Christian Bartz
Christian Bartz
it is used to build new models from scratch. No finetuning from svhn or fsns models is necessary
Hmm, not much I suppose... Just make sure you have already cropped text lines... you don;t really need to create a multistep curriculum for text recognition.
Remember: The `char_map` is only used as a mapping from a predicted class to a character. In order to make the code work with another `char_map` that has less classes,...
Hmm, okay I had a look at the code again. Turns out, the number of classes is already automatically adjusted based on the number of entries in the `char_map`. So...
When the error `KeyError: '35'` comes, you also get `training curriculum has finished. terminating the training process.`?
It seems that the system thinks your training converged enough, so that it can use the second level in the curriculum, which does not exist {look here](https://github.com/Bartzi/see/blob/master/chainer/utils/baby_step_curriculum.py#L82)... you could set...
please try to set `min_delta` to `1e-8` and try again
How many epochs did you train? Did it run for 200 epochs? Can you see any loss improvement? How large is your dataset? You could try to increase the batch...
It takes some time until things start to get better. Training a model using our approach does not work like training a model on ImageNet or something. The loss takes...
Did you have a look at the predictions of the model on a sample image (images in `bboxes` folder in log dir)? What happens there over the course of the...