使用目录迭代器的 Keras Hyperband 搜索
Keras Hyperband Search Using Directory Iterator
我正在使用 Tensorflow 的 flow_from_directory 收集大型图像数据集，然后对其进行训练。我想使用 Keras Tuner 但是当我 运行
tuner.search(test_data_gen, epochs=50,
validation_split=0.2, callbacks=[stop_early])
它抛出以下错误，
ValueError: `validation_split` is only supported for Tensors or NumPy arrays, found following types in the input: [<class 'tensorflow.python.keras.preprocessing.image.DirectoryIterator'>]
我不太了解 AI 中数据类型之间的转换，因此非常感谢任何帮助。
这是我的其余代码：
import tensorflow as tf
from tensorflow import keras
import numpy as np
import matplotlib.pyplot as plt
import IPython.display as display
from PIL import Image, ImageSequence
import os
import pathlib
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import cv2
import datetime
import kerastuner as kt
tf.compat.v1.enable_eager_execution()
epochs = 50
steps_per_epoch = 10
batch_size = 20
IMG_HEIGHT = 200
IMG_WIDTH = 200
train_dir = "Data/Train"
test_dir = "Data/Val"
train_image_generator = ImageDataGenerator(rescale=1. / 255)
test_image_generator = ImageDataGenerator(rescale=1. / 255)
train_data_gen = train_image_generator.flow_from_directory(batch_size=batch_size,
directory=train_dir,
shuffle=True,
target_size=(IMG_HEIGHT, IMG_WIDTH),
class_mode='sparse')
test_data_gen = test_image_generator.flow_from_directory(batch_size=batch_size,
directory=test_dir,
shuffle=True,
target_size=(IMG_HEIGHT, IMG_WIDTH),
class_mode='sparse')
def model_builder(hp):
model = keras.Sequential()
model.add(Conv2D(265, 3, padding='same', activation='relu', input_shape=(IMG_HEIGHT, IMG_WIDTH ,3)))
model.add(MaxPooling2D())
model.add(Conv2D(64, 3, padding='same', activation='relu'))
model.add(MaxPooling2D())
model.add(Conv2D(32, 3, padding='same', activation='relu'))
model.add(MaxPooling2D())
model.add(Flatten())
model.add(keras.layers.Dense(256, activation="relu"))
hp_units = hp.Int('units', min_value=32, max_value=512, step=32)
model.add(keras.layers.Dense(hp_units, activation="relu"))
model.add(keras.layers.Dense(80, activation="softmax"))
hp_learning_rate = hp.Choice('learning_rate', values=[1e-2, 1e-3, 1e-4])
model.compile(optimizer=keras.optimizers.Adam(learning_rate=hp_learning_rate),
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['top_k_categorical_accuracy'])
return model
tuner = kt.Hyperband(model_builder,
objective='val_accuracy',
max_epochs=30,
factor=3,
directory='Hypertuner_Dir',
project_name='AIOS')
stop_early = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=5)
并开始搜索tuner
tuner.search(train_data_gen, epochs=50, validation_split=0.2, callbacks=[stop_early])
# Get the optimal hyperparameters
best_hps=tuner.get_best_hyperparameters(num_trials=1)[0]
print(f"""
The hyperparameter search is complete. The optimal number of units in the first densely-connected
layer is {best_hps.get('units')} and the optimal learning rate for the optimizer
is {best_hps.get('learning_rate')}.
""")
model = tuner.hypermodel.build(best_hps)
model.summary()
tf.keras.utils.plot_model(model, to_file="model.png", show_shapes=True, show_layer_names=True, rankdir='TB')
checkpoint_path = "training/cp.ckpt"
checkpoint_dir = os.path.dirname(checkpoint_path)
cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_path,
save_weights_only=True,
verbose=1)
os.system("rm -r logs")
log_dir = "logs/fit/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)
#history = model.fit(train_data_gen,steps_per_epoch=steps_per_epoch,epochs=epochs,validation_data=test_data_gen,validation_steps=10,callbacks=[cp_callback, tensorboard_callback])
history = model.fit(train_data_gen,steps_per_epoch=steps_per_epoch,epochs=epochs,validation_split=0.2,validation_steps=10,callbacks=[cp_callback, tensorboard_callback])
model.load_weights(tf.train.latest_checkpoint(checkpoint_dir))
model.save('model.h5', include_optimizer=True)
test_loss, test_acc = model.evaluate(test_data_gen)
print("Tested Acc: ", test_acc)
print("Tested Acc: ", test_acc*100, "%")
val_acc_per_epoch = history.history['val_accuracy']
best_epoch = val_acc_per_epoch.index(max(val_acc_per_epoch)) + 1
print('Best epoch: %d' % (best_epoch,))
===================================编辑====================================
不幸的是，validation_split=0.2 在这种情况下不起作用，因为该参数假定数据是 Tensor 或 NumPy 数组。由于您将数据存储为生成器（这是个好主意），因此您不能简单地拆分它。
您需要创建一个验证生成器，就像您对 test_data_gen 所做的那样，并将 validation_split=0.2 更改为 validation_data=val_data_gen。
根据doc关于validation_split：
validation_split: Float between 0 and 1. Fraction of the training data to be used as validation data. The model will set apart this fraction of the training data, will not train on it, and will evaluate the loss and any model metrics on this data at the end of each epoch. The validation data is selected from the last samples in the x and y data provided, before shuffling. This argument is not supported when x is a dataset, generator or keras.utils.Sequence instance.
