Commit b34e01b0 authored by Shenthuri Vimaleshwaran's avatar Shenthuri Vimaleshwaran

Merge branch 'revert-09224a38' into 'master'

Revert "Merge branch 'IT19972626_StudentConcentration' into 'master'"

See merge request !4
parents cfc9b11f 150ae15e
import cv2
import os
# Load and create faceCascade Classifier
facePath = os.path.dirname(cv2.__file__) + "/data/haarcascade_frontalface_default.xml"
faceCascade = cv2.CascadeClassifier(facePath)
eyePath = os.path.dirname(cv2.__file__) + "/data/haarcascade_eye.xml"
eyeCascade = cv2.CascadeClassifier(eyePath)
out = cv2.VideoWriter('faceEyeDetection.mp4', -1, 20.0, (640, 480))
video = cv2.VideoCapture(0)
while True:
try:
ret, frames = video.read()
gray = cv2.cvtColor(frames, cv2.COLOR_BGR2GRAY)
# Face Detection
faces = faceCascade.detectMultiScale(gray)
for (x, y, w, h) in faces: cv2.rectangle(frames, (x, y), (x + w, y + h), (255, 255, 0), 2)
# Eye Detection
eyes = eyeCascade.detectMultiScale(gray)
for (x, y, w, h) in eyes: cv2.rectangle(frames, (x, y), (x + w, y + h), (0, 165, 255), 2)
# Save and Show the Video
out.write(frames)
cv2.imshow('WebCam', frames)
if cv2.waitKey(1) & 0xFF == ord('q'): break
except Exception as e:
print(str(e))
break
video.release()
out.release()
cv2.destroyAllWindows()
\ No newline at end of file
# import face_recognition
import numpy as np
import cv2 as cv
import copy
from matplotlib import pyplot as plt
import pyautogui
import time
import os
import cv2
# Load the cascade
face_cascade = cv2.CascadeClassifier("haarcascade_frontalface_default.xml")
eye_cascade = cv2.CascadeClassifier("haarcascade_eye.xml")
# Load the video
cap = cv2.VideoCapture(0)
# Variables to store the last position of the eyes
eye_pos_x = None
eye_pos_y = None
while True:
# Read the frame
_, frame = cap.read()
# Convert to grayscale
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# Detect faces
faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5)
# Loop over the face detections
for (x, y, w, h) in faces:
roi_gray = gray[y:y + h, x:x + w]
roi_color = frame[y:y + h, x:x + w]
# Detect eyes
eyes = eye_cascade.detectMultiScale(roi_gray)
# Loop over the eye detections
for (ex, ey, ew, eh) in eyes:
# Draw a rectangle around the eyes
cv2.rectangle(roi_color, (ex, ey), (ex + ew, ey + eh), (0, 255, 0), 2)
# Check if the eyes are open or closed
if ew > 20:
# Check if this is the first frame
if eye_pos_x is None and eye_pos_y is None:
eye_pos_x = ex + ew / 2
eye_pos_y = ey + eh / 2
else:
# Calculate the displacement of the eyes
displacement_x = (ex + ew / 2) - eye_pos_x
displacement_y = (ey + eh / 2) - eye_pos_y
# Draw the displacement vector
cv2.arrowedLine(roi_color, (int(eye_pos_x), int(eye_pos_y)),
(int(eye_pos_x + displacement_x), int(eye_pos_y + displacement_y)), (255, 0, 0), 2)
# Check if the eyes are looking to the left or right
if displacement_x < 0:
print("Eyes are looking to the left.")
elif displacement_x > 0:
print("Eyes are looking to the right.")
