目录整理
来源:互联网 发布:php上传文件原理 编辑:程序博客网 时间:2024/06/05 20:15
overall
Location of data
Text: /home/c-nrong/VQA/draw/Json/question_answers_jan.json
/home/c-nrong/VQA/draw/Json/question_answers_genome.json
Images: /home/c-nrong/VQA/VG_100K_all/
/home/c-nrong/VQA/VG_100K/
/home/c-nrong/VQA/VG_100K_2/
experiment
There are three main directories:
VQA/
fixtestset/
fixtestset_2/
About “VQA/”
the number of training samples and test samples are changed in each file folder, though the sum of the two number is fixed.
However, since the number of test samples are not fixed, the results of those experiments are uncomparable.
That why I created “fixtestset/” and “fixtestset2/”
In each file folder, there is a “READMED.md” whch shows descriptions/details for the file folder.
About “fixtestset_2/”
copy from ../fixtestset/
the difference is that when train the model, this dir will be initialized by /home/c-nrong/fixtestset/Jan_HieCoAttenVQA_3by10/save/train_vgg_Alternating/model_id0_iter0.t7
conclusion
1. “fixtestset_2” is useless.
2. most of the file folders in “VQA/” are useless.
3. focus on “fixtestset/”
VQA/
outlines for each file folder
by default: training is random.
DataLoaderDish.lua:ix = split_ix[torch.random(max_index)]
To make different experiments comparable, I change it to “order”.
that is: DataLoaderDish.lua:ix = split_ix[ri]
HieCoAttenVQA/ : for testing(for example:sometime I may wanna know the dimension of a variable)
train: 345049 test:317564HieCoAttenVQA2/: use to generate genome english attenmaps (github: VQA_en)
- Jan_HieCoAttenVQA/: (check “_readme”) (github: VQA_jan)
v1_all_1dividedby196(done)
v1_all_1(done)
v2_onlyA(done) - Jan_HieCoAttenVQA2/: a copy of “3”. (only to run “without attenmaps”)
th train.lua -use_english_attenmaps 0
res1: train randomly. (done)
res2: train according to order.(DataLoaderDish.lua:ix = split_ix[torch.random(max_index)], ix = split_ix[ri])
(done) - Jan_HieCoAttenVQA3/: a copy of “3”. (2016.11.02-14:53)
v2_addone: attenmaps=attenmaps + 1 (changed prepro/prepro_atten_new.py)
(running) [screen: addone] - Jan_HieCoAttenVQA4//: a copy of “3”.
v2_onlyA_order [screen:onlyA_order] - Jan_HieCoAttenVQA5//: a copy of “5”
v2_addone_order[screen:addone_order]
[8-12: order]
8. Jan_HieCoAttenVQA6/: a copy of “6” (trainset and testset number are changed)) train=train*(1/10)
train: 35146 test:780214
9. Jan_HieCoAttenVQA7/: a copy of “8” (trainset and testset number are changed)) train=train*(3/10)
train:103042 test:677405
10. Jan_HieCoAttenVQA8/: a copy of “8” (trainset and testset number are changed)) train=train*(5/10)
train:170422 test:574596
11. Jan_HieCoAttenVQA9/: a copy of “8” (trainset and testset number are changed)) train=train*(7/10)
train:237258 test:471787
12. Jan_HieCoAttenVQA10/: a copy of “8” (trainset and testset number are changed)) train=train+test(1:trainum/2)
fixtestset/
outline for each folder
test=7566 ( copy from ~/VQA/Jan_HieCoAttenVQA10/genIDs/testID.txt)--VQA/Jan_HieCoAttenVQA_1by10/: copy from ~/VQA/Jan_HieCoAttenVQA6/train=~/VQA/Jan_HieCoAttenVQA6/genIDs/trainID.txt--VQA/Jan_HieCoAttenVQA_3by10/: copy from ~/VQA/Jan_HieCoAttenVQA6/train=~/VQA/Jan_HieCoAttenVQA7/genIDs/trainID.txt--VQA/Jan_HieCoAttenVQA_5by10/: copy from ~/VQA/Jan_HieCoAttenVQA6/train=~/VQA/Jan_HieCoAttenVQA8/genIDs/trainID.txt--VQA/Jan_HieCoAttenVQA_7by10/: copy from ~/VQA/Jan_HieCoAttenVQA6/train=~/VQA/Jan_HieCoAttenVQA9/genIDs/trainID.txt--VQA/Jan_HieCoAttenVQA_10by10/: copy from ~/VQA/Jan_HieCoAttenVQA6/train=~/VQA/Jan_HieCoAttenVQA4/genIDs/trainID.txt--VQA/Jan_HieCoAttenVQA_15by10/: copy from /VQA/Jan_HieCoAttenVQA10/
about “experiment/”
There are two types of attention: “alternating”(default) and “parallel”.
