# -*- coding: utf-8 -*-
"""
Run a YOLO_v3 style detection model on test images.
"""
import cv2
import json
import colorsys
import os
import random
from timeit import time
from timeit import default_timer as timer ### to calculate FPS
import numpy as np
from keras import backend as K
from keras.models import load_model
from PIL import Image, ImageFont, ImageDraw
from yolo3.model import yolo_eval
from yolo3.utils import letterbox_image
class YOLO(object):
def __init__(self):
self.model_path = 'model_data/yolo.h5'
self.anchors_path = 'model_data/yolo_anchors.txt'
# self.classes_path = 'model_data/coco_classes.txt'
self.classes_path = 'model_data/voc_6c_classes.txt'
self.score = 0.3
self.iou = 0.5
self.class_names = self._get_class()
self.anchors = self._get_anchors()
self.sess = K.get_session()
self.model_image_size = (416, 416) # fixed size or (None, None)
self.is_fixed_size = self.model_image_size != (None, None)
self.boxes, self.scores, self.classes = self.generate()
def _get_class(self):
classes_path = os.path.expanduser(self.classes_path)
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
def _get_anchors(self):
anchors_path = os.path.expanduser(self.anchors_path)
with open(anchors_path) as f:
anchors = f.readline()
anchors = [float(x) for x in anchors.split(',')]
anchors = np.array(anchors).reshape(-1, 2)
return anchors
def generate(self):
model_path = os.path.expanduser(self.model_path)
assert model_path.endswith('.h5'), 'Keras model must be a .h5 file.'
self.yolo_model = load_model(model_path, compile=False)
print('{} model, anchors, and classes loaded.'.format(model_path))
# Generate colors for drawing bounding boxes.
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(
map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
random.seed(10101) # Fixed seed for consistent colors across runs.
random.shuffle(self.colors) # Shuffle colors to decorrelate adjacent classes.
random.seed(None) # Reset seed to default.
# Generate output tensor targets for filtered bounding boxes.
self.input_image_shape = K.placeholder(shape=(2, ))
boxes, scores, classes = yolo_eval(self.yolo_model.output, self.anchors,
len(self.class_names), self.input_image_shape,
score_threshold=self.score, iou_threshold=self.iou)
return boxes, scores, classes
def detect_image(self, pathall):
image = Image.open(pathall)
start = time.time()
# imgcv = cv2.imread(image)##########
if self.is_fixed_size:
assert self.model_image_size[0]%32 == 0, 'Multiples of 32 required'
assert self.model_image_size[1]%32 == 0, 'Multiples of 32 required'
boxed_image = letterbox_image(image, tuple(reversed(self.model_image_size)))
else:
new_image_size = (image.width - (image.width % 32),
image.height - (image.height % 32))
boxed_image = letterbox_image(image, new_image_size)
image_data = np.array(boxed_image, dtype='float32')
print(image_data.shape)
image_data /= 255.
image_data = np.expand_dims(image_data, 0) # Add batch dimension.
out_boxes, out_scores, out_classes = self.sess.run(
[self.boxes, self.scores, self.classes],
feed_dict={
self.yolo_model.input: image_data,
self.input_image_shape: [image.size[1], image.size[0]],
K.learning_phase(): 0
})
print('Found {} boxes for {}'.format(len(out_boxes), 'img'))
font = ImageFont.truetype(font='font/FiraMono-Medium.otf',
size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
thickness = (image.size[0] + image.size[1]) // 300
resultsForJSON = []#+++
for i, c in reversed(list(enumerate(out_classes))):
predicted_class = self.class_names[c]
box = out_boxes[i]
score = out_scores[i]
label = '{} {:.2f}'.format(predicted_class, score)
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
top, left, bottom, right = box
top = max(0, np.floor(top + 0.5).astype('int32'))
left = max(0, np.floor(left + 0.5).astype('int32'))
bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))
right = min(image.size[0], np.floor(right + 0.5).astype('int32'))
print(label, (left, top), (right, bottom))
area=(bottom-top)*(right-left)#####+
resultsForJSON.append({"label": predicted_class,\
"confidence": float('%.2f' % score),\
"topleft": {"x": float(left), "y": float(top)},\
"bottomright": {"x": float(right), "y": float(bottom)},\
"area":float(area)})
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]])
else:
text_origin = np.array([left, top + 1])
