i mean see this text " Implementation 5.1 Setup and Installation 5.1.1 Installing…
- User
i mean see this text " Implementation 5.1 Setup and Installation 5.1.1 Installing Required Libraries The code begins by importing necessary libraries. TensorFlow (tensorflow) is used for building and training deep learning models. Matplotlib (matplotlib) is employed for visualizing training metrics such as accuracy and loss. Pandas (pandas) and Seaborn (seaborn) are imported for data manipulation and enhanced visualizations, respectively. Scikit-learn (sklearn) is utilized for model evaluation metrics like confusion matrices and classification reports. 5.2 Data Loading and Preprocessing Resizing and Interpolation: Images from the ’train’ and ’valid’ directories are resized to 128x128 pixels using bilinear interpolation to maintain aspect ratio and ensure uniformity in input size for the neural network. Color Mode and Batch Processing: Loaded in RGB color mode, images are processed in batches of 32 during training, optimizing computational efficiency and enabling simultaneous weight updates based on multiple samples. 1 t r a i n i n g s e t = t f . k e ra s . u t i l s . i m a g e d a t a s e t f r o m d i r e c t o r y ( 2 ’ t r a i n ’ , 3 l a b e l s=” i n f e r r e d ” , 4 la b el mo d e=” c a t e g o r i c a l ” , 5 colo r mode=” rgb ” , 6 b a t c h s i z e =32, 7 i m a g e s i z e =(128 , 128 ) , 8 s h u f f l e=True , 9 i n t e r p o l a t i o n=” b i l i n e a r ” 13 10 ) 11 12 v a l i d a t i o n s e t = t f . k e ra s . u t i l s . i m a g e d a t a s e t f r o m d i r e c t o r y ( 13 ’ v a l i d ’ , 14 l a b e l s=” i n f e r r e d ” , 15 la b el mo d e=” c a t e g o r i c a l ” , 16 colo r mode=” rgb ” , 17 b a t c h s i z e =32, 18 i m a g e s i z e =(128 , 128 ) , 19 s h u f f l e=True , 20 i n t e r p o l a t i o n=” b i l i n e a r ” 21 ) 5.3 Model Definition Here we are defining the model to extract spatial features from images, followed by max pooling layers (MaxPool2D) to reduce dimensionality and extract dominant features. Dropout layers (Dropout) are incorporated to prevent overfitting by randomly deactivating neurons during training. The extracted features are flattened using Flatten and passed through dense layers (Dense) for final classification. The output layer employs a softmax activation function (softmax) suitable for multi-class classification tasks. 22 cnn = t f . k e ra s . models . S e q u e n ti al ( [ 23 t f . k e ra s . l a y e r s . Conv2D ( f i l t e r s =32, k e r n e l s i z e =3, padding=’ same ’ , a c t i v a t i o n=’ r e l u ’ , i n p u t s ha p e =[128 , 128 , 3 ] ) , 24 t f . k e ra s . l a y e r s . Conv2D ( f i l t e r s =32, k e r n e l s i z e =3, a c t i v a t i o n=’ r e l u ’ ) , 25 t f . k e ra s . l a y e r s . MaxPool2D ( p o o l s i z e =2, s t r i d e s =2) , 26 Department of Computer Science and Engineering 14 27 t f . k e ra s . l a y e r s . Conv2D ( f i l t e r s =128, k e r n e l s i z e =3, padding=’ same ’ , a c t i v a t i o n=’ r e l u ’ ) , 28 t f . k e ra s . l a y e r s . Conv2D ( f i l t e r s =128, k e r n e l s i z e =3, a c t i v a t i o n=’ r e l u ’ ) , 29 t f . k e ra s . l a y e r s . MaxPool2D ( p o o l s i z e =2, s t r i d e s =2) , 30 31 t f . k e ra s . l a y e r s . Conv2D ( f i l t e r s =256, k e r n e l s i z e =3, padding=’ same ’ , a c t i v a t i o n=’ r e l u ’ ) , 32 t f . k e ra s . l a y e r s . Conv2D ( f i l t e r s =256, k e r n e l s i z e =3, a c t i v a t i o n=’ r e l u ’ ) , 33 t f . k e ra s . l a y e r s . MaxPool2D ( p o o l s i z e =2, s t r i d e s =2) , 34 35 t f . k e ra s . l a y e r s . Conv2D ( f i l t e r s =512, k e r n e l s i z e =3, padding=’ same ’ , a c t i v a t i o n=’ r e l u ’ ) , 36 t f . k e ra s . l a y e r s . Conv2D ( f i l t e r s =512, k e r n e l s i z e =3, a c t i v a t i o n=’ r e l u ’ ) , 37 t f . k e ra s . l a y e r s . MaxPool2D ( p o o l s i z e =2, s t r i d e s =2) , 38 39 t f . k e ra s . l a y e r s . Dropout ( 0 . 