# construct the training image generator for data augmentation
aug = ImageDataGenerator(rotation_range=20, width_shift_range=0.2,
height_shift_range=0.2, shear_range=0.15, zoom_range=0.15,
horizontal_flip=True, fill_mode="nearest")
# load the RGB means for the training set
means = json.loads(open(config.DATASET_MEAN).read())
# initialize the image preprocessors
sp = SimplePreprocessor(64, 64)
mp = MeanPreprocessor(means["R"], means["G"], means["B"])
iap = ImageToArrayPreprocessor()
# initialize the training and validation dataset generators
bs = 64
trainGen = HDF5DatasetGenerator(config.TRAIN_HDF5, batchSize=bs, aug=aug,
preprocessors=[sp, mp, iap], classes=config.NUM_CLASSES)
valGen = HDF5DatasetGenerator(config.VAL_HDF5, batchSize=bs,
preprocessors=[sp, mp, iap], classes=config.NUM_CLASSES)
# if there is no specific model checkpoint supplied, then initialize
# the network and compile the model
if args["model"] is None:
print("[INFO] compiling model...")
opt = Adam(lr=1e-3)
model = DeeperGoogLeNet.build(width=64, height=64, depth=3,
classes=config.NUM_CLASSES, reg=0.0002)
model.compile(loss="categorical_crossentropy", optimizer=opt,
metrics=["accuracy"])
# otherwise, load the checkpoint from disk
else:
print("[INFO] loading {}...".format(args["model"]))
# initialize the image preprocessors
sp = SimplePreprocessor(227, 227)
mp = MeanPreprocessor(means["R"], means["G"], means["B"])
cp = CropPreprocessor(227, 227)
iap = ImageToArrayPreprocessor()
# load the pretrained network
print("[INFO] loading model...")
model = load_model(config.MODEL_PATH)
# initialize the testing dataset generators, then make predictions on
# the testing data
print("[INFO] predicting on test data (no crops)...")
bs = 8
testGen = HDF5DatasetGenerator(config.TEST_HDF5,
batchSize=bs,
preprocessors=[sp, mp, iap],
classes=2)
predictions = model.predict_generator(testGen.generator(),
steps=testGen.numImages // bs,
max_queue_size=bs * 2)
# compute the rank-1 and rank-5 accuracies
(rank1, _) = rank5_accuracy(predictions, testGen.db["labels"])
print("[INFO] rank-1: {:.2f}%".format(rank1 * 100))
testGen.close()
# re-initialzie the testing set generator excluding the SimplePreprocessor
testGen = HDF5DatasetGenerator(config.TEST_HDF5,
batchSize=bs,
preprocessors=[mp],
classes=2)
args = vars(ap.parse_args())
# construct the training and testing image generators for data augmentation
# then initialize the image preprocessor
trainAug = ImageDataGenerator(rotation_range=10,
zoom_range=0.1,
horizontal_flip=True,
rescale=1 / 255.0,
fill_mode="nearest")
valAug = ImageDataGenerator(rescale=1 / 255.0)
iap = ImageToArrayPreprocessor()
# initialize the training and validation dataset generators
trainGen = HDF5DatasetGenerator(config.TRAIN_HDF5,
config.BATCH_SIZE,
aug=trainAug,
preprocessors=[iap],
classes=config.NUM_CLASSES)
valGen = HDF5DatasetGenerator(config.VAL_HDF5,
config.BATCH_SIZE,
aug=valAug,
preprocessors=[iap],
classes=config.NUM_CLASSES)
# if there is no specific model checkpoint supplied, then initialize the network
# and compile the model
if args["model"] is None:
print("Compiling model...")
model = EmotionVGGNet.build(width=48,
height=48,
depth=1,
# --model is the path to the specific model checkpoint to load
ap = argparse.ArgumentParser()
ap.add_argument("-m",
"--model",
type=str,
help="path to model checkpoint to load")
args = vars(ap.parse_args())
# initialize the testing data generator and image preprocessor
testAug = ImageDataGenerator(rescale=1 / 255.0)
iap = ImageToArrayPreprocessor()
# initialize the testing dataset generator
testGen = HDF5DatasetGenerator(config.TEST_HDF5,
config.BATCH_SIZE,
aug=testAug,
preprocessors=[iap],
classes=config.NUM_CLASSES)
# load the model from disk
print("Loading {}...".format(args["model"]))
model = load_model(args["model"])
# evaluate the network
(loss,
acc) = model.evaluate_generator(testGen.generator(),
steps=testGen.numImages // config.BATCH_SIZE,
max_queue_size=config.BATCH_SIZE * 2)
print("Accuracy: {:.2f}".format(acc * 100))
zoom_range=0.15,
width_shift_range=0.2,
height_shift_range=0.2,
shear_range=0.15,
horizontal_flip=True,
fill_mode="nearest")
iap = ImageToArrayPreprocessor()
pp = PatchPreprocessor(227, 227)
sp = SimplePreprocessor(227, 227)
mp = MeanPreprocessor(means["R"], means["G"], means["B"])
#initialize the dataset generators
#initialize the dataset generators
trainGen = HDF5DatasetGenerator(config.TRAIN_HDF5,
4,
aug=aug,
preprocessors=[pp, mp, iap],
classes=3)
valGen = HDF5DatasetGenerator(config.VAL_HDF5,
4,
aug=aug,
preprocessors=[sp, mp, iap],
classes=3)
#compile the model and do al the deep learning
optimizer = Adam(lr=1e-3)
model = AlexNet.build(width=227, height=227, depth=3, reg=0.0002, classes=3)
model.compile(loss="binary_crossentropy",
optimizer=optimizer,
metrics=["accuracy"])
#importing the necessasry libnrariea
from config import dogs_vs_cats_config as config
from utilities.preprocessing import CropPreprocessor
from utilities.preprocessing import MeanPreprocessor, ImageToArrayPreprocessor
from utilities.io import HDF5DatasetGenerator
from sklearn.metrics import classification_report
from keras.models import load_model
import json
import numpy as np
#brings in from the meanPreprocessor
means = json.loads(open(config.DATASET_MEAN).read())
mp = MeanPreprocessor(means['R'], means['G'], means['B'])
iap = ImageToArrayPreprocessor(227, 227)
cp = CropPreprocessor(227, 227)
model = load_model(config.MODEL_PATH)
#making a generator obhject
testGen = HDF5DatasetGenerator(config.TEST_HDF5,
32,
preprocessors=[mp],
classes=2)
predictions = []
for (images, labels) in testGen.generator(passes=1):
for image in images:
crops = cp.preprocess(image)
crops = np.array([iap.preprocess(c) for c in crops], dtype="float32")
pred = model.predict(crops)
predictions.append(pred.mean(axis=0))