Skip to content

Latest commit

 

History

History
 
 

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 

README.md

HTR Model

HTR models have to be used with Kraken.

Except for preliminary experimentations (bleu.mlmodel), we use the same test set, available here, to compare the efficiency of the different models.

Models are named after cheeses, following an alphabetical order.

bleu.mlmodel

Production

This model was produced with the v 1.0 of the dataset. It was divided in three sets : train (training set), val (evaluation set) and test (test set), created with the following script.

  1. train contained 82.76% of total dataset.
  2. val contained 7.61% of total dataset.
  3. test contained 9.62% of total dataset.

Commands used are:

  • ketos train -t train.txt -e val.txt -u NFKD -f alto for training
  • ketos test -m model -f alto -e test.txt for testing

Results

Accuracy is:

  • 96% on the evaluation set
  • 91% on the test set.

cheddar.mlmodel

Production

This model was produced with the v. 2.0 of the dataset. It was divided in three sets : train (training set), val (evaluation set) and test (test set). The first two were created with train_val_prep.py. The test set is available here.

  1. train contained 75% of total dataset.
  2. val contained 10% of total dataset.
  3. test contained 15% of total dataset.

Note: a problem occured during training. This model should not be used.

Commands used are:

  • ketos train -t train.txt -e val.txt -f alto -d cuda --normalization NFD for training
  • ketos test -m model -f alto -e test.txt for testing

Results

Accuracy is:

  • 96.3% on the evaluation set

dentduchat.mlmodel

Production

This model was produced with the v. 2.0 of the dataset. It was divided in three sets : train (training set), val (evaluation set) and test (test set). The first two were created with train_val_prep.py. The test set is available here.

  1. train contained 75% of total dataset.
  2. val contained 10% of total dataset.
  3. test contained 15% of total dataset.

Commands used are:

  • ketos train -t train.txt -e val.txt -f alto -d cuda --normalization NFD for training
  • ketos test -m model -f alto -e test.txt for testing

Results

Accuracy is:

  • 96.6% on the evaluation set