mirror of
https://github.com/AntoineHX/smart_augmentation.git
synced 2025-05-03 11:40:46 +02:00
RandAugment
This commit is contained in:
Harle, Antoine (Contracteur)
parent
7221142a9a
commit
6277e268c1
3 changed files with 407 additions and 73 deletions
271
augmentations_randaugment.py
Normal file
271
augmentations_randaugment.py
Normal file
|
|
@ -0,0 +1,271 @@
|
|||
# code in this file is adpated from rpmcruz/autoaugment
|
||||
# https://github.com/rpmcruz/autoaugment/blob/master/transformations.py
|
||||
import random
|
||||
|
||||
import PIL, PIL.ImageOps, PIL.ImageEnhance, PIL.ImageDraw
|
||||
import numpy as np
|
||||
import torch
|
||||
from PIL import Image
|
||||
|
||||
def ShearX(img, v): # [-0.3, 0.3]
|
||||
assert -0.3 <= v <= 0.3
|
||||
if random.random() > 0.5:
|
||||
v = -v
|
||||
return img.transform(img.size, PIL.Image.AFFINE, (1, v, 0, 0, 1, 0))
|
||||
|
||||
|
||||
def ShearY(img, v): # [-0.3, 0.3]
|
||||
assert -0.3 <= v <= 0.3
|
||||
if random.random() > 0.5:
|
||||
v = -v
|
||||
return img.transform(img.size, PIL.Image.AFFINE, (1, 0, 0, v, 1, 0))
|
||||
|
||||
|
||||
def TranslateX(img, v): # [-150, 150] => percentage: [-0.45, 0.45]
|
||||
assert -0.45 <= v <= 0.45
|
||||
if random.random() > 0.5:
|
||||
v = -v
|
||||
v = v * img.size[0]
|
||||
return img.transform(img.size, PIL.Image.AFFINE, (1, 0, v, 0, 1, 0))
|
||||
|
||||
|
||||
def TranslateXabs(img, v): # [-150, 150] => percentage: [-0.45, 0.45]
|
||||
assert 0 <= v
|
||||
if random.random() > 0.5:
|
||||
v = -v
|
||||
return img.transform(img.size, PIL.Image.AFFINE, (1, 0, v, 0, 1, 0))
|
||||
|
||||
|
||||
def TranslateY(img, v): # [-150, 150] => percentage: [-0.45, 0.45]
|
||||
assert -0.45 <= v <= 0.45
|
||||
if random.random() > 0.5:
|
||||
v = -v
|
||||
v = v * img.size[1]
|
||||
return img.transform(img.size, PIL.Image.AFFINE, (1, 0, 0, 0, 1, v))
|
||||
|
||||
|
||||
def TranslateYabs(img, v): # [-150, 150] => percentage: [-0.45, 0.45]
|
||||
assert 0 <= v
|
||||
if random.random() > 0.5:
|
||||
v = -v
|
||||
return img.transform(img.size, PIL.Image.AFFINE, (1, 0, 0, 0, 1, v))
|
||||
|
||||
|
||||
def Rotate(img, v): # [-30, 30]
|
||||
assert -30 <= v <= 30
|
||||
if random.random() > 0.5:
|
||||
v = -v
|
||||
return img.rotate(v)
|
||||
|
||||
|
||||
def AutoContrast(img, _):
|
||||
return PIL.ImageOps.autocontrast(img)
|
||||
|
||||
|
||||
def Invert(img, _):
|
||||
return PIL.ImageOps.invert(img)
|
||||
|
||||
|
||||
def Equalize(img, _):
|
||||
return PIL.ImageOps.equalize(img)
|
||||
|
||||
|
||||
def Flip(img, _): # not from the paper
|
||||
return PIL.ImageOps.mirror(img)
|
||||
|
||||
def FlipLR(img, v):
|
||||
return img.transpose(Image.FLIP_LEFT_RIGHT)
|
||||
|
||||
def FlipUD(img, v):
|
||||
return img.transpose(Image.FLIP_TOP_BOTTOM)
|
||||
|
||||
