In some of our previous articles, we have also done a lot of testing projects related to agriculture. If you are interested, you can read it by yourself. Here are only the two most recent ones:
“How far is laser weeding from our actual agricultural life? A field crop weed detection and identification system was developed based on yolov8 based on what we have seen recently”
“Facilitating the detection and identification of crop diseases and insect pests, developing and constructing a potato crop beetle detection and identification system based on yolov3-yolov8”
The main purpose of this article is to develop and construct a detection model based on the weed data constructed by ourselves based on the yolov7 model. First, let’s take a look at the overall effect:
Next, let’s take a brief look at the data details:
The content of the instance annotation data is as follows:
16 0.401333 0.409 0.12 0.218 16 0.632667 0.441 0.113333 0.222 16 0.169333 0.646 0.157333 0.184
An example of xml annotation content is as follows:
<annotation> <folder>data</folder> <filename>0391.jpg</filename> <path>0391.jpg</path> <source> <database>Unknown</database> </source> <size> <width>750</width> <height>500</height> <depth>3</depth> </size> <segmented>0</segmented> <object> <name>gouweibacao</name> <pose>Unspecified</pose> <truncated>0</truncated> <difficult>0</difficult> <bndbox> <xmin>181</xmin> <ymin>95</ymin> <xmax>287</xmax> <ymax>154</ymax> </bndbox> </object> <object> <name>gouweibacao</name> <pose>Unspecified</pose> <truncated>0</truncated> <difficult>0</difficult> <bndbox> <xmin>219</xmin> <ymin>163</ymin> <xmax>264</xmax> <ymax>239</ymax> </bndbox> </object> <object> <name>gouweibacao</name> <pose>Unspecified</pose> <truncated>0</truncated> <difficult>0</difficult> <bndbox> <xmin>310</xmin> <ymin>225</ymin> <xmax>370</xmax> <ymax>285</ymax> </bndbox> </object> <object> <name>gouweibacao</name> <pose>Unspecified</pose> <truncated>0</truncated> <difficult>0</difficult> <bndbox> <xmin>289</xmin> <ymin>160</ymin> <xmax>448</xmax> <ymax>236</ymax> </bndbox> </object> <object> <name>gouweibacao</name> <pose>Unspecified</pose> <truncated>0</truncated> <difficult>0</difficult> <bndbox> <xmin>458</xmin> <ymin>192</ymin> <xmax>570</xmax> <ymax>235</ymax> </bndbox> </object> <object> <name>gouweibacao</name> <pose>Unspecified</pose> <truncated>0</truncated> <difficult>0</difficult> <bndbox> <xmin>485</xmin> <ymin>217</ymin> <xmax>535</xmax> <ymax>302</ymax> </bndbox> </object> <object> <name>gouweibacao</name> <pose>Unspecified</pose> <truncated>0</truncated> <difficult>0</difficult> <bndbox> <xmin>624</xmin> <ymin>232</ymin> <xmax>675</xmax> <ymax>316</ymax> </bndbox> </object> </annotation>
In this article, the yolov7 model with a relatively moderate number of parameters is selected. The model file is as follows:
# parameters
nc: 20 # 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, IDetect, [nc, anchors]], # Detect(P3, P4, P5)
]
The default iterative calculation is 100 epochs, and the result details are as follows:
【Confusion Matrix】
【F1 value curve】
【Accuracy Curve】
【Recall Curve】
【PR】Curve
【Training Visualization】
【Calculation Example】
To facilitate deployment and use, a dedicated visualization system interface has been developed here, which can support inference calculations of both image and video data. A simple example rendering is as follows:
【Image Reasoning】
【Video Reasoning】
If you are interested, you can develop and practice it yourself!