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

minor changes

Browse source
This commit is contained in:
Harle, Antoine (Contracteur) 2020-01-31 10:34:44 -05:00
parent bf29d4fb6d
commit cd6e159b77
6 changed files with 59 additions and 95 deletions
Download patch file Download diff file Expand all files Collapse all files

17
higher/smart_aug/model.py → higher/smart_aug/LeNet.py
View file

@ -36,3 +36,20 @@ class LeNet(nn.Module):
""" """
return "LeNet" return "LeNet"
#MNIST
class MLPNet(nn.Module):
def __init__(self):
super(MLPNet, self).__init__()
self.fc1 = nn.Linear(28*28, 500)
self.fc2 = nn.Linear(500, 256)
self.fc3 = nn.Linear(256, 10)
def forward(self, x):
x = x.view(-1, 28*28)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
def name(self):
return "MLP"

12
higher/smart_aug/benchmark.py
View file

@ -1,4 +1,3 @@
from model import *
from dataug import * from dataug import *
#from utils import * #from utils import *
from train_utils import * from train_utils import *
@ -19,9 +18,9 @@ optim_param={
} }
} }
res_folder="../res/benchmark/CIFAR10" res_folder="../res/benchmark/CIFAR10/"
epochs= 200 epochs= 150
dataug_epoch_starts=0 dataug_epoch_start=0
# Use available TF (see transformations.py) # Use available TF (see transformations.py)
tf_names = [ tf_names = [
@ -131,7 +130,6 @@ if __name__ == "__main__":
### HP Search ### ### HP Search ###
inner_its = [1] inner_its = [1]
dist_mix = [0.0, 0.5, 0.8, 1.0] dist_mix = [0.0, 0.5, 0.8, 1.0]
dataug_epoch_starts= [0]
N_seq_TF= [2, 3, 4] N_seq_TF= [2, 3, 4]
mag_setup = [(True,True), (False, False)] #(FxSh, Independant) mag_setup = [(True,True), (False, False)] #(FxSh, Independant)
#prob_setup = [True, False] #prob_setup = [True, False]
@ -154,7 +152,7 @@ if __name__ == "__main__":
t0 = time.process_time() t0 = time.process_time()
model = getattr(model_list.keys()[0], 'resnet18')(pretrained=False) model = getattr(models.resnet, 'resnet18')(pretrained=False)
model = Higher_model(model) #run_dist_dataugV3 model = Higher_model(model) #run_dist_dataugV3
aug_model = Augmented_model(Data_augV5(TF_dict=tf_dict, N_TF=n_tf, mix_dist=dist, fixed_prob=p_setup, fixed_mag=m_setup[0], shared_mag=m_setup[1]), model).to(device) aug_model = Augmented_model(Data_augV5(TF_dict=tf_dict, N_TF=n_tf, mix_dist=dist, fixed_prob=p_setup, fixed_mag=m_setup[0], shared_mag=m_setup[1]), model).to(device)
#aug_model = Augmented_model(RandAug(TF_dict=tf_dict, N_TF=2), model).to(device) #aug_model = Augmented_model(RandAug(TF_dict=tf_dict, N_TF=2), model).to(device)
@ -177,7 +175,7 @@ if __name__ == "__main__":
out = {"Accuracy": max([x["acc"] for x in log]), "Time": (np.mean(times),np.std(times), exec_time), 'Optimizer': optim_param, "Device": device_name, "Param_names": aug_model.TF_names(), "Log": log} out = {"Accuracy": max([x["acc"] for x in log]), "Time": (np.mean(times),np.std(times), exec_time), 'Optimizer': optim_param, "Device": device_name, "Param_names": aug_model.TF_names(), "Log": log}
print(str(aug_model),": acc", out["Accuracy"], "in:", out["Time"][0], "+/-", out["Time"][1]) print(str(aug_model),": acc", out["Accuracy"], "in:", out["Time"][0], "+/-", out["Time"][1])
filename = "{}-{} epochs (dataug:{})- {} in_it-{}".format(str(aug_model),epochs,dataug_epoch_start,n_inner_iter, run) filename = "{}-{} epochs (dataug:{})- {} in_it-{}".format(str(aug_model),epochs,dataug_epoch_start,n_inner_iter, run)
with open("../res/log/%s.json" % filename, "w+") as f: with open(res_folder+"log/%s.json" % filename, "w+") as f:
try: try:
json.dump(out, f, indent=True) json.dump(out, f, indent=True)
print('Log :\"',f.name, '\" saved !') print('Log :\"',f.name, '\" saved !')