def Solarize(img, v): # [0, 256]
|
||||
assert 0 <= v <= 256
|
||||
return PIL.ImageOps.solarize(img, v)
|
||||
|
||||
|
||||
def SolarizeAdd(img, addition=0, threshold=128):
|
||||
img_np = np.array(img).astype(np.int)
|
||||
img_np = img_np + addition
|
||||
img_np = np.clip(img_np, 0, 255)
|
||||
img_np = img_np.astype(np.uint8)
|
||||
img = Image.fromarray(img_np)
|
||||
return PIL.ImageOps.solarize(img, threshold)
|
||||
|
||||
|
||||
def Posterize(img, v): # [4, 8]
|
||||
v = int(v)
|
||||
v = max(1, v)
|
||||
return PIL.ImageOps.posterize(img, v)
|
||||
|
||||
|
||||
def Contrast(img, v): # [0.1,1.9]
|
||||
assert 0.1 <= v <= 1.9
|
||||
return PIL.ImageEnhance.Contrast(img).enhance(v)
|
||||
|
||||
|
||||
def Color(img, v): # [0.1,1.9]
|
||||
assert 0.1 <= v <= 1.9
|
||||
return PIL.ImageEnhance.Color(img).enhance(v)
|
||||
|
||||
|
||||
def Brightness(img, v): # [0.1,1.9]
|
||||
assert 0.1 <= v <= 1.9
|
||||
return PIL.ImageEnhance.Brightness(img).enhance(v)
|
||||
|
||||
|
||||
def Sharpness(img, v): # [0.1,1.9]
|
||||
assert 0.1 <= v <= 1.9
|
||||
return PIL.ImageEnhance.Sharpness(img).enhance(v)
|
||||
|
||||
|
||||
def Cutout(img, v): # [0, 60] => percentage: [0, 0.2]
|
||||
assert 0.0 <= v <= 0.2
|
||||
if v <= 0.:
|
||||
return img
|
||||
|
||||
v = v * img.size[0]
|
||||
return CutoutAbs(img, v)
|
||||
|
||||
|
||||
def CutoutAbs(img, v): # [0, 60] => percentage: [0, 0.2]
|
||||
# assert 0 <= v <= 20
|
||||
if v < 0:
|
||||
return img
|
||||
w, h = img.size
|
||||
x0 = np.random.uniform(w)
|
||||
y0 = np.random.uniform(h)
|
||||
|
||||
x0 = int(max(0, x0 - v / 2.))
|
||||
y0 = int(max(0, y0 - v / 2.))
|
||||
x1 = min(w, x0 + v)
|
||||
y1 = min(h, y0 + v)
|
||||
|
||||
xy = (x0, y0, x1, y1)
|
||||
color = (125, 123, 114)
|
||||
# color = (0, 0, 0)
|
||||
img = img.copy()
|
||||
PIL.ImageDraw.Draw(img).rectangle(xy, color)
|
||||
return img
|
||||
|
||||
|
||||
def SamplePairing(imgs): # [0, 0.4]
|
||||
def f(img1, v):
|
||||
i = np.random.choice(len(imgs))
|
||||
img2 = PIL.Image.fromarray(imgs[i])
|
||||
return PIL.Image.blend(img1, img2, v)
|
||||
|
||||
return f
|
||||
|
||||
|
||||
def Identity(img, v):
|
||||
return img
|
||||
|
||||
|
||||
def augment_list(): # 16 oeprations and their ranges
|
||||
# https://github.com/google-research/uda/blob/master/image/randaugment/policies.py#L57
|
||||
l = [
|
||||
(Identity, 0., 1.0),
|
||||
(FlipUD, 0., 1.0),
|
||||
(FlipLR, 0., 1.0),
|
||||
(Rotate, 0, 30), # 4
|
||||
(TranslateX, 0., 0.33), # 2
|
||||
(TranslateY, 0., 0.33), # 3
|
||||
(ShearX, 0., 0.3), # 0
|
||||
(ShearY, 0., 0.3), # 1
|
||||
#(AutoContrast, 0, 1), # 5
|
||||
#(Invert, 0, 1), # 6
|
||||
#(Equalize, 0, 1), # 7
|
||||
(Contrast, 0.1, 1.9), # 10
|
||||
(Color, 0.1, 1.9), # 11
|
||||
(Brightness, 0.1, 1.9), # 12
|
||||
