我在SVHN（街景门牌号码）数据集上使用了带有TensorFlow的VGG16，并且准确性极低（〜18％）。这是一个多类分类问题（10个类）
我使用了从互联网获得的相同代码，但不幸的是，获得的精度却不一样。
我尝试使用不同的优化器，不同的学习率，不同的动力，不同的时期数，不同的批次大小。
已附加代码。有人可以帮忙吗？
import numpy as np
import scipy.io
import keras
import keras.layers
import keras.preprocessing
import cv2
from keras.models import Sequential, Model
from keras.layers import Dense, Flatten, MaxPool2D
from keras.layers import Conv2D, MaxPooling2D, Dropout, Input, ZeroPadding2D, Convolution2D
from keras.utils import np_utils
from keras.optimizers import SGD, Adam
from keras.callbacks import History
from keras.preprocessing.image import ImageDataGenerator
from keras.models import load_model
from keras.applications import VGG16
def vgg16Model(X_train, y_train, X_test, y_test, input_shape):
sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
adam = Adam(lr=0.1, beta_1=0.9, beta_2=0.999, epsilon=None, decay=1e-6, amsgrad=False)
epochs = 20
loss = 'categorical_crossentropy'
optimizer = sgd
metrics = ['accuracy']
samples_per_epoch = X_train.shape[0]
batch_size = 64
input_shape = (32, 32, 3)
img_input = Input(shape=input_shape, name='img_input')
x = Conv2D(64, (3, 3), padding='same', activation='relu', name='block1_conv1')(img_input)
x = Conv2D(64, (3, 3), padding='same', activation='relu', name='block1_conv2')(x)
x = MaxPool2D((2, 2), strides=(2, 2), name='block1_pool')(x)
x = Conv2D(128, (3, 3), padding='same', activation='relu', name='block2_conv1')(x)
x = Conv2D(128, (3, 3), padding='same', activation='relu', name='block2_conv2')(x)
x = MaxPool2D((2, 2), strides=(2, 2), name='block2_pool')(x)
x = Conv2D(256, (3, 3), padding='same', activation='relu', name='block3_conv1')(x)
x = Conv2D(256, (3, 3), padding='same', activation='relu', name='block3_conv2')(x)
x = Conv2D(256, (3, 3), padding='same', activation='relu', name='block3_conv3')(x)
x = MaxPool2D((2, 2), strides=(2, 2), name='block3_pool')(x)
x = Conv2D(512, (3, 3), padding='same', activation='relu', name='block4_conv1')(x)
x = Conv2D(512, (3, 3), padding='same', activation='relu', name='block4_conv2')(x)
x = Conv2D(512, (3, 3), padding='same', activation='relu', name='block4_conv3')(x)
x = MaxPool2D((2, 2), strides=(2, 2), name='block4_pool')(x)
x = Conv2D(512, (3, 3), padding='same', activation='relu', name='block5_conv1')(x)
x = Conv2D(512, (3, 3), padding='same', activation='relu', name='block5_conv2')(x)
x = Conv2D(512, (3, 3), padding='same', activation='relu', name='block5_conv3')(x)
x = MaxPool2D((2, 2), strides=(2, 2), name='block5_pool')(x)
x = Flatten(name='flatten')(x)
x = Dense(4096, activation='relu', name='fc1')(x)
x = Dense(4096, activation='relu', name='fc2')(x)
x = Dense(10, activation='softmax', name='predictions')(x)
vgg16model = Model(inputs=img_input, outputs=x, name='vgg16-funcapi')
vgg16model.summary()
vgg16model.compile(optimizer=optimizer, loss=loss, metrics=metrics)
history = History()
early_stop = keras.callbacks.EarlyStopping(monitor='acc',min_delta=0,patience=2,verbose=0,mode='auto')
callbacks = [history, early_stop]
datagen = ImageDataGenerator(
featurewise_center=True,
featurewise_std_normalization=True,
rotation_range=180,
width_shift_range=0.2,
height_shift_range=0.2,
horizontal_flip=True)
datagen.fit(X_train)
model_history = vgg16model.fit_generator(datagen.flow(X_train, y_train, batch_size=batch_size),
steps_per_epoch=int(samples_per_epoch/batch_size),
verbose=1,
epochs=epochs,
callbacks=callbacks,
shuffle=True)
filename = 'models/vgg16_' + str(epochs) + '_' + str(batch_size)+'.h'
vgg16model.save(filename)
print('SCORE')
score = vgg16model.evaluate(X_test, y_test, batch_size=64)
print(vgg16model.metrics_names)
print(score)
return vgg16model, model_history, score
def preprocess():
train_data = scipy.io.loadmat('data/train_32x32.mat')
test_data = scipy.io.loadmat('data/test_32x32.mat')
train_imgs = train_data['X'][:, :, :, :].astype(np.float32)
train_labels = train_data['y']
test_imgs = test_data['X'][:, :, :, :].astype(np.float32)
test_labels = test_data['y']
train_imgs /= 255.
test_imgs /= 255.
(X_train, y_train) = np.moveaxis(train_imgs, 3, 0), train_labels.flatten()
(X_test, y_test) = np.moveaxis(test_imgs, 3, 0), test_labels.flatten()
y_train[y_train == 10] = 0
y_test[y_test == 10] = 0
y_train = np_utils.to_categorical(y_train.reshape(1, -1)[0], num_classes=10)
y_test = np_utils.to_categorical(y_test.reshape(1, -1)[0], num_classes=10)
return (X_train, y_train, X_test, y_test)
if __name__ == '__main__':
(X_train, y_train, X_test, y_test) = preprocess()
vgg16model, vgg16model_history, vgg16score = vgg16Model(X_train, y_train, X_test, y_test, input_shape=(32, 32, 3))
print('-' * 100)
print('This is the history of the vgg16 model, trained from scratch')
print(vgg16model_history.history)
print('-' * 100)
print('This is the score')
print(vgg16score)