首页 > 代码库 > deep learning实践经验总结2--准确率再次提升,到达0.8,再来总结一下
deep learning实践经验总结2--准确率再次提升,到达0.8,再来总结一下
deep learning实践经验总结2
最近拿caffe来做图片分类,遇到不少问题,同时也吸取不少教训和获得不少经验。
这次拿大摆裙和一步裙做分类,
多次训练效果一直在0.7,后来改动了全链接层的初始化参数。高斯分布的标准差由0.001改为0.0001,就是调小了。
然后效果很明显,准确率高了,权重图画出来后,也看得出是有意义的了,部分权重图是人的轮廓或者裙子的轮廓。
先看看图片:
大摆裙
一步裙
然后找一些响应图看一下,当然我这里展示的是一些效果好的响应图。
大摆裙
一步裙
一些权重图:
这是网络的结构参数:
name: "CIFAR10_full_train" layers { layer { name: "cifar" type: "data" #source: "/home/linger/linger/testfile/crop_train_db" #source: "/home/linger/linger/testfile/collar_train_db" source: "/home/linger/linger/testfile/skirt_train_db" #source: "/home/linger/linger/testfile/pattern_train_db" meanfile: "/home/linger/linger/testfile/skirt_train_mean.binaryproto" #cropsize: 200 batchsize: 20 } top: "data" top: "label" } layers { layer { name: "conv1" type: "conv" num_output: 16 kernelsize: 5 stride:1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0. } blobs_lr: 1. blobs_lr: 1. weight_decay: 0.001 weight_decay: 0. } bottom: "data" top: "conv1" } layers { layer { name: "relu1" type: "relu" } bottom: "conv1" top: "conv1" } layers { layer { name: "pool1" type: "pool" pool: MAX kernelsize: 2 stride:1 } bottom: "conv1" top: "pool1" } layers { layer { name: "conv2" type: "conv" num_output: 16 group: 2 kernelsize: 5 stride:1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0. } blobs_lr: 1. blobs_lr: 1. weight_decay: 0.001 weight_decay: 0. } bottom: "pool1" top: "conv2" } layers { layer { name: "relu2" type: "relu" } bottom: "conv2" top: "conv2" } layers { layer { name: "pool2" type: "pool" pool: MAX kernelsize: 2 stride: 1 } bottom: "conv2" top: "pool2" } layers { layer { name: "ip1" type: "innerproduct" num_output: 100 weight_filler { type: "gaussian" std: 0.0001 } bias_filler { type: "constant" value: 0. } blobs_lr: 1. blobs_lr: 1. weight_decay: 0.001 weight_decay: 0. } bottom: "pool2" top: "ip1" } layers { layer { name: "ip2" type: "innerproduct" num_output: 2 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0. } blobs_lr: 1. blobs_lr: 1. weight_decay: 0.001 weight_decay: 0. } bottom: "ip1" top: "ip2" } #-----------------------output------------------------ layers { layer { name: "loss" type: "softmax_loss" } bottom: "ip2" bottom: "label" }
name: "CIFAR10_full_test" layers { layer { name: "cifar" type: "data" #source: "/home/linger/linger/testfile/collar_test_db" #source: "/home/linger/linger/testfile/crop_test_db" source: "/home/linger/linger/testfile/skirt_test_db" #source: "/home/linger/linger/testfile/pattern_test_db" meanfile: "/home/linger/linger/testfile/skirt_test_mean.binaryproto" #cropsize: 200 batchsize: 10 } top: "data" top: "label" } layers { layer { name: "conv1" type: "conv" num_output: 16 kernelsize: 5 stride:1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0. } blobs_lr: 1. blobs_lr: 1. weight_decay: 0.001 weight_decay: 0. } bottom: "data" top: "conv1" } layers { layer { name: "relu1" type: "relu" } bottom: "conv1" top: "conv1" } layers { layer { name: "pool1" type: "pool" pool: MAX kernelsize: 2 stride:1 } bottom: "conv1" top: "pool1" } layers { layer { name: "conv2" type: "conv" num_output: 16 group: 2 kernelsize: 5 stride:1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0. } blobs_lr: 1. blobs_lr: 1. weight_decay: 0.001 weight_decay: 0. } bottom: "pool1" top: "conv2" } layers { layer { name: "relu2" type: "relu" } bottom: "conv2" top: "conv2" } layers { layer { name: "pool2" type: "pool" pool: MAX kernelsize: 2 stride: 1 } bottom: "conv2" top: "pool2" } layers { layer { name: "ip1" type: "innerproduct" num_output: 100 weight_filler { type: "gaussian" std: 0.0001 } bias_filler { type: "constant" value: 0. } blobs_lr: 1. blobs_lr: 1. weight_decay: 0.001 weight_decay: 0. } bottom: "pool2" top: "ip1" } layers { layer { name: "ip2" type: "innerproduct" num_output: 2 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0. } blobs_lr: 1. blobs_lr: 1. weight_decay: 0.001 weight_decay: 0. } bottom: "ip1" top: "ip2" } #-----------------------output------------------------ layers { layer { name: "prob" type: "softmax" } bottom: "ip2" top: "prob" } layers { layer { name: "accuracy" type: "accuracy" } bottom: "prob" bottom: "label" top: "accuracy" }
# reduce learning rate after 120 epochs (60000 iters) by factor 0f 10 # then another factor of 10 after 10 more epochs (5000 iters) # The training protocol buffer definition train_net: "cifar10_full_train.prototxt" # The testing protocol buffer definition test_net: "cifar10_full_test.prototxt" # test_iter specifies how many forward passes the test should carry out. # In the case of CIFAR10, we have test batch size 100 and 100 test iterations, # covering the full 10,000 testing images. test_iter: 20 # Carry out testing every 1000 training iterations. test_interval: 100 # The base learning rate, momentum and the weight decay of the network. base_lr: 0.00001 momentum: 0.9 weight_decay: 0.004 # The learning rate policy lr_policy: "fixed" # Display every 200 iterations display: 20 # The maximum number of iterations max_iter: 60000 # snapshot intermediate results snapshot: 1000 snapshot_prefix: "cifar10_full" # solver mode: 0 for CPU and 1 for GPU solver_mode: 1
真的是多玩数据,才会对数据形成一种感觉啊。
下次玩3类的。敬请期待!
声明:以上内容来自用户投稿及互联网公开渠道收集整理发布,本网站不拥有所有权,未作人工编辑处理,也不承担相关法律责任,若内容有误或涉及侵权可进行投诉: 投诉/举报 工作人员会在5个工作日内联系你,一经查实,本站将立刻删除涉嫌侵权内容。