(Sharpness, 0.1, 1.9), # 13
|
||||
(Posterize, 4, 8), # 9
|
||||
(Solarize, 1, 256), # 8
|
||||
|
||||
# (Cutout, 0, 0.2), # 14
|
||||
# (SamplePairing(imgs), 0, 0.4), # 15
|
||||
]
|
||||
|
||||
# https://github.com/tensorflow/tpu/blob/8462d083dd89489a79e3200bcc8d4063bf362186/models/official/efficientnet/autoaugment.py#L505
|
||||
#l = [
|
||||
# (AutoContrast, 0, 1),
|
||||
# (Equalize, 0, 1),
|
||||
# (Invert, 0, 1),
|
||||
# (Rotate, 0, 30),
|
||||
# (Posterize, 0, 4),
|
||||
# (Solarize, 0, 256),
|
||||
# (SolarizeAdd, 0, 110),
|
||||
# (Color, 0.1, 1.9),
|
||||
# (Contrast, 0.1, 1.9),
|
||||
# (Brightness, 0.1, 1.9),
|
||||
# (Sharpness, 0.1, 1.9),
|
||||
# (ShearX, 0., 0.3),
|
||||
# (ShearY, 0., 0.3),
|
||||
# (CutoutAbs, 0, 40),
|
||||
# (TranslateXabs, 0., 100),
|
||||
# (TranslateYabs, 0., 100),
|
||||
#]
|
||||
|
||||
return l
|
||||
|
||||
|
||||
class Lighting(object):
|
||||
"""Lighting noise(AlexNet - style PCA - based noise)"""
|
||||
|
||||
def __init__(self, alphastd, eigval, eigvec):
|
||||
self.alphastd = alphastd
|
||||
self.eigval = torch.Tensor(eigval)
|
||||
self.eigvec = torch.Tensor(eigvec)
|
||||
|
||||
def __call__(self, img):
|
||||
if self.alphastd == 0:
|
||||
return img
|
||||
|
||||
alpha = img.new().resize_(3).normal_(0, self.alphastd)
|
||||
rgb = self.eigvec.type_as(img).clone() \
|
||||
.mul(alpha.view(1, 3).expand(3, 3)) \
|
||||
.mul(self.eigval.view(1, 3).expand(3, 3)) \
|
||||
.sum(1).squeeze()
|
||||
|
||||
return img.add(rgb.view(3, 1, 1).expand_as(img))
|
||||
|
||||
|
||||
class CutoutDefault(object):
|
||||
"""
|
||||
Reference : https://github.com/quark0/darts/blob/master/cnn/utils.py
|
||||
"""
|
||||
def __init__(self, length):
|
||||
self.length = length
|
||||
|
||||
def __call__(self, img):
|
||||
h, w = img.size(1), img.size(2)
|
||||
mask = np.ones((h, w), np.float32)
|
||||
y = np.random.randint(h)
|
||||
x = np.random.randint(w)
|
||||
|
||||
y1 = np.clip(y - self.length // 2, 0, h)
|
||||
y2 = np.clip(y + self.length // 2, 0, h)
|
||||
x1 = np.clip(x - self.length // 2, 0, w)
|
||||
x2 = np.clip(x + self.length // 2, 0, w)
|
||||
|
||||
mask[y1: y2, x1: x2] = 0.
|
||||
mask = torch.from_numpy(mask)
|
||||
mask = mask.expand_as(img)
|
||||
img *= mask
|
||||
return img
|
||||
|
||||
PARAMETER_MAX = 1
|
||||
class RandAugment:
|
||||
def __init__(self, n, m):
|
||||
self.n = n
|
||||
self.m = m # [0, PARAMETER_MAX]
|
||||
self.augment_list = augment_list()
|
||||
|
||||
def __call__(self, img):
|
||||
ops = random.choices(self.augment_list, k=self.n)
|
||||
for op, minval, maxval in ops:
|
||||
val = (float(self.m) / PARAMETER_MAX) * float(maxval - minval) + minval
|
||||
img = op(img, val)
|
||||
|
||||
return img
|
||||
|
|
@ -1,3 +1,6 @@
|
|||
""" Script to run series of experiments.