def maxAndMin(featCoords,mult = 1):
adj = 10/mult
listX = []
listY = []
for tup in featCoords:
listX.append(tup[0])
listY.append(tup[1])
maxminList = np.array([min(listX)-adj,min(listY)-adj,max(listX)+adj,max(listY)+adj])
print(maxminList)
return (maxminList*mult).astype(int), (np.array([sum(listX)/len(listX)-maxminList[0], sum(listY)/len(listY)-maxminList[1]])*mult).astype(int)
def findCircs(img):
circles = cv.HoughCircles(img, cv.HOUGH_GRADIENT, 2, 20, param1 = 200, param2 = 50, minRadius=1, maxRadius=40)#, minRadius = 0, maxRadius = 30)
# circles = np.uint16(np.around(circles))
return circles
def findBlobs(img):
params = cv.SimpleBlobDetector_Params()
params.minThreshold = 10
params.maxThreshold = 200
# params.filterByColor = True
# params.blobColor = 0
params.filterByArea = True
params.maxArea = 3000
# params.filterByCircularity = True
# params.minCircularity = 0.1
detector = cv.SimpleBlobDetector_create(params)
keypoints = detector.detect(img)
# imkeypoints = cv.drawKeypoints(img, keypoints, np.array([]),
# (0, 0, 255),
# cv.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
return keypoints
def getWebcam(feed=False):
webcam = cv.VideoCapture(0)
# Frame coordinates go frame[y][x]
haventfoundeye = True
screenw = 1440
screenh = 900
while True:
ret, frame = webcam.read()
smallframe = cv.resize(copy.deepcopy(frame), (0,0), fy=.15, fx=.15)
smallframe = cv.cvtColor(smallframe, cv.COLOR_BGR2GRAY)
feats = face_recognition.face_landmarks(smallframe)
if len(feats) > 0:
leBds,leCenter = maxAndMin(feats[0]['left_eye'],mult = 1/.15)
# reBds,_ = maxAndMin(feats[0]['right_eye'])
# print(leBds)
left_eye = frame[leBds[1]:leBds[3], leBds[0]:leBds[2]]
# right_eye = frame[reBds[1]:reBds[3], reBds[0]:reBds[2]]
left_eye = cv.cvtColor(left_eye, cv.COLOR_BGR2GRAY)
ret, thresh = cv.threshold(left_eye, 50, 255, 0)
# Find weighted average for center of the eye
TMP = 255 - np.copy(thresh)#.astype(int)
# TMP = TMP[0:-1, 10:-10]
# cv.imshow("tmp", TMP)
# TMP = cv.blur(TMP, (3, 3))
y = np.sum(TMP, axis=1)
x = np.sum(TMP, axis=0)
# x = TMP[int(len(TMP)/2)]
y = y / len(TMP[0])
x = x / len(TMP)
y = y > np.average(y) + np.std(y)#*1.2
x = x > np.average(x) + np.std(x)#*1.2
try:
y = int(np.dot(np.arange(1, len(y) + 1), y) / sum(y))
except:
y = int(np.dot(np.arange(1, len(y) + 1), y) / 1)
try:
x = int(np.dot(np.arange(1, len(x) + 1), x) / sum(x))
except:
x = int(np.dot(np.arange(1, len(x) + 1), x) / 1)
haventfoundeye = False
left_eye = cv.cvtColor(left_eye, cv.COLOR_GRAY2BGR)
cv.circle(left_eye, (x, y), 2, (20, 20, 120), 3)
cv.circle(left_eye, (int(leCenter[0]), int(leCenter[1])), 2, (120, 20, 20), 3)
if feed:
cv.imshow('frame', left_eye)
if cv.waitKey(1) & 0xFF == ord('q'):
break
elif not haventfoundeye:
plt.imshow(left_eye)
plt.show()
return left_eye
def getEye(times = 1,frameShrink = 0.15, coords = (0,0), counterStart = 0, folder = "eyes"):
os.makedirs(folder, exist_ok=True)
webcam = cv.VideoCapture(0)
counter = counterStart
ims = []
while counter < counterStart+times:
ret, frame = webcam.read()
smallframe = cv.resize(copy.deepcopy(frame), (0, 0), fy=frameShrink, fx=frameShrink)
smallframe = cv.cvtColor(smallframe, cv.COLOR_BGR2GRAY)
feats = face_recognition.face_landmarks(smallframe)
if len(feats) > 0:
leBds, leCenter = maxAndMin(feats[0]['left_eye'], mult=1/frameShrink)
left_eye = frame[leBds[1]:leBds[3], leBds[0]:leBds[2]]
# right_eye = frame[reBds[1]:reBds[3], reBds[0]:reBds[2]]
left_eye = cv.cvtColor(left_eye, cv.COLOR_BGR2GRAY)
left_eye = cv.resize(left_eye, dsize=(100, 50))
# D
# isplay the image - DEBUGGING ONLY
cv.imshow('frame', left_eye)
if cv.waitKey(1) & 0xFF == ord('q'):
break
cv.imwrite(
folder + "/" + str(coords[0]) + "." + str(coords[1]) + "." + str(
counter) + ".jpg", left_eye)
counter += 1
# # 1440x900
# for i in [0,720,1440]:
# for j in [0,450,900]:q
for i in [404,951]:
for j in [383,767]:
print(i,j)
pyautogui.moveTo(i, j)
input("Press Enter to continue...")
