是什么导致了 Tensorflow 中的控制台输出？

Question

Tensorflow 在控制台中输出了很多输出，你能告诉我我的程序中的哪些代码导致了这个输出吗？另外，我该如何抑制它？
…… 变量/初始化器/initial_value/7859，变量/初始化器/initial_value/7860，变量/初始化器/initial_value/7861，变量/初始化器/initial_value/7862，变量/初始化器/initial_value/7863，变量/初始化器/initial_value/7864，变量/ Initializer/initial_value/7865，Variable/Initializer/initial_value/7866，Variable/Initializer/initial_value/7867，Variable/Initializer/initial_value/7868，Variable/Initializer/initial_value/7869，Variable/Initializer/initial_value/7870，Variable/Initializer/初始值/7871、变量/初始化器/initial_value/7872、变量/初始化器/initial_value/7873、变量/初始化器/initial_value/7874、变量/初始化器/initial_value/7875、变量/初始化器/initial_value/7876、变量/初始化器/initial_value/ 7877，变量/初始化程序/initial_value/7878，变量/初始化程序/initial_value/7879，变量/初始化程序/initial_value/7880，变量/初始化程序/initial_value/7881，变量/初始化程序/initial_value/7882，变量/初始化izer/initial_value/7883、Variable/Initializer/initial_value/7884、Variable/Initializer/initial_value/7885、Variable/Initializer/initial_value/7886、Variable/Initializer/initial_value/7887、Variable/Initializer/initial_value/7888、Variable/Initializer/初始值/7889，变量/初始化器/initial_value/7890，变量/初始化器/initial_value/7891，变量/初始化器/initial_value/7892，变量/初始化器/initial_value/7893，变量/初始化器/initial_value/7894，变量/初始化器/initial_value/ 7895，变量/初始化器/initial_value/7896，变量/初始化器/initial_value/7897，变量/初始化器/initial_value/7898，变量/初始化器/initial_value/7899，变量/初始化器/initial_value/7900，变量/初始化器/initial_value/7901， Variable/Initializer/initial_value/7902, Variable/Initializer/initial_value/7903, Variable/Initializer/initial_value/7904)' 输入形状：[7], [7], [7], [7], [7], [ 7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7] , [7], [7], [7], [7], [7], [6], [7], [7], [7], [7], [7], [7], [7], [7 ], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7] ]，[7]， [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7] ], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7] ], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7] ], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7] ], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7] ], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7] ], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7]、[7]、[7]、[7]、[7]、[7]、[7]、 [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7] ], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7] ], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7] ], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7] ], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7] ], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7] ], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7]、[7]、[7]、[7]、[7]、[7]、[7]、 [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7] ], [7], [7], [7], [7], [7], [7], [7], [7], [7], [7],......
这是我的代码

class LSTMmodel(tf.Module):
    def __init__(self, arg_name=None):
        super().__init__(name=arg_name)
        self.__input = tf.Variable(initial_value=[0.0 for x in range(7)], dtype=tf.float32)
        self.__input_reshaped = tf.reshape(self.__input, [1, 7, 1])
        self.__network = tf.keras.layers.LSTM(units=7, input_shape=(7,1))
        self.__output = tf.Variable(initial_value=[0.0 for x in range(7)], dtype=tf.float32)
        self.__output = tf.reshape(self.__output, [1, 7, 1])
    @tf.function
    def networkTraining(self, arg_data_train, arg_labels, arg_learning_rate):
        with tf.GradientTape() as t:
            print('loc 1')
            self.__input = tf.Variable(arg_data_train)
            print('loc 2')
            self.__input_reshaped = tf.reshape(self.__input, [1, 7, 1])
            self.__output = self.__network(self.__input_reshaped)
            print('loc 3')
            loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=arg_labels, logits=self.__output)
            print('loc 4')
            dw, db = t.gradient(loss, [self.w, self.b])
            print('loc 5')
        self.w.assign_sub(arg_learning_rate * dw)
        self.b.assign_sub(arg_learning_rate * db)

    @tf.function
    def __call__(self, arg_input=[0 for x in range(7)]):
        self.__input = tf.Variable(arg_input)
        self.__output = self.__network(self.__input)
        return self.__output

# some other code
#
#
#
modela.networkTraining(cgm ,labels, 0.4)

编辑：
'Variable/Ini..../' 发生在 print('loc 4')

之前

# ###########################FULL-CODE
import pandas
import scipy.io as loader
import tensorflow as tf
import keras
import numpy

tf.get_logger().setLevel('INFO')
class LSTMmodel(tf.Module):
    def __init__(self, arg_name=None):
        super().__init__(name=arg_name)
        self.__input = tf.Variable(initial_value=[0.0 for x in range(7)], dtype=tf.float32)
        self.__input_reshaped = tf.reshape(self.__input, [1, 7, 1])
        self.__network = tf.keras.layers.LSTM(units=7, input_shape=(7,1))
        self.__output = tf.Variable(initial_value=[0.0 for x in range(7)], dtype=tf.float32)
        self.__output = tf.reshape(self.__output, [1, 7, 1])
    @tf.function
    def networkTraining(self, arg_data_train, arg_labels, arg_learning_rate):
        with tf.GradientTape() as t:
            print('loc 1')
            self.__input = tf.Variable(arg_data_train)
            print('loc 2')
            self.__input_reshaped = tf.reshape(self.__input, [1, 7, 1])
            self.__output = self.__network(self.__input_reshaped)
            print('loc 3')
            loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=arg_labels, logits=self.__output)
            print('loc 4')
            dw, db = t.gradient(loss, [self.w, self.b])
            print('loc 5')
        self.w.assign_sub(arg_learning_rate * dw)
        self.b.assign_sub(arg_learning_rate * db)

    @tf.function
    def __call__(self, arg_input=[0 for x in range(7)]):
        self.__input = tf.Variable(arg_input)
        self.__output = self.__network(self.__input)
        return self.__output
    # tf.nn.sigmoid_cross_entropy_with_logits(labels=None, logits=None)

correct = numpy.load('save.npy')
# link for the .mat file for your convenience
# https://drive.google.com/file/d/1NOZOeRm1oLOU12p3J4-zw3RrPnJZvw4-/view?usp=sharing
insulin = loader.loadmat('InsulinGlucoseData2.mat')
also = pandas.read_csv('dates222.csv')

# print(type(insulin['numCGM'][0:5]))
# quit()
cgm = []
temp = []
labels = []
# print(insulin['numCGM'])
# print(insulin['actBolusDelivered'])
counter = also.shape[0] - 1
counta = 0
# print(len(insulin['numCGM']))
while counter >= 0:
    if also['classification2'][counter] == 1:
        cgm.append(insulin['numCGM'][0][counter:counter + 6])
        labels.append([0, 0, 0, 0, 0, 0, 1])
        counter = counter - 7
    elif also['classification2'][counter] == 0:
        counter = counter - 1
        counta = counta + 1
        temp.append(insulin['numCGM'][0][counter])
        if counta == 7:
            counta = 0
            cgm.append(temp)
            temp = []
            labels.append([0, 0, 0, 0, 0, 0, 0])
    if counter - 7 < 0: break
    # print(counter)
# print(len(cgm[0]))
# quit()
modela = LSTMmodel(arg_name='ghajini_disease')
# print('------------------------------------------------')
# cgm = numpy.array(cgm, numpy.float32)
for each in labels:
    for each_one in each:
        each_one = float(each_one)
# print(len(labels))
# print('------------------------------------------------')
modela.networkTraining(cgm ,labels, 0.4)

out = modela(cgm)
print(out)

for each in out:
    su = su + each[-1]

train_accuracy = su/sum(labels) * 100

test = modela(new)

编辑：
我怀疑这个问题是在self.__input = tf.Variable(arg_data_train) 行引起的。 arg_data_train实际上是python列表的python列表。不过我还是不明白控制台的输出。

Answer 1

这些日志可能是由于您的代码循环造成的。 您可以使用

关闭这些日志

import os
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
import tensorflow as tf