def train(args):
joint_transform = transforms.Compose([
transforms.RandomScale(),
transforms.Mirror(),
transforms.RandomCrop()
])
trainset = datasets[args.dataset](mode=args.mode, root=args.dataset_root)
net = models[args.g]
def __init__(self, train=True):
self.root = './data/ESC50/ESC-50-master/audio/'
self.train = train
#getting name of all files inside the all of the train_folds
temp = open('./data/ESC50/ESC10_file_names.txt',
'r').read().split('\n')
temp.sort()
self.file_names = []
if train:
for i in range(len(temp)):
if int(temp[i].split('-')[0]) in config.train_folds:
self.file_names.append(temp[i])
else:
for i in range(len(temp)):
if int(temp[i].split('-')[0]) in config.test_fold:
self.file_names.append(temp[i])
if self.train:
self.wave_transforms = torchvision.transforms.Compose([
transforms.ToTensor1D(),
transforms.RandomScale(max_scale=1.25),
transforms.RandomPadding(out_len=220500),
transforms.RandomCrop(out_len=220500)
])
self.spec_transforms = torchvision.transforms.Compose([
torchvision.transforms.ToTensor(),
transforms.FrequencyMask(max_width=config.freq_masks_width,
numbers=config.freq_masks),
transforms.TimeMask(max_width=config.time_masks_width,
numbers=config.time_masks)
])
else: #for test
self.wave_transforms = torchvision.transforms.Compose([
transforms.ToTensor1D(),
transforms.RandomPadding(out_len=220500),
transforms.RandