def test_pretrained(self):
# Load efficientdet pretrained on VOC2007
model = EfficientDet.from_pretrained('D0-VOC', score_threshold=.6)
print('Done loading...')
image = io.load_image('test/data/VOC2007/JPEGImages/000002.jpg',
(model.config.input_size, ) * 2)
n_image = normalize_image(image)
n_image = tf.expand_dims(n_image, axis=0)
classes = voc.IDX_2_LABEL
boxes, labels, scores = model(n_image, training=False)
labels = [classes[l] for l in labels[0]]
im = image.numpy()
for l, box, s in zip(labels, boxes[0].numpy(), scores[0]):
x1, y1, x2, y2 = box.astype('int32')
cv2.rectangle(im, (x1, y1), (x2, y2), (0, 255, 0), 2)
cv2.putText(im, l + ' {:.2f}'.format(s), (x1, y1 - 10),
cv2.FONT_HERSHEY_PLAIN, 2, (0, 255, 0), 2)
plt.imshow(im)
plt.axis('off')
plt.savefig('test.png')
plt.show(block=True)
def test_keras_pretrained(self):
# Load efficientdet pretrained on VOC2007
model = EfficientDet(D=0,
num_classes=20,
weights='D0-VOC',
score_threshold=.4)
print('Done loading...')
image = io.load_image('imgs/cat-dog.jpg', model.config.input_size)
n_image = normalize_image(image)
n_image = tf.expand_dims(n_image, axis=0)
classes = voc.IDX_2_LABEL
boxes, labels, scores = model(n_image, training=False)
labels = [classes[l] for l in labels[0]]
colors = visualizer.colors_per_labels(labels)
im = visualizer.draw_boxes(image,
boxes[0],
labels,
scores[0],
colors=colors)
plt.imshow(im)
plt.axis('off')
plt.savefig('test.png')
plt.show(block=True)
from efficientdet import EfficientDet
import tensorflow as tf
from PIL import Image
import numpy as np
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)
efficientdet = EfficientDet()
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)
# 转变成Image
frame = Image.fromarray(np.uint8(frame))
# 进行检测
frame = np.array(efficientdet.detect_image(frame))
# RGBtoBGR满足opencv显示格式
frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
fps = (fps + (1. / (time.time() - t1))) / 2
print("fps= %.2f" % (fps))
from efficientdet import EfficientDet
from PIL import Image
import tensorflow as tf
gpus = tf.config.experimental.list_physical_devices(device_type='GPU')
for gpu in gpus:
tf.config.experimental.set_memory_growth(gpu, True)
efficientdet = EfficientDet()
# while True:
# img = "./VOCdevkit_test/VOC2007/JPEGImages/000008.jpg"
# try:
# image = Image.open(img)
# except:
# print('Open Error! Try again!')
# else:
# r_image = efficientdet.detect_image(image)
# r_image.save("img/000008.jpg")
test_img_files = open('./pascal_voc_testing_data.txt')
test_img_dir = './VOCdevkit_test/VOC2007/JPEGImages/'
test_images = []
for line in test_img_files:
line = line.strip()
ss = line.split(' ')
test_images.append(ss[0])
output_file = open('./test_prediction.txt', 'w')
for img_name in test_images:
img = test_img_dir + img_name
#-------------------------------------#
# 对单张图片进行预测
#-------------------------------------#
from efficientdet import EfficientDet
from PIL import Image
efficientdet = EfficientDet()
while True:
img = input('Input image filename:')
try:
image = Image.open(img)
except:
print('Open Error! Try again!')
continue
else:
r_image = efficientdet.detect_image(image)
r_image.show()
#-------------------------------------#
# 对单张图片进行预测
#-------------------------------------#
from efficientdet import EfficientDet
from PIL import Image
efficientdet = EfficientDet(
'./logs/Epoch29-Total_Loss0.7971-Val_Loss0.7432.pth')
while True:
img = input('Input image filename:')
try:
image = Image.open(img)
except:
print('Open Error! Try again!')