33
higher/smart_aug/datasets.py
View file

@ -27,25 +27,26 @@ pin_memory=False #True :+ GPU memory / + Lent
#]) #])
transform = torchvision.transforms.Compose([ transform = torchvision.transforms.Compose([
torchvision.transforms.ToTensor(), torchvision.transforms.ToTensor(),
#torchvision.transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)), #CIFAR10 # torchvision.transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)), #CIFAR10
]) ])
#data_train = torchvision.datasets.MNIST( from RandAugment import RandAugment
# "./data", train=True, download=True, # Add RandAugment with N, M(hyperparameter)
# transform=torchvision.transforms.Compose([ transform_train = torchvision.transforms.Compose([
# #torchvision.transforms.RandomAffine(degrees=180, translate=None, scale=None, shear=None, resample=False, fillcolor=0), #transforms.RandomHorizontalFlip(),
# torchvision.transforms.ToTensor() #transforms.RandomVerticalFlip(),
# ]) torchvision.transforms.ToTensor(),
#) ])
#data_test = torchvision.datasets.MNIST( #transform_train.transforms.insert(0, RandAugment(n=2, m=30))
# "./data", train=False, download=True, transform=torchvision.transforms.ToTensor()
#)
### Classic Dataset ### ### Classic Dataset ###
#Training data #MNIST
data_train = torchvision.datasets.CIFAR10("../data", train=True, download=download_data, transform=transform) #data_train = torchvision.datasets.MNIST("../data", train=True, download=True, transform=transform_train)
#data_val = torchvision.datasets.CIFAR10("../data", train=True, download=download_data, transform=transform) #data_val = torchvision.datasets.MNIST("../data", train=True, download=True, transform=transform)
#Testing data #data_test = torchvision.datasets.MNIST("../data", train=False, download=True, transform=transform)
#CIFAR
data_train = torchvision.datasets.CIFAR10("../data", train=True, download=download_data, transform=transform_train)
data_val = torchvision.datasets.CIFAR10("../data", train=True, download=download_data, transform=transform)
data_test = torchvision.datasets.CIFAR10("../data", train=False, download=download_data, transform=transform) data_test = torchvision.datasets.CIFAR10("../data", train=False, download=download_data, transform=transform)
train_subset_indices=range(int(len(data_train)/2)) train_subset_indices=range(int(len(data_train)/2))
@ -54,5 +55,5 @@ val_subset_indices=range(int(len(data_train)/2),len(data_train))
#val_subset_indices=range(BATCH_SIZE*10, BATCH_SIZE*20) #val_subset_indices=range(BATCH_SIZE*10, BATCH_SIZE*20)
dl_train = torch.utils.data.DataLoader(data_train, batch_size=BATCH_SIZE, shuffle=False, sampler=SubsetRandomSampler(train_subset_indices), num_workers=num_workers, pin_memory=pin_memory) dl_train = torch.utils.data.DataLoader(data_train, batch_size=BATCH_SIZE, shuffle=False, sampler=SubsetRandomSampler(train_subset_indices), num_workers=num_workers, pin_memory=pin_memory)
dl_val = torch.utils.data.DataLoader(data_train, batch_size=BATCH_SIZE, shuffle=False, sampler=SubsetRandomSampler(val_subset_indices), num_workers=num_workers, pin_memory=pin_memory) dl_val = torch.utils.data.DataLoader(data_val, batch_size=BATCH_SIZE, shuffle=False, sampler=SubsetRandomSampler(val_subset_indices), num_workers=num_workers, pin_memory=pin_memory)
dl_test = torch.utils.data.DataLoader(data_test, batch_size=TEST_SIZE, shuffle=False, num_workers=num_workers, pin_memory=pin_memory) dl_test = torch.utils.data.DataLoader(data_test, batch_size=TEST_SIZE, shuffle=False, num_workers=num_workers, pin_memory=pin_memory)