|
||||
|
||||
"""
|
||||
from dataug import *
|
||||
#from utils import *
|
||||
from train_utils import *
|
||||
|
|
@ -13,14 +16,16 @@ optim_param={
|
|||
},
|
||||
'Inner':{
|
||||
'optim': 'SGD',
|
||||
'lr':1e-1, #1e-2 #1e-1 for ResNet
|
||||
'lr':1e-2, #1e-2 #1e-1 for ResNet
|
||||
'momentum':0.9, #0.9
|
||||
}
|
||||
}
|
||||
|
||||
res_folder="../res/benchmark/CIFAR10/"
|
||||
epochs= 150
|
||||
#res_folder="../res/HPsearch/"
|
||||
epochs= 200
|
||||
dataug_epoch_start=0
|
||||
nb_run= 3
|
||||
|
||||
# Use available TF (see transformations.py)
|
||||
tf_names = [
|
||||
|
|
@ -80,60 +85,107 @@ if __name__ == "__main__":
|
|||
'''
|
||||
for model_type in model_list.keys():
|
||||
for model_name in model_list[model_type]:
|
||||
model = getattr(model_type, model_name)(pretrained=False)
|
||||
for run in range(nb_run):
|
||||
|
||||
t0 = time.process_time()
|
||||
torch.cuda.reset_max_memory_cached() #reset_peak_stats
|
||||
t0 = time.perf_counter()
|
||||
|
||||
model = Higher_model(model) #run_dist_dataugV3
|
||||
if n_inner_iter!=0:
|
||||
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)
|
||||
else:
|
||||
aug_model = Augmented_model(RandAug(TF_dict=tf_dict, N_TF=n_tf), model).to(device)
|
||||
model = getattr(model_type, model_name)(pretrained=False)
|
||||
|
||||
print("{} on {} for {} epochs - {} inner_it".format(str(aug_model), device_name, epochs, n_inner_iter))
|
||||
log= run_dist_dataugV3(model=aug_model,
|
||||
epochs=epochs,
|
||||
inner_it=n_inner_iter,
|
||||
dataug_epoch_start=dataug_epoch_start,
|
||||
opt_param=optim_param,
|
||||
print_freq=epochs/4,
|
||||
unsup_loss=1,
|
||||
hp_opt=False,
|
||||
save_sample_freq=None)
|
||||
model = Higher_model(model, model_name) #run_dist_dataugV3
|
||||
if n_inner_iter!=0:
|
||||
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)
|
||||
else:
|
||||
aug_model = Augmented_model(RandAug(TF_dict=tf_dict, N_TF=n_tf), model).to(device)
|
||||
|
||||
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, "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])
|
||||
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:
|
||||
try:
|
||||
json.dump(out, f, indent=True)
|
||||
print('Log :\"',f.name, '\" saved !')
|
||||
except:
|
||||
print("Failed to save logs :",f.name)
|
||||
print("{} on {} for {} epochs - {} inner_it".format(str(aug_model), device_name, epochs, n_inner_iter))
|
||||
log= run_dist_dataugV3(model=aug_model,
|
||||
epochs=epochs,
|
||||
inner_it=n_inner_iter,
|
||||
dataug_epoch_start=dataug_epoch_start,
|
||||
opt_param=optim_param,
|
||||
print_freq=epochs/4,
|
||||
unsup_loss=1,
|
||||
hp_opt=False,
|
||||
save_sample_freq=None)
|
||||
|
||||
print('Execution Time : %.00f '%(exec_time))
|
||||
print('-'*9)
|
||||
|
||||
exec_time=time.perf_counter() - t0
|
||||
max_cached = torch.cuda.max_memory_cached()/(1024.0 * 1024.0) #torch.cuda.max_memory_reserved() #MB
|
||||
####
|
||||
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,
|
||||
"Device": device_name,
|
||||
"Memory": max_cached,
|
||||
"Param_names": aug_model.TF_names(),
|
||||
"Log": log}
|
||||
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)
|
||||
with open(res_folder+"log/%s.json" % filename, "w+") as f:
|
||||
try:
|
||||
json.dump(out, f, indent=True)
|
||||
print('Log :\"',f.name, '\" saved !')
|
||||
except:
|
||||
print("Failed to save logs :",f.name)
|
||||
|
||||
print('Execution Time : %.00f '%(exec_time))
|
||||
print('-'*9)
|
||||
'''
|
||||
### Benchmark - RandAugment ###
|
||||
for model_type in model_list.keys():
|
||||
for model_name in model_list[model_type]:
|
||||
for run in range(nb_run):
|
||||
torch.cuda.reset_max_memory_cached() #reset_peak_stats
|
||||
t0 = time.perf_counter()
|
||||
|
||||
model = getattr(model_type, model_name)(pretrained=False).to(device)
|
||||
|
||||
print("RandAugment(N{}-M{})-{} on {} for {} epochs".format(rand_aug['N'],rand_aug['M'],model_name, device_name, epochs))
|
||||
log= train_classic(model=model, opt_param=optim_param, epochs=epochs, print_freq=epochs/4)
|
||||
|
||||
exec_time=time.perf_counter() - t0
|
||||
max_cached = torch.cuda.max_memory_cached()/(1024.0 * 1024.0) #torch.cuda.max_memory_reserved() #MB
|
||||
####
|
||||
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,
|
||||
"Device": device_name,
|
||||
"Memory": max_cached,
|
||||
"Rand_Aug": rand_aug,
|
||||
"Log": log}
|
||||
print("RandAugment-",model_name,": acc", out["Accuracy"], "in:", out["Time"][0], "+/-", out["Time"][1])
|
||||
filename = "RandAugment(N{}-M{})-{}-{} epochs -{}".format(rand_aug['N'],rand_aug['M'],model_name,epochs, run)
|
||||
with open(res_folder+"log/%s.json" % filename, "w+") as f:
|
||||
try:
|
||||
json.dump(out, f, indent=True)
|
||||
print('Log :\"',f.name, '\" saved !')
