AntoineH/smart_augmentation
1
0
Fork 0
mirror of https://github.com/AntoineHX/smart_augmentation.git synced 2025-05-04 20:20:46 +02:00
Code Issues Projects Releases Packages Wiki Activity

Ajout des B_TF + chgt mag initiale

Browse source
This commit is contained in:
Harle, Antoine (Contracteur) 2019-11-22 11:22:57 -05:00
parent 758d6e9b78
commit 12ff3ee115
3 changed files with 29 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

6
higher/dataug.py
View file

@ -548,8 +548,8 @@ class Data_augV5(nn.Module): #Optimisation jointe (mag, proba)
#self._fixed_mag=5 #[0, PARAMETER_MAX] #self._fixed_mag=5 #[0, PARAMETER_MAX]
self._params = nn.ParameterDict({ self._params = nn.ParameterDict({
"prob": nn.Parameter(torch.ones(self._nb_tf)/self._nb_tf), #Distribution prob uniforme "prob": nn.Parameter(torch.ones(self._nb_tf)/self._nb_tf), #Distribution prob uniforme
"mag" : nn.Parameter(torch.tensor(0.5) if self._shared_mag "mag" : nn.Parameter(torch.tensor(float(TF.PARAMETER_MAX)) if self._shared_mag
else torch.tensor(0.5).expand(self._nb_tf)), #[0, PARAMETER_MAX] else torch.tensor(float(TF.PARAMETER_MAX)).expand(self._nb_tf)), #[0, PARAMETER_MAX]
}) })
#for t in TF.TF_no_mag: self._params['mag'][self._TF.index(t)].data-=self._params['mag'][self._TF.index(t)].data #Mag inutile pour les TF ignore_mag #for t in TF.TF_no_mag: self._params['mag'][self._TF.index(t)].data-=self._params['mag'][self._TF.index(t)].data #Mag inutile pour les TF ignore_mag
@ -631,7 +631,7 @@ class Data_augV5(nn.Module): #Optimisation jointe (mag, proba)
self._params['prob'].data = self._params['prob']/sum(self._params['prob']) #Contrainte sum(p)=1 self._params['prob'].data = self._params['prob']/sum(self._params['prob']) #Contrainte sum(p)=1
#self._params['mag'].data = self._params['mag'].data.clamp(min=0.0,max=TF.PARAMETER_MAX) #Bloque une fois au extreme #self._params['mag'].data = self._params['mag'].data.clamp(min=0.0,max=TF.PARAMETER_MAX) #Bloque une fois au extreme
self._params['mag'].data = F.relu(self._params['mag'].data) - F.relu(self._params['mag'].data - TF.PARAMETER_MAX) #Bloque a PARAMETER_MAX self._params['mag'].data = F.relu(self._params['mag'].data) - F.relu(self._params['mag'].data - TF.PARAMETER_MAX)
def loss_weight(self): def loss_weight(self):
# 1 seule TF # 1 seule TF

