feat: 合并yolov5-dnf项目

README.md

@@ -1,10 +1,15 @@
 # yolov5
 
 1. 代码中涉及到使用opencv对小地图和技能栏进行模板匹配和二值化等操作，注意，不同游戏分辨率和电脑显示器分辨率是不一致的，代码中给出的（0,0,1280,800）是本人游戏中的分辨率，而small_recgonize.py和skill_recgonize.py中的img[45:65, 1107:1270]， img[733: 793, 538:750, 2]是根据不同显示器的分辨率决定的，使用时需要自己调整。
-
 2. 本人训练的yolov5模型还有待提高，我的训练集只有294张图片，因此效果一般。
+详细教学请移步b站，有很详细的讲解：https://www.bilibili.com/video/BV18r4y1A7BF/
+
+
+1. 屏幕检测
+2. 怪物，材料的图像识别
+3. 控制打怪和捡材料
+4. 下一关
 
 
 1. 识别地图中怪物
-2. 寻找位置，释放技能，清理残余，寻找下一个门，进图
-3. 
+2. 寻找位置，释放技能，清理残余，寻找下一个门，进图

models/common.py

@@ -41,6 +41,61 @@ def forward(self, x):
         return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))
 
 
+import warnings
+
+class SPPF(nn.Module):
+    # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
+    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_ * 4, c2, 1, 1)
+        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
+
+    def forward(self, x):
+        x = self.cv1(x)
+        with warnings.catch_warnings():
+            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
+            y1 = self.m(x)
+            y2 = self.m(y1)
+            return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))
+
+
+
+
+class CrossConv(nn.Module):
+    # Cross Convolution Downsample
+    def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
+        # ch_in, ch_out, kernel, stride, groups, expansion, shortcut
+        super(CrossConv, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, (1, k), (1, s))
+        self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+class C3(nn.Module):
+    # Cross Convolution CSP
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(C3, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
+        self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
+        self.cv4 = Conv(2 * c_, c2, 1, 1)
+        self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
+        self.act = nn.LeakyReLU(0.1, inplace=True)
+        self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])
+
+    def forward(self, x):
+        y1 = self.cv3(self.m(self.cv1(x)))
+        y2 = self.cv2(x)
+        return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))
+
+
+
 def autopad(k, p=None):  # kernel, padding
     # Pad to 'same'
     if p is None:

small_recgonize.py

@@ -2,7 +2,7 @@
 import numpy as np
 
 
-img_path = "datasets/guiqi/test/61_93.jpg"
+img_path = "test/DNF.png"
 img = cv.imread(img_path)
 
 def img_show(img):

test/cv2_test.py

@@ -0,0 +1,9 @@
+import cv2
+from ..grabscreen import grab_screen
+
+img = grab_screen((0, 0, 1280, 800))
+img0 = cv2.cvtColor(img, cv2.COLOR_BGRA2BGR)
+dnf = cv2.imread(img0)
+cv2.imshow('rgb', dnf)
+# BGR = cv2.cvtColor(dnf,cv2.COLOR_RGB2BGR)
+# cv2.imshow('BGR',BGR)

wx-read/globalSearch.py

@@ -21,7 +21,7 @@ def sortWay(book):
     return book['bookInfo']['newRating']
 
 
-def getWXBooks(queryPath):
+def getWXBooks(queryPath,searchWord):
     # booksTitleSet = client.hget(searchKeyWord, 'booksTitleSet') or set()
     # maxIdx = int(client.hget(searchKeyWord, 'maxIdx')) if client.hget(searchKeyWord, 'maxIdx') is not None else 0
     maxIdx = 0
@@ -33,7 +33,7 @@ def getWXBooks(queryPath):
         rTime = random.randint(1, 3)  # 随机延迟，从1到3内取一个整数值
         time.sleep(rTime)  # 把随机取出的整数值传到等待函数中
         res = requests.get(
-            queryPath, params={'maxIdx': maxIdx, 'keyword': searchKeyWord, 'fragmentSize': 120, 'count': 20})
+            queryPath, params={'maxIdx': maxIdx, 'keyword': searchWord, 'fragmentSize': 120, 'count': 20})
         books = res.json()['books']
         if not totalCount:
             totalCount = res.json()['totalCount']
@@ -60,5 +60,5 @@ def getWXBooks(queryPath):
     return bookList
 
 
-books = getWXBooks('https://weread.qq.com/web/search/global')
+books = getWXBooks('https://weread.qq.com/web/search/global',searchKeyWord)
 mongodbWrite(searchKeyWord, books)