#----------------------------------------------------#
# 对视频中的predict.py进行了修改，
# 将单张图片预测、摄像头检测和FPS测试功能
# 整合到了一个py文件中，通过指定mode进行模式的修改。
#----------------------------------------------------#
import time
import cv2
import numpy as np
from retinaface import Retinaface
if __name__ == "__main__":
retinaface = Retinaface()
#-------------------------------------------------------------------------#
# mode用于指定测试的模式：
# 'predict'表示单张图片预测
# 'video'表示视频检测
# 'fps'表示测试fps
#-------------------------------------------------------------------------#
mode = "predict"
#-------------------------------------------------------------------------#
# video_path用于指定视频的路径，当video_path=0时表示检测摄像头
# video_save_path表示视频保存的路径，当video_save_path=""时表示不保存
# video_fps用于保存的视频的fps
# video_path、video_save_path和video_fps仅在mode='video'时有效
# 保存视频时需要ctrl+c退出才会完成完整的保存步骤，不可直接结束程序。
#-------------------------------------------------------------------------#
video_path = 0
video_save_path = ""
video_fps = 25.0
import tensorflow as tf
import tqdm
from retinaface import Retinaface
from utils.utils_map import evaluation
gpus = tf.config.experimental.list_physical_devices(device_type='GPU')
for gpu in gpus:
tf.config.experimental.set_memory_growth(gpu, True)
#-------------------------------------------#
# 进行retinaface的map计算
# 需要现在retinaface.py里面修改model_path
#-------------------------------------------#
if __name__ == '__main__':
mAP_retinaface = Retinaface(confidence=0.01, nms_iou=0.5)
save_folder = './widerface_evaluate/widerface_txt/'
gt_dir = "./widerface_evaluate/ground_truth/"
imgs_folder = './data/widerface/val/images/'
sub_folders = os.listdir(imgs_folder)
test_dataset = []
for sub_folder in sub_folders:
image_names = os.listdir(os.path.join(imgs_folder, sub_folder))
for image_name in image_names:
test_dataset.append(os.path.join(sub_folder, image_name))
num_images = len(test_dataset)
for img_name in tqdm.tqdm(test_dataset):
image = cv2.imread(os.path.join(imgs_folder, img_name))
#-------------------------------------#
# 调用摄像头检测
#-------------------------------------#
from retinaface import Retinaface
from PIL import Image
import numpy as np
import tensorflow as tf
import time
import cv2
gpus = tf.config.experimental.list_physical_devices(device_type='GPU')
for gpu in gpus:
tf.config.experimental.set_memory_growth(gpu, True)
retinaface = Retinaface()
# 调用摄像头
capture = cv2.VideoCapture(0) # capture=cv2.VideoCapture("1.mp4")
fps = 0.0
while (True):
t1 = time.time()
# 读取某一帧
ref, frame = capture.read()
# 格式转变，BGRtoRGB
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
# 进行检测
frame = np.array(retinaface.detect_image(frame))
# RGBtoBGR满足opencv显示格式
frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
import os
from retinaface import Retinaface
'''
在更换facenet网络后一定要重新进行人脸编码，运行encoding.py。
'''
retinaface = Retinaface(1)
list_dir = os.listdir("face_dataset")
image_paths = []
names = []
for name in list_dir:
image_paths.append("face_dataset/" + name)
names.append(name.split("_")[0])
retinaface.encode_face_dataset(image_paths, names)
'''
predict.py有几个注意点
1、无法进行批量预测，如果想要批量预测，可以利用os.listdir()遍历文件夹，利用cv2.imread打开图片文件进行预测。
2、如果想要保存，利用cv2.imwrite("img.jpg", r_image)即可保存。
3、如果想要获得框的坐标，可以进入detect_image函数，读取(b[0], b[1]), (b[2], b[3])这四个值。
4、如果想要截取下目标，可以利用获取到的(b[0], b[1]), (b[2], b[3])这四个值在原图上利用矩阵的方式进行截取。
'''
import cv2
from retinaface import Retinaface
retinaface = Retinaface()
while True:
img = input('Input image filename:')
image = cv2.imread(img)
if image is None:
print('Open Error! Try again!')
continue
else:
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
r_image = retinaface.detect_image(image)
r_image = cv2.cvtColor(r_image, cv2.COLOR_RGB2BGR)
cv2.imshow("after", r_image)
cv2.waitKey(0)
from predict import norm_size
import numpy as np
import tensorflow as tf
from keras.preprocessing.image import img_to_array
import imutils
import time
import cv2
from lenet import LeNet
from train import CLASS_NUM
mp = {'[0]': 'sun', '[1]': 'wang', '[2]': 'gong', '[3]': 'xie', '[4]': 'xu'}
gpus = tf.config.experimental.list_physical_devices(device_type='GPU')
for gpu in gpus:
tf.config.experimental.set_memory_growth(gpu, True)
retinaface = Retinaface()
MODEL = 'ResNet'
# model = load_model("test_sign.model") ## TODO: TEMP
if MODEL == 'LeNet':
model = LeNet.build(width=norm_size,
height=norm_size,
depth=3,
classes=CLASS_NUM)
else:
###
from keras.applications.resnet50 import ResNet50
from keras.preprocessing import image
from keras.models import Model
from keras.layers import Dense, GlobalAveragePooling2D
from keras import backend as K
import tensorflow as tf
import keras
from urllib import request
import configs
from retinaface import Retinaface
app = flask.Flask(__name__)
global graph, sess
graph = tf.get_default_graph()
sess = keras.backend.get_session()
with sess.as_default():
with graph.as_default():
retinaface = Retinaface()
@app.route('/face_detection')
def face_detection():
ans = {'status': 200, 'err_msg': ''}
try:
image_path = flask.request.args.get('image_path')
face_image = configs.get_url + '/' + image_path
face_image = request.urlopen(face_image)
face_image = cv2.imdecode(
np.asarray(bytearray(face_image.read()), dtype="uint8"),
cv2.IMREAD_COLOR)
face_image = cv2.cvtColor(face_image, cv2.COLOR_BGR2RGB)
print(face_image.shape)
with graph.as_default():