现在，作为生成器，尝试如下操作，reference
tuner.search(train_data_gen,
epochs=50,
validation_data=test_data_gen,
callbacks=[stop_early])
此外，请确保您的每个生成器都能正确生成有效的批次。
我正在使用 Tensorflow 的 flow_from_directory 收集大型图像数据集，然后对其进行训练。我想使用 Keras Tuner 但是当我 运行
tuner.search(test_data_gen, epochs=50,
validation_split=0.2, callbacks=[stop_early])
它抛出以下错误，
ValueError: `validation_split` is only supported for Tensors or NumPy arrays, found following types in the input: [<class 'tensorflow.python.keras.preprocessing.image.DirectoryIterator'>]
我不太了解 AI 中数据类型之间的转换，因此非常感谢任何帮助。
这是我的其余代码：
import tensorflow as tf
from tensorflow import keras
import numpy as np
import matplotlib.pyplot as plt
import IPython.display as display
from PIL import Image, ImageSequence
import os
import pathlib
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import cv2
import datetime
import kerastuner as kt
tf.compat.v1.enable_eager_execution()
epochs = 50
steps_per_epoch = 10
batch_size = 20
IMG_HEIGHT = 200
IMG_WIDTH = 200
train_dir = "Data/Train"
test_dir = "Data/Val"
train_image_generator = ImageDataGenerator(rescale=1. / 255)
test_image_generator = ImageDataGenerator(rescale=1. / 255)
train_data_gen = train_image_generator.flow_from_directory(batch_size=batch_size,
directory=train_dir,
shuffle=True,
target_size=(IMG_HEIGHT, IMG_WIDTH),
class_mode='sparse')
test_data_gen = test_image_generator.flow_from_directory(batch_size=batch_size,
directory=test_dir,
shuffle=True,
target_size=(IMG_HEIGHT, IMG_WIDTH),
class_mode='sparse')
def model_builder(hp):
model = keras.Sequential()
model.add(Conv2D(265, 3, padding='same', activation='relu', input_shape=(IMG_HEIGHT, IMG_WIDTH ,3)))
model.add(MaxPooling2D())
model.add(Conv2D(64, 3, padding='same', activation='relu'))
model.add(MaxPooling2D())
model.add(Conv2D(32, 3, padding='same', activation='relu'))
model.add(MaxPooling2D())
model.add(Flatten())
model.add(keras.layers.Dense(256, activation="relu"))
hp_units = hp.Int('units', min_value=32, max_value=512, step=32)
model.add(keras.layers.Dense(hp_units, activation="relu"))
model.add(keras.layers.Dense(80, activation="softmax"))
hp_learning_rate = hp.Choice('learning_rate', values=[1e-2, 1e-3, 1e-4])
model.compile(optimizer=keras.optimizers.Adam(learning_rate=hp_learning_rate),
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['top_k_categorical_accuracy'])
return model
tuner = kt.Hyperband(model_builder,
objective='val_accuracy',
max_epochs=30,
factor=3,
directory='Hypertuner_Dir',
project_name='AIOS')
stop_early = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=5)
并开始搜索tuner
tuner.search(train_data_gen, epochs=50, validation_split=0.2, callbacks=[stop_early])
# Get the optimal hyperparameters
best_hps=tuner.get_best_hyperparameters(num_trials=1)[0]
print(f"""
The hyperparameter search is complete. The optimal number of units in the first densely-connected
layer is {best_hps.get('units')} and the optimal learning rate for the optimizer
is {best_hps.get('learning_rate')}.
""")
model = tuner.hypermodel.build(best_hps)
model.summary()
tf.keras.utils.plot_model(model, to_file="model.png", show_shapes=True, show_layer_names=True, rankdir='TB')
checkpoint_path = "training/cp.ckpt"
checkpoint_dir = os.path.dirname(checkpoint_path)
cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_path,
save_weights_only=True,
verbose=1)
os.system("rm -r logs")
log_dir = "logs/fit/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)
#history = model.fit(train_data_gen,steps_per_epoch=steps_per_epoch,epochs=epochs,validation_data=test_data_gen,validation_steps=10,callbacks=[cp_callback, tensorboard_callback])
history = model.fit(train_data_gen,steps_per_epoch=steps_per_epoch,epochs=epochs,validation_split=0.2,validation_steps=10,callbacks=[cp_callback, tensorboard_callback])
model.load_weights(tf.train.latest_checkpoint(checkpoint_dir))
model.save('model.h5', include_optimizer=True)
test_loss, test_acc = model.evaluate(test_data_gen)
print("Tested Acc: ", test_acc)
print("Tested Acc: ", test_acc*100, "%")
val_acc_per_epoch = history.history['val_accuracy']
best_epoch = val_acc_per_epoch.index(max(val_acc_per_epoch)) + 1
print('Best epoch: %d' % (best_epoch,))
===================================编辑====================================
不幸的是，validation_split=0.2 在这种情况下不起作用，因为该参数假定数据是 Tensor 或 NumPy 数组。由于您将数据存储为生成器（这是个好主意），因此您不能简单地拆分它。
您需要创建一个验证生成器，就像您对 test_data_gen 所做的那样，并将 validation_split=0.2 更改为 validation_data=val_data_gen。
根据doc关于validation_split：
validation_split: Float between 0 and 1. Fraction of the training data to be used as validation data. The model will set apart this fraction of the training data, will not train on it, and will evaluate the loss and any model metrics on this data at the end of each epoch. The validation data is selected from the last samples in the x and y data provided, before shuffling. This argument is not supported when x is a dataset, generator or keras.utils.Sequence instance.
现在，作为生成器，尝试如下操作，reference
tuner.search(train_data_gen,
epochs=50,
validation_data=test_data_gen,
callbacks=[stop_early])
此外，请确保您的每个生成器都能正确生成有效的批次。