# My kingdom for a good redistributable image drawing library.
for i in range(thickness):
draw.rectangle(
[left + i, top + i, right - i, bottom - i],
outline=self.colors[c])
draw.rectangle(
[tuple(text_origin), tuple(text_origin + label_size)],
fill=self.colors[c])
draw.text(text_origin, label, fill=(0, 0, 0), font=font)
del draw
end = time.time()
print(end - start)
####################保存json##########start
print(resultsForJSON)
imgdir = "/Users/sisyphus/keras-yolo3/" ###########+
outfolder = os.path.join(imgdir, 'out')
img_name = os.path.join(outfolder, os.path.basename(pathall))
# cv2.imwrite(img_name, image)
if resultsForJSON == []:
resultsForJSON.append({"label": "Normal",\
"confidence": float(0), \
"topleft": {"x": float(0), "y": float(0)}, \
"bottomright": {"x": float(0), "y": float(0)},\
"area":float(0)})
textJSON = json.dumps(resultsForJSON)
textFile = os.path.splitext(img_name)[0] + ".json"
print('\n')
with open(textFile, 'w') as f:
f.write(textJSON)
print('Normal\n')
else:
textJSON = json.dumps(resultsForJSON)
textFile = os.path.splitext(img_name)[0] + ".json"
print(textFile)
print('\n')
with open(textFile, 'w') as f:
f.write(textJSON)
####################保存json##########end
return image
def close_session(self):
self.sess.close()
def detect_image_video(self, image, curr_fps):
start = time.time()
if self.is_fixed_size:
assert self.model_image_size[0]%32 == 0, 'Multiples of 32 required'
assert self.model_image_size[1]%32 == 0, 'Multiples of 32 required'
boxed_image = letterbox_image(image, tuple(reversed(self.model_image_size)))
else:
new_image_size = (image.width - (image.width % 32),
image.height - (image.height % 32))
boxed_image = letterbox_image(image, new_image_size)
image_data = np.array(boxed_image, dtype='float32')
print(image_data.shape)
image_data /= 255.
image_data = np.expand_dims(image_data, 0) # Add batch dimension.
out_boxes, out_scores, out_classes = self.sess.run(
[self.boxes, self.scores, self.classes],
feed_dict={
self.yolo_model.input: image_data,
self.input_image_shape: [image.size[1], image.size[0]],
K.learning_phase(): 0
})
print('Found {} boxes for {}'.format(len(out_boxes), 'img'))
font = ImageFont.truetype(font='font/FiraMono-Medium.otf',
size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
thickness = (image.size[0] + image.size[1]) // 300
resultsForJSON = []#+++
for i, c in reversed(list(enumerate(out_classes))):
predicted_class = self.class_names[c]
box = out_boxes[i]
score = out_scores[i]
label = '{} {:.2f}'.format(predicted_class, score)
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
top, left, bottom, right = box
top = max(0, np.floor(top + 0.5).astype('int32'))
left = max(0, np.floor(left + 0.5).astype('int32'))
bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))
right = min(image.size[0], np.floor(right + 0.5).astype('int32'))
print(label, (left, top), (right, bottom))
area=(bottom-top)*(right-left)#####+
resultsForJSON.append({"label": predicted_class,\
"confidence": float('%.2f' % score),\
"topleft": {"x": float(left), "y": float(top)},\
"bottomright": {"x": float(right), "y": float(bottom)},\
"area":float(area)})
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]])
else:
text_origin = np.array([left, top + 1])
