Comments (4)
@wangxi123 Generally,training the SynthText and ICDAR 2013 with 300300 is enough, and the performance is even better if 700700 training is applied after 300*300. For SynthText, I trained it 50k iterations with batch size 32. For ICDAR 2013 dataset, I trained it 2k iterations with batch size 32.
Note that the parameter "min_dim" should not be changed when you change your training input size.
from textboxes.
@MhLiao Thanks,i will have a try.by the way,what your final loss about when you train SynthText for 300*300 size? I always feels that the loss of my training is too high...
from textboxes.
嗨,MhLiao。
我已经在SynthText和icdar2013上实现了你的TextBoxes。但是这里有一些困扰我的问题。我在icdar测试集中得到了700x700单一刻度的结果召回率= 0.488,精度= 0.938和f-measure = 0.64。对于多尺度,f-测量值为0.73。这似乎比你的结果更糟糕。
我的培训的详细信息如下:_第1步:预先_训练
synthText数据。
- pretrain模型:VGG_ILSVRC_16_layers_fc_reduced.caffemodel
- 列车数据:约85w SynthText,列车大小:700x700,批量大小:8(GPU限制)
- lr:0.0001用于6w迭代,0.00001用于其余12w迭代。总共18w迭代(损失约2.0)。
第2步:训练icdar2013列车数据- pretrain模型:步骤1的模型。
- 列车大小:700x700,batch_size = 4。
- lr:0.00001用于3k次迭代。(损失大约1.5)
我尝试了其他设置:列车数据调整大小为500x500但仍然有较低的召回率(约0.46)。顺便说一句,最终损失降至约2.0,当受过训练时synthdata,我不知道我是否没有
考虑到。
期待你的回复。
您能分享一下synthtext格式转换为icder格式的脚本吗?谢谢鸭!
from textboxes.
嗨,MhLiao。
我已经在SynthText和icdar2013上实现了你的TextBoxes。但是这里有一些困扰我的问题。我在icdar测试集中得到了700x700单一刻度的结果召回率= 0.488,精度= 0.938和f-measure = 0.64。对于多尺度,f-测量值为0.73。这似乎比你的结果更糟糕。
我的培训的详细信息如下:_第1步:预先_训练
synthText数据。
- pretrain模型:VGG_ILSVRC_16_layers_fc_reduced.caffemodel
- 列车数据:约85w SynthText,列车大小:700x700,批量大小:8(GPU限制)
- lr:0.0001用于6w迭代,0.00001用于其余12w迭代。总共18w迭代(损失约2.0)。
第2步:训练icdar2013列车数据- pretrain模型:步骤1的模型。
- 列车大小:700x700,batch_size = 4。
- lr:0.00001用于3k次迭代。(损失大约1.5)
我尝试了其他设置:列车数据调整大小为500x500但仍然有较低的召回率(约0.46)。顺便说一句,最终损失降至约2.0,当受过训练时synthdata,我不知道我是否没有
考虑到。
期待你的回复。
您能分享一下synthtext格式转换为icdar格式的脚本吗?谢谢鸭!
from textboxes.
Related Issues (20)
- Running TextBoxes on Caffe installed in Anaconda3 env HOT 2
- can not compile the CRNN HOT 5
- cannot find -lopencv_imgcodes HOT 1
- 关于模型的参数设置问题 HOT 3
- demo.py takes about 0.4s per image, when the model load only once and single scale is 700*700
- 关于 multi-scale的问题
- 关于Test的一些问题 HOT 8
- when i run "python examples/TextBoxes/train_icdar13.py",the error is occured when i train on my dataset.
- importError: libhdf5.so.101 HOT 1
- Where to place the downloaded model?
- Failed to run make -j8 HOT 1
- 请问如何您有synthtext数据集格式转换为icdar格式的脚本嘛,谢谢您分享一下鸭
- 请问如何能分享一下synthtext格式转换为icdar格式的脚本吗,谢谢鸭
- testing results on Total-Text HOT 1
- call for loss info/curve.
- 关于TextBoxes_icdar13.caffemodel模型
- Question about mismatch between the code with original paper
- icdar13 dataset consists of 229 training images and 233 testing images,
- will this work as an OCR solution? HOT 1
- Fine tuning on custom dataset: converting to LMDB HOT 5
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from textboxes.