실습) Google Net

미리 학습된 GoogLeNet 학습 모델 및 구성 파일 다운로드

• Caffe Model Zoo: https://github.com/BVLC/caffe
  
  • 모델 파일: http://dl.caffe.berkeleyvision.org/bvlc_googlenet.caffemodel
  • 설정 https://github.com/BVLC/caffe/blob/master/models/bvlc_googlenet/ deployprototxt
• ONNX model zoo: https://github.com/onnx/models
  
  • 모델 파일: https://github.com/onnx/models/tree/master/vision/classification/inception_and_googlenet/googlenet
• 클래스 이름파일:
  
  • 1~1000번 클래스에 대한 설명을 저장한 텍스트 파일
  • https://github.com/opencv/opencv/blob/4.1.0/samples/data/dnn/ classification_classes_ILSVRC2012.txt

 

# Load input image
filename = 'space_shuttle.jpg'
if len(sys.argv) > 1:
	filename = sys.argv[1]

# Load network
model = 'googlenet/bvlc_googlenet.caffemodel'
config = 'googlenet/deploy.prototxt' 
#model = 'googlenet/inception-v1-9.onnx' 
#config = ''

net = cv2.dnn.readNet(model, config)

# Load class names
classNames = None
with open('classification_classes_ILSVRC2012.txt', 'rt') as f: 
	classNames = f.read().rstrip('\n').split('\n')
    
# Inference
blob = cv2.dnn.blobFromImage(img, 1, (224, 224), (104, 117, 123)) 
net.setInput(blob, 'data')
prob = net.forward()

out = prob.flatten() cla
ssId = np.argmax(out) co
nfidence = out[classId]

text = f'{classNames[classId]} ({confidence * 100:4.2f}%)'
cv2.putText(img, text, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 0, 255),
			1, cv2.LINE_AA)
            
cv2.imshow('img', img) 
cv2.waitKey() cv2.dest
royAllWindows()