2 5 ) , 40 t f . k e ra s . l a y e r s . Fla t t e n ( ) , 41 t f . k e ra s . l a y e r s . Dense ( u ni t s =1500, a c t i v a t i o n=’ r e l u ’ ) , 42 t f . k e ra s . l a y e r s . Dropout ( 0 . 4 ) , 43 t f . k e ra s . l a y e r s . Dense ( u ni t s=n um cla s se s , a c t i v a t i o n=’ softmax ’ ) 44 ] ) Department of Computer Science and Engineering 15 5.4 Model Training and Evaluation Here we are training and Evaluating our model through epochs 46 cnn . compile ( o p timi z e r=t f . k e ra s . o p timi z e r s .Adam( l e a r n i n g r a t e =0.0001) , l o s s=’ c a t e g o r i c a l c r o s s e n t r o p y ’ , 47 m e t ri c s =[ ’ accu ra c y ’ ] ) 48 cnn . summary ( ) 49 t r a i n i n g h i s t o r y = cnn . f i t ( x=t r a i n i n g s e t , v a l i d a t i o n d a t a= v a l i d a t i o n s e t , epoch s =10) 50 t r a i n l o s s , t r a i n a c c = cnn . e v al u a t e ( t r a i n i n g s e t ) 51 pr int ( ’ T rai ni ng ac cu rac y : ’ , t r a i n a c c ) 52 v a l l o s s , v a l a c c = cnn . e v al u a t e ( v a l i d a t i o n s e t ) 53 pr int ( ’ V ali d a ti o n accu rac y : ’ , v a l a c c ) Figure 5.1: Model Training Department of Computer Science and Engineering 16 Figure 5.2: Model Training 5.5 Visualization of Training History 54 import m a t pl o tli b . p y plo t a s p l t 55 epoch s = range ( 1 , 11 ) 56 p l t . pl o t ( epochs , t r a i n i n g h i s t o r y . h i s t o r y [ ’ accu ra c y ’ ] , c o l o r=’ red ’ , l a b e l=’ T rai ni ng Accuracy ’ ) 57 p l t . pl o t ( epochs , t r a i n i n g h i s t o r y . h i s t o r y [ ’ v al a c c u r a c y ’ ] , c o l o r=’ bl u e ’ , l a b e l=’ V ali d a ti o n Accuracy ’ ) 58 p l t . x l a b e l ( ’No . of Epochs ’ ) 59 p l t . t i t l e ( ’ V i s u a l i z a t i o n of Accuracy R e s ul t ’ ) 60 p l t . l eg e n d ( ) 61 p l t . show ( ) Figure 5.3: Visualisation of Accuracy Result Department of Computer Science and Engineering 17 5.6 Model Evaluation Metrics 62 t e s t s e t = t f . k e ra s . u t i l s . i m a g e d a t a s e t f r o m d i r e c t o r y ( 63 ’ v a l i d ’ , 64 l a b e l s=” i n f e r r e d ” , 65 la b el mo d e=” c a t e g o r i c a l ” , 66 colo r mode=” rgb ” , 67 b a t c h s i z e =1, 68 i m a g e s i z e =(128 , 128 ) , 69 s h u f f l e=Fal se , 70 i n t e r p o l a t i o n=” b i l i n e a r ” 71 ) 72 73 # P r e d i c t c l a s s e s f o r t e s t s e t 74 y p red = cnn . p r e d i c t ( t e s t s e t ) 75 p r e d i c t e d c a t e g o r i e s = t f . argmax ( y pred , a x i s =1) . numpy ( ) 76 t r u e c a t e g o r i e s = t f . conca t ( [ y for x , y in t e s t s e t ] , a x i s =0) 77 Y t rue = t f . argmax ( t r u e c a t e g o r i e s , a x i s =1) . numpy ( ) 78 79 # Compute c o n f u s i o n m a t r ix and c l a s s i f i c a t i o n r e p o r t 80 cla s s nam e s = v a l i d a t i o n s e t . cl a s s nam e s 81 cm = c o nf u si o n m a t ri x ( Y true , p r e d i c t e d c a t e g o r i e s ) 82 pr int ( c l a s s i f i c a t i o n r e p o r t ( Y true , p r e d i c t e d c a t e g o r i e s , ta rg e t nam e s=cl a s s nam e s ) ) 83 84 # Pl o t c o n f u s i o n m a t r ix 85 p l t . f i g u r e ( f i g s i z e =(10 , 8 ) ) 86 s n s . heatmap (cm, annot=True , annot kws={” s i z e ” : 10} , fmt=”d” , cmap=” Blue s ” , x t i c k l a b e l s=cla s s nam e s , 87 y t i c k l a b e l s=cla s s n am e s ) 88 p l t . x l a b e l ( ’ P r e di c t e d Cla s s ’ , f o n t s i z e =12) Department of Computer Science and Engineering 18 89 p l t . y l a b e l ( ’ Ac tual Cla s s ’ , f o n t s i z e =12) 90 p l t . t i t l e ( ’ Plan t Di s ea s e P r e di c ti o n Confu sion Matrix ’ , f o n t s i z e =15) 91 p l t . show ( ) 92 cla s s nam e s = v a l i d a t i