OpenCV_4.2.0/opencv-4.2.0/samples/dnn/classification.py

85 lines
3.7 KiB
Python
Raw Normal View History

2024-07-25 16:47:56 +08:00
import cv2 as cv
import argparse
import numpy as np
from common import *
backends = (cv.dnn.DNN_BACKEND_DEFAULT, cv.dnn.DNN_BACKEND_HALIDE, cv.dnn.DNN_BACKEND_INFERENCE_ENGINE, cv.dnn.DNN_BACKEND_OPENCV)
targets = (cv.dnn.DNN_TARGET_CPU, cv.dnn.DNN_TARGET_OPENCL, cv.dnn.DNN_TARGET_OPENCL_FP16, cv.dnn.DNN_TARGET_MYRIAD)
parser = argparse.ArgumentParser(add_help=False)
parser.add_argument('--zoo', default=os.path.join(os.path.dirname(os.path.abspath(__file__)), 'models.yml'),
help='An optional path to file with preprocessing parameters.')
parser.add_argument('--input', help='Path to input image or video file. Skip this argument to capture frames from a camera.')
parser.add_argument('--framework', choices=['caffe', 'tensorflow', 'torch', 'darknet'],
help='Optional name of an origin framework of the model. '
'Detect it automatically if it does not set.')
parser.add_argument('--backend', choices=backends, default=cv.dnn.DNN_BACKEND_DEFAULT, type=int,
help="Choose one of computation backends: "
"%d: automatically (by default), "
"%d: Halide language (http://halide-lang.org/), "
"%d: Intel's Deep Learning Inference Engine (https://software.intel.com/openvino-toolkit), "
"%d: OpenCV implementation" % backends)
parser.add_argument('--target', choices=targets, default=cv.dnn.DNN_TARGET_CPU, type=int,
help='Choose one of target computation devices: '
'%d: CPU target (by default), '
'%d: OpenCL, '
'%d: OpenCL fp16 (half-float precision), '
'%d: VPU' % targets)
args, _ = parser.parse_known_args()
add_preproc_args(args.zoo, parser, 'classification')
parser = argparse.ArgumentParser(parents=[parser],
description='Use this script to run classification deep learning networks using OpenCV.',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
args = parser.parse_args()
args.model = findFile(args.model)
args.config = findFile(args.config)
args.classes = findFile(args.classes)
# Load names of classes
classes = None
if args.classes:
with open(args.classes, 'rt') as f:
classes = f.read().rstrip('\n').split('\n')
# Load a network
net = cv.dnn.readNet(args.model, args.config, args.framework)
net.setPreferableBackend(args.backend)
net.setPreferableTarget(args.target)
winName = 'Deep learning image classification in OpenCV'
cv.namedWindow(winName, cv.WINDOW_NORMAL)
cap = cv.VideoCapture(args.input if args.input else 0)
while cv.waitKey(1) < 0:
hasFrame, frame = cap.read()
if not hasFrame:
cv.waitKey()
break
# Create a 4D blob from a frame.
inpWidth = args.width if args.width else frame.shape[1]
inpHeight = args.height if args.height else frame.shape[0]
blob = cv.dnn.blobFromImage(frame, args.scale, (inpWidth, inpHeight), args.mean, args.rgb, crop=False)
# Run a model
net.setInput(blob)
out = net.forward()
# Get a class with a highest score.
out = out.flatten()
classId = np.argmax(out)
confidence = out[classId]
# Put efficiency information.
t, _ = net.getPerfProfile()
label = 'Inference time: %.2f ms' % (t * 1000.0 / cv.getTickFrequency())
cv.putText(frame, label, (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0))
# Print predicted class.
label = '%s: %.4f' % (classes[classId] if classes else 'Class #%d' % classId, confidence)
cv.putText(frame, label, (0, 40), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0))
cv.imshow(winName, frame)