def create_uncertainty_model(learning_rate=1e-3, num_hidden_units=20, type = 'mobilenet_v2'):
mu_input = Input(shape=(num_classes,))
if type == 'mobilenet_v2':
base_model = mobilenet_v2.MobileNetV2(include_top=False, weights='imagenet', input_tensor=None,
input_shape=(224, 224, 3), pooling='avg', classes=num_classes)
elif type == 'vgg16':
base_model = vgg16.VGG16(include_top=False, weights='imagenet', input_tensor=None,
input_shape=(224, 224, 3), pooling='avg', classes=num_classes)
elif type == 'resnet50':
base_model = resnet50.ResNet50(include_top=False, weights='imagenet', input_tensor=None,
input_shape=(224, 224, 3), pooling='avg', classes=num_classes)
elif type == 'vgg19':
base_model = vgg19.VGG19(include_top=False, weights='imagenet', input_tensor=None,
input_shape=(224, 224, 3), pooling='avg', classes=num_classes)
elif type == 'inception_v3':
base_model = inception_v3.InceptionV3(include_top=False, weights='imagenet', input_tensor=None,
input_shape=(224, 224, 3), pooling='avg', classes=num_classes)
else:
base_model = mobilenet_v2.MobileNetV2(include_top=False, weights='imagenet', input_tensor=None,
input_shape=(224, 224, 3), pooling='avg', classes=num_classes)
base_model.trainable = False
beta = base_model.output
beta = Dense(num_hidden_units, activation='relu')(beta)
beta = Dense(num_hidden_units, activation='relu')(beta)
beta = Dense(num_hidden_units, activation='relu')(beta)
# beta = Dense(num_hidden_units,activation='relu')(beta)
beta = Dense(1, activation='sigmoid')(beta)
output = concatenate([mu_input, beta])
model = Model(inputs=[mu_input, base_model.input], outputs=output)
model.compile(loss=dirichlet_aleatoric_cross_entropy,
optimizer=Adam(lr=learning_rate),
metrics=[max_beta, min_beta]
)
return model
def main(mode='train', gpu='0'):
os.environ["CUDA_VISIBLE_DEVICES"]=gpu
data = data_utils.ISIC2018_data(4)
num_classes = 7
# extract feature
base_model = resnet50.ResNet50(weights='imagenet', include_top=False, pooling='avg', input_shape=(224,224,3))
images_feature = []
y_list = []
with tf.Session() as sess:
try:
if mode == 'train_evaluation':
x, y = data.read_record('train_evaluation')
outputname = 'images_feature_with_labels_from_vgg16_train'
elif mode == 'evaluate':
x, y = data.read_record('evaluate')
outputname = 'images_feature_with_labels_from_vgg16_evaluate'
sess.run(tf.global_variables_initializer())
cnt = 0
while True:
x_, y_ = sess.run([x, y])
features = base_model.predict(x_)
y_list.append((np.argmax(y_, axis=1)))
#print(features.shape)
images_feature.append(features)
cnt += 1
print('batch %d' % cnt)
except tf.errors.OutOfRangeError:
print('load finish labels')
x_y = [images_feature, y_list]
np.save(outputname, x_y)
def model(nb_classes=10,
logits=False,
input_ph=None,
nb_rows=28,
nb_cols=28,
nb_channels=1):
# load the resnet50 model
model = resnet50.ResNet50(include_top=False, weights='imagenet')
print('---------> Shape : ', model.output_shape[1:])
# define the top-model
top_model = Sequential()
layers = [
Flatten(input_shape=model.output_shape[1:]),
Dense(120, activation='relu'),
Dense(84, activation='relu'),
Dense(nb_classes)
]
# add layers to the model
for layer in layers:
top_model.add(layer)
# add top_model to model
model.add(top_model)
# check if logits need to be returned
if logits == True and input_ph is not None:
logits_tensor = model(input_ph)
# add softmax
model.add(Activation('softmax'))
if logits == True and input_ph is not None:
return model, logits_tensor
else:
return model
def main(mode='train', gpu='0'):
os.environ["CUDA_VISIBLE_DEVICES"] = gpu
data = data_utils.ISIC2018_data(4)
num_classes = 7
# using resnet50
base_model = resnet50.ResNet50(weights='imagenet',
include_top=False,
pooling='avg',
input_shape=(224, 224, 3))
# using resnet152
#base_model = resnet152.ResNet152(weights='imagenet', include_top=False, pooling='avg', input_shape=(224,224,3))
# using resnet152
#base_model = resnet.ResNet152(weights='imagenet', include_top=False, pooling='avg', input_shape=(224,224,3))