|
||||
except:
|
||||
print("Failed to save logs :",f.name)
|
||||
|
||||
#plot_resV2(log, fig_name=res_folder+filename)
|
||||
|
||||
print('Execution Time : %.00f '%(exec_time))
|
||||
print('-'*9)
|
||||
|
||||
### HP Search ###
|
||||
'''
|
||||
from LeNet import *
|
||||
inner_its = [1]
|
||||
dist_mix = [0.0, 0.5, 0.8, 1.0]
|
||||
N_seq_TF= [2, 3, 4]
|
||||
N_seq_TF= [3, 2, 4]
|
||||
mag_setup = [(True,True), (False, False)] #(FxSh, Independant)
|
||||
#prob_setup = [True, False]
|
||||
nb_run= 3
|
||||
|
||||
try:
|
||||
os.mkdir(res_folder)
|
||||
|
|
@ -150,9 +202,10 @@ if __name__ == "__main__":
|
|||
p_setup=False
|
||||
for run in range(nb_run):
|
||||
|
||||
t0 = time.process_time()
|
||||
t0 = time.perf_counter()
|
||||
|
||||
model = getattr(models.resnet, 'resnet18')(pretrained=False)
|
||||
#model = getattr(models.resnet, 'resnet18')(pretrained=False)
|
||||
model = LeNet(3,10)
|
||||
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(RandAug(TF_dict=tf_dict, N_TF=2), model).to(device)
|
||||
|
|
@ -168,7 +221,7 @@ if __name__ == "__main__":
|
|||
hp_opt=False,
|
||||
save_sample_freq=None)
|
||||
|
||||
exec_time=time.process_time() - t0
|
||||
exec_time=time.perf_counter() - t0
|
||||
####
|
||||
print('-'*9)
|
||||
times = [x["time"] for x in log]
|
||||
|
|
@ -184,4 +237,4 @@ if __name__ == "__main__":
|
|||
|
||||
print('Execution Time : %.00f '%(exec_time))
|
||||
print('-'*9)
|
||||
#'''
|
||||
'''
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
""" Dataset definition.
|
||||
|
||||
MNIST / CIFAR10
|
||||
MNIST / CIFAR10 / CIFAR100 / SVHN / ImageNet
|
||||
"""
|
||||
import torch
|
||||
from torch.utils.data.dataset import ConcatDataset
|
||||
|
|
@ -37,9 +37,16 @@ transform_train = torchvision.transforms.Compose([
|
|||
#transforms.RandomVerticalFlip(),
|
||||
torchvision.transforms.ToTensor(),
|
||||
])
|
||||
#from RandAugment import RandAugment
|
||||
|
||||
## RandAugment ##
|
||||
from RandAugment import RandAugment
|
||||
# Add RandAugment with N, M(hyperparameter)
|
||||
#transform_train.transforms.insert(0, RandAugment(n=2, m=30))
|
||||
rand_aug={'N': 2, 'M': 1}
|
||||
#rand_aug={'N': 2, 'M': 9./30} #RN-ImageNet
|
||||
#rand_aug={'N': 3, 'M': 5./30} #WRN-CIFAR10
|
||||
#rand_aug={'N': 2, 'M': 14./30} #WRN-CIFAR100
|
||||
#rand_aug={'N': 3, 'M': 7./30} #WRN-SVHN
|
||||
transform_train.transforms.insert(0, RandAugment(n=rand_aug['N'], m=rand_aug['M']))
|
||||
|
||||
### Classic Dataset ###
|
||||
|
||||
|
|
@ -50,7 +57,7 @@ transform_train = torchvision.transforms.Compose([
|
|||
|
||||
#CIFAR
|
||||
data_train = torchvision.datasets.CIFAR10(dataroot, train=True, download=download_data, transform=transform_train)
|
||||
#data_val = torchvision.datasets.CIFAR10(dataroot, train=True, download=download_data, transform=transform)
|
||||
data_val = torchvision.datasets.CIFAR10(dataroot, train=True, download=download_data, transform=transform)
|
||||
data_test = torchvision.datasets.CIFAR10(dataroot, train=False, download=download_data, transform=transform)
|
||||
|
||||
#data_train = torchvision.datasets.CIFAR100(dataroot, train=True, download=download_data, transform=transform_train)