4
higher/smart_aug/dataug.py
View file

@ -35,7 +35,7 @@ class Data_augV5(nn.Module): #Optimisation jointe (mag, proba)
_TF (list) : List of TF names. _TF (list) : List of TF names.
_nb_tf (int) : Number of TF used. _nb_tf (int) : Number of TF used.
_N_seqTF (int) : Number of TF to be applied sequentially to each inputs _N_seqTF (int) : Number of TF to be applied sequentially to each inputs
_shared_mag (bool) : Wether to share a single magnitude parameters for all TF. _shared_mag (bool) : Wether to share a single magnitude parameters for all TF. Beware using shared mag with basic color TF as their lowest magnitude is at PARAMETER_MAX/2.
_fixed_mag (bool): Wether to lock the TF magnitudes. _fixed_mag (bool): Wether to lock the TF magnitudes.
_fixed_prob (bool): Wether to lock the TF probabilies. _fixed_prob (bool): Wether to lock the TF probabilies.
_samples (list): Sampled TF index during last forward pass. _samples (list): Sampled TF index during last forward pass.
@ -320,7 +320,7 @@ class Data_augV7(nn.Module): #Proba sequentielles
_TF (list) : List of TF names. _TF (list) : List of TF names.
_nb_tf (int) : Number of TF used. _nb_tf (int) : Number of TF used.
_N_seqTF (int) : Number of TF to be applied sequentially to each inputs _N_seqTF (int) : Number of TF to be applied sequentially to each inputs
_shared_mag (bool) : Wether to share a single magnitude parameters for all TF. _shared_mag (bool) : Wether to share a single magnitude parameters for all TF. Beware using shared mag with basic color TF as their lowest magnitude is at PARAMETER_MAX/2.
_fixed_mag (bool): Wether to lock the TF magnitudes. _fixed_mag (bool): Wether to lock the TF magnitudes.
_fixed_prob (bool): Wether to lock the TF probabilies. _fixed_prob (bool): Wether to lock the TF probabilies.
_samples (list): Sampled TF index during last forward pass. _samples (list): Sampled TF index during last forward pass.

83
higher/smart_aug/test_dataug.py
View file

@ -2,7 +2,7 @@
""" """
from model import * from LeNet import *
from dataug import * from dataug import *
#from utils import * #from utils import *
from train_utils import * from train_utils import *
@ -13,19 +13,19 @@ tf_names = [
'Identity', 'Identity',
'FlipUD', 'FlipUD',
'FlipLR', 'FlipLR',
'Rotate', #'Rotate',
'TranslateX', #'TranslateX',
'TranslateY', #'TranslateY',
'ShearX', #'ShearX',
'ShearY', #'ShearY',
## 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
#Color TF (Common mag scale) #Color TF (Common mag scale)
#'+Contrast', #'+Contrast',
@ -76,7 +76,6 @@ if __name__ == "__main__":
tasks={ tasks={
#'classic', #'classic',
'aug_model' 'aug_model'
#'aug_dataset', #Moved to old code
} }
#Parameters #Parameters
n_inner_iter = 1 n_inner_iter = 1
@ -131,7 +130,7 @@ if __name__ == "__main__":
tf_dict = {k: TF.TF_dict[k] for k in tf_names} tf_dict = {k: TF.TF_dict[k] for k in tf_names}
model = Higher_model(model) #run_dist_dataugV3 model = Higher_model(model) #run_dist_dataugV3
aug_model = Augmented_model(Data_augV5(TF_dict=tf_dict, N_TF=2, mix_dist=0.8, fixed_prob=False, fixed_mag=False, shared_mag=False), model).to(device) aug_model = Augmented_model(Data_augV5(TF_dict=tf_dict, N_TF=3, mix_dist=0.8, fixed_prob=False, fixed_mag=False, shared_mag=False), model).to(device)
#aug_model = Augmented_model(RandAug(TF_dict=tf_dict, N_TF=2), model).to(device) #aug_model = Augmented_model(RandAug(TF_dict=tf_dict, N_TF=2), model).to(device)
print("{} on {} for {} epochs - {} inner_it".format(str(aug_model), device_name, epochs, n_inner_iter)) print("{} on {} for {} epochs - {} inner_it".format(str(aug_model), device_name, epochs, n_inner_iter))
@ -140,7 +139,7 @@ if __name__ == "__main__":
inner_it=n_inner_iter, inner_it=n_inner_iter,
dataug_epoch_start=dataug_epoch_start, dataug_epoch_start=dataug_epoch_start,
opt_param=optim_param, opt_param=optim_param,
print_freq=1, print_freq=20,
unsup_loss=1, unsup_loss=1,
hp_opt=False, hp_opt=False,
save_sample_freq=None) save_sample_freq=None)
@ -164,56 +163,4 @@ if __name__ == "__main__":
print("Failed to plot res") print("Failed to plot res")
print('Execution Time : %.00f '%(exec_time)) print('Execution Time : %.00f '%(exec_time))
print('-'*9) print('-'*9)
#### Augmented Dataset ####
'''
if 'aug_dataset' in tasks:
t0 = time.process_time()
#data_train_aug = AugmentedDataset("./data", train=True, download=download_data, transform=transform, subset=(0,int(len(data_train)/2)))
#data_train_aug.augement_data(aug_copy=30)
#print(data_train_aug)
#dl_train = torch.utils.data.DataLoader(data_train_aug, batch_size=BATCH_SIZE, shuffle=True)
#xs, ys = next(iter(dl_train))
#viz_sample_data(imgs=xs, labels=ys, fig_name='samples/data_sample_{}'.format(str(data_train_aug)))
#model = model.to(device)
#print("{} on {} for {} epochs".format(str(model), device_name, epochs))
#log= train_classic(model=model, epochs=epochs, print_freq=10)
##log= train_classic_higher(model=model, epochs=epochs)
data_train_aug = AugmentedDatasetV2("./data", train=True, download=download_data, transform=transform, subset=(0,int(len(data_train)/2)))
data_train_aug.augement_data(aug_copy=1)
print(data_train_aug)
unsup_ratio = 5
dl_unsup = torch.utils.data.DataLoader(data_train_aug, batch_size=BATCH_SIZE*unsup_ratio, shuffle=True, num_workers=num_workers, pin_memory=pin_memory)
unsup_xs, sup_xs, ys = next(iter(dl_unsup))
viz_sample_data(imgs=sup_xs, labels=ys, fig_name='samples/data_sample_{}'.format(str(data_train_aug)))
viz_sample_data(imgs=unsup_xs, labels=ys, fig_name='samples/data_sample_{}_unsup'.format(str(data_train_aug)))
model = model.to(device)
print("{} on {} for {} epochs".format(str(model), device_name, epochs))
log= train_UDA(model=model, dl_unsup=dl_unsup, epochs=epochs, opt_param=optim_param, print_freq=10)
exec_time=time.process_time() - t0
####
print('-'*9)
times = [x["time"] for x in log]
out = {"Accuracy": max([x["acc"] for x in log]), "Time": (np.mean(times),np.std(times), exec_time), 'Optimizer': optim_param['Inner'], "Device": device_name, "Param_names": data_train_aug._TF, "Log": log}
print(str(model),": acc", out["Accuracy"], "in:", out["Time"][0], "+/-", out["Time"][1])
filename = "{}-{}-{} epochs".format(str(data_train_aug),str(model),epochs)
with open("res/log/%s.json" % filename, "w+") as f:
json.dump(out, f, indent=True)
print('Log :\"',f.name, '\" saved !')
plot_res(log, fig_name="res/"+filename)
print('Execution Time : %.00f '%(exec_time))
print('-'*9)
'''

