我有一个张量流模型，我的问题是精度没有增加，或者错误率没有降低
我已经尝试降低学习率并将辍学应用于每个图层，但结果并未显示出模型的任何改进。
如何提高模型的准确性和错误率？
----这是model.py中的模型代码
import tensorflow as tf
import os
import time
import sys
import numpy as np
from tensorflow.python.platform import gfile
class cnn(object):
def __init__(self, sizevocab, lengthsequence, num_class, batch_size):
self.x = tf.placeholder(tf.int32, [None, lengthsequence], name = "x")
self.y = tf.placeholder(tf.float32, [None, num_class], name = "y")
self.keep_drop = tf.placeholder(tf.float32)
print("target")
print(self.y)
# ------for svm model------
self.dimension = 64
self.sizefilter = [2,3,4]
self.numfilter = 8
self.is_training = tf.placeholder(tf.bool,[], name= "is_training")
self.global_step = tf.Variable(0, name = "global_step")
self.learning_rate = 0.0001
with tf.name_scope("embeddings"):
# word_embedding = tf.get_variable("word_embedding", [vocabulary, dimension])
# embedded_word_id = tf.nn.embedding_lookup(word_embedding, self.x)
self.word_embedded = tf.Variable(tf.truncated_normal([sizevocab, self.dimension], 1, 2), name = "embedding")
print("input")
print(self.word_embedded)
self.embeddedlook = tf.nn.embedding_lookup(self.word_embedded, self.x)
print("embed")
print(self.embeddedlook)
self.embedinput = tf.expand_dims(self.embeddedlook, -1)
print("embedded")
print(self.embedinput)
pool_output = []
for i,filter_size in enumerate(self.sizefilter):
weight = tf.truncated_normal([filter_size, self.dimension, 1, self.numfilter], stddev = 0.1)
print("weight1:")
print(weight)
bias = tf.zeros([self.numfilter])
print("bias1")
print(bias)
convolutionlayer = tf.nn.conv2d(self.embedinput, weight, strides=[1,1,1,1], padding = 'VALID') + bias
print("convolutional layer")
print(convolutionlayer)
rectified = tf.nn.relu(convolutionlayer)
drop1 = tf.nn.dropout(rectified, self.keep_drop)
# poolinglayer
# continue layer -IrwanMaryam
print("convolutional layer ")
print(convolutionlayer)
print("rectified layer")
print(rectified)
pooling = tf.nn.max_pool2d(drop1, [1, lengthsequence - filter_size +1 , 1, 1], [1,2,2,1], padding = 'VALID', name = "pool")
print("pooling")
print(pooling)
pool_output.append(pooling)
print("shape pool")
print(pool_output)
# full connected layer
self.totalfilter = self.numfilter * len(self.sizefilter)
flat1 = tf.concat(pool_output, 3)
flat = tf.reshape(flat1, [-1, self.totalfilter])
print("totalfilter")
print(self.totalfilter)
print("flat output")
print(flat1)
print("flat_fc")
print(flat)
weight_fc = tf.truncated_normal([self.totalfilter, 16], stddev = 0.01)
bias_fc = tf.zeros([16])
fc = tf.matmul(flat, weight_fc) + bias_fc
drop = tf.nn.dropout(fc, self.keep_drop)
# weight_fc2 = tf.truncated_normal([lengthsequence, lengthsequence])
# bias_fc2 = tf.zeros([lengthsequence])
# fc2 = tf.matmul(fc,weight_fc2) + bias_fc2
# reshape_svm = tf.reshape(fc2, [-1, lengthsequence])
# print("fc2 :")
# print(fc2.shape)
weightsvm = tf.truncated_normal([16, num_class], stddev = 0.01)
print("weight svm")
print(weightsvm)
B = tf.zeros([num_class])
raw = tf.subtract(tf.matmul(drop,weightsvm), B)
drop2 = tf.nn.dropout(raw, self.keep_drop)
print("output :")
print(raw)
# ----SVM Model-------
with tf.name_scope('SVM_MODEL'):
l2_norm = tf.reduce_mean(tf.square(weightsvm))
alpha = tf.constant([0.1])
classification_term = tf.reduce_mean(tf.maximum(0., tf.subtract(1., tf.multiply(drop2, self.y))))
self.loss = tf.add(classification_term, tf.multiply(alpha, l2_norm))
pred = tf.sign(raw)
self.accuracy = tf.reduce_mean(tf.cast(tf.equal(pred, self.y), tf.float32))
optimizer = tf.train.AdamOptimizer(learning_rate = self.learning_rate)
gradvars = optimizer.compute_gradients(self.loss, aggregation_method = 2)
self.trainop = optimizer.apply_gradients(gradvars, global_step = self.global_step)
---这是在train.py中进行训练的循环
import tensorflow as tf
import numpy as np
import os
import time
import datetime
from filtertext import *
import sys
from cnnsvm import cnn
# from utils import *
from sklearn.model_selection import train_test_split
from tensorflow.contrib import learn
x, y, vocabulary, vocabulary_invi = load_data()
keep_probability = tf.placeholder(tf.float32)
sizevocab = len(vocabulary)
epoch = 10000
batch_size = 512
Xtrain, xtest, ytrain, ytest = train_test_split(x, y, test_size = 0.1)
lengthsequence = Xtrain.shape[1]
num_class = ytrain.shape[1]
with tf.Session() as sess:
model = cnn(sizevocab, lengthsequence, num_class, batch_size)
init_op = tf.compat.v1.global_variables_initializer()
sess.run(init_op)
saver = tf.compat.v1.train.Saver(tf.global_variables())
trainBatch = batch_iter(Xtrain, ytrain, batch_size, epoch)
for batch in trainBatch:
Xbatch,Ybatch = batch
train_dict = {model.x: Xbatch, model.y:Ybatch, model.keep_drop: 0.5}
_, step, loss, accuracy = sess.run([model.trainop, model.global_step, model.loss, model.accuracy], feed_dict = train_dict)
print("step {0}: loss = {1} accuracy = {2}".format(step, loss, accuracy))
# current_step = tf.train.global_step(sess, model.global_step)
if step % 300 == 0:
feed_dict = {model.x: xtest, model.y: ytest, model.keep_drop: 1.0}
print("Evaluate : ")
accuracy, loss= sess.run([model.accuracy, model.loss], feed_dict = feed_dict)
# train_accuracy = sess.run(model.accuracy, feed_dict = feed_dict)
print("step {0}: accuracy = {1} loss = {2}".format(step, accuracy, loss))
学习的结果如下：
step 11690: loss = [0.9972683] accuracy = 0.3134765625
step 11691: loss = [1.0026996] accuracy = 0.1650390625
step 11692: loss = [1.0028301] accuracy = 0.1689453125
step 11693: loss = [0.9968007] accuracy = 0.3642578125
step 11694: loss = [0.9940929] accuracy = 0.3857421875
step 11695: loss = [1.0010462] accuracy = 0.22265625
step 11696: loss = [1.0015349] accuracy = 0.201171875
step 11697: loss = [0.99722] accuracy = 0.3349609375
step 11698: loss = [0.99936765] accuracy = 0.2724609375
step 11699: loss = [1.0001634] accuracy = 0.21875
step 11700: loss = [0.9981262] accuracy = 0.2783203125
Evaluate :
step 11700: accuracy = 0.254451721906662 loss = [0.9997652]