Hugging Face's logo

InternsProgressUpdate
/
Venket

Model card Files
xet
 Community
Venket / configs /generate.yaml
venki101's picture
venki101
Add files using upload-large-folder tool
97b64b9 verified
Raw History Blame Contribute Delete
3.32 kB
# Example large-batch dataset generation config.
#
# Merged on top of configs/default.yaml. Only values that differ from the
# defaults need to be listed here. Run with:
#
# python main.py --config configs/generate.yaml --count 10000
#
# (--count on the command line overrides generation.count below.)
seed: 20240601
paths:
output_dir: output
generation:
count: 2000
workers: 4
save_visualization: false
overwrite: false
run_validation: true
# document.template left as null -> every sample independently and
# deterministically picks one of the 9 discovered templates.
document:
template: null
# signer.name/role left as null -> a synthetic name is generated per sample
# and the role is taken from the chosen signature box's annotation.
signer:
name: null
role: null
signature_selection:
source_filter: genuine
placement:
scale_factor:
min: 0.75
max: 0.98
rotation_deg:
min: -6.0
max: 6.0
margin: 0.07
misplacement_probability: 0.15
misplacement_strength:
min: 0.15
max: 0.5
allow_partial_outside: true
rendering:
blend_mode: multiply
ink_opacity:
min: 0.7
max: 0.97
blur_sigma:
min: 0.15
max: 0.6
feather_px:
min: 0.4
max: 2.0
scanner_noise: 0.02
augmentation:
stroke_dilation:
enabled: true
strength: { min: 0.1, max: 0.35 }
probability: 0.2
gaussian_blur:
enabled: true
strength: { min: 0.05, max: 0.3 }
probability: 0.3
motion_blur:
enabled: true
strength: { min: 0.1, max: 0.35 }
probability: 0.12
ink_fading:
enabled: true
strength: { min: 0.1, max: 0.5 }
probability: 0.2
ink_bleed:
enabled: true
strength: { min: 0.1, max: 0.4 }
probability: 0.15
perspective:
enabled: true
strength: { min: 0.05, max: 0.2 }
probability: 0.12
contrast:
enabled: true
strength: { min: 0.05, max: 0.3 }
probability: 0.4
gamma:
enabled: true
strength: { min: 0.05, max: 0.25 }
probability: 0.2
coffee_stain:
enabled: true
strength: { min: 0.2, max: 0.6 }
probability: 0.08
stain:
enabled: true
strength: { min: 0.2, max: 0.6 }
probability: 0.1
type: random
shadow:
enabled: true
strength: { min: 0.2, max: 0.6 }
probability: 0.35
type: random
crumple:
enabled: true
strength: { min: 0.1, max: 0.4 }
probability: 0.12
wrinkle_density: { min: 0.2, max: 0.7 }
discoloration:
enabled: true
strength: { min: 0.1, max: 0.4 }
probability: 0.45
tone: random
page_tilt:
enabled: true
strength: { min: 0.1, max: 0.5 }
probability: 0.3
dust:
enabled: true
strength: { min: 0.1, max: 0.4 }
probability: 0.2
scanner_streaks:
enabled: true
strength: { min: 0.1, max: 0.35 }
probability: 0.1
scanner_noise:
enabled: true
strength: { min: 0.02, max: 0.1 }
probability: 1.0
salt_pepper:
enabled: true
strength: { min: 0.01, max: 0.06 }
probability: 0.15
jpeg_compression:
enabled: true
strength: { min: 0.2, max: 0.6 }
probability: 0.5
min_quality: 40
max_quality: 92
quality:
scanner_quality: { min: 0.6, max: 0.98 }
paper_quality: { min: 0.6, max: 0.98 }
render_quality: { min: 0.6, max: 0.98 }
validation:
strict: false