pyautogui.moveTo(i, j)
getEye(times = 10, coords=(i,j),counterStart=0, folder = "testeyes")
import cv2
# Load the cascade
face_cascade = cv2.CascadeClassifier("haarcascade_frontalface_default.xml")
# Load the video
cap = cv2.VideoCapture(0)
# Get the video dimensions
width = int(cap.get(3))
height = int(cap.get(4))
# Define the center of the frame
center_x = width // 2
center_y = height // 2
while True:
# Read the frame
_, frame = cap.read()
# Convert to grayscale
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# Detect faces
faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5)
# Loop over the face detections
for (x, y, w, h) in faces:
cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 2)
# Get the center of the face
face_center_x = x + w // 2
face_center_y = y + h // 2
# Check the direction of the face
if face_center_x < center_x - 50:
print("Face is looking to the left.")
# Send an alert
#alert()
elif face_center_x > center_x + 50:
print("Face is looking to the right.")
# Send an alert
#alert()
else:
print("Face is looking straight ahead.")
# Show the frame
cv2.imshow("Face Detection", frame)
# Exit if the user presses 'q'
if cv2.waitKey(1) == ord('q'):
break
import cv2
# Load the pre-trained model
net = cv2.dnn.readNetFromCaffe("mobilenet_iter_73000.caffemodel")
# Load the video
cap = cv2.VideoCapture(0)
while True:
# Read the frame
_, frame = cap.read()
# Get the dimensions of the frame
height, width = frame.shape[:2]
# Create a blob from the frame
blob = cv2.dnn.blobFromImage(frame, 0.007843, (width, height), (127.5, 127.5, 127.5), False)
# Pass the blob through the model
net.setInput(blob)
detections = net.forward()
# Loop over the detections
for i in range(detections.shape[2]):
# Get the confidence of the detection
confidence = detections[0, 0, i, 2]
# Filter out weak detections
if confidence > 0.5:
# Get the class label of the detection
class_id = int(detections[0, 0, i, 1])
# Check if the class label is a mobile phone
if class_id == 7:
# Get the bounding box of the detection
x1 = int(detections[0, 0, i, 3] * width)
y1 = int(detections[0, 0, i, 4] * height)
x2 = int(detections[0, 0, i, 5] * width)
y2 = int(detections[0, 0, i, 6] * height)
# Draw a rectangle around the detection
cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 0, 255), 2)
# Show the frame
cv2.imshow("Mobile Phone Detection", frame)
# Exit if the user presses 'q'
if cv2.waitKey(1) == ord('q'):
break
import os
import numpy as np
import torch
import glob
import torch.nn as nn
from torchvision.transforms import transforms
from torch.utils.data import DataLoader
from torch.optim import Adam
from torch.autograd import Variable
import torchvision
import pathlib
# checking for device
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# Transforms
transformer = transforms.Compose([
transforms.Resize((150, 150)),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(), # 0-255 to 0-1, numpy to tensors
transforms.Normalize([0.5, 0.5, 0.5], # 0-1 to [-1,1] , formula (x-mean)/std
[0.5, 0.5, 0.5])
])
# Dataloader
# Path for training and testing directory
fo = open('paths', 'r').read().splitlines()
train_path = fo[0]
test_path = fo[1]
pred_path = fo[2]
# train_path='/home/r33j4n/Desktop/CNN/Train'
# test_path='/home/r33j4n/Desktop/CNN/Test'
train_loader = DataLoader(
torchvision.datasets.ImageFolder(train_path, transform=transformer),
batch_size=64, shuffle=True
)
test_loader = DataLoader(
torchvision.datasets.ImageFolder(test_path, transform=transformer),
batch_size=64, shuffle=True
)
# categories
root = pathlib.Path(train_path)
classes = sorted([j.name.split('/')[-1] for j in root.iterdir()])
# CNN Network
class ConvNet(nn.Module):
def __init__(self, num_classes=8):
super(ConvNet, self).__init__()
# Output size after convolution filter
# ((w-f+2P)/s) +1
# Input shape= (256,3,150,150)
self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=3, stride=1, padding=1)
# Shape= (256,12,150,150)
self.bn1 = nn.BatchNorm2d(num_features=12)
# Shape= (256,12,150,150)
self.relu1 = nn.ReLU()
# Shape= (256,12,150,150)
self.pool = nn.MaxPool2d(kernel_size=2)
