我已经将Yolo模型转换为.tflite以便在android中使用。这就是它在python中的用法-
net = cv2.dnn.readNet("yolov2.weights", "yolov2.cfg")
classes = []
with open("yolov3.txt", "r") as f:
classes = [line.strip() for line in f.readlines()]
layer_names = net.getLayerNames()
output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]
colors = np.random.uniform(0, 255, size=(len(classes), 3))
cap= cv2.VideoCapture(0)
while True:
_,frame= cap.read()
height,width,channel= frame.shape
blob = cv2.dnn.blobFromImage(frame, 0.00392, (320, 320), (0, 0, 0), True, crop=False)
net.setInput(blob)
outs = net.forward(output_layers)
for out in outs:
for detection in out:
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence > 0.2:
# Object detected
center_x = int(detection[0] * width)
center_y = int(detection[1] * height)
w = int(detection[2] * width)
h = int(detection[3] * height)
# Rectangle coordinates
x = int(center_x - w / 2)
y = int(center_y - h / 2)
我用netron https://github.com/lutzroeder/netron来可视化模型。输入被描述为名称:输入, 类型:float32 [1,416,416,3], 量化:0≤q≤255, 位置:399 和输出为 名称:output_boxes, 类型:float32 [1,10647,8], 位置:400。
我的问题是关于在android中使用此模型。我已经在“ Interpreter tflite”中加载了模型,我正在以byte []格式从摄像机获取输入帧。如何将其转换为tflite.run(输入,输出)所需的输入?
答案 0 :(得分:1)
您需要调整输入图像的大小以与TensorFlow-Lite
模型的输入大小相匹配,然后将其转换为RGB
格式以提供给模型。
通过使用ImageProcessor
支持库中的TensorFlow-Lite
,您可以轻松地进行图像大小调整和转换。
ImageProcessor imageProcessor =
new ImageProcessor.Builder()
.add(new ResizeWithCropOrPadOp(cropSize, cropSize))
.add(new ResizeOp(imageSizeX, imageSizeY, ResizeMethod.NEAREST_NEIGHBOR))
.add(new Rot90Op(numRoration))
.add(getPreprocessNormalizeOp())
.build();
return imageProcessor.process(inputImageBuffer);
接下来要与解释器进行推理,您将预处理的图像馈送到TensorFlow-Lite
解释器:
tflite.run(inputImageBuffer.getBuffer(), outputProbabilityBuffer.getBuffer().rewind());