print("[Info] compiling model...")
opt = SGD(lr=1e-1)
model = ResNet.build(32, 32, 3, 10, (9, 9, 9),
(64, 64, 128, 256), reg=0.0005)
model.compile(loss="categorical_crossentropy", optimizer=opt,
metrics=["accuracy"])
else:
print("[Info] load {}...".format(args["model"]))
model = load_model(args["model"])
# update the learning rate
print("[Info] old learn rate:{}".format(
K.get_value(model.optimizer.lr)))
K.set_value(model.optimizer.lr, 1e-2)
print("[Info] new learn rate:{}".format(
K.get_value(model.optimizer.lr)))
callbacks = [
EpochCheckpoint(args["checkpoints"], every=5,
startAt=args["start_epoch"]),
TrainingMonitor("output/resnet56_cifar10.png",
jsonPath="output/resnet56_cifar10.json",
startAt=args["start_epoch"])]
print("[Info] training network...")
model.fit_generator(
aug.flow(trainX, trainY, batch_size=128),
validation_data=(testX, testY),
steps_per_epoch=len(trainX) // 128, epochs=80,
callbacks=callbacks, verbose=1)
# initialize the label names for the CIFAR-10 dataset
labelNames = [
"airplane", "automobile", "bird", "cat", "deer", "dog", "frog", "horse",
"ship", "truck"
]
print("[INFO] compiling model... ")
opt = SGD(lr=0.01, momentum=0.9, nesterov=True)
model = MiniVGGNet.built(width=32, height=32, depth=3, classes=10)
model.compile(loss="categorical_crossentropy",
optimizer=opt,
metrics=["accuracy"])
figPath = os.path.sep.join([args["output"], "{}.jpg".format(os.getpid())])
jsonPath = os.path.sep.join([args["output"], "{}.json".format(os.getpid())])
callbacks = [TrainingMonitor(figPath, jsonPath=jsonPath)]
print("[INFO] training network...")
model.fit(trainX,
trainY,
validation_data=(trainX, trainY),
batch_size=64,
epochs=100,
callbacks=callbacks,
verbose=1)
aug=aug,
preprocessors=[pp, mp, iap],
classes=2)
valGen = HDF5DatasetGenerator(config.VAL_HDF5,
bSize,
preprocessors=[sp, mp, iap],
classes=2)
# initialize the optimizer
opt = Adam(lr=1e-3)
model = AlexNet.build(width=227, height=227, depth=3, classes=2, reg=0.0002)
model.compile(loss="binary_crossentropy", optimizer=opt, metrics=["accuracy"])
# construct the set of callbacks
path = os.path.sep.join([config.OUTPUT_PATH, "{}.png".format(os.getpid())])
callbacks = [TrainingMonitor(path)]
# train the network
model.fit_generator(trainGen.generator(),
steps_per_epoch=trainGen.numImages // bSize,
validation_data=valGen.generator(),
validation_steps=valGen.numImages // bSize,
epochs=75,
max_queue_size=bSize * 2,
callbacks=callbacks,
verbose=1)
# save the model to file
print("[INFO] serializing model...")
model.save(config.MODEL_PATH, overwrite=True)
test_size=0.20,
stratify=labels,
random_state=42)
#initialize the model
print("[INFO] compiling model...")
model = MiniVGGNetwork.build(width=28, height=28, depth=1, classes=2)
model.compile(loss="binary_crossentropy",
optimizer="adam",
metrics=["accuracy"])
# construct the set of callbacks
# initialize the training monitor
figPath = os.path.sep.join([args["figure"], "{}.png".format(os.getpid())])
jsonPath = os.path.sep.join([args["figure"], "{}.json".format(os.getpid())])
training_monitor = TrainingMonitor(figPath=figPath, jsonPath=jsonPath)
# initialize the checkpoint improvements
checkpoint_improvements = ModelCheckpoint(args["model"],
monitor="val_loss",
mode="min",
save_best_only=True,
verbose=1)
# initialize the callbacks
callbacks = [training_monitor, checkpoint_improvements]
# train the network
print("[INFO] training network...")