# Reduce the image size be factor 2
# Shape= (256,12,75,75)
self.conv2 = nn.Conv2d(in_channels=12, out_channels=20, kernel_size=3, stride=1, padding=1)
# Shape= (256,20,75,75)
self.relu2 = nn.ReLU()
# Shape= (256,20,75,75)
self.conv3 = nn.Conv2d(in_channels=20, out_channels=32, kernel_size=3, stride=1, padding=1)
# Shape= (256,32,75,75)
self.bn3 = nn.BatchNorm2d(num_features=32)
# Shape= (256,32,75,75)
self.relu3 = nn.ReLU()
# Shape= (256,32,75,75)
self.fc = nn.Linear(in_features=75 * 75 * 32, out_features=num_classes)
# Feed forwad function
def forward(self, input):
output = self.conv1(input)
output = self.bn1(output)
output = self.relu1(output)
output = self.pool(output)
output = self.conv2(output)
output = self.relu2(output)
output = self.conv3(output)
output = self.bn3(output)
output = self.relu3(output)
# Above output will be in matrix form, with shape (256,32,75,75)
output = output.view(-1, 32 * 75 * 75)
output = self.fc(output)
return output
model = ConvNet(num_classes=8).to(device)
# Optmizer and loss function
optimizer = Adam(model.parameters(), lr=0.001, weight_decay=0.0001)
loss_function = nn.CrossEntropyLoss()
num_epochs = 15
# calculating the size of training and testing images
train_count = len(glob.glob(train_path + '/**/*.jpeg'))
test_count = len(glob.glob(test_path + '/**/*.jpeg'))
# Model training and saving best model
best_accuracy = 0.0
for epoch in range(num_epochs):
# Evaluation and training on training dataset
model.train()
train_accuracy = 0.0
train_loss = 0.0
for i, (images, labels) in enumerate(train_loader):
if torch.cuda.is_available():
images = Variable(images.cuda())
labels = Variable(labels.cuda())
optimizer.zero_grad()
outputs = model(images)
loss = loss_function(outputs, labels)
loss.backward()
optimizer.step()
train_loss += loss.cpu().data * images.size(0)
_, prediction = torch.max(outputs.data, 1)
train_accuracy += int(torch.sum(prediction == labels.data))
train_accuracy = train_accuracy / train_count
train_loss = train_loss / train_count
# Evaluation on testing dataset
model.eval()
test_accuracy = 0.0
for i, (images, labels) in enumerate(test_loader):
if torch.cuda.is_available():
images = Variable(images.cuda())
labels = Variable(labels.cuda())
outputs = model(images)
_, prediction = torch.max(outputs.data, 1)
test_accuracy += int(torch.sum(prediction == labels.data))
test_accuracy = test_accuracy / test_count
print('Epoch: ' + str(epoch) + ' Train Loss: ' + str(train_loss) + ' Train Accuracy: ' + str(
train_accuracy) + ' Test Accuracy: ' + str(test_accuracy))
# Save the best model
if test_accuracy > best_accuracy:
torch.save(model.state_dict(), 'best_checkpoint.model')
best_accuracy = test_accuracy
import cv2
# Load the pre-trained model
net = cv2.dnn.readNetFromCaffe("mobilenet_iter_73000.caffemodel")
# Load the video
cap = cv2.VideoCapture(0)
while True:
# Read the frame
_, frame = cap.read()
# Get the dimensions of the frame
height, width = frame.shape[:2]
# Create a blob from the frame
blob = cv2.dnn.blobFromImage(frame, 0.007843, (width, height), (127.5, 127.5, 127.5), False)
# Pass the blob through the model
net.setInput(blob)
detections = net.forward()
# Loop over the detections
for i in range(detections.shape[2]):
# Get the confidence of the detection
confidence = detections[0, 0, i, 2]
# Filter out weak detections
if confidence > 0.5:
# Get the class label of the detection
class_id = int(detections[0, 0, i, 1])
# Check if the class label is a mobile phone
if class_id == 7:
# Get the bounding box of the detection
x1 = int(detections[0, 0, i, 3] * width)
y1 = int(detections[0, 0, i, 4] * height)
x2 = int(detections[0, 0, i, 5] * width)
y2 = int(detections[0, 0, i, 6] * height)
# Draw a rectangle around the detection
cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 0, 255), 2)
# Show the frame
cv2.imshow("Mobile Phone Detection", frame)
# Exit if the user presses 'q'
if cv2.waitKey(1) == ord('q'):
break
import os
import numpy as np
import torch
import glob
import torch.nn as nn
from torchvision.transforms import transforms
from torch.utils.data import DataLoader
from torch.optim import Adam
from torch.autograd import Variable
import torchvision
import pathlib