continue
else:
r_image = efficientdet.detect_image(image)
r_image.show()
from keras.layers import Input
from efficientdet import EfficientDet
from PIL import Image
import numpy as np
import time
import cv2
efficientdet = EfficientDet()
# 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)
# 转变成Image
frame = Image.fromarray(np.uint8(frame))
# 进行检测
frame = np.array(efficientdet.detect_image(frame))
# RGBtoBGR满足opencv显示格式
frame = cv2.cvtColor(frame,cv2.COLOR_RGB2BGR)
fps = ( fps + (1./(time.time()-t1)) ) / 2
print("fps= %.2f"%(fps))
frame = cv2.putText(frame, "fps= %.2f"%(fps), (0, 40), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
help='do you have a gpu?',
default=True)
parser.add_argument('-n',
"--num2show",
type=int,
help='num img 2 show',
default=1)
parser.add_argument('-r',
"--root",
type=str,
help='root dir filled with *.jpg')
parser.add_argument('-i', "--filename", type=str, help='filename', default='')
args = parser.parse_args()
efficientdet = EfficientDet(args.model_path, args.version, args.conf,
args.cuda)
if args.num2show == 1:
image = Image.open(os.path.join(args.root, args.filename))
res, cls, score = efficientdet.detect_image(image)
print(cls, score)
# r_image.show()
else:
print('结果将会保存到temp.png')
files = os.listdir(args.root)
idx = [
int(len(os.listdir(args.root)) * random.random())
for i in range(args.num2show)
]
imgs = [Image.open(os.path.join(args.root, files[id])) for id in idx]
from efficientdet import EfficientDet
from efficientdet.data import preprocess
from efficientdet.utils.io import load_image
from efficientdet.data.voc import IDX_2_LABEL
# import efficientdet
print(hub.__version__)
print(tf.__version__)
model_url = "https://tfhub.dev/tensorflow/efficientdet/d3/1"
# base_model = hub.KerasLayer(model_url, input_shape=(299, 299, 3))
# base_model = hub.load(model_url)
# print(base_model.summary())
"""my_model = tf.keras.applications.VGG16()
print(my_model.summary())
"""
"""hub_layer = hub.KerasLayer(model_url, output_shape=[20], input_shape=[], dtype=tf.string, trainable=True)
model = tf.keras.Sequential()
model.add(hub_layer)
model.add(tf.keras.layers.Dense(16, activation="relu", input_shape=[20]))
model.add(tf.keras.layers.Dense(1, activation="sigmoid"))
print(model.summary())"""
"""bla = tarfile.open("efficientdet-d0.tar.gz")
bla.extractall()
print(bla)
print("done")"""
model = EfficientDet.from_pretrained("D0-VOC", score_threshold=0.3)
image_size = model.config.input_size
print(image_size)
from efficientdet import EfficientDet
from PIL import Image
efficientdet = EfficientDet()
while True:
img = input('Input image filename:')
try:
image = Image.open(img)
except:
print('Open Error! Try again!')
continue
else:
r_image = efficientdet.detect_image(image)
r_image.show()
efficientdet.close_session()
# In[ ]:
from efficientdet import visualizer
from efficientdet import EfficientDet
from efficientdet.data import preprocess
from efficientdet.utils.io import load_image
from efficientdet.data.voc import IDX_2_LABEL
import tensorflow as tf
# In[3]:
model = EfficientDet.from_pretrained('D0-VOC', score_threshold=.3)
image_size = model.config.input_size
# In[4]:
image = load_image('sample.jpg', image_size)
image.shape
# In[ ]:
n_image = preprocess.normalize_image(image)
n_image = tf.expand_dims(n_image, 0)
from efficientdet.utils import postprocess
import matplotlib.pyplot as plt
from torchvision import transforms
from dataset.augmentation import MaxSizeResizer, ToTensor, SquarePad, Augmenter
parser = argparse.ArgumentParser()
parser.add_argument('--input', default='data/letters/my/-11_issues.png')
parser.add_argument('--output', default='output.jpg')
parser.add_argument('--weights', default='model/letters-nandos-efficientdet-d0-e3000.pth')
parser.add_argument('--network', default='efficientdet-d0')
parser.add_argument('--num_classes', default=1)
args = parser.parse_args()
if __name__ == '__main__':
model = EfficientDet(args.num_classes, network=args.network)
model.load_state_dict(torch.load(args.weights))
model.eval()
image = cv2.imread(args.input)
transforms = transforms.Compose(
[
MaxSizeResizer(1280),
SquarePad(),
ToTensor(),
]
)
image = transforms({'image': image})['image'].float()
image = image.view(1, *image.size())
classes_, _, train_rects, output_rects = model(image.float())
out_classes, out_rects = postprocess(classes_[0], output_rects[0], 0.15)
#----------------------------------------------------#
# 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 PIL import Image
from efficientdet import EfficientDet
if __name__ == "__main__":
efficientdet = EfficientDet()
#-------------------------------------------------------------------------#
# 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 = ""
MaxSizeResizer(1280),
SquarePad(),
ToTensor(),
]))
elif args.dataset == 'letters':
train_dataset = LetterDataset(args.image_dir,
args.label_path,
device=device,
transform=transforms.Compose([
MaxSizeResizer(1536),
SquarePad(),
ToTensor(),
]))
model = EfficientDet(train_dataset.num_classes(),
network=args.network,
device=device).to(device)
model.eval()
init_epoch = 0
if args.checkpoint:
checkpoint_name = os.path.basename(args.checkpoint)
init_epoch = int(re.findall(r'e\d+', checkpoint_name)[0][1:])
model.load_state_dict(torch.load(args.checkpoint))
model.train()
optimizer = ranger(model.parameters(), 1e-3)
for e in range(init_epoch, args.epochs):
losses = []
for images, rects, classes in DataLoader(train_dataset, 1, False):