H = model.fit(trainX,
trainY,
maxlen=length_max,
padding='post')
#X_test_pad = sequence.pad_sequences(X_test_tokens, maxlen=length_max, padding='post')
figPath = os.path.sep.join([
'/home/pavel/PycharmProjects/nn/pyimagesearch/plot/',
"{}_.png".format(os.getpid())
])
jsonPath = os.path.sep.join([
'/home/pavel/PycharmProjects/nn/pyimagesearch/plot/',
"{}.json".format(os.getpid())
])
optimizer = SGD(lr=0.01, momentum=0.9, nesterov=True)
callbacks = [
TrainingMonitor(jsonPath=jsonPath, figPath=figPath, val=False),
LearningRateScheduler(step_decay)
]
model = RnnForWord().build(vocab_size=vocabulary_size,
max_review_length=length_max,
embedding_vector_length=length_max)
print("[INFO] compiling model...")
model.compile(loss='binary_crossentropy',
optimizer=optimizer,
metrics=['accuracy'])
history = model.fit(X_train_bad,
y_train,
epochs=50,
batch_size=16,
callbacks=callbacks)
else:
print("[INFO] loading {}...".format(args["model"]))
model = load_model(args["model"])
# upate the learning rate
print("[INFO] old learning rate: {}".format(K.get_value(
model.optimizer.lr)))
K.set_value(model.optimizer.lr, 1e-5)
print("[INFO] new learning rate: {}".format(K.get_value(
model.optimizer.lr)))
# construct the set of callbacks
callbacks = [
EpochCheckpoint(args["checkpoints"], every=5, startAt=args["start_epoch"]),
TrainingMonitor(config.FIG_PATH,
jsonPath=config.JSON_PATH,
startAt=args["start_epoch"])
]
# train the network
model.fit_generator(trainGen.generator(),
steps_per_epoch=trainGen.numImages // 64,
validation_data=valGen.generator(),
validation_steps=valGen.numImages // 64,
epochs=10,
max_queue_size=64 * 2,
callbacks=callbacks,
verbose=1)
# close the database
trainGen.close()
train_generator = HDF5DatasetGenerator(db_path=configs.TRAIN_HDF5,
batch_size=configs.BATCH_SIZE,
preprocessors=[pp, mp, iap],
aug=aug,
binarize=True,
classes=2)
val_generator = HDF5DatasetGenerator(db_path=configs.TEST_HDF5,
batch_size=configs.BATCH_SIZE,
preprocessors=[sp, mp, iap],
aug=None,
binarize=True,
classes=2)
path = os.path.sep.join([configs.OUTPUT_PATH, f"{os.getpid()}.png"])
callbacks = [TrainingMonitor(plot_path=path)]
opt = Adam(lr=1e-3)
model = AlexNet.build(width=227, height=227, classes=configs.NUM_CLASSES)
model.compile(opt, loss="binary_crossentropy", metrics=["accuracy"])
model.fit(
train_generator.generate(),
epochs=EPOCH,
steps_per_epoch=train_generator.num_images // configs.BATCH_SIZE,
validation_steps=val_generator.num_images // configs.BATCH_SIZE,
validation_data=val_generator.generate(),
max_queue_size=configs.BATCH_SIZE * 2,
callbacks=callbacks,
)
else:
# load the checkpoint from disk
print("[INFO] loading {}...".format(args["model"]))
model = load_model(args["model"])
# update the learning rate
print("[INFO] old learning rate: {}".format(K.get_value(
model.optimizer.lr)))
K.set_value(model.optimizer.lr, 1e-2)
print("[INFO] new learning rate: {}".format(K.get_value(
model.optimizer.lr)))
# build the path to the training plot and training history
plotPath = os.path.sep.join(["output", "resnet_fashion_mnist.png"])
jsonPath = os.path.sep.join(["output", "resnet_fashion_mnist.json"])
# construct the set of callbacks
callbacks = [
EpochCheckpoint(args["checkpoints"], every=5, startAt=args["start_epoch"]),
TrainingMonitor(plotPath, jsonPath=jsonPath, startAt=args["start_epoch"])
]
# train the network
print("[INFO] training network...")
model.fit(x=aug.flow(trainX, trainY, batch_size=128),
validation_data=(testX, testY),
steps_per_epoch=len(trainX) // 128,
epochs=80,
callbacks=callbacks,
verbose=1)
# convert the labels from integers to vectors
lb = LabelBinarizer()
trainY = lb.fit_transform(trainY)
testY = lb.transform(testY)
# construct the image generator for data augmentation
aug = ImageDataGenerator(width_shift_range=0.1,
height_shift_range=0.1,
horizontal_flip=True,
fill_mode="nearest")
# construct the set of callbacks
figPath = os.path.sep.join([args["output"], "{}.png".format(os.getpid())])
jsonPath = os.path.sep.join([args["output"], "{}.png".format(os.getpid())])
callbacks = [
TrainingMonitor(figPath, jsonPath=jsonPath),
LearningRateScheduler(poly_decay)
]
# initialize the optimizer and model (ResNet-56)
print("[INFO] compiling model...")
