width_shift_range=0.1,
height_shift_range=0.1,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True,
fill_mode="nearest")
# grab the list of images that we'll be describing, then extract
# the class label names from the image paths
print("[INFO] loading images...")
imagePaths = list(paths.list_images(args["dataset"]))
classNames = [pt.split(os.path.sep)[-2] for pt in imagePaths]
classNames = [str(x) for x in np.unique(classNames)]
# initialize the image preprocessors
aap = AspectAwarePreprocessor(224, 224)
iap = ImageToArrayPreprocessor()
# load the dataset from disk then scale the raw pixel intensities to
# the range [0, 1]
sdl = SimpleDatasetLoader(preprocessors=[aap, iap])
(data, labels) = sdl.load(imagePaths, verbose=500)
data = data.astype("float") / 255.0
# partition the data into training and testing split using 75% of
# the data for training and the remaining 25% for testing
(trainX, testX, trainY, testY) = train_test_split(data,
labels,
test_size=0.25,
random_state=42)
from imutils import paths
import matplotlib.pyplot as plt
import numpy as np
import argparse
import os
ap = argparse.ArgumentParser()
ap.add_argument("-d", "--dataset", required=True, help="path to input dataset")
args = vars(ap.parse_args())
print("[INFO] loading images ...")
imagePaths = list(paths.list_images(args["dataset"]))
classNames = [pt.split(os.path.sep)[-2] for pt in imagePaths]
classNames = [str(x) for x in np.unique(classNames)]
aap = AspectAwarePreprocessor(64, 64)
iap = ImageToArrayPreprocessor()
sdl = SimpleDatasetLoader(preprocessors=[aap, iap])
(data, labels) = sdl.load(imagePaths, verbose=500)
data = data.astype("float") / 255.0
(trainX, testX, trainY, testY) = train_test_split(data,
labels,
test_size=0.25,
random_state=42)
trainY = LabelBinarizer().fit_transform(trainY)
testY = LabelBinarizer().fit_transform(testY)
print("[INFO] compiling model ...")
split = train_test_split(trainPaths,
trainLabels,
test_size=config.NUM_VAL_IMAGES,
stratify=trainLabels,
random_state=42)
(trainPaths, valPaths, trainLabels, valLabels) = split
# construct a list pairing the training, validation, and testing
# image paths along with their corresponding labels and output HDF5
# files
datasets = [("train", trainPaths, trainLabels, config.TRAIN_HDF5),
("val", valPaths, valLabels, config.VAL_HDF5),
("test", testPaths, testLabels, config.TEST_HDF5)]
# initialize the image preprocessor and the lists of RGB chanel averages
aap = AspectAwarePreprocessor(256, 256)
(R, G, B) = ([], [], [])
# loop over the dataset tuples
for (dType, paths, labels, outputPath) in datasets:
# create HDF5 writer
print("[INFO] building {} ...".format(outputPath))
writer = HDF5DatasetWriter((len(paths), 256, 256, 3), outputPath)
# initialize the progress bar
widgets = [
"Building Dataset: ",
progressbar.Percentage(), " ",
progressbar.Bar(), " ",
progressbar.ETA()
]
train_label,
test_size=configs.VAL_SPLIT,
stratify=train_label,
random_state=42)
datasets = [
("train", train_path, train_label, configs.TRAIN_IMAGE),
("test", test_path, test_label, configs.TEST_IMAGE),
("val", val_path, val_label, configs.VAL_IMAGE),
]
# initialize the array to store training dataset's image channel
# and also initialize the preprocessor to use on all image
(R, G, B) = ([], [], [])
aap = AspectAwarePreprocessor(width=configs.IMAGE_WIDTH,
height=configs.IMAGE_HEIGHT,
interpolation=configs.INTERPOLATION)
# loop over each dataset group(train, val, test)
for (d_type, paths, labels, output_path) in datasets:
# construct image shape and initialize the dataset writer class
input_shape = (len(paths), configs.IMAGE_HEIGHT, configs.IMAGE_WIDTH, 3)
db = SimpleDatasetWriter(np.unique(train_label), parent_dir=output_path)
# displays progress
print(f"[INFO] building {output_path}")
widgets = [
"Building dataset: ",
progressbar.Percentage(), " ",
progressbar.Bar(), " ",
default=200,
help="width size")
ap.add_argument("-hs",
"--height",
required=False,
default=200,
help="height size")
args = vars(ap.parse_args())
# grab the image paths then initialize the dictionary of character
# counts
imagePaths = list(paths.list_images(args["input"]))
count = 0
# initiate aspectawarepreprocessor
aap = AspectAwarePreprocessor(args["width"], args["height"])
# loop over the image paths
for (i, imagePath) in enumerate(imagePaths):
# display an update to the user
print("[INFO] processing image {}/{}".format(i + 1, len(imagePaths)))
try:
# load the image
image = cv2.imread(imagePath)
# resize the image
image = aap.preprocess(image)
# construct the path the output directory
dirPath = os.path.join(args["annot"], args["folder"])