def train(trial: Trial):
context = Optuna.get_optuna_conext('minist_optuna', trial)
print("New trial ", trial.number, "++++++++++++++++++++++++++++", context)
ENABLE_SUSPEND_RESUME_TRAINING()
print(context)
Optuna.suggest_float(name='lr', low=1e-6, high=1e-2, log=True)
train, train_len = Mnist.get_train_dataset()
validation, validation_len = Mnist.get_test_dataset()
train = train.map(ImageDatasetUtil.image_reguralization()).map(
ImageDatasetUtil.one_hot(CLASS_NUM))
validation = validation.map(ImageDatasetUtil.image_reguralization()).map(
ImageDatasetUtil.one_hot(CLASS_NUM))
optimizer = OptimizerBuilder.get_optimizer(name="rmsprop",
lr=Optuna.get_value(
'lr', default=0.1))
model = SimpleClassificationModel.get_model(input_shape=(IMAGE_SIZE,
IMAGE_SIZE, 1),
classes=CLASS_NUM)
callbacks = CallbackBuilder.get_callbacks(tensorboard=True,
reduce_lr_on_plateau=True,
reduce_patience=5,
reduce_factor=0.25,
early_stopping_patience=16)
history = TrainingExecutor.train_classification(
train_data=train,
train_size=train_len,
batch_size=BATCH_SIZE,
validation_data=validation,
validation_size=validation_len,
shuffle_size=SHUFFLE_SIZE,
model=model,
callbacks=callbacks,
optimizer=optimizer,
loss="categorical_crossentropy",
max_epoch=EPOCHS)
return history.history['val_loss'][-1]
# mvtec_ad, len = MVTecAd.get_train_dataset("bottle")
# mvtec_ad = mvtec_ad.map(ImageDatasetUtil.resize(IMAGE_SIZE,IMAGE_SIZE))
# (train, len),(validation, validation_len) =ImageDatasetUtil.devide_train_validation(mvtec_ad,len,0.9)
cats_vs_dogs, total_len = CatsVsDogs.get_train_dataset()
cats_vs_dogs = cats_vs_dogs.map(
ImageDatasetUtil.map_max_square_crop_and_resize(IMAGE_SIZE, IMAGE_SIZE))
(train, len), (validation,
validation_len) = ImageDatasetUtil.devide_train_validation(
cats_vs_dogs, total_len, 0.9)
train = train.map(ImageDatasetUtil.image_reguralization(),
num_parallel_calls=tf.data.experimental.AUTOTUNE
) # .map(ImageDatasetUtil.resize(64,64))
validation_r = validation.map(ImageDatasetUtil.image_reguralization(),
num_parallel_calls=tf.data.experimental.AUTOTUNE
) # .map(ImageDatasetUtil.resize(64,64))
model = SSIMAutoEncoderModel.get_model(input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))
optimizer = OptimizerBuilder.get_optimizer("rmsprop")
callback = CallbackBuilder.get_callbacks()
loss = ssim_color_loss
ImageTrain.train_image_autoencoder(train, len, BATCH_SIZE, validation_r,
validation_len, 100, model, callback,
optimizer, loss, EPOCHS, False)
# model.load_weights(Context.get_model_path())
ImageTrain.show_autoencoder_results(model, validation, 15)
ImageTrain.calucurate_reconstruction_error(model, validation, 10)
TRAINING_NAME="20200519141141") # .TRAINING_NAME:})
ENABLE_SUSPEND_RESUME_TRAIN()
BATCH_SIZE = 500
CLASS_NUM = 10
IMAGE_SIZE = 28
EPOCHS = 20
SHUFFLE_SIZE = 1000
train, train_len = Mnist.get_train_dataset()
validation, validation_len = Mnist.get_test_dataset()
train = train.map(ImageDatasetUtil.image_reguralization()).map(
ImageDatasetUtil.one_hot(CLASS_NUM))
validation = validation.map(ImageDatasetUtil.image_reguralization()).map(
ImageDatasetUtil.one_hot(CLASS_NUM))
