如何获取/定义图形的输入输出名称或以适当的形式冻结它 [英] How can i obtain/define input output names of my graph or freeze it in proper form

问题描述

大家好，我们一直试图将模型保存为.bytes格式，以便我们可以在c#脚本中使用它.我们正在使用tensorflow 1.7.0这是我们的模型:

Hi everyone we have been trying to save our model in .bytes format so that we can use it in a c# script. We are using tensorflow 1.7.0 Here is our model:

bsize=16


# define cnn model
def define_model():
    # load model
    model = VGG16(include_top=False, input_shape=(224, 224, 3))
    # mark loaded layers as not trainable
    for layer in model.layers:
        layer.trainable = False
    # add new classifier layers
    flat1 = Flatten()(model.layers[-1].output)
    class1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)
    output = Dense(2, activation='softmax')(class1)
    # define new model
    model = Model(inputs=model.inputs, outputs=output)
    # compile model
    # compile model
    opt = Adam(lr=0.001)
    model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])
    return model

培训:

sess=tf.Session()
tf.global_variables_initializer().run(session=sess)
model = define_model()
# create data generator
datagen = ImageDataGenerator(rescale=1.0/255.0)
# prepare iterators
train_it = datagen.flow_from_directory(mpath+'/train',
class_mode='categorical', batch_size=bsize, target_size=(224, 224))
test_it = datagen.flow_from_directory(mpath+'/test',
class_mode='categorical', batch_size=bsize, target_size=(224, 224))
# fit model
history = model.fit_generator(train_it, steps_per_epoch=len(train_it),
validation_data=test_it, validation_steps=len(test_it), epochs=1, verbose=0)
# evaluate model
_, acc = model.evaluate_generator(test_it, steps=len(test_it), verbose=0)
print('> %.3f' % (acc * 100.0))

model.save_weights("weights.h5")

冻结:

K.clear_session()
K.set_learning_phase(0)
model = define_model()
model.load_weights("weights.h5")

save_dir = "./out"


tf.saved_model.simple_save(K.get_session(),
                           save_dir,
                           inputs={"input": model.inputs[0]},
                           outputs={"output": model.outputs[0]})

freeze_graph.freeze_graph(None,
                          None,
                          None,
                          None,
                          model.outputs[0].op.name,
                          None,
                          None,
                          os.path.join(save_dir, "frozen_model.bytes"),
                          False,
                          "",
                          input_saved_model_dir=save_dir)

然后我们尝试使用以下命令查看输入和输出名称:

Then we try to see input and output names using:

    model.inputs[0].name
    model.ouputs[0].name

最后，我们希望在c#中将此图形用作:

Finally we would like to use this graph in c# as:

.AddInput(graph["input_1_1:0"][0], tensor).Fetch(graph["output"][0]);

但是，从错误中我们可以理解，输入和输出名称是错误的.而且，只要我们打电话

However, as we understand from the error input and output names are wrong. Moreover whenever we call

model.inputs[0].name
model.ouputs[0].name

即使我们将输出名称定义为name ="output"

they print different input and output names even if we define output name as name="output"

您对如何冻结此模型，获取输入和输出名称等有任何建议

Do you have any suggestions about how to freeze this model, obtain input and output names etc

致谢

推荐答案

对于有类似问题的人:

model.inputs[0].name
model.ouputs[0].name

这样的收益:

input_1:0
dense_2/Softmax:0

但是您不应该在.AddInput中直接使用它们，而不是:

but you shouldnt use them directly in .AddInput so instead of:

.AddInput(graph["input_1:0"][0], tensor).Fetch(graph[dense_2/Softmax:0][0]);

这样做:

.AddInput(graph["input_1"][0], tensor).Fetch(graph[dense_2/Softmax][0]);

因此，上面的代码实际上是有效的，只是省略了名称字符串中的:0部分，仅此而已:D

So the code above actually works just omit the :0 part from the name strings and thats all :D

这篇关于如何获取/定义图形的输入输出名称或以适当的形式冻结它的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！