34
higher/test_dataug.py
View file

@ -6,21 +6,27 @@ from train_utils import *
tf_names = [ tf_names = [
## Geometric TF ## ## Geometric TF ##
'Identity', 'Identity',
#'FlipUD', 'FlipUD',
'FlipLR', 'FlipLR',
'Rotate', 'Rotate',
#'TranslateX', 'TranslateX',
#'TranslateY', 'TranslateY',
'ShearX', 'ShearX',
'ShearY', 'ShearY',
#'BRotate',
#'BTranslateX',
#'BTranslateY',
#'BShearX',
#'BShearY',
## Color TF (Expect image in the range of [0, 1]) ## ## Color TF (Expect image in the range of [0, 1]) ##
'Contrast', 'Contrast',
'Color', 'Color',
'Brightness', 'Brightness',
'Sharpness', 'Sharpness',
'Posterize', 'Posterize',
#'Solarize', #=>Image entre [0,1] #Pas opti pour des batch 'Solarize', #=>Image entre [0,1] #Pas opti pour des batch
#Non fonctionnel #Non fonctionnel
#'Auto_Contrast', #Pas opti pour des batch (Super lent) #'Auto_Contrast', #Pas opti pour des batch (Super lent)
@ -37,7 +43,7 @@ else:
########################################## ##########################################
if __name__ == "__main__": if __name__ == "__main__":
n_inner_iter = 0 n_inner_iter = 10
epochs = 100 epochs = 100
dataug_epoch_start=0 dataug_epoch_start=0
@ -68,11 +74,11 @@ if __name__ == "__main__":
t0 = time.process_time() t0 = time.process_time()
tf_dict = {k: TF.TF_dict[k] for k in tf_names} tf_dict = {k: TF.TF_dict[k] for k in tf_names}
#tf_dict = TF.TF_dict #tf_dict = TF.TF_dict
aug_model = Augmented_model(Data_augV5(TF_dict=tf_dict, N_TF=2, mix_dist=0.5, fixed_mag=True, shared_mag=True), LeNet(3,10)).to(device) aug_model = Augmented_model(Data_augV5(TF_dict=tf_dict, N_TF=1, mix_dist=0.0, fixed_mag=False, shared_mag=False), LeNet(3,10)).to(device)
#aug_model = Augmented_model(Data_augV5(TF_dict=tf_dict, N_TF=2, mix_dist=0.5, fixed_mag=True, shared_mag=True), WideResNet(num_classes=10, wrn_size=160)).to(device) #aug_model = Augmented_model(Data_augV5(TF_dict=tf_dict, N_TF=2, mix_dist=0.5, fixed_mag=True, shared_mag=True), WideResNet(num_classes=10, wrn_size=160)).to(device)
print(str(aug_model), 'on', device_name) print(str(aug_model), 'on', device_name)
#run_simple_dataug(inner_it=n_inner_iter, epochs=epochs) #run_simple_dataug(inner_it=n_inner_iter, epochs=epochs)
log= run_dist_dataugV2(model=aug_model, epochs=epochs, inner_it=n_inner_iter, dataug_epoch_start=dataug_epoch_start, print_freq=10, loss_patience=None) log= run_dist_dataugV2(model=aug_model, epochs=epochs, inner_it=n_inner_iter, dataug_epoch_start=dataug_epoch_start, print_freq=1, loss_patience=None)
#### ####
print('-'*9) print('-'*9)
@ -91,16 +97,16 @@ if __name__ == "__main__":
''' '''
#### TF tests #### #### TF tests ####
#''' #'''
res_folder="res/good_TF_tests/" res_folder="res/brutus-tests/"
epochs= 100 epochs= 150
inner_its = [0, 10] inner_its = [0, 1, 10]
dist_mix = [0.0, 0.5] dist_mix = [0.0, 0.5, 1]
dataug_epoch_starts= [0] dataug_epoch_starts= [0]
tf_dict = {k: TF.TF_dict[k] for k in tf_names} tf_dict = {k: TF.TF_dict[k] for k in tf_names}
TF_nb = [len(tf_dict)] #range(10,len(TF.TF_dict)+1) #[len(TF.TF_dict)] TF_nb = [len(tf_dict)] #range(10,len(TF.TF_dict)+1) #[len(TF.TF_dict)]
N_seq_TF= [1]#[1, 2, 3, 4] N_seq_TF= [1, 2, 3, 4]
mag_setup = [(True,True)]#[(True,True), (False,True), (False, False)] mag_setup = [(True,True), (False,True), (False, False)]
nb_run= 1 nb_run= 3
try: try:
os.mkdir(res_folder) os.mkdir(res_folder)

6
higher/transformations.py
View file

@ -39,6 +39,12 @@ TF_dict={ #Dataugv5
'ShearX': (lambda x, mag: shear(x, shear=zero_stack(rand_floats(size=(x.shape[0],), mag=mag, maxval=0.3), zero_pos=0))), 'ShearX': (lambda x, mag: shear(x, shear=zero_stack(rand_floats(size=(x.shape[0],), mag=mag, maxval=0.3), zero_pos=0))),
'ShearY': (lambda x, mag: shear(x, shear=zero_stack(rand_floats(size=(x.shape[0],), mag=mag, maxval=0.3), zero_pos=1))), 'ShearY': (lambda x, mag: shear(x, shear=zero_stack(rand_floats(size=(x.shape[0],), mag=mag, maxval=0.3), zero_pos=1))),
'BRotate': (lambda x, mag: rotate(x, angle=rand_floats(size=x.shape[0], mag=mag, maxval=30*3))),
'BTranslateX': (lambda x, mag: translate(x, translation=zero_stack(rand_floats(size=(x.shape[0],), mag=mag, maxval=20*3), zero_pos=0))),
'BTranslateY': (lambda x, mag: translate(x, translation=zero_stack(rand_floats(size=(x.shape[0],), mag=mag, maxval=20*3), zero_pos=1))),
'BShearX': (lambda x, mag: shear(x, shear=zero_stack(rand_floats(size=(x.shape[0],), mag=mag, maxval=0.3*3), zero_pos=0))),
'BShearY': (lambda x, mag: shear(x, shear=zero_stack(rand_floats(size=(x.shape[0],), mag=mag, maxval=0.3*3), zero_pos=1))),
## Color TF (Expect image in the range of [0, 1]) ## ## Color TF (Expect image in the range of [0, 1]) ##
'Contrast': (lambda x, mag: contrast(x, contrast_factor=rand_floats(size=x.shape[0], mag=mag, minval=0.1, maxval=1.9))), 'Contrast': (lambda x, mag: contrast(x, contrast_factor=rand_floats(size=x.shape[0], mag=mag, minval=0.1, maxval=1.9))),
'Color':(lambda x, mag: color(x, color_factor=rand_floats(size=x.shape[0], mag=mag, minval=0.1, maxval=1.9))), 'Color':(lambda x, mag: color(x, color_factor=rand_floats(size=x.shape[0], mag=mag, minval=0.1, maxval=1.9))),