opt = SGD(lr=INIT_LR, momentum=0.9)
model = ResNet.build(32, 32, 3, 10, (9, 9, 9), (64, 64, 128, 256), reg=0.0005)
model.compile(loss="categorical_crossentropy",
optimizer=opt,
metrics=["accuracy"])
# train the network
print("[INFO] training network...")
model.fit_generator(aug.flow(trainX, trainY, batch_size=128),
validation_data=(testX, testY),
lb = LabelBinarizer()
trainY = lb.fit_transform(trainY)
testY = lb.transform(testY)
labelNames = [
"airplane", "automobile", "bird", "cat", "deer", "dog", "frog", "horse",
"ship", "truck"
]
print("[INFO] compiling model...")
opt = SGD(lr=0.01, momentum=0.9, nesterov=True)
model = MiniVGGNet.build(width=32, height=32, depth=3, classes=10)
model.compile(loss="categorical_crossentropy",
optimizer=opt,
metrics=["accuracy"])
figPath = os.path.sep.join([args["output"], "{}_.png".format(os.getpid())])
jsonPath = os.path.sep.join([args["output"], "{}.json".format(os.getpid())])
callbacks = [
TrainingMonitor(jsonPath=jsonPath, figPath=figPath),
LearningRateScheduler(step_decay)
]
model.fit(trainX,
trainY,
validation_data=(testX, testY),
batch_size=64,
epochs=40,
callbacks=callbacks,
verbose=1)
# Run model
model = main_model()
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
plotPath = os.path.sep.join(["output", "CNN.png"])
jsonPath = os.path.sep.join(["output", "CNN.json"])
callbacks = [
CSVLogger('log_%d_%d.csv' % (BATCH_SIZE, EPOCHS),
append=True,
separator=';'),
EpochCheckpoint(args["checkpoints"], every=5, startAt=0),
TrainingMonitor(plotPath, jsonPath=jsonPath, startAt=0),
]
#model.fit(model_train, [y_train, y_train],
# batch_size=BATCH_SIZE,
# epochs=EPOCHS,
# validation_data=(model_val, [y_val, y_val]))
model.fit(model_train,
y_train,
batch_size=BATCH_SIZE,
epochs=EPOCHS,
validation_data=(model_val, y_val),
callbacks=[csv_logger])
model.predict()
if args["model"] is None:
print("[Info] compiling model...")
opt = SGD(lr=INIT_LR, momentum=0.9)
model = ResNet.build(32, 32, 3, 10, (9, 9, 9),
(64, 64, 128, 256), reg=0.0005)
model.compile(loss="categorical_crossentropy", optimizer=opt,
metrics=["accuracy"])
else:
print("[Info] load {}...".format(args["model"]))
model = load_model(args["model"])
# update the learning rate
print("[Info] old learn rate:{}".format(
K.get_value(model.optimizer.lr)))
K.set_value(model.optimizer.lr, 1e-5)
print("[Info] new learn rate:{}".format(
K.get_value(model.optimizer.lr)))
callbacks = [
TrainingMonitor("output/resnet56_cifar10.png",
jsonPath="output/resnet56_cifar10.json"),
LearningRateScheduler(poly_decay)]
print("[Info] training network...")
model.fit_generator(
aug.flow(trainX, trainY, batch_size=128),
validation_data=(testX, testY),
steps_per_epoch=len(trainX) // 128, epochs=80,
callbacks=callbacks, verbose=1)
fill_mode="nearest",
horizontal_flip=True,
preprocessing_function=train_preprocessors.preprocess)
val_aug = ImageDataGenerator(
preprocessing_function=val_preprocessors.preprocess)
train_generator = train_aug.flow_from_directory(directory=configs.TRAIN_IMAGE,
batch_size=configs.BATCH_SIZE)
val_generator = val_aug.flow_from_directory(directory=configs.TEST_IMAGE,
batch_size=configs.BATCH_SIZE)
# callback
path = os.path.sep.join([configs.OUTPUT_PATH, f"{os.getpid()}.png"])
callbacks = [
TrainingMonitor(plot_path=path),
]
# initialize optimizer and model
opt = Adam(lr=1e-3)
model = AlexNet.build(width=227, height=227, classes=configs.NUM_CLASSES)
# compile and train model
model.compile(opt, loss="binary_crossentropy", metrics=["accuracy"])
model.fit(
train_generator,
epochs=EPOCH,
steps_per_epoch=train_generator.samples // configs.BATCH_SIZE,
validation_data=val_generator,
validation_steps=val_generator.samples // configs.BATCH_SIZE,
max_queue_size=configs.BATCH_SIZE * 2,