keras写resnet34应用时输出不变
网络结构如下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
#对于identity_Block的nb_filter以及bottleneck_Block的nb_filters进行说明：如上图所示：resNet34里面，每一个卷积层当中的nb_filter仅仅是一种，而resnet50里面每一层的filter有多种
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()
return x
else:
x = add()
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
但是通过
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
不论输入什么图片都会输出相同的结果这是为什么
之前用model.add的时候就不会有这种问题，是不是结构写法跟
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,
)
model.compile(loss='categorical_crossentropy',
optimizer=optimizers.RMSprop(lr=lr),
metrics=['accuracy'])
print ('Model Compiled')
target_best_valacc_dir = './modelresnetbest/'
if not os.path.exists(target_best_valacc_dir):
os.mkdir(target_best_valacc_dir)
checkpoint = ModelCheckpoint(target_best_valacc_dir,
monitor='val_acc', save_weights_only=True,verbose=1,save_best_only=True, period=1)
model.fit_generator(
train_generator,
steps_per_epoch=steps_per_epoch,
epochs=EPOCH,
validation_data=vaild_generator,
validation_steps=validation_steps)
不兼容导致的 您好，看到你的关于测试模式 的问题 不知道您解决了没有？我最近用pytorch也遇到了相同的问题？想请教一下
页:
[1]