5
higher/smart_aug/train_utils.py
View file

@ -144,6 +144,7 @@ def train_classic(model, opt_param, epochs=1, print_freq=1):
#print_torch_mem("Start epoch") #print_torch_mem("Start epoch")
t0 = time.process_time() t0 = time.process_time()
for i, (features, labels) in enumerate(dl_train): for i, (features, labels) in enumerate(dl_train):
#viz_sample_data(imgs=features, labels=labels, fig_name='../samples/data_sample_epoch{}_noTF'.format(epoch))
#print_torch_mem("Start iter") #print_torch_mem("Start iter")
features,labels = features.to(device), labels.to(device) features,labels = features.to(device), labels.to(device)
@ -277,7 +278,7 @@ def run_dist_dataugV3(model, opt_param, epochs=1, inner_it=1, dataug_epoch_start
meta_opt.step() meta_opt.step()
#Adjust Hyper-parameters #Adjust Hyper-parameters
model['data_aug'].adjust_param(soft=False) #Contrainte sum(proba)=1 model['data_aug'].adjust_param() #Contrainte sum(proba)=1
if hp_opt: if hp_opt:
for param_group in diffopt.param_groups: for param_group in diffopt.param_groups:
for param in list(opt_param['Inner'].keys())[1:]: for param in list(opt_param['Inner'].keys())[1:]:
@ -289,7 +290,7 @@ def run_dist_dataugV3(model, opt_param, epochs=1, inner_it=1, dataug_epoch_start
meta_opt.zero_grad() meta_opt.zero_grad()
elif not high_grad_track: elif not high_grad_track:
diffopt.detach_() #diffopt.detach_()
model['model'].detach_() model['model'].detach_()
tf = time.process_time() tf = time.process_time()