from pyimagesearch.nn.conv import shallownet
from keras.optimizers import SGD
from imutils import paths
import matplotlib.pyplot as plt
import numpy as np
import argparse
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"]))
sp = simplePreprocessor.SimplePreprocessor(32, 32)
iap = imagetoarraypreprocessor.ImageToArrayPreprocessor()
sdl = simpleDatasetLoader.SimpleDatasetLoader(preprocessors=[sp, iap])
(data, labels) = sdl.load(imagePaths, verbose=50)
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)
# initialize the network
from keras.preprocessing.image import ImageDataGenerator
from keras.optimizers import Adam
import json
import os
aug = ImageDataGenerator(rotation_range=20,
zoom_range=0.15,
width_shift_range=0.2,
height_shift_range=0.2,
shear_range=0.15,
horizontal_flip=True,
fill_mode="nearest")
means = json.loads(open(config.DATASET_MEAN).read())
sp = simplePreprocessor.SimplePreprocessor(227, 227)
pp = patchpreprocessor.PatchPreprocessor(227, 227)
mp = meanpreprocessor.MeanPreprocessor(means["R"], means["G"], means["B"])
iap = imagetoarraypreprocessor.ImageToArrayPreprocessor()
batchSize = 64
trainGen = hdf5datasetgenerator.HDF5DatasetGenerator(
config.TRAIN_HDF5,
batchSize,
aug=aug,
preprocessors=[pp, mp, iap],
classes=config.NUM_CLASSES)
valGen = hdf5datasetgenerator.HDF5DatasetGenerator(config.VAL_HDF5,
batchSize,
aug=aug,
from keras.optimizers import SGD
from keras.callbacks import LearningRateScheduler
import json
import os
aug = ImageDataGenerator(rotation_range=20,
zoom_range=0.15,
width_shift_range=0.2,
height_shift_range=0.2,
shear_range=0.15,
horizontal_flip=True,
fill_mode="nearest")
means = json.loads(open(config.DATASET_MEAN).read())
sp = simplePreprocessor.SimplePreprocessor(64, 64)
mp = meanpreprocessor.MeanPreprocessor(means["R"], means["G"], means["B"])
iap = imagetoarraypreprocessor.ImageToArrayPreprocessor()
batchSize = 32
trainGen = hdf5datasetgenerator.HDF5DatasetGenerator(
config.TRAIN_HDF5,
batchSize,
aug=aug,
preprocessors=[sp, mp, iap],
classes=config.NUM_CLASSES)
valGen = hdf5datasetgenerator.HDF5DatasetGenerator(config.VAL_HDF5,
batchSize,
aug=aug,
preprocessors=[sp, mp, iap],
help="path to output label binarizer")
args = vars(ap.parse_args())
inputWidth = 32
inputHeight = 32
inputDepth = 3
trainingEpochs = 500
print("[INFO] loading images...")
imagePaths = sorted(list(paths.list_images(args["dataset"])))
random.seed(42)
random.shuffle(imagePaths)
sp = simplePreprocessor.SimplePreprocessor(inputWidth, inputHeight)
iap = imagetoarraypreprocessor.ImageToArrayPreprocessor()
sdl = simpleDatasetLoader.SimpleDatasetLoader(preprocessors=[sp, iap])
(data, labels) = sdl.load(imagePaths, depth=inputDepth, verbose=100)
data = data.astype("float") / 255.0
classNames = sorted(list(set(labels)))
classes = len(classNames)
print(classNames)
labels = np.array(labels)
lb = LabelBinarizer()
labels = lb.fit_transform(labels)
print(lb.classes_)
args = vars(ap.parse_args())
aug = ImageDataGenerator(rotation_range=30,
width_shift_range=0.1,
height_shift_range=0.1,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True,
fill_mode="nearest")
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)]
sp = simplePreprocessor.SimplePreprocessor(224, 224)
iap = imagetoarraypreprocessor.ImageToArrayPreprocessor()
sdl = simpleDatasetLoader.SimpleDatasetLoader(preprocessors=[sp, iap])
(data, labels) = sdl.load(imagePaths, verbose=500)
data = data.astype("float") / 255.0
lb = LabelBinarizer()
labels = lb.fit_transform(labels)
(trainX, testX, trainY, testY) = train_test_split(data,
labels,
test_size=0.25,
random_state=42)
trainY = LabelBinarizer().fit_transform(trainY)