习知识简要普及****

14.目标检测算法------10种深度学习框架介绍****

15.目标检测算法------为什么我选择PyTorch？****

16.知识经验分享------超全激活函数解析（数学原理+优缺点）****

17.知识经验分享------卷积神经网络（CNN）****

18.[海带软件分享------Office 2021全家桶安装教程（附报错解决方法）](https://blog.csdn.net/m0_53578855/article/details/128088345?spm=1001.2014.3001.5502 "海带软件分享——Office 2021全家桶安装教程（附报错解决方法）

标签： yolov7改进
0/300
全部评论0
0/300