# using densenet
#base_model = densenet.DenseNet201(weights='imagenet', include_top=False, pooling='avg', input_shape=(224,224,3))
# inception v3
#base_model = inception_v3.InceptionV3(weights='imagenet', include_top=False, pooling='avg', input_shape=(224,224,3))
model = models.Sequential()
model.add(base_model)
# remove fully connected according to paper
model.add(layers.Dense(1024, activation='relu'))
model.add(layers.Dense(7, activation='relu'))
#model.add(layers.Dense(1000, activation='relu'))
model.add(layers.Dense(num_classes, activation='softmax', name='fc7'))
base_model.trainable = False
#model.compile(loss=median_weight_class_loss,
#model.compile(loss='categorical_crossentropy',
model.compile(loss=focal_loss,
optimizer=SGD(lr=0.001, momentum=0.9, decay=0.0),
metrics=[metrics.categorical_accuracy])
#model_dir = '/home/jiaxin/myGithub/Reverse_CISI_Classification/src/densenet201_keras_pre/model_fc'
#model_dir = '/home/jiaxin/myGithub/Reverse_CISI_Classification/src/resnet152_keras_pre/model_fc'
#model_dir = '/home/jiaxin/myGithub/Reverse_CISI_Classification/src/resnet152_keras_pre/model_fc'
#model_dir = '/home/jiaxin/myGithub/Reverse_CISI_Classification/src/resnet50_keras_pre/model_cw'
model_dir = '/home/jiaxin/myGithub/Reverse_CISI_Classification/src/resnet50_keras_pre/model_fc_repeat'
#model_dir = '/home/jiaxin/myGithub/Reverse_CISI_Classification/src/resnet50_keras_pre/model_fc_3_m'
#model_dir = '/home/jiaxin/myGithub/Reverse_CISI_Classification/src/resnet50_keras_pre/model_fc_cw_nor'
os.makedirs(model_dir, exist_ok=True)
print('model_dir', model_dir)
est = tf.keras.estimator.model_to_estimator(keras_model=model,
model_dir=model_dir)
train_spec = tf.estimator.TrainSpec(
input_fn=lambda: data.read_record('train'))
eval_spec = tf.estimator.EvalSpec(
input_fn=lambda: data.read_record('train_evaluation'))
if mode == 'train':
tf.estimator.train_and_evaluate(est, train_spec, eval_spec)
elif mode == 'evaluate':
with tf.Session() as sess:
try:
x, y = data.read_record('evaluate')
sess.run(tf.global_variables_initializer())
y_list = []
while True:
_, y_ = sess.run([x, y])
y_list.extend((np.argmax(y_, axis=1)))
except tf.errors.OutOfRangeError:
print('load finish labels')
# test
#cnt = 0
#while True:
# try:
# x, y = data.read_record('evaluate')
# sess.run(tf.global_variables_initializer())
# y_list_ = []
# while True:
# _, y_ = sess.run([x, y])
# y_list_.extend((np.argmax(y_, axis=1)))
# except tf.errors.OutOfRangeError:
# cnt += 1
# print(cnt)
# assert all([a==b for a, b in zip(y_list, y_list_)])
pp = []
while True:
predictions = est.predict(
input_fn=lambda: data.read_record('evaluate'))
predictions_list = []
for pre in predictions:
p = np.argmax(pre['fc7'])
predictions_list.append(p)
statistics_ = statistics.statistics(hps, mode='evaluate')
statistics_.add_labels_predictions(predictions_list, y_list)
statistics_.get_acc_normal()
result = statistics_.get_acc_imbalanced()
np.save('predictions_label_fc_repeat',
[predictions_list, y_list])
#np.save('predictions_label_fc_3_m', [predictions_list, y_list])
#np.save('predictions_label_fc_without_fulcon', [predictions_list, y_list])
pp.append(result)
print('---')
np.save('result_fc_repeat', pp)
#np.save('result_fc_3_m', pp)
#np.save('result_fc_without_fulcon', pp)
time.sleep(120)
def get_resnet50_model(weights='imagenet', input_tensor=None):
return resnet50.ResNet50(weights=weights, include_top=False, input_tensor=input_tensor)
#-*-encoding:utf-8-*-
import numpy as np
from tensorflow.python.keras.preprocessing import image
from tensorflow.python.keras.applications import resnet50
import warnings
warnings.filterwarnings("ignore")
img = image.load_img('dog.png')
# print(image.img_to_array(img).shape)
model = resnet50.ResNet50(weights='imagenet')
img = image.load_img('dog.png', target_size=(224, 224))
img = image.img_to_array(img)
img = np.expand_dims(img, axis=0)
print(img.shape)
img = resnet50.preprocess_input(img)
#模型预测
pred = model.predict(img)
n = 10
top_n = resnet50.decode_predictions(pred, n)
for i in top_n[0]:
print(i)