# checking for device
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# Transforms
transformer = transforms.Compose([
transforms.Resize((150, 150)),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(), # 0-255 to 0-1, numpy to tensors
transforms.Normalize([0.5, 0.5, 0.5], # 0-1 to [-1,1] , formula (x-mean)/std
[0.5, 0.5, 0.5])
])
# Dataloader
# Path for training and testing directory
fo = open('paths', 'r').read().splitlines()
train_path = fo[0]
test_path = fo[1]
pred_path = fo[2]
# train_path='/home/r33j4n/Desktop/CNN/Train'
# test_path='/home/r33j4n/Desktop/CNN/Test'
train_loader = DataLoader(
torchvision.datasets.ImageFolder(train_path, transform=transformer),
batch_size=64, shuffle=True
)
test_loader = DataLoader(
torchvision.datasets.ImageFolder(test_path, transform=transformer),
batch_size=64, shuffle=True
)
# categories
root = pathlib.Path(train_path)
classes = sorted([j.name.split('/')[-1] for j in root.iterdir()])
# CNN Network
class ConvNet(nn.Module):
def __init__(self, num_classes=8):
super(ConvNet, self).__init__()
# Output size after convolution filter
# ((w-f+2P)/s) +1
# Input shape= (256,3,150,150)
self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=3, stride=1, padding=1)
# Shape= (256,12,150,150)
self.bn1 = nn.BatchNorm2d(num_features=12)
# Shape= (256,12,150,150)
self.relu1 = nn.ReLU()
# Shape= (256,12,150,150)
self.pool = nn.MaxPool2d(kernel_size=2)
# Reduce the image size be factor 2
# Shape= (256,12,75,75)
self.conv2 = nn.Conv2d(in_channels=12, out_channels=20, kernel_size=3, stride=1, padding=1)
# Shape= (256,20,75,75)
self.relu2 = nn.ReLU()
# Shape= (256,20,75,75)
self.conv3 = nn.Conv2d(in_channels=20, out_channels=32, kernel_size=3, stride=1, padding=1)
# Shape= (256,32,75,75)
self.bn3 = nn.BatchNorm2d(num_features=32)
# Shape= (256,32,75,75)
self.relu3 = nn.ReLU()
# Shape= (256,32,75,75)
self.fc = nn.Linear(in_features=75 * 75 * 32, out_features=num_classes)
# Feed forwad function
def forward(self, input):
output = self.conv1(input)
output = self.bn1(output)
output = self.relu1(output)
output = self.pool(output)
output = self.conv2(output)
output = self.relu2(output)
output = self.conv3(output)
output = self.bn3(output)
output = self.relu3(output)
# Above output will be in matrix form, with shape (256,32,75,75)
output = output.view(-1, 32 * 75 * 75)
output = self.fc(output)
return output
model = ConvNet(num_classes=8).to(device)
# Optmizer and loss function
optimizer = Adam(model.parameters(), lr=0.001, weight_decay=0.0001)
loss_function = nn.CrossEntropyLoss()
num_epochs = 15
# calculating the size of training and testing images
train_count = len(glob.glob(train_path + '/**/*.jpeg'))
test_count = len(glob.glob(test_path + '/**/*.jpeg'))
# Model training and saving best model
best_accuracy = 0.0
for epoch in range(num_epochs):
# Evaluation and training on training dataset
model.train()
train_accuracy = 0.0
train_loss = 0.0
for i, (images, labels) in enumerate(train_loader):
if torch.cuda.is_available():
images = Variable(images.cuda())
labels = Variable(labels.cuda())
optimizer.zero_grad()
outputs = model(images)
loss = loss_function(outputs, labels)
loss.backward()
optimizer.step()
train_loss += loss.cpu().data * images.size(0)
_, prediction = torch.max(outputs.data, 1)
train_accuracy += int(torch.sum(prediction == labels.data))
train_accuracy = train_accuracy / train_count
train_loss = train_loss / train_count
# Evaluation on testing dataset
model.eval()
test_accuracy = 0.0
for i, (images, labels) in enumerate(test_loader):
if torch.cuda.is_available():
images = Variable(images.cuda())
labels = Variable(labels.cuda())
outputs = model(images)
_, prediction = torch.max(outputs.data, 1)
test_accuracy += int(torch.sum(prediction == labels.data))
test_accuracy = test_accuracy / test_count
print('Epoch: ' + str(epoch) + ' Train Loss: ' + str(train_loss) + ' Train Accuracy: ' + str(
train_accuracy) + ' Test Accuracy: ' + str(test_accuracy))
# Save the best model
if test_accuracy > best_accuracy:
torch.save(model.state_dict(), 'best_checkpoint.model')
best_accuracy = test_accuracy
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment