qurator-spk/sbb_pixelwise_segmentation
1
0
Fork 0
mirror of https://github.com/qurator-spk/sbb_pixelwise_segmentation.git synced 2025-06-07 19:05:24 +02:00
Code Issues Releases Wiki Activity

Update README.md

Browse source
This commit is contained in:
Clemens Neudecker 2020-01-15 19:43:31 +01:00 • committed by GitHub
parent d2a8119fee
commit a9c86b2bcb
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

9
README.md
View file

@ -7,6 +7,9 @@ This repository contains the source code for training an encoder model for docum
## Installation ## Installation
Either clone the repository via `git clone https://github.com/qurator-spk/sbb_pixelwise_segmentation.git` or download and unpack the [ZIP](https://github.com/qurator-spk/sbb_pixelwise_segmentation/archive/master.zip). Either clone the repository via `git clone https://github.com/qurator-spk/sbb_pixelwise_segmentation.git` or download and unpack the [ZIP](https://github.com/qurator-spk/sbb_pixelwise_segmentation/archive/master.zip).
### Pretrained encoder
Download our pretrained weights and add them to a ``pretrained_model`` folder:
~~https://file.spk-berlin.de:8443/pretrained_encoder/~~
## Usage ## Usage
### Train ### Train
@ -34,7 +37,7 @@ If you have an image label for a binary case it should look like this:
The train and evaluation folders should contain subfolders of images and labels. The train and evaluation folders should contain subfolders of images and labels.
The output folder should be an empty folder where the output model will be written to. The output folder should be an empty folder where the output model will be written to.
# Patches ### Patches
If you want to train your model with patches, the height and width of If you want to train your model with patches, the height and width of
the patches should be defined and also the number of batches (how many patches the patches should be defined and also the number of batches (how many patches
should be seen by the model in each iteration). should be seen by the model in each iteration).
@ -42,6 +45,4 @@ should be seen by the model in each iteration).
In the case that the model should see the image once, like page extraction, In the case that the model should see the image once, like page extraction,
patches should be set to ``false``. patches should be set to ``false``.
### Pretrained encoder
Download our pretrained weights and add them to a ``pretrained_model`` folder:
~~https://file.spk-berlin.de:8443/pretrained_encoder/~~