Fix the test set, and change the number of training set(6 values in total): Jan_HieCoAttenVQA_${i}by10/
, Jan_HieCoAttenVQA_${i}by10_without/
where i={1,3,5,7,10,15}
And since the intialization does influence the performance of the model, each experiment will be run five times.
So, finally:
Alternating
“./fixtestset/1/”
“./fixtestset/2/”
“./fixtestset/3/”
“./fixtestset/4/”
“./fixtestset/5/”
Parallel
“./fixtestset/experiments/Parallel/1/”
“./fixtestset/experiments/Parallel/2/”
“./fixtestset/experiments/Parallel/3/”
“./fixtestset/experiments/Parallel/4/”
“./fixtestset/experiments/Parallel/5/”
fixtestset2/
outline for each file folder
test=7566 ( copy from ~/VQA/Jan_HieCoAttenVQA10/genIDs/testID.txt)copy from ../fixtestset/the difference is that when train the model, this dir will be initialized by /home/c-nrong/fixtestset/Jan_HieCoAttenVQA_3by10/save/train_vgg_Alternating/model_id0_iter0.t7----------------------train.lua -use_english_attenmaps 0 -start_from /home/c-nrong/fixtestset/Jan_HieCoAttenVQA_3by10/save/train_vgg_Alternating/model_id0_iter0.t7th train.lua -start_from /home/c-nrong/fixtestset/Jan_HieCoAttenVQA_3by10/save/train_vgg_Alternating/model_id0_iter0.t7
Analysis
In “fixtest/” directory, there are three “Analysis” file folders:
1. /home/c-nrong/fixtestset/Analysis/
2. /home/c-nrong/fixtestset/experiments/Analysis
3. /home/c-nrong/fixtestset/experiments/Parallel/Analysis
(copy from 2./home/c-nrong/fixtestset/experiments/Analysis
)
If you just want to check the result for one experiment, use “1”.
If you want to check the results for five experiments(since the initialization does influence the perfomance, for each setting, the experiment will be run five times), use “2”.
other analysis
/home/c-nrong/VQA/draw/
/home/c-nrong/fixtestset/experiments/DivideDataset
“2” is important.
Most of graphs(mainly about the dataset) which are used in the paper can be generated here.
- 整理目录
- 目录整理
- 目录操作整理
- Android学习整理目录
- iOS学习整理目录
- 数据结构学习整理目录
- 博客文章目录整理
- 面试题整理:目录
- jQuery整理笔记目录
- 数字目录整理
- 最近整理博客目录
- Java多线程目录整理
- Android 博客目录整理
- 资料整理(目录)
- 010 资源目录整理
- 笔记整理目录
- 资料整理(目录)
- Django目录整理
- Laravel设置timezone时区
- ebay产品名称分析
- HTML语义化
- JavaScript加载速度倍增的方法。
- JQery图片淡入淡出效果案例
- 目录整理
- C++中的虚函数(virtual function)
- CodeFroces 817D Imbalanced Array(单调栈)
- iOS索引,按字母排序
- Spring中@Bean与@Configuration
- 游戏引擎概念----快速了解
- hashmap在初始化的时候直接赋值的方法
- 信息学蒟蒻域ACM模拟赛题解
- 测试ip是否可用(ip代理时)