File size: 5,403 Bytes
9066b94 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 |
# import the necessary packages
from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.models import load_model
from imutils.video import VideoStream
import numpy as np
import imutils
import time
import cv2
import os
import gradio as gr
# load our serialized face detector model from disk
prototxtPath = r"assets/model/deploy.prototxt.txt"
weightsPath = r"assets/model/res10_300x300_ssd_iter_140000.caffemodel"
faceNet = cv2.dnn.readNet(prototxtPath,weightsPath)
# load the face mask detector model from disk
maskNet = load_model("assets/model/mask_detector.keras")
def detect_and_predict_mask(frame, faceNet, maskNet):
try:
# grab the dimensions of the frame and then construct a blob from it
(h, w) = frame.shape[:2]
blob = cv2.dnn.blobFromImage(frame, 1.0, (224,224),(104.0,177.0,123.0) )
# pass the blob through the network and obtain the face detections
faceNet.setInput(blob)
detections = faceNet.forward()
print(detections.shape)
# initialize our list of faces, their corresponding locations, and the list of predictions from our face mask network
faces = []
locs = []
preds = []
# loop over the detections
for i in range(0,detections.shape[2]):
# extract the confidence (i.e., probability) associated with the detection
confidence = detections[0,0,i,2]
# filter out weak detections by ensuring the confidence is greater than minimum confidence
if confidence > 0.5:
# compute the (x, y)-cordinates of the bounding box for the object
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
# ensure the bounding boxes fall within the dimensions of the frame
(startX , startY) = (max(0,startX) , max(0,startY))
(endX, endY) = (min(w-1,endX) , min(h-1,endY))
# extract the face ROI, convert it from BGR to RGB channel ordering, resize it to 224x224, and preprocess it face=frame[startY:endY, startX:endX]
# bounding mask only for face detected
face = frame[startY:endY , startX:endX]
face = cv2.cvtColor(face, cv2.COLOR_BGR2RGB)
face = cv2.resize(face, (224,224))
face = img_to_array(face)
face = preprocess_input(face)
# add the face and bounding boxes to their respective lists
faces.append(face)
locs.append((startX, startY, endX, endY))
# only make a predictions if at least one face was detected
if len(faces) > 0:
# far faster inference we'll make batch predictions on *all* faces at the same time rather than one-by-one predictions in the above 'for' loop
faces = np.array(faces,dtype="float32")
preds = maskNet.predict(faces, batch_size=32)
# return a 2-tuple of the face locations and their corresponding locations
return (locs, preds)
except Exception as e:
print(e)
def webcam_stream(frame):
if type(frame)==type(None):
return
while True:
try:
# grab the frame from the threaded video stream and resize it to have a max width of 400 pixels
frame = imutils.resize(frame,width=400)
# detect faces in the frame and determine if they are wearing a face mask or not
(locs, preds) = detect_and_predict_mask(frame, faceNet, maskNet)
# loop over the detected face locations and their correspondings locations
for (box, pred) in zip(locs, preds):
# unpack the bounding box and predictions
(startX, startY, endX, endY) = box
(mask, withoutMask) = pred
# determine the class label and color we'll use to draw the bounding box and text
label = "Mask" if mask> withoutMask else "No Mask"
color = (0,255,0) if label=="Mask" else (0,0,255)
# include the probability in the label
label = "{}: {:.2f}%".format(label,max(mask, withoutMask) *100)
# display the label and bounding box rectangle on the output frame
cv2.putText(frame,label,(startX,startY-10), cv2.FONT_HERSHEY_SIMPLEX, 0.45, color, 2)
cv2.rectangle(frame, (startX,startY), (endX,endY),color,2)
# show the output frame
# cv2.imshow("Frame",frame)
# key = cv2.waitKey(1) & 0xFF
# if the 'q' key was pressed, break from the loop
# if key == ord("q"):
# break
except Exception as e:
print(e)
return frame
# do a bit of cleanup
# cv2.destroyAllWindows()
webcam = gr.Image(sources=["webcam"],streaming=True,every="float",mirror_webcam=True)
output = gr.Image(sources=["webcam"])
# Create a Gradio interface with the webcam_stream function
app = gr.Interface(webcam_stream,inputs=webcam,outputs=output,live=True)
# Start the app
app.launch()
gr.close_all() |