o n s e t . cl a s s nam e s 93 94 # Load t h e t r a i n e d model 95 cnn = t f . k e ra s . models . load model ( ’ t r a i n e d p l a n t d i s e a s e m o d e l . k e ra s ’ ) 96 97 # Path t o t h e image t o be t e s t e d 98 image pa th = r ”C: \ U se r s \ g o u ri \OneDrive\Documents\Desktoppla n t d i s e a s e \ c a u l i . jpg ” 99 100 # Read and p r e p r o c e s s t h e image 101 image = t f . k e ra s . p r e p r o c e s s i n g . image . load img ( image path , t a r g e t s i z e =(128 , 128 ) ) 102 i n p u t a r r = t f . k e ra s . p r e p r o c e s s i n g . image . im g t o a r r a y ( image ) 103 i n p u t a r r = np . a r ra y ( [ i n p u t a r r ] ) # Conver t s i n g l e image t o a b a t c h 104 105 # Make p r e d i c t i o n s 106 p r e d i c t i o n s = cnn . p r e d i c t ( i n p u t a r r ) 107 108 # P r i n t p r e d i c t i o n s 109 pr int ( p r e d i c t i o n s ) 110 111 # Get t h e p r e d i c t e d c l a s s i n d e x 112 r e s u l t i n d e x = np . argmax ( p r e d i c t i o n s ) # Return i n d e x o f max elemen t 113 pr int ( r e s u l t i n d e x ) Department of Computer Science and Engineering 19 114 115 # Get t h e c l a s s name o f t h e p r e d i c t e d c l a s s 116 m o d el p r e di c ti o n = cla s s nam e s [ r e s u l t i n d e x ] 117 118 # D i s pl a y t h e image w i t h t h e p r e d i c t i o n 119 p l t . imshow ( image ) 120 p l t . t i t l e ( f ” Di s ea s e Name: { m o d el p r e di c ti o n }” ) 121 p l t . x t i c k s ( [ ] ) 122 p l t . y t i c k s ( [ ] ) 123 p l t . show ( ) 124 125 # Make p r e d i c t i o n s on t h e v a l i d a t i o n s e t 126 y p red = cnn . p r e d i c t ( v a l i d a t i o n s e t ) 127 p r e d i c t e d c l a s s e s = np . argmax ( y pred , a x i s =1) 128 129 # Get t r u e c l a s s e s 130 t r u e c l a s s e s = np . co n ca t e na t e ( [ y for x , y in v a l i d a t i o n s e t ] , a x i s =0) 131 t r u e c l a s s e s = np . argmax ( t r u e c l a s s e s , a x i s =1) 132 133 # Genera te c l a s s i f i c a t i o n r e p o r t 134 r e p o r t = c l a s s i f i c a t i o n r e p o r t ( t r u e c l a s s e s , p r e d i c t e d c l a s s e s , ta rg e t nam e s=cla s s nam e s , o u t p u t di c t =True ) 135 136 # E x t r a c t p r e c i s i o n and r e c a l l v a l u e s 137 p r e c i s i o n v a l u e s = [ r e p o r t [ cla s s nam e ] [ ’ p r e c i s i o n ’ ] for cla s s nam e in cl a s s nam e s ] 138 r e c a l l v a l u e s = [ r e p o r t [ cla s s nam e ] [ ’ r e c a l l ’ ] for cla s s nam e in cl a s s nam e s ] 139 140 # Pl o t p r e c i s i o n h i s t og r am f o r each c l a s s Department of Computer Science and Engineering 20 141 p l t . f i g u r e ( f i g s i z e =(10 , 6 ) ) 142 p l t . bar ( cla s s nam e s , p r e c i s i o n v a l u e s , c o l o r=’ s k y bl u e ’ , alpha =0.7 , l a b e l=’ P r e c i s i o n ’ ) 143 p l t . x l a b e l ( ’ Cla s s ’ ) 144 p l t . y l a b e l ( ’ P r e c i s i o n ’ ) 145 p l t . t i t l e ( ’ P r e c i s i o n f o r Each Cla s s ’ ) 146 p l t . x t i c k s ( r o t a t i o n =45) 147 p l t . ylim ( [ 0 , 1 ] ) 148 p l t . t i g h t l a y o u t ( ) 149 p l t . l eg e n d ( ) 150 p l t . show ( ) 151 152 # Pl o t r e c a l l h i s t og r am f o r each c l a s s 153 p l t . f i g u r e ( f i g s i z e =(10 , 6 ) ) 154 p l t . bar ( cla s s nam e s , r e c a l l v a l u e s , c o l o r=’ l i g h t c o r a l ’ , alpha =0.7 , l a b e l=’ R e c all ’ ) 155 p l t . x l a b e l ( ’ Cla s s ’ ) 156 p l t . y l a b e l ( ’ R e c all ’ ) 157 p l t . t i t l e ( ’ R e c all f o r Each Cla s s ’ ) 158 p l t . x t i c k s ( r o t a t i o n =45) 159 p l t . ylim ( [ 0 , 1 ] ) 160 p l t . t i g h t l a y o u t ( ) 161 p l t . l eg e n d ( ) 162 p l t . show ( ) 163 164 # P r i n t t h e p r e c i s i o n and r e c a l l v a l u e s f o r r e f e r e n c e 165 for cla s s name , p r e c i s i o n , r e c a l l in z ip ( cla s s nam e s , p r e c i s i o n v a l u e s , r e c a l l v a l u e s ) : 166 pr int ( f ’ Cla s s : { cla s s nam e } , P r e c i s i o n : { p r e c i s i o n : . 