我正在使用keras中的inception_v3模型进行一些图像分类，但是，在整个训练过程中，我的训练精度低于验证。从第一个时期开始，我的验证准确性就超过了0.95。我还发现火车损失比验证损失高得多。最后，测试精度为0.5，这是非常糟糕的。
起初，我的优化器是Adam，学习率等于0.00001，结果很差。然后我将其更改为SGD，学习率为0.00001，这不会对不良结果产生任何影响。我还尝试将学习率提高到0.1，但测试准确度仍在0.5左右
import numpy as np
import pandas as pd
import keras
from keras import layers
from keras.applications.inception_v3 import preprocess_input
from keras.models import Model
from keras.layers.core import Dense
from keras.layers import GlobalAveragePooling2D
from keras.optimizers import Adam, SGD, RMSprop
from keras.preprocessing.image import ImageDataGenerator
from keras.utils.np_utils import to_categorical
from keras.utils import plot_model
from keras.models import model_from_json
from sklearn.metrics import confusion_matrix
import itertools
import matplotlib.pyplot as plt
import math
import copy
import pydotplus
train_path = 'data/train'
valid_path = 'data/validation'
test_path = 'data/test'
top_model_weights_path = 'model_weigh.h5'
# number of epochs to train top model
epochs = 100
# batch size used by flow_from_directory and predict_generator
batch_size = 2
img_width, img_height = 299, 299
fc_size = 1024
nb_iv3_layers_to_freeze = 172
train_datagen = ImageDataGenerator(preprocessing_function=preprocess_input,
rotation_range=30,
width_shift_range=0.2,
height_shift_range=0.2,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
# this is the augmentation configuration we will use for testing:
# only rescaling
valid_datagen = ImageDataGenerator(preprocessing_function=preprocess_input,
rotation_range=30,
width_shift_range=0.2,
height_shift_range=0.2,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
train_batches =
train_datagen.flow_from_directory(train_path,
target_size=(img_width, img_height),
classes=None,
class_mode='categorical',
batch_size=batch_size,
shuffle=True)
valid_batches =
valid_datagen.flow_from_directory(valid_path,
target_size=(img_width,img_height),
classes=None,
class_mode='categorical',
batch_size=batch_size,
shuffle=True)
test_batches =
ImageDataGenerator().flow_from_directory(test_path,
target_size=(img_width,
img_height),
classes=None,
class_mode='categorical',
batch_size=batch_size,
shuffle=False)
nb_train_samples = len(train_batches.filenames)
# get the size of the training set
nb_classes_train = len(train_batches.class_indices)
# get the number of classes
predict_size_train = int(math.ceil(nb_train_samples / batch_size))
nb_valid_samples = len(valid_batches.filenames)
nb_classes_valid = len(valid_batches.class_indices)
predict_size_validation = int(math.ceil(nb_valid_samples / batch_size))
nb_test_samples = len(test_batches.filenames)
nb_classes_test = len(test_batches.class_indices)
predict_size_test = int(math.ceil(nb_test_samples / batch_size))
def add_new_last_layer(base_model, nb_classes):
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(fc_size, activation='relu')(x)
pred = Dense(nb_classes, activation='softmax')(x)
model = Model(input=base_model.input, output=pred)
return model
# freeze base_model layer in order to get the bottleneck feature
def setup_to_transfer_learn(model, base_model):
for layer in base_model.layers:
layer.trainable = False
model.compile(optimizer=Adam(lr=0.00001),
loss='categorical_crossentropy',
metrics=['accuracy'])
base_model = keras.applications.inception_v3.InceptionV3(weights='imagenet', include_top=False)
model = add_new_last_layer(base_model, nb_classes_train)
setup_to_transfer_learn(model, base_model)
model.summary()
train_labels = train_batches.classes
train_labels = to_categorical(train_labels, num_classes=nb_classes_train)
validation_labels = valid_batches.classes
validation_labels = to_categorical(validation_labels, num_classes=nb_classes_train)
