AntoineH/smart_augmentation
1
0
Fork 0
mirror of https://github.com/AntoineHX/smart_augmentation.git synced 2025-05-04 12:10:45 +02:00
Code Issues Projects Releases Packages Wiki Activity

Modif Dataugv6

Browse source
This commit is contained in:
Harle, Antoine (Contracteur) 2019-12-02 06:37:19 -05:00
parent ebee1b789f
commit 3ec99bf729
6 changed files with 334 additions and 36 deletions
Download patch file Download diff file Expand all files Collapse all files

9
higher/transformations.py
View file

@ -46,7 +46,7 @@ TF_dict={ #Dataugv5 #AutoAugment
'Brightness':(lambda x, mag: brightness(x, brightness_factor=rand_floats(size=x.shape[0], mag=mag, minval=0.1, maxval=1.9))),
'Sharpness':(lambda x, mag: sharpeness(x, sharpness_factor=rand_floats(size=x.shape[0], mag=mag, minval=0.1, maxval=1.9))),
'Posterize': (lambda x, mag: posterize(x, bits=rand_floats(size=x.shape[0], mag=mag, minval=4., maxval=8.))),#Perte du gradient
'Solarize': (lambda x, mag: solarize(x, thresholds=rand_floats(size=x.shape[0], mag=mag, minval=1/256., maxval=256/256.))), #Perte du gradient #=>Image entre [0,1] #Pas opti pour des batch
'Solarize': (lambda x, mag: solarize(x, thresholds=rand_floats(size=x.shape[0], mag=mag, minval=1/256., maxval=256/256.))), #Perte du gradient #=>Image entre [0,1]
#Non fonctionnel
#'Auto_Contrast': (lambda mag: None), #Pas opti pour des batch (Super lent)
@ -70,7 +70,7 @@ TF_dict={ #Dataugv5
'Brightness':(lambda x, mag: brightness(x, brightness_factor=rand_floats(size=x.shape[0], mag=mag, minval=0.1, maxval=1.9))),
'Sharpness':(lambda x, mag: sharpeness(x, sharpness_factor=rand_floats(size=x.shape[0], mag=mag, minval=0.1, maxval=1.9))),
'Posterize': (lambda x, mag: posterize(x, bits=rand_floats(size=x.shape[0], mag=mag, minval=4., maxval=8.))),#Perte du gradient
'Solarize': (lambda x, mag: solarize(x, thresholds=rand_floats(size=x.shape[0], mag=mag, minval=1/256., maxval=256/256.))), #Perte du gradient #=>Image entre [0,1] #Pas opti pour des batch
'Solarize': (lambda x, mag: solarize(x, thresholds=rand_floats(size=x.shape[0], mag=mag, minval=1/256., maxval=256/256.))), #Perte du gradient #=>Image entre [0,1]
#Color TF (Common mag scale)
'+Contrast': (lambda x, mag: contrast(x, contrast_factor=rand_floats(size=x.shape[0], mag=mag, minval=1.0, maxval=1.9))),
@ -82,7 +82,7 @@ TF_dict={ #Dataugv5
'-Brightness':(lambda x, mag: brightness(x, brightness_factor=invScale_rand_floats(size=x.shape[0], mag=mag, minval=0.1, maxval=1.0))),
'-Sharpness':(lambda x, mag: sharpeness(x, sharpness_factor=invScale_rand_floats(size=x.shape[0], mag=mag, minval=0.1, maxval=1.0))),
'=Posterize': (lambda x, mag: posterize(x, bits=invScale_rand_floats(size=x.shape[0], mag=mag, minval=4., maxval=8.))),#Perte du gradient
'=Solarize': (lambda x, mag: solarize(x, thresholds=invScale_rand_floats(size=x.shape[0], mag=mag, minval=1/256., maxval=256/256.))), #Perte du gradient #=>Image entre [0,1] #Pas opti pour des batch
'=Solarize': (lambda x, mag: solarize(x, thresholds=invScale_rand_floats(size=x.shape[0], mag=mag, minval=1/256., maxval=256/256.))), #Perte du gradient #=>Image entre [0,1]
'BRotate': (lambda x, mag: rotate(x, angle=rand_floats(size=x.shape[0], mag=mag, maxval=30*3))),
@ -295,8 +295,7 @@ def equalize(x): #PAS OPTIMISE POUR DES BATCH
return float_image(x)
def solarize(x, thresholds): #PAS OPTIMISE POUR DES BATCH
# Optimisation : Mask direct sur toute les donnees (Mask = (B,C,H,W)> (B))
def solarize(x, thresholds):
batch_size, channels, h, w = x.shape
#imgs=[]
#for idx, t in enumerate(thresholds): #Operation par image