2 f } , R e c all : { r e c a l l : . 2 f } ’ ) Department of Computer Science and Engineering 21 Figure 5.4: Model Evaluation Metrics (Confusion Matrix) Figure 5.5: Model Evaluation Metrics (Prediction by Each Class) Department of Computer Science and Engineering 22 Figure 5.6: Model Evaluation Metrics (Precision For Each Class) Figure 5.7: Recall for each class Department of Computer Science and Engineering 23 CHAPTER 6" how desciptive its about the code i wanted like this but change the structure of language you use in the text but for the code “from tkinter import messagebox from tkinter import * from tkinter import simpledialog import tkinter from tkinter import filedialog from tkinter.filedialog import askopenfilename import cv2 as cv import numpy as np
import os from keras.preprocessing.image import load_img from keras.utils import to_categorical from keras.preprocessing.image import img_to_array
from sklearn.model_selection import train_test_split
import pickle from keras.models import load_model from keras.applications import VGG16 from keras.layers import Flatten from keras.layers import Dropout from keras.layers import Dense from keras.layers import Input from keras.models import Model from keras.optimizers import Adam from keras.models import model_from_json
main = tkinter.Tk() main.title(“SSLA Based Traffic Sign and Lane Detection for Autonomous cars”) main.geometry(“1300x1200”)
global filename global model
old = None class_labels = [‘Speed limit (20km/h)’,‘Speed limit (30km/h)’,‘Speed limit (50km/h)’,‘Speed limit (60km/h)’,‘Speed limit (70km/h)’, ‘Speed limit (80km/h)’,‘End of speed limit (80km/h)’,‘Speed limit (100km/h)’,‘Speed limit (120km/h)’,‘No passing’,‘Stop’,‘No Entry’, ‘General caution’,‘Traffic signals’]
def cannyDetection(img): grayImg = cv.cvtColor(img, cv.COLOR_RGB2GRAY) blurImg = cv.GaussianBlur(grayImg, (5, 5), 0) cannyImg = cv.Canny(blurImg, 50, 150) return cannyImg
def segmentDetection(img): height = img.shape[0] polygons = np.array([[(0, height), (800, height), (380, 290)]]) maskImg = np.zeros_like(img) cv.fillPoly(maskImg, polygons, 255) segmentImg = cv.bitwise_and(img, maskImg) return segmentImg
def calculateLines(frame, lines): left = [] right = [] for line in lines: x1, y1, x2, y2 = line.reshape(4) parameters = np.polyfit((x1, x2), (y1, y2), 1) slope = parameters[0] y_intercept = parameters[1] if slope < 0: left.append((slope, y_intercept)) else: right.append((slope, y_intercept)) left_avg = np.average(left, axis = 0) right_avg = np.average(right, axis = 0) left_line = calculateCoordinates(frame, left_avg) right_line = calculateCoordinates(frame, right_avg) return np.array([left_line, right_line])
def calculateCoordinates(frame, parameters): global old #print(str(parameters)+” “+str(type(parameters))+” “+str(np.isnan(parameters))) if old is None: old = parameters if np.isnan(parameters.any()) == False: parameters = old slope, intercept = parameters y1 = frame.shape[0] y2 = int(y1 - 150) x1 = int((y1 - intercept) / slope) x2 = int((y2 - intercept) / slope) return np.array([x1, y1, x2, y2])
def visualizeLines(frame, lines): lines_visualize = np.zeros_like(frame) if lines is not None: for x1, y1, x2, y2 in lines: cv.line(lines_visualize, (x1, y1), (x2, y2), (0, 255, 0), 5) return lines_visualize
def loadModel(): global model model = load_model(‘model/model.h5’) pathlabel.config(text=“Machine Learning Traffic Sign Detection Model Loaded”) text.delete(‘1.0’, END) text.insert(END,“Machine Learning Traffic Sign Detection Model Loaded\n\n”);
def detectSignal(): global model filename = filedialog.askopenfilename(initialdir=“Videos”) pathlabel.config(text=filename) text.delete(‘1.0’, END) text.insert(END,filename+” loaded\n\n") text.update_idletasks() cap = cv.VideoCapture(filename) while (cap.isOpened()): ret, frame = cap.read() if frame is not None: canny = cannyDetection(frame) cv.imshow(“cannyImage”, canny) segment = segmentDetection(canny) hough = cv.HoughLinesP(segment, 2, np.pi / 180, 100, np.array([]), minLineLength = 100, maxLineGap = 50) if hough is not None: lines = calculateLines(frame, hough) linesVisualize = visualizeLines(frame, lines) cv.imshow(“hough”, linesVisualize) output = cv.addWeighted(frame, 0.9, linesVisualize, 1, 1) cv.imwrite(“test.jpg”,output) temps = cv.imread(“test.jpg”) h, w, c = temps.shape image = load_img(“test.jpg”, target_size=(80, 80)) image = img_to_array(image) / 255.0 image = np.expand_dims(image, axis=0) (boxPreds, labelPreds) = model.predict(image) print(boxPreds) boxPreds = boxPreds[0] startX = int(boxPreds[0] * w) startY = int(boxPreds[1] * h) endX = int(boxPreds[2] * w) endY = int(boxPreds[3] * h) predict= np.argmax(labelPreds, axis=1) predict = predict[0] accuracy = np.amax(labelPreds, axis=1) print(str(class_labels[predict])+" "+str(accuracy)) if accuracy > 0.97: cv.putText(output, "Recognized As “+str(class_labels[predict]), (startX, startY), cv.FONT_HERSHEY_SIMPLEX, 0.7, (0, 255, 0), 2) cv.rectangle(output, (startX, startY), (endX, endY), (0, 255, 0), 2) cv.imshow(“output”, output) if cv.waitKey(10) & 0xFF == ord(‘q’): break cap.release() cv.destroyAllWindows()
def close(): main.destroy()
font = (‘times’, 16, ‘bold’) title = Label(main, text=‘SSLA Based Traffic Sign and Lane Detection for Autonomous cars’,anchor=W, justify=CENTER) title.config(bg=‘yellow4’, fg=‘white’) title.config(font=font) title.config(height=3, width=120) title.place(x=0,y=5)
font1 = (‘times’, 14, ‘bold’) upload = Button(main, text=“Generate & Load Machine Learning Model”, command=loadModel) upload.place(x=50,y=100) upload.config(font=font1)
pathlabel = Label(main) pathlabel.config(bg=‘yellow4’, fg=‘white’) pathlabel.config(font=font1) pathlabel.place(x=50,y=150)
markovButton = Button(main, text=“Upload Video & Detect Hough Lane, Signal”, command=detectSignal) markovButton.place(x=50,y=200) markovButton.config(font=font1)
predictButton = Button(main, text=“Exit”, command=close) predictButton.place(x=50,y=250) predictButton.config(font=font1)
font1 = (‘times’, 12, ‘bold’) text=Text(main,height=15,width=78) scroll=Scrollbar(text) text.configure(yscrollcommand=scroll.set) text.place(x=450,y=100) text.config(font=font1)
main.config(bg=‘magenta3’) main.mainloop() ”
- Assistant
Certainly! Here’s a detailed description of the code you provided, structured similarly to your initial sample but using different language conventions:
Implementation
5.1 Preparation and Library Setup
5.1.1 Installation of Necessary Libraries
Before executing the script, ensure all required libraries are available. This code primarily uses the Tkinter library for creating graphical user interfaces. For image processing tasks, it employs OpenCV (cv2) and NumPy. Additionally, Keras is used for loading and predicting with machine learning models. Below is the list of libraries to import:
from tkinter import messagebox, * from tkinter import simpledialog, filedialog import tkinter from tkinter.filedialog import askopenfilename import cv2 as cv import numpy as np import os from keras.preprocessing.image import load_img, img_to_array from keras.utils import to_categorical # from sklearn.model_selection import train_test_split import pickle from keras.models import load_model, model_from_json from keras.applications import VGG16 from keras.layers import Flatten, Dropout, Dense, Input from keras.models import Model from keras.optimizers import Adam5.2 GUI Initialization and Global Variables
The main Tkinter window is set up and titled "SSLA Based Traffic Sign and Lane Detection for Autonomous cars". Essential global variables and class labels are defined here:
main = tkinter.Tk() main.title("SSLA Based Traffic Sign and Lane Detection for Autonomous cars") main.geometry("1300x1200") global filename, model, old old = None class_labels = ['Speed limit (20km/h)', 'Speed limit (30km/h)', 'Speed limit (50km/h)', 'Speed limit (60km/h)', 'Speed limit (70km/h)', 'Speed limit (80km/h)', 'End of speed limit (80km/h)', 'Speed limit (100km/h)', 'Speed limit (120km/h)', 'No passing', 'Stop', 'No Entry', 'General caution', 'Traffic signals']5.3 Image Processing Functions
Several functions are implemented to perform canny edge detection, segment detection, and calculations for lane lines:
def cannyDetection(img): grayImg = cv.cvtColor(img, cv.COLOR_RGB2GRAY) blurImg = cv.GaussianBlur(grayImg, (5, 5), 0) cannyImg = cv.Canny(blurImg, 50, 150) return cannyImg def segmentDetection(img): height = img.shape[0] polygons = np.array([[(0, height), (800, height), (380, 290)]]) maskImg = np.zeros_like(img) cv.fillPoly(maskImg, polygons, 255) segmentImg = cv.bitwise_and(img, maskImg) return segmentImg def calculateLines(frame, lines): left, right = [], [] for line in lines: x1, y1, x2, y2 = line.reshape(4) parameters = np.polyfit((x1, x2), (y1, y2), 1) slope, y_intercept = parameters if slope < 0: left.append((slope, y_intercept)) else: right.append((slope, y_intercept)) left_avg = np.average(left, axis=0) right_avg = np.average(right, axis=0) left_line = calculateCoordinates(frame, left_avg) right_line = calculateCoordinates(frame, right_avg) return np.array([left_line, right_line]) def calculateCoordinates(frame, parameters): global old if old is None: old = parameters if np.isnan(parameters.any()) == False: parameters = old slope, intercept = parameters y1 = frame.shape[0] y2 = int(y1 - 150) x1 = int((y1 - intercept) / slope) x2 = int((y2 - intercept) / slope) return np.array([x1, y1, x2, y2]) def visualizeLines(frame, lines): lines_visualize = np.zeros_like(frame) if lines is not None: for x1, y1, x2, y2 in lines: cv.line(lines_visualize, (x1, y1), (x2, y2), (0, 255, 0), 5) return lines_visualize5.4 Model Loading and User Interface
The
loadModeland main GUI elements are coded to load a trained machine learning model and initialize the user interface components:def loadModel(): global model model = load_model('model/model.h5') pathlabel.config(text="Machine Learning Traffic Sign Detection Model Loaded") text.delete('1.0', END) text.insert(END,"Machine Learning Traffic Sign Detection Model Loaded\n\n") def detectSignal(): global model filename = filedialog.askopenfilename(initialdir="Videos") pathlabel.config(text=filename) text.delete('1.0', END) text.insert(END,filename + " loaded\n\n") text.update_idletasks() cap = cv.VideoCapture(filename) while (cap.isOpened()): ret, frame = cap.read() if frame is not None: canny = cannyDetection(frame) cv.imshow("cannyImage", canny) segment = segmentDetection(canny) hough = cv.HoughLinesP(segment, 2, np.pi / 180, 100, np.array([]), minLineLength=100, maxLineGap=50) if hough is not None: lines = calculateLines(frame, hough) linesVisualize = visualizeLines(frame, lines) cv.imshow("hough", linesVisualize) output = cv.addWeighted(frame, 0.9, linesVisualize, 1, 1) cv.imwrite("test.jpg", output) temps = cv.imread("test.jpg") h, w, c = temps.shape image = load_img("test.jpg", target_size=(80, 80)) image = img_to_array(image) / 255.0 image = np.expand_dims(image, axis=0) (boxPreds, labelPreds) = model.predict(image) boxPreds = boxPreds[0] startX = int(boxPreds[0] * w) startY = int(boxPreds[1] * h) endX = int(boxPreds[2] * w) endY = int(boxPreds[3] * h) predict = np.argmax(labelPreds, axis=1)[0] accuracy = np.amax(labelPreds, axis=1) if accuracy > 0.97: cv.putText(output, "Recognized As " + str(class_labels[predict]), (startX, startY), cv.FONT_HERSHEY_SIMPLEX, 0.7, (0, 255, 