Comments (10)
@bgshih If I want the model to recognize words and multi-digit numbers both then will fine-tuning the model (already trained on VGG Synthetic word dataset) on dataset like Street View House Number (SVHN) gonna help? Or I need to retrain the model from the scratch?
from crnn.
@rayush7 I strongly feel fine-tuning be a better choice than starting from scratch.
from crnn.
The model is trained on a dataset that is heavily biased towards a-z characters. Training on a balanced dataset would help.
from crnn.
Thanks @bgshih
from crnn.
@bgshih Could you please explain the format of the single/multi digit labels for creating lmdb datasets?
Example if there is a word "Apple" in the image then setting its groundtruth label as the string 'Apple' is working for me. I can convert it into lmdb format and create my train and validation set and train my own model.
But if I have numerical labels for example number 350 in the image then by setting its label to string '350' is giving me error in the ascii2label function (in utilities.lua). Even though in ascii2label function if conditions are present to take into account the numerical digit values but still its throwing the error. Please explain what should be the groundtruth format of the single/multi digit labels for creating lmdb datasets?
from crnn.
@rayush7 This is not an expected behavior. What was the error message and where was it thrown?
from crnn.
@bgshih Hey the problem was in my lmdb dataset and not in code. The label string was in unreadable form. I resolved this problem. Now giving the '350' as a label for a image with number 350 in it works like a charm! Thanks @bgshih
from crnn.
@bgshih I am trying to finetune the crnn model (pretrained on vgg synthetic dataset) on svhn dataset. The images (32x32) I am using look like these
While finetuning, the training loss is showing random patterns and no legitimate inference can be drawn because of that. Also all the validation set images are classified as "1". I am unable to figure out if this is a problem due to wrong choice of optimization parameters or crnn is unfit for training on such images. I am using the default config.lua file with adadelta as the optimizer. Any suggestions on what mistake I am making and how can I rectify that?
from crnn.
@bgshih , @rayush7 can you tell me the steps you followed to fine tune the pre-trained mode with your own dataset. l'm newbie on fine tuning pre-trained model. l want to try it for the first time .
Thank you
from crnn.
@rayush7 Did you train the model with digits? If so, could you post it online?
from crnn.
Related Issues (20)
- compile fbthrift in ubuntu 16.04
- Could you give me some suggestions for training dataset? HOT 1
- About BK-tree you mentioned in the paper HOT 2
- The recognition results are reversed
- 我是cpu环境咋办
- create_dataset occur something wrong
- index-pack failed
- how to generate rgb lmdb by your tools
- Estimating receptive field to feature sequence vector mapping
- lmdb.Error:../data: Function not implemented
- Nan will appear with GPU training, but not with CPU
- lmdb.Error HOT 4
- how to run this command in google colab th main_train.lua ../models/foo_model/
- Update README as some links is invalid
- Data Requirement
- which dataset I can use for crnn training ? HOT 2
- Outdated docker
- How to convert Synth900k to lmdb? HOT 1
- manifest unknown -> manifest for kaixhin/cuda-torch:latest not found: manifest unknown: manifest unknown
- Creating lmdb dataset in google colab HOT 1
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 crnn.