keras resnet应用时不论输入什么图片输出是固定的

Question

用下面这样的代码测试的时候result都是固定值
之前都是用model.add这样来写结构的 不知道是不是结构写法的问题，model.add这样就没问题

x = load_img(file, target_size=(img_width,img_height))
x = img_to_array(x)
x = np.expand_dims(x, axis=0)
array = model.predict(x)
result = array[0]

training.py:

# coding=utf-8
from keras.models import Model
from keras.layers import Input, Dense, Dropout, BatchNormalization, Conv2D, MaxPooling2D, AveragePooling2D, concatenate, \
    Activation, ZeroPadding2D
from keras.layers import add, Flatten
from keras.utils import plot_model
from keras.metrics import top_k_categorical_accuracy
from keras.preprocessing.image import ImageDataGenerator
from keras.models import load_model
from keras import optimizers
import os
import sys
import tensorflow as tf
from keras import callbacks

config = tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True))
sess = tf.Session(config=config)

DEV = False
argvs = sys.argv
argc = len(argvs)
if argc > 1 and (argvs[1] == "--development" or argvs[1] == "-d"):
  DEV = True
if DEV:
  EPOCH=4
else:
  EPOCH=1

# Global Constants
samples_per_epoch = 3750
validation_steps = 490
NB_CLASS=5
IM_WIDTH=100
IM_HEIGHT=100
train_root='data/train'
vaildation_root='data/test'
batch_size=16
lr=0.0004
# train data
train_datagen = ImageDataGenerator(
    width_shift_range=0.1,
    height_shift_range=0.1,
    shear_range=0.1,
    zoom_range=0.1,
    horizontal_flip=True,
    rescale=1./255
)
train_generator = train_datagen.flow_from_directory(
    train_root,
    target_size=(IM_WIDTH, IM_HEIGHT),
    batch_size=batch_size,
    shuffle=True
)
# vaild data
vaild_datagen = ImageDataGenerator(
    width_shift_range=0.1,
    height_shift_range=0.1,
    shear_range=0.1,
    zoom_range=0.1,
    horizontal_flip=True,
    rescale=1./255
)
vaild_generator = train_datagen.flow_from_directory(
    vaildation_root,
    target_size=(IM_WIDTH, IM_HEIGHT),
    batch_size=batch_size,
)

def Conv2d_BN(x, nb_filter, kernel_size, strides=(1, 1), padding='same', name=None):
    if name is not None:
        bn_name = name + '_bn'
        conv_name = name + '_conv'
    else:
        bn_name = None
        conv_name = None
    x = Conv2D(nb_filter, kernel_size, padding=padding, strides=strides, activation='relu', name=conv_name)(x)
    x = BatchNormalization(axis=3, name=bn_name)(x)
    return x

def identity_Block(inpt, nb_filter, kernel_size, strides=(1, 1), with_conv_shortcut=False):
    x = Conv2d_BN(inpt, nb_filter=nb_filter, kernel_size=kernel_size, strides=strides, padding='same')
    x = Conv2d_BN(x, nb_filter=nb_filter, kernel_size=kernel_size, padding='same')
    if with_conv_shortcut:#shortcut的含义是：将输入层x与最后的输出层y进行连接，如上图所示
        shortcut = Conv2d_BN(inpt, nb_filter=nb_filter, strides=strides, kernel_size=kernel_size)
        x = add([x, shortcut])
        return x
    else:
        x = add([x, inpt])
        return x

def resnet_34(width,height,channel,classes):
    inpt = Input(shape=(width, height, channel))
    x = ZeroPadding2D((3, 3))(inpt)
    #conv1
    x = Conv2d_BN(x, nb_filter=64, kernel_size=(7, 7), strides=(2, 2), padding='valid')
    x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), padding='same')(x)
    #conv2_x
    x = identity_Block(x, nb_filter=64, kernel_size=(3, 3))
    x = identity_Block(x, nb_filter=64, kernel_size=(3, 3))
    x = identity_Block(x, nb_filter=64, kernel_size=(3, 3))
    #conv3_x
    x = identity_Block(x, nb_filter=128, kernel_size=(3, 3), strides=(2, 2), with_conv_shortcut=True)
    x = identity_Block(x, nb_filter=128, kernel_size=(3, 3))
    x = identity_Block(x, nb_filter=128, kernel_size=(3, 3))
    x = identity_Block(x, nb_filter=128, kernel_size=(3, 3))
    #conv4_x
    x = identity_Block(x, nb_filter=256, kernel_size=(3, 3), strides=(2, 2), with_conv_shortcut=True)
    x = identity_Block(x, nb_filter=256, kernel_size=(3, 3))
    x = identity_Block(x, nb_filter=256, kernel_size=(3, 3))
    x = identity_Block(x, nb_filter=256, kernel_size=(3, 3))
    x = identity_Block(x, nb_filter=256, kernel_size=(3, 3))
    x = identity_Block(x, nb_filter=256, kernel_size=(3, 3))
    #conv5_x
    x = identity_Block(x, nb_filter=512, kernel_size=(3, 3), strides=(2, 2), with_conv_shortcut=True)
    x = identity_Block(x, nb_filter=512, kernel_size=(3, 3))
    x = identity_Block(x, nb_filter=512, kernel_size=(3, 3))
    x = AveragePooling2D(pool_size=(4, 4))(x)
    x = Flatten()(x)
    x = Dense(classes, activation='softmax')(x)
    model = Model(inputs=inpt, outputs=x)
    return model

if __name__ == '__main__':

    if (os.path.exists('modelresnet') and DEV):
        model = load_model('./modelresnet/resnet_50.h5')########
        model.load_weights('./modelresnet/weights.h5')
    else:
        model = resnet_34(IM_WIDTH,IM_HEIGHT,3,NB_CLASS)
    model.compile(loss='categorical_crossentropy',
              optimizer=optimizers.RMSprop(lr=lr),
              metrics=['accuracy'])

    print ('Model Compiled')

    model.fit_generator(
        train_generator,
        samples_per_epoch=samples_per_epoch,
        epochs=EPOCH,
        validation_data=vaild_generator,
        validation_steps=validation_steps)

    target_dir = './modelresnet/'
    if not os.path.exists(target_dir):
        os.mkdir(target_dir)
    model.save('./modelresnet/resnet_50.h5')
    model.save_weights('./modelresnet/weights.h5')
    #loss,acc,top_acc=model.evaluate_generator(test_generator, steps=test_generator.n / batch_size)
    #print 'Test result:loss:%f,acc:%f,top_acc:%f' % (loss, acc, top_acc)

Answer 1

https://blog.csdn.net/lucky404/article/details/82931322