0), 2) cv.rectangle(output, (startX, startY), (endX, endY), (0, 255, 0), 2) cv.imshow("output", output) if cv.waitKey(10) & 0xFF == ord('q'): break cap.release() cv.destroyAllWindows() def close(): main.destroy() font = ('times', 16, 'bold') title = Label(main, text='SSLA Based Traffic Sign and Lane Detection for Autonomous cars', anchor=W, justify=CENTER) title.config(bg='yellow4', fg='white', font=font, height=3, width=120) title.place(x=0, y=5) font1 = ('times', 14, 'bold') upload = Button(main, text="Generate & Load Machine Learning Model", command=loadModel) upload.place(x=50, y=100) upload.config(font=font1) pathlabel = Label(main, bg='yellow4', fg='white', font=font1) pathlabel.place(x=50, y=150) markovButton = Button(main, text="Upload Video & Detect Hough Lane, Signal", command=detectSignal) markovButton.place(x=50, y=200) markovButton.config(font=font1) predictButton = Button(main, text="Exit", command=close) predictButton.place(x=50, y=250) predictButton.config(font=font1) text = Text(main, height=15, width=78, font=font1) scroll = Scrollbar(text) text.configure(yscrollcommand=scroll.set) text.place(x=450, y=100) main.config(bg='magenta3') main.mainloop()This comprehensive breakdown walks you through setting up the environment, initializing the GUI, performing image processing, and interacting with machine learning models using the Keras library.
- User
i want this code to display in this indentation andstyle in latex text give me synatx to wrap the code part around only sysntax
- Assistant
Certainly! To present the code with proper indentation and styling in LaTeX, you can use the
listingspackage, which is specifically designed for this purpose. Here’s how you can wrap your code in LaTeX syntax for typesetting:First, make sure to include the
listingsandxcolorpackages in the preamble of your LaTeX document:\documentclass{article} \usepackage{listings} \usepackage{xcolor} \lstset{ language=Python, basicstyle=\ttfamily\footnotesize, keywordstyle=\color{blue}\bfseries, commentstyle=\color{green}, stringstyle=\color{red}, showstringspaces=false, breaklines=true, frame=single, }Now, you can wrap your Python code within the
lstlistingenvironment:\begin{document} \lstset{language=Python} \begin{lstlisting} from tkinter import messagebox, * from tkinter import simpledialog, filedialog import tkinter from tkinter.filedialog import askopenfilename import cv2 as cv import numpy as np import os from keras.preprocessing.image import load_img, img_to_array from keras.utils import to_categorical # from sklearn.model_selection import train_test_split import pickle from keras.models import load_model, model_from_json from keras.applications import VGG16 from keras.layers import Flatten, Dropout, Dense, Input from keras.models import Model from keras.optimizers import Adam main = tkinter.Tk() main.title("SSLA Based Traffic Sign and Lane Detection for Autonomous cars") main.geometry("1300x1200") global filename, model, old old = None class_labels = ['Speed limit (20km/h)', 'Speed limit (30km/h)', 'Speed limit (50km/h)', 'Speed limit (60km/h)', 'Speed limit (70km/h)', 'Speed limit (80km/h)', 'End of speed limit (80km/h)', 'Speed limit (100km/h)', 'Speed limit (120km/h)', 'No passing', 'Stop', 'No Entry', 'General caution', 'Traffic signals'] def cannyDetection(img): grayImg = cv.cvtColor(img, cv.COLOR_RGB2GRAY) blurImg = cv.GaussianBlur(grayImg, (5, 5), 0) cannyImg = cv.Canny(blurImg, 50, 150) return cannyImg def segmentDetection(img): height = img.shape[0] polygons = np.array([[(0, height), (800, height), (380, 290)]]) maskImg = np.zeros_like(img) cv.fillPoly(maskImg, polygons, 255) segmentImg = cv.bitwise_and(img, maskImg) return segmentImg def calculateLines(frame, lines): left, right = [], [] for line in lines: x1, y1, x2, y2 = line.reshape(4) parameters = np.polyfit((x1, x2), (y1, y2), 1) slope, y_intercept = parameters if slope < 0: left.append((slope, y_intercept)) else: right.append((slope, y_intercept)) left_avg = np.average(left, axis=0) right_avg = np.average(right, axis=0) left_line = calculateCoordinates(frame, left_avg) right_line = calculateCoordinates(frame, right_avg) return np.array([left_line, right_line]) def calculateCoordinates(frame, parameters): global old if old is None: old = parameters if np.isnan(parameters.any()) == False: parameters = old slope, intercept = parameters y1 = frame.shape[0] y2 = int(y1 - 150) x1 = int((y1 - intercept) / slope) x2 = int((y2 - intercept) / slope) return np.array([x1, y1, x2, y2]) def visualizeLines(frame, lines): lines_visualize = np.zeros_like(frame) if lines is not None: for x1, y1, x2, y2 in lines: cv.line(lines_visualize, (x1, y1), (x2, y2), (0, 255, 0), 5) return lines_visualize def loadModel(): global model model = load_model('model/model.h5') pathlabel.config(text="Machine Learning Traffic Sign Detection Model Loaded") text.delete('1.0', END) text.insert(END,"Machine Learning Traffic Sign Detection Model Loaded\n\n") def detectSignal(): global model filename = filedialog.askopenfilename(initialdir="Videos") pathlabel.config(text=filename) text.delete('1.0', END) text.insert(END,filename + " loaded\n\n") text.update_idletasks() cap = cv.VideoCapture(filename) while (cap.isOpened()): ret, frame = cap.read() if frame is not None: canny = cannyDetection(frame) cv.imshow("cannyImage", canny) segment = segmentDetection(canny) hough = cv.HoughLinesP(segment, 2, np.pi / 180, 100, np.array([]), minLineLength=100, maxLineGap=50) if hough is not None: lines = calculateLines(frame, hough) linesVisualize = visualizeLines(frame, lines) cv.imshow("hough", linesVisualize) output = cv.addWeighted(frame, 0.9, linesVisualize, 1, 1) cv.imwrite("test.jpg", output) temps = cv.imread("test.jpg") h, w, c = temps.shape image = load_img("test.jpg", target_size=(80, 80)) image = img_to_array(image) / 255.0 image = np.expand_dims(image, axis=0) (boxPreds, labelPreds) = model.predict(image) boxPreds = boxPreds[0] startX = int(boxPreds[0] * w) startY = int(boxPreds[1] * h) endX = int(boxPreds[2] * w) endY = int(boxPreds[3] * h) predict = np.argmax(labelPreds, axis=1)[0] accuracy = np.amax(labelPreds, axis=1) if accuracy > 0.97: cv.putText(output, "Recognized As " + str(class_labels[predict]), (startX, startY), cv.FONT_HERSHEY_SIMPLEX, 0.7, (0, 255, 0), 2) cv.rectangle(output, (startX, startY), (endX, endY), (0, 255, 0), 2) cv.imshow("output", output) if cv.waitKey(10) & 0xFF == ord('q'): break cap.release() cv.destroyAllWindows() def close(): main.destroy() font = ('times', 16, 'bold') title = Label(main, text='SSLA Based Traffic Sign and Lane Detection for Autonomous cars', anchor=W, justify=CENTER) title.config(bg='yellow4', fg='white', font=font, height=3, width=120) title.place(x=0, y=5) font1 = ('times', 14, 'bold') upload = Button(main, text="Generate & Load Machine Learning Model", command=loadModel) upload.place(x=50, y=100) upload.config(font=font1) pathlabel = Label(main, bg='yellow4', fg='white', font=font1) pathlabel.place(x=50, y=150) markovButton = Button(main, text="Upload Video & Detect Hough Lane, Signal", command=detectSignal) markovButton.place(x=50, y=200) markovButton.config(font=font1) predictButton = Button(main, text="Exit", command=close) predictButton.place(x=50, y=250) predictButton.config(font=font1) text = Text(main, height=15, width=78, font=font1) scroll = Scrollbar(text) text.configure(yscrollcommand=scroll.set) text.place(x=450, y=100) main.config(bg='magenta3') main.mainloop() \end{lstlisting} \end{document}Copy and paste the above LaTeX text into your
.texfile, and this will format your code snippet with proper indentation and styling using the LaTeXlistingspackage. Make sure you adjust the file paths and other settings according to your needs.