Skip to content
This repository has been archived by the owner on Mar 8, 2023. It is now read-only.

DOCKERFILE Merge flag TRANSFER_LEARNING and DROP_SOURCE_LAYER #99

Open
Mte90 opened this issue Aug 28, 2020 · 2 comments
Open

DOCKERFILE Merge flag TRANSFER_LEARNING and DROP_SOURCE_LAYER #99

Mte90 opened this issue Aug 28, 2020 · 2 comments
Labels
help wanted Extra attention is needed

Comments

@Mte90
Copy link
Member

Mte90 commented Aug 28, 2020

immagine

@Mte90 Mte90 added help wanted Extra attention is needed hacktoberfest labels Aug 28, 2020
@ilyasmg
Copy link
Collaborator

ilyasmg commented Oct 3, 2020

What should be done here? Only removing every TRANSFER_LEARNING in the DeepSpeech folder and putting a comment that when DROP_SOURCE_LAYER > 0 is transfer learning? Or should something else be done also?

@nefastosaturo
Copy link
Collaborator

Basically yes. As written on deepspeech doc when the option DROP_SOURCE_LAYER is > 0 you drop the number of layers specified and then start training with some previouos checkpoint from another train (eg: english checkpoint). Right now the script checks if TRANSFER_LEARNING is true and the starts downloading the ENG deepspeech checkpoints.

There is a recurrent case that need to be handled: how continue a previous training. In fact if I start again with the same flags (DROP_SOURCE_LAYER and TRANSFER LEARNING) the script (if I remember correctly) will skip the ENG checkpoints download but it will DROP the N layers from the previous iteration. And this could be a problem :)

In the second bullet point I added a quite extreme case that is load a previous IT checkpoint and dropping some layers (if we want for example start a new training from the IT release checkpoint while adding new characters to the alphabet this could be an option)

@nefastosaturo nefastosaturo changed the title Merge flag TRANSFER_LEARNING and DROP_SOURCE_LAYER DOCKERFILE Merge flag TRANSFER_LEARNING and DROP_SOURCE_LAYER Dec 17, 2020
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
help wanted Extra attention is needed
Projects
None yet
Development

No branches or pull requests

3 participants