关于训练时Loss值不变的情况分析

今天在搭建简单模型训练花数据的时候发现loss,始终为一个数。

loss:实际输出值和标签值之间的误差距离。在分类任务中，如何评判输出和期望之间的接近？

交叉熵：刻画了两个概率分布之间的距离。是分类问题中应用比较广的一种损失函数。

反向更新权重：有了损失函数，知道了实际输出和真实值之间的距离，用梯度求导更新权重。

学习率：公式中的a就是学习率，表示的是每次权重更新的大小。

学习率设置：当学习率设置过大，x会在谷间震动，并没有更新。可以设置随着步伐增加，减小学习率。

import tensorflow as tf
import cv2 as cv
import numpy as np

filepath="/home/zw/数据集/flower_photos.tfrecords"
filequeue=tf.train.string_input_producer([filepath],shuffle=False)

reader=tf.TFRecordReader()

_,example=reader.read(filequeue)
features=tf.parse_single_example(
    example,
    features={
        'image':tf.FixedLenFeature([],tf.string),
        'label':tf.FixedLenFeature([],tf.int64),
    })
image=features['image']
decode_image=tf.decode_raw(image,tf.uint8)
decode_image=tf.reshape(decode_image,[600,600,3])
img = tf.cast(decode_image, tf.float32) * (1. / 255) - 0.5
label = tf.cast(features['label'], tf.int64)
img_batch,labels_batch=tf.train.shuffle_batch([img,label],batch_size=20,capacity=160,min_after_dequeue=100)


with tf.variable_scope('conv1') as scop1:
    w1=tf.get_variable('w1',[3,3,3,8],dtype=tf.float32,initializer=tf.truncated_normal_initializer(stddev=0.1,dtype=tf.float32))
    b1=tf.get_variable('b1',shape=[8],dtype=tf.float32,initializer=tf.constant_initializer(0.1,dtype=tf.float32))
    conv1=tf.nn.conv2d(img_batch,w1,strides=[1,2,2,1],padding='SAME')
    pre_activate1=tf.nn.bias_add(conv1,b1)
    relu1=tf.nn.relu(pre_activate1)
with tf.variable_scope('pooling5') as scop4:
    pooling5=tf.nn.max_pool(relu1,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
with tf.variable_scope('fc1') as scop5:
    dim=pooling5.get_shape().as_list()
    nodes=dim[1]*dim[2]*dim[3]
    reshape = tf.reshape(pooling5, [dim[0],nodes])
    wfc1=tf.get_variable('wfc1',shape=[nodes,1000],dtype=tf.float32,initializer=tf.truncated_normal_initializer(stddev=0.1,dtype=tf.float32))
    bfc1=tf.get_variable('bfc1',shape=[1000],dtype=tf.float32,initializer=tf.constant_initializer(0.1,dtype=tf.float32))
    fc1=tf.nn.relu(tf.matmul(reshape,wfc1)+bfc1)
with tf.variable_scope('fc3') as scop6:
    wfc3=tf.get_variable('wfc3',[1000,5],dtype=tf.float32,initializer=tf.truncated_normal_initializer(stddev=0.1))
    bfc3=tf.get_variable('bfc3',[5],dtype=tf.float32,initializer=tf.constant_initializer(0.1,dtype=tf.float32))
    fc3=tf.nn.relu(tf.matmul(fc1,wfc3)+bfc3)
    print(fc3)

with tf.variable_scope('loss') as scop7:
    cross_entropy=tf.nn.sparse_softmax_cross_entropy_with_logits(labels=labels_batch,logits=fc3,name='xentropy_pre_example')
    loss=tf.reduce_mean(cross_entropy)

with tf.variable_scope('optimizer') as scop8:
    optimizer=tf.train.AdamOptimizer(learning_rate=0.00000001)
    #global_step=tf.Variable(0,name='global_step',trainable=False)
    train_op=optimizer.minimize(cross_entropy)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    coord=tf.train.Coordinator()
    threads=tf.train.start_queue_runners(sess=sess,coord=coord)
    for i in range(2000):
        lossed,trained=sess.run([loss,train_op],)
        print(lossed)
    coord.request_stop()
    coord.join(threads)