Я использую yolo - python для обнаружения объекта по нескольким изображениям.
Мне нужно перебрать результат (описать обнаруженный объект), чтобы записать этот результат в несколько текстовых файлов (одно имя с именем изображения).
Пример: 1.jpg обнаружил 1 машину и 1 собаку => 1.txt содержит машину и собаку.
я попытался создать несколько текстовых файлов с glob (входная папка с изображениями)
я пробовал циклически проходить текст (описывать обнаруженный объект), но я не могу записать результат каждого изображения в каждый текстовый файл. Что-то не так с петлей.
Пожалуйста, проверьте код внизу, часть cv2.putText.
import numpy as np
import argparse
import time
import cv2
import os, os.path
import glob
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--input", required=True,
help="path to input image")
ap.add_argument("-y", "--yolo", required=True,
help="base path to YOLO directory")
ap.add_argument("-c", "--confidence", type=float, default=0.5,
help="minimum probability to filter weak detections")
ap.add_argument("-t", "--threshold", type=float, default=0.3,
help="threshold when applyong non-maxima suppression")
args = vars(ap.parse_args())
num = 1
text_path_list = []
def create_result_text(textDir = "input"):
for i in glob.glob("input/*.jpg"):
f = open(i.rsplit( ".", 1 )[ 0 ] + ".txt", "w+")
f.close()
temp = os.listdir(textDir)
for i in temp:
if (i.endswith("txt")):
text_path_list.append(i)
create_result_text()
print(text_path_list)
# load the COCO class labels our YOLO model was trained on
labelsPath = os.path.sep.join([args["yolo"], "yolov3.txt"])
LABELS = open(labelsPath).read().strip().split("\n")
# initialize a list of colors to represent each possible class label
np.random.seed(42)
COLORS = np.random.randint(0, 255, size=(len(LABELS), 3),
dtype="uint8")
# derive the paths to the YOLO weights and model configuration
weightsPath = os.path.sep.join([args["yolo"], "yolov3.weights"])
configPath = os.path.sep.join([args["yolo"], "yolov3.cfg"])
# load our YOLO object detector trained on COCO dataset (80 classes)
print("[INFO] loading YOLO from disk...")
net = cv2.dnn.readNetFromDarknet(configPath, weightsPath)
# read input image
imageDir = "input" #specify your path here
image_path_list = []
valid_image_extensions = [".jpg", ".jpeg", ".png", ".tif", ".tiff"] #specify your vald extensions here
valid_image_extensions = [item.lower() for item in valid_image_extensions]
for file in os.listdir(imageDir):
extension = os.path.splitext(file)[1]
if extension.lower() not in valid_image_extensions:
continue
image_path_list.append(os.path.join(imageDir, file))
# load input image and grab its spatial dimensions
for imagePath in image_path_list:
image = cv2.imread(imagePath)
(H, W) = image.shape[:2]
# determine only the *output* layer names that we need from YOLO
ln = net.getLayerNames()
ln = [ln[i[0] - 1] for i in net.getUnconnectedOutLayers()]
# construct a blob from the input image and then perform a forward
# pass of the YOLO object detector, giving us our bounding boxes and
# associated probabilities
blob = cv2.dnn.blobFromImage(image, 1 / 255.0, (416, 416),
swapRB=True, crop=False)
net.setInput(blob)
start = time.time()
layerOutputs = net.forward(ln)
end = time.time()
# show timing information on YOLO
print("[INFO] YOLO took {:.6f} seconds".format(end - start))
# initialize our lists of detected bounding boxes, confidences, and
# class IDs, respectively
boxes = []
confidences = []
classIDs = []
# loop over each of the layer outputs
for output in layerOutputs:
# loop over each of the detections
for detection in output:
# extract the class ID and confidence (i.e., probability) of
# the current object detection
scores = detection[5:]
classID = np.argmax(scores)
confidence = scores[classID]
# filter out weak predictions by ensuring the detected
# probability is greater than the minimum probability
if confidence > args["confidence"]:
# scale the bounding box coordinates back relative to the
# size of the image, keeping in mind that YOLO actually
# returns the center (x, y)-coordinates of the bounding
# box followed by the boxes' width and height
box = detection[0:4] * np.array([W, H, W, H])
(centerX, centerY, width, height) = box.astype("int")
# use the center (x, y)-coordinates to derive the top and
# and left corner of the bounding box
x = int(centerX - (width / 2))
y = int(centerY - (height / 2))
# update our list of bounding box coordinates, confidences,
# and class IDs
boxes.append([x, y, int(width), int(height)])
confidences.append(float(confidence))
classIDs.append(classID)
# apply non-maxima suppression to suppress weak, overlapping bounding
# boxes
idxs = cv2.dnn.NMSBoxes(boxes, confidences, args["confidence"],
args["threshold"])
result_texts = []
# ensure at least one detection exists
if len(idxs) > 0:
# loop over the indexes we are keeping
for i in idxs.flatten():
# extract the bounding box coordinates
(x, y) = (boxes[i][0], boxes[i][1])
(w, h) = (boxes[i][2], boxes[i][3])
# draw a bounding box rectangle and label on the image
color = [int(c) for c in COLORS[classIDs[i]]]
cv2.rectangle(image, (x, y), (x + w, y + h), color, 2)
text = "{}: {:.4f}".format(LABELS[classIDs[i]], confidences[i])
cv2.putText(image, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX,
0.5, color, 2)
result_texts.append(text)
print(result_texts)
for text in result_texts:
np.savetxt("input/" + str(num) + ".txt", np.array(result_texts), fmt="%s")
num += 1
Я ожидаю, что у каждого текста есть имя объекта каждого изображения.
но весь текст имеет название объекта последнего изображения.