history = model.fit_generator(train_batches,
epochs=epochs,
steps_per_epoch=nb_train_samples // batch_size,
validation_data=valid_batches,
validation_steps=nb_valid_samples // batch_size,
class_weight='auto')
# save model to json
model_json = model.to_json()
with open("model.json", "w") as json_file:
json_file.write(model_json)
# serialize model to HDF5
model.save_weights(top_model_weights_path)
print("Saved model to disk")
# model visualization
plot_model(model,
show_shapes=True,
show_layer_names=True,
to_file='model.png')
(eval_loss, eval_accuracy) = model.evaluate_generator(
valid_batches,
steps=nb_valid_samples // batch_size,
verbose=1)
print("[INFO] evaluate accuracy: {:.2f}%".format(eval_accuracy * 100))
print("[INFO] evaluate loss: {}".format(eval_loss))
test_batches.reset()
predictions = model.predict_generator(test_batches,
steps=nb_test_samples / batch_size,
verbose=0)
# print(predictions)
predicted_class_indices = np.argmax(predictions, axis=1)
# print(predicted_class_indices)
labels = train_batches.class_indices
labels = dict((v, k) for k, v in labels.items())
final_predictions = [labels[k] for k in predicted_class_indices]
# print(final_predictions)
# save as csv file
filenames = test_batches.filenames
results = pd.DataFrame({"Filename": filenames,
"Predictions": final_predictions})
results.to_csv("results.csv", index=False)
# evaluation test result
(test_loss, test_accuracy) = model.evaluate_generator(
test_batches,
steps=nb_train_samples // batch_size,
verbose=1)
print("[INFO] test accuracy: {:.2f}%".format(test_accuracy * 100))
print("[INFO] test loss: {}".format(test_loss))
这里是培训过程的简短摘要：
Epoch 1/100
2000/2000 [==============================] - 146s 73ms/step - loss: 0.4941 - acc: 0.7465 - val_loss: 0.1612 - val_acc: 0.9770
Epoch 2/100
2000/2000 [==============================] - 140s 70ms/step - loss: 0.4505 - acc: 0.7725 - val_loss: 0.1394 - val_acc: 0.9765
Epoch 3/100
2000/2000 [==============================] - 139s 70ms/step - loss: 0.4505 - acc: 0.7605 - val_loss: 0.1643 - val_acc: 0.9560
......
Epoch 98/100
2000/2000 [==============================] - 141s 71ms/step - loss: 0.1348 - acc: 0.9467 - val_loss: 0.0639 - val_acc: 0.9820
Epoch 99/100
2000/2000 [==============================] - 140s 70ms/step - loss: 0.1495 - acc: 0.9365 - val_loss: 0.0780 - val_acc: 0.9770
Epoch 100/100
2000/2000 [==============================] - 138s 69ms/step - loss: 0.1401 - acc: 0.9458 - val_loss: 0.0471 - val_acc: 0.9890
这是我得到的结果：
[INFO] evaluate accuracy: 98.55%
[INFO] evaluate loss: 0.05201659869024259
2000/2000 [==============================] - 47s 23ms/step
[INFO] test accuracy: 51.70%
[INFO] test loss: 7.737395915810134
我希望有人能帮助我解决这个问题。
答案 0 :(得分：0)
就像现在的代码一样，您不会冻结模型的各个层以进行迁移学习。在setup_to_transfer_learn中，您要冻结base_model中的层，然后编译新模型（包含来自基础模型的层），但实际上并没有冻结新模型。只需更改setup_to_transfer_learn：
def setup_to_transfer_learn(model):
for layer in model.layers[:-3]: # since you added three new layers (which should not freeze)
layer.trainable = False
model.compile(optimizer=Adam(lr=0.00001),
loss='categorical_crossentropy',
metrics=['accuracy'])
然后像这样调用函数：
model = add_new_last_layer(base_model, nb_classes_train)
setup_to_transfer_learn(model)
调用model.summary()
答案 1 :(得分：0)
最后，我解决了这个问题。我忘记对测试数据进行图像预处理。添加完之后，一切正常。 我改变了这个：
test_batches = ImageDataGenerator().flow_from_directory(test_path,
target_size=(img_width, img_height),
classes=None,
class_mode='categorical',
batch_size=batch_size,
shuffle=False)
对此：
test_datagen = ImageDataGenerator(preprocessing_function=preprocess_input)
test_batches = test_datagen.flow_from_directory(test_path,
target_size=(img_width, img_height),
classes=None,
class_mode='categorical',
batch_size=batch_size,
shuffle=False)
测试精度为0.98，测试损失为0.06。