Yolov12for traffic lights

clusterdensity.py

@@ -0,0 +1,39 @@
+import cv2 as cv
+import numpy as np
+
+img = cv.imread("imagewithbounds.jpg")
+
+original = cv.imread("Screenshot 2025-05-19 152029.png")
+
+# Taking a matrix of size 5 as the kernel
+kernel = np.ones((5, 5), np.uint8)
+
+img_erosion = cv.erode(img, kernel, iterations=1)
+
+#Define structuring element.
+boundary = img - img_erosion
+
+img_dilate = cv.dilate(boundary, kernel, iterations = 2)
+
+img_blur  = cv.GaussianBlur(img,(5,5),10)
+
+img_enhance = cv.Laplacian(boundary, cv.CV_64F, ksize=1)
+
+# Create a mask for the color
+mask = cv.inRange(img_dilate, (0,0,0), (0,255,0))
+
+# Apply the mask to the original image
+result = cv.bitwise_and(img,img, mask=mask)
+
+result = cv.cvtColor(result, cv.COLOR_BGR2GRAY)
+
+result = cv.bitwise_and(original,original, mask=result)
+
+cv.imshow('result', result)
+
+#components = cv.connectedComponentsWithStats(result)
+#(totalcomponents,ID, pixelvalues, centroid) = components
+
+#print(totalcomponents)
+cv.waitKey(0)
+cv.destroyAllWindows()

drawbounds.py

@@ -0,0 +1,44 @@
+#program to manually draw boxes and find the amount of boxes within those bounds
+import cv2 as cv
+
+#manually draw circles on images
+img = cv.imread("Screenshot 2025-05-19 152029.png")
+drawing = False
+mode = False
+ix, iy = -1,-1
+def draw_circle(event, x, y, flags, param):
+    global drawing,mode,ix,iy
+    if event == cv.EVENT_LBUTTONDOWN:
+        drawing = True
+        ix, iy = x, y
+    elif event == cv.EVENT_MOUSEMOVE:
+        if drawing:
+            if mode:
+                cv.rectangle(img, (ix,iy), (x, y), (0,255,0), -1)
+            else:
+                cv.circle(img, (x, y), 25, (0, 255, 0), -1)
+
+    elif event == cv.EVENT_LBUTTONUP:
+        drawing = False
+        if mode:
+            cv.rectangle(img, (ix, iy), (x, y), (0, 255, 0), -1)
+        else:
+            cv.circle(img, (x, y), 25, (0, 255, 0), -1)
+
+
+
+cv.namedWindow(winname="test drawing")
+cv.setMouseCallback("test drawing", draw_circle)
+while True:
+    cv.imshow('test drawing',img)
+    k = cv.waitKey(1)
+    if k == ord('m'):
+        mode = not mode
+    elif k == ord('s'):
+        cv.imwrite("imagewithbounds.jpg", img)
+
+#save new image
+
+
+
+cv.destroyAllWindows()

runs/detect/train/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov12n.yaml
+data: coco.yaml
+epochs: 600
+time: null
+patience: 100
+batch: 256
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: null
+name: train
+exist_ok: false
+pretrained: true
+optimizer: auto
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+save_hybrid: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.01
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.0
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+copy_paste: 0.1
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+crop_fraction: 1.0
+cfg: null
+tracker: botsort.yaml
+save_dir: D:\yolov12\runs\detect\train

train.py

@@ -0,0 +1,25 @@
+from ultralytics import YOLO
+import torch
+
+model = YOLO('yolov12n.yaml')
+
+
+# Train the model
+results = model.train(
+  data='coco.yaml',
+  epochs=600,
+  batch=256,
+  imgsz=640,
+  scale=0.5,  # S:0.9; M:0.9; L:0.9; X:0.9
+  mosaic=1.0,
+  mixup=0.0,  # S:0.05; M:0.15; L:0.15; X:0.2
+  copy_paste=0.1,  # S:0.15; M:0.4; L:0.5; X:0.6
+  device="0", #can change to "0,1,2,3" for multi gpu
+)
+
+# Evaluate model performance on the validation set
+metrics = model.val()
+
+# Perform object detection on an image
+results = model("carsonroad.jpg")
+results[0].show()