# My kingdom for a good redistributable image drawing library.
for i in range(thickness):
draw.rectangle(
[left + i, top + i, right - i, bottom - i],
outline=self.colors[c])
draw.rectangle(
[tuple(text_origin), tuple(text_origin + label_size)],
fill=self.colors[c])
draw.text(text_origin, label, fill=(0, 0, 0), font=font)
del draw
end = time.time()
print(end - start)
####################保存json##########start
print(resultsForJSON)
imgdir = "/Users/sisyphus/keras-yolo3/" ###########+
outfolder = os.path.join(imgdir, 'video_out/')
# img_name = os.path.join(outfolder, curr_fps)
# cv2.imwrite(img_name, image)
if resultsForJSON == []:
resultsForJSON.append({"label": "Normal",\
"confidence": float(0), \
"topleft": {"x": float(0), "y": float(0)}, \
"bottomright": {"x": float(0), "y": float(0)},\
"area":float(0)})
textJSON = json.dumps(resultsForJSON)
textFile = outfolder + str(curr_fps) + ".json"
print('\n')
with open(textFile, 'w') as f:
f.write(textJSON)
print('Normal\n')
else:
textJSON = json.dumps(resultsForJSON)
textFile = outfolder + str(curr_fps) + ".json"
print(textFile)
print('\n')
with open(textFile, 'w') as f:
f.write(textJSON)
####################保存json##########end
####################保存图片##########start
imgdir = "/Users/sisyphus/keras-yolo3/" ###########+
outfolder = os.path.join(imgdir, 'video_out/')
img_name = outfolder + str(curr_fps) + ".jpg"
image.save(img_name)
####################保存图片##########end
return image
def close_session(self):
self.sess.close()
def detect_video(yolo, video_path):
import cv2
vid = cv2.VideoCapture(video_path)
if not vid.isOpened():
raise IOError("Couldn't open webcam or video")
accum_time = 0
curr_fps = 0
fps = "FPS: ??"
prev_time = timer()
while True:
return_value, frame = vid.read()
# frame = np.asarray(frame)####+
image = Image.fromarray(frame)
image = yolo.detect_image_video(image, curr_fps)
result = np.asarray(image)
curr_time = timer()
exec_time = curr_time - prev_time
prev_time = curr_time
accum_time = accum_time + exec_time
curr_fps = curr_fps + 1
print(str(curr_fps)+"########")
if accum_time > 1:
accum_time = accum_time - 1
fps = "FPS: " + str(curr_fps)
# curr_fps = 0
cv2.putText(result, text=fps, org=(3, 15), fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=0.50, color=(255, 0, 0), thickness=2)
cv2.namedWindow("result", cv2.WINDOW_NORMAL)
cv2.imshow("result", result)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
# choice = cv2.waitKey(1)
# if choice == 27: break
# cap.release()
# cv2.destroyAllWindows()
yolo.close_session()
#def detect_img(yolo):
# while True:
# img = input('Input image filename:')
## img = "/Users/sisyphus/keras-yolo3/sample_img_test30/000271.jpg"
# try:
# image = Image.open(img)
# except:
# print('Open Error! Try again!')
# continue
# else:
# r_image = yolo.detect_image(image)
# r_image.show()
# yolo.close_session()
#####################################单张图片预测
#def detect_img(yolo):
# img = "/Users/sisyphus/keras-yolo3/sample_img_test30/000271.jpg"
# image = Image.open(img)
# r_image = yolo.detect_image(image)
# r_image.show()
####################################文件夹内所有图片预测
def detect_img(yolo):
imgdir = "/Users/sisyphus/keras-yolo3/" ###########+
outfolder = os.path.join(imgdir, 'out')
path = "/Users/sisyphus/keras-yolo3/sample_img_test1"
for xd in os.listdir(path):
print(xd)
print(os.path.join(path,xd))
pathall = os.path.join(path,xd)
r_image = yolo.detect_image(pathall)
# r_image.show()
img_name = os.path.join(outfolder, os.path.basename(pathall))
r_image.save(img_name)
if __name__ == '__main__':
detect_img(YOLO())
没有评论:
发表评论