欧美一区二区三区老妇人-欧美做爰猛烈大尺度电-99久久夜色精品国产亚洲a-亚洲福利视频一区二区

tensorflowpbtotflite精度下降的問(wèn)題-創(chuàng)新互聯(lián)

這篇文章主要講解了tensorflow pb to tflite精度下降的問(wèn)題,內(nèi)容清晰明了,對(duì)此有興趣的小伙伴可以學(xué)習(xí)一下,相信大家閱讀完之后會(huì)有幫助。

成都做網(wǎng)站、網(wǎng)站制作、成都外貿(mào)網(wǎng)站建設(shè)的關(guān)注點(diǎn)不是能為您做些什么網(wǎng)站,而是怎么做網(wǎng)站,有沒(méi)有做好網(wǎng)站,給創(chuàng)新互聯(lián)一個(gè)展示的機(jī)會(huì)來(lái)證明自己,這并不會(huì)花費(fèi)您太多時(shí)間,或許會(huì)給您帶來(lái)新的靈感和驚喜。面向用戶(hù)友好,注重用戶(hù)體驗(yàn),一切以用戶(hù)為中心。

之前希望在手機(jī)端使用深度模型做OCR,于是嘗試在手機(jī)端部署tensorflow模型,用于圖像分類(lèi)。

思路主要是想使用tflite部署到安卓端,但是在使用tflite的時(shí)候發(fā)現(xiàn)模型的精度大幅度下降,已經(jīng)不能支持業(yè)務(wù)需求了,最后就把OCR模型調(diào)用寫(xiě)在服務(wù)端了,但是精度下降的原因目前也沒(méi)有找到,現(xiàn)在這里記錄一下。

工作思路:

1.訓(xùn)練圖像分類(lèi)模型;2.模型固化成pb;3.由pb轉(zhuǎn)成tflite文件;

但是使用python 的tf interpreter 調(diào)用tflite文件就已經(jīng)出現(xiàn)精度下降的問(wèn)題,android端部署也是一樣。

1.網(wǎng)絡(luò)結(jié)構(gòu)

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
 
import tensorflow as tf
slim = tf.contrib.slim
 
def ttnet(images, num_classes=10, is_training=False,
   dropout_keep_prob=0.5,
   prediction_fn=slim.softmax,
   scope='TtNet'):
 end_points = {}
 
 with tf.variable_scope(scope, 'TtNet', [images, num_classes]):
 net = slim.conv2d(images, 32, [3, 3], scope='conv1')
 # net = slim.conv2d(images, 64, [3, 3], scope='conv1_2')
 net = slim.max_pool2d(net, [2, 2], 2, scope='pool1')
 net = slim.batch_norm(net, activation_fn=tf.nn.relu, scope='bn1')
 # net = slim.conv2d(net, 128, [3, 3], scope='conv2_1')
 net = slim.conv2d(net, 64, [3, 3], scope='conv2')
 net = slim.max_pool2d(net, [2, 2], 2, scope='pool2')
 net = slim.conv2d(net, 128, [3, 3], scope='conv3')
 net = slim.max_pool2d(net, [2, 2], 2, scope='pool3')
 net = slim.conv2d(net, 256, [3, 3], scope='conv4')
 net = slim.max_pool2d(net, [2, 2], 2, scope='pool4')
 net = slim.batch_norm(net, activation_fn=tf.nn.relu, scope='bn2')
 # net = slim.conv2d(net, 512, [3, 3], scope='conv5')
 # net = slim.max_pool2d(net, [2, 2], 2, scope='pool5')
 net = slim.flatten(net)
 end_points['Flatten'] = net
 
 # net = slim.fully_connected(net, 1024, scope='fc3')
 net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
      scope='dropout3')
 logits = slim.fully_connected(net, num_classes, activation_fn=None,
         scope='fc4') 
 end_points['Logits'] = logits
 end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
 
 return logits, end_points
ttnet.default_image_size = 28
 
def ttnet_arg_scope(weight_decay=0.0):
 with slim.arg_scope(
  [slim.conv2d, slim.fully_connected],
  weights_regularizer=slim.l2_regularizer(weight_decay),
  weights_initializer=tf.truncated_normal_initializer(stddev=0.1),
  activation_fn=tf.nn.relu) as sc:
 return sc

網(wǎng)頁(yè)名稱(chēng):tensorflowpbtotflite精度下降的問(wèn)題-創(chuàng)新互聯(lián)
鏈接URL:http://chinadenli.net/article10/ichgo.html

成都網(wǎng)站建設(shè)公司_創(chuàng)新互聯(lián),為您提供動(dòng)態(tài)網(wǎng)站、網(wǎng)站改版、全網(wǎng)營(yíng)銷(xiāo)推廣定制網(wǎng)站、商城網(wǎng)站、靜態(tài)網(wǎng)站

廣告

聲明:本網(wǎng)站發(fā)布的內(nèi)容(圖片、視頻和文字)以用戶(hù)投稿、用戶(hù)轉(zhuǎn)載內(nèi)容為主,如果涉及侵權(quán)請(qǐng)盡快告知,我們將會(huì)在第一時(shí)間刪除。文章觀點(diǎn)不代表本網(wǎng)站立場(chǎng),如需處理請(qǐng)聯(lián)系客服。電話(huà):028-86922220;郵箱:631063699@qq.com。內(nèi)容未經(jīng)允許不得轉(zhuǎn)載,或轉(zhuǎn)載時(shí)需注明來(lái)源: 創(chuàng)新互聯(lián)

綿陽(yáng)服務(wù)器托管