|
||||
|
|
@ -72,32 +79,18 @@ data_test = torchvision.datasets.CIFAR10(dataroot, train=False, download=downloa
|
|||
|
||||
#Validation set size [0, 1]
|
||||
valid_size=0.1
|
||||
#train_subset_indices=range(int(len(data_train)*(1-valid_size)))
|
||||
#val_subset_indices=range(int(len(data_train)*(1-valid_size)),len(data_train))
|
||||
train_subset_indices=range(int(len(data_train)*(1-valid_size)))
|
||||
val_subset_indices=range(int(len(data_train)*(1-valid_size)),len(data_train))
|
||||
#train_subset_indices=range(BATCH_SIZE*10)
|
||||
#val_subset_indices=range(BATCH_SIZE*10, BATCH_SIZE*20)
|
||||
|
||||
#from torch.utils.data import SubsetRandomSampler
|
||||
#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)
|
||||
from torch.utils.data import SubsetRandomSampler
|
||||
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_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)
|
||||
|
||||
#Cross Validation
|
||||
'''
|
||||
from skorch.dataset import CVSplit
|
||||
import numpy as np
|
||||
cvs = CVSplit(cv=valid_size, stratified=True) #Stratified =True for unbalanced dataset #ShuffleSplit
|
||||
|
||||
def next_CVSplit():
|
||||
|
||||
train_subset, val_subset = cvs(data_train, y=np.array(data_train.targets))
|
||||
dl_train = torch.utils.data.DataLoader(train_subset, batch_size=BATCH_SIZE, shuffle=True, num_workers=num_workers, pin_memory=pin_memory)
|
||||
dl_val = torch.utils.data.DataLoader(val_subset, batch_size=BATCH_SIZE, shuffle=True, num_workers=num_workers, pin_memory=pin_memory)
|
||||
|
||||
return dl_train, dl_val
|
||||
|
||||
dl_train, dl_val = next_CVSplit()
|
||||
'''
|
||||
import numpy as np
|
||||
from sklearn.model_selection import ShuffleSplit
|
||||
from sklearn.model_selection import StratifiedShuffleSplit
|
||||
|
|
@ -134,7 +127,7 @@ class CVSplit(object):
|
|||
else:
|
||||
cv_cls = ShuffleSplit
|
||||
|
||||
self._cv= cv_cls(test_size=val_size, random_state=0)
|
||||
self._cv= cv_cls(test_size=val_size, random_state=0) #Random state w/ fixed seed
|
||||
|
||||
def next_split(self):
|
||||
""" Get next cross-validation split.
|
||||
|
|
@ -157,4 +150,21 @@ class CVSplit(object):
|
|||
return dl_train, dl_val
|
||||
|
||||
cvs = CVSplit(data_train, val_size=valid_size)
|
||||
dl_train, dl_val = cvs.next_split()
|
||||
dl_train, dl_val = cvs.next_split()
|
||||
'''
|
||||
|
||||
'''
|
||||
from skorch.dataset import CVSplit
|
||||
import numpy as np
|
||||
cvs = CVSplit(cv=valid_size, stratified=True) #Stratified =True for unbalanced dataset #ShuffleSplit
|
||||
|
||||
def next_CVSplit():
|
||||
|
||||
train_subset, val_subset = cvs(data_train, y=np.array(data_train.targets))
|
||||
dl_train = torch.utils.data.DataLoader(train_subset, batch_size=BATCH_SIZE, shuffle=True, num_workers=num_workers, pin_memory=pin_memory)
|
||||
dl_val = torch.utils.data.DataLoader(val_subset, batch_size=BATCH_SIZE, shuffle=True, num_workers=num_workers, pin_memory=pin_memory)
|
||||
|
||||
return dl_train, dl_val
|
||||
|
||||
dl_train, dl_val = next_CVSplit()
|
||||
'''
|
||||
Loading…
Add table
Add a link
Reference in a new issue