Add a guide with steps to train the text detection and recognition models from scratch. Along the way various improvements to the text detection training tool and other things were needed.
Remove torch, torchvision from the Pipfile and install them separately. This is needed because the dependencies vary by platform and GPU
Fix warning about antialias setting in Resize transform by setting it explicitly
Move option for exporting text detection model to training script
Fix a sporadic failure during text detection training due to target masks having values slightly outside the [0, 1] range after applying transforms
Add Weights and Biases integration to the text detection training script
Speed up testing/validation phase of text detection training by optimizing box intersection tests when computing metrics
Add a guide with steps to train the text detection and recognition models from scratch. Along the way various improvements to the text detection training tool and other things were needed.
torch
,torchvision
from the Pipfile and install them separately. This is needed because the dependencies vary by platform and GPUantialias
setting inResize
transform by setting it explicitlyFixes https://github.com/robertknight/ocrs-models/issues/6