我已经使用Nvidia Digits码头工人图片训练了自定义对象检测模型。现在,我想使用 only OpenCV python(即不是Caffe,TensorRT等)运行该模型,我能够使用OpenCV的DNN模块成功加载并运行我的模型,但是我必须删除最后一个“ deploy.prototxt”中名为“ ClusterDetections”的层,因为OpenCV不支持这种类型的层,从而引发错误:
无法在函数“ getLayerInstance”中创建类型为“ Python”的图层“ cluster”
如前所述,如果我从“ deploy.prototxt”中删除了不受支持的层,那么该错误就消失了,但是如果没有“ ClusterDetections”层,我将不熟悉net.forward()
返回的原始数据格式与网络的预期输出有很大不同。
运行print(print(detections[0,0,i,2])
(通常是每个类别的置信度分数)返回:
-11.059842 -14.562948 -14.037464 -13.557558 -13.167087 -12.759864 -12.131538 -11.58218 -11.353993 -11.398977 -11.459799 -11.529523 -11.670803 -11.776192 -12.514015 -14.56443 -16.339668 -16.761234 -18.237602 -20.796967 -13.148532 -5.987872
这可能只是意味着我传递给模型的图像中没有检测到任何对象,但是由于缺少“ ClusterDetection”层,我倾向于认为图像中可能检测到对象,而我我只是错误地解释了数据。
我尝试按照this post的建议在python中实现自定义检测群集功能,但无济于事。 Another solution我发现使用Caffe来实现不受支持的层。但是正如我之前提到的,对于我的应用程序,我只想使用OpenCV python来运行模型。在先前询问的related question中,有人告诉我使用OpenCV的“自定义层机制”。但是,即使在通读the documentation,之后,我仍然对使用所述层机制从头开始编写某些东西的方法还没有足够的了解。
基本上,我的问题是,有没有一种简单的方法可以补偿不受支持的“ ClusterDetections”层并仍然使用OpenCV运行我的对象检测模型?因为我找到的每个解决方案都不起作用,或者说您必须使用另一个库,例如Caffe或TensorRT。
这是我的代码,摘自this tutorial:
# import the necessary packages
import numpy as np
import argparse
import cv2
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
help="path to input image")
ap.add_argument("-p", "--prototxt", required=True,
help="path to Caffe 'deploy' prototxt file")
ap.add_argument("-m", "--model", required=True,
help="path to Caffe pre-trained model")
ap.add_argument("-c", "--confidence", type=float, default=0.2,
help="minimum probability to filter weak detections")
args = vars(ap.parse_args())
# initialize the list of class labels MobileNet SSD was trained to
# detect, then generate a set of bounding box colors for each class
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
"dog", "horse", "motorbike", "person", "pottedplant", "sheep",
"sofa", "train", "tvmonitor"]
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))
# load our serialized model from disk
print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])
# load the input image and construct an input blob for the image
# by resizing to a fixed 300x300 pixels and then normalizing it
# (note: normalization is done via the authors of the MobileNet SSD
# implementation)
image = cv2.imread(args["image"])
(h, w) = image.shape[:2]
blob = cv2.dnn.blobFromImage(cv2.resize(image, (1248, 352)), 0.007843,
(1248, 352), 127.5)
# pass the blob through the network and obtain the detections and
# predictions
print("[INFO] computing object detections...")
net.setInput(blob)
detections = net.forward()
# loop over the detections
for i in np.arange(0, detections.shape[2]):
# extract the confidence (i.e., probability) associated with the
# prediction
confidence = detections[0, 0, i, 2]
print(detections[0,0,i,2])
# filter out weak detections by ensuring the `confidence` is
# greater than the minimum confidence
if confidence > args["confidence"]:
# extract the index of the class label from the `detections`,
# then compute the (x, y)-coordinates of the bounding box for
# the object
idx = int(detections[0, 0, i, 1])
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
# display the prediction
label = "{}: {:.2f}%".format(CLASSES[idx], confidence * 100)
print("[INFO] {}".format(label))
cv2.rectangle(image, (startX, startY), (endX, endY),
COLORS[idx], 2)
y = startY - 15 if startY - 15 > 15 else startY + 15
cv2.putText(image, label, (startX, y),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)
# show the output image
cv2.imshow("Output", image)
cv2.waitKey(0)
Here是我在其上运行模型的图像。
我正在运行python 3.6和OpenCV 4.1.1。可以在Google驱动器here.
中找到重现我当前功能所需的文件。