optimizer = OptimizerBuilder.get_optimizer(name="rmsprop")
model = SimpleClassificationModel.get_model(input_shape=(IMAGE_SIZE,
IMAGE_SIZE, 1),
classes=CLASS_NUM)
callbacks = CallbackBuilder.get_callbacks(tensorboard=False,
reduce_lr_on_plateau=True,
reduce_patience=3,
reduce_factor=0.25,
early_stopping_patience=5)
ImageTrain.train_image_classification(train_data=train,
train_size=train_len,
batch_size=BATCH_SIZE,
validation_data=validation,
validation_size=validation_len,
shuffle_size=SHUFFLE_SIZE,
model=model,
from tftk.image.model import ResNet50 from tftk.train import TrainingExecutor from tftk.image.augument import ImageAugument from tftk.callback import CallbackBuilder from tftk.optimizer import OptimizerBuilder BATCH_SIZE = 24 CLASS_NUM = 365 IMAGE_SIZE = 224 SHUFFLE_SIZE = 10000 # トレーニングデータ train, train_len = Place365Small.get_train_dataset() train = train.map(ImageDatasetUtil.resize_with_crop_or_pad(IMAGE_SIZE,IMAGE_SIZE)) train = train.map(ImageAugument.randaugment_map(3,10)) train = train.map(ImageDatasetUtil.image_reguralization()).map(ImageDatasetUtil.one_hot(CLASS_NUM)) # バリデーションデータ validation, validation_len = Place365Small.get_validation_dataset() validation = validation.map(ImageDatasetUtil.resize_with_crop_or_pad(IMAGE_SIZE,IMAGE_SIZE)) validation = validation.map(ImageDatasetUtil.image_reguralization()).map(ImageDatasetUtil.one_hot(CLASS_NUM)) # Optimizerの準備 optimizer = OptimizerBuilder.get_optimizer(name="sgd",lr=0.01) # モデルの準備 model = ResNet50.get_model(input_shape=(IMAGE_SIZE,IMAGE_SIZE,3),classes=CLASS_NUM) # Callbackの準備 callbacks = CallbackBuilder.get_callbacks(tensorboard_log_dir="tmp\\log",save_weights="tmp\\weigths.hdf5", consine_annealing=False) # トレーニングの実施 TrainingExecutor.train_classification(train_data=train,train_size=train_len,batch_size=BATCH_SIZE,validation_data=validation,validation_size=validation_len,shuffle_size=SHUFFLE_SIZE,model=model,callbacks=callbacks,optimizer=optimizer,loss="categorical_crossentropy",max_epoch=50)
train = train.map(
ImageDatasetUtil.image_reguralization(),
num_parallel_calls=tf.data.experimental.AUTOTUNE).map(
ImageDatasetUtil.one_hot(CLASS_NUM),
num_parallel_calls=tf.data.experimental.AUTOTUNE).apply(
ImageAugument.mixup_apply(200, 0.1))
validation = validation.map(
ImageDatasetUtil.map_max_square_crop_and_resize(
IMAGE_SIZE, IMAGE_SIZE),
num_parallel_calls=tf.data.experimental.AUTOTUNE).map(
ImageDatasetUtil.image_reguralization(),
num_parallel_calls=tf.data.experimental.AUTOTUNE).map(
ImageDatasetUtil.one_hot(CLASS_NUM),
num_parallel_calls=tf.data.experimental.AUTOTUNE)
optimizer = OptimizerBuilder.get_optimizer()
model = KerasEfficientNetB2.get_model(
input_shape=(IMAGE_SIZE, IMAGE_SIZE, CHANNELS),
classes=CLASS_NUM,
weights="imagenet"
) # resnest=True,resnet_c=True,resnet_d=True,mish=True)
callbacks = CallbackBuilder.get_callbacks(tensorboard=True,
consine_annealing=False,
reduce_lr_on_plateau=True,
reduce_patience=6,
reduce_factor=0.25,
early_stopping_patience=10)
ImageTrain.train_image_classification(train_data=train,
train_size=train_len,
batch_size=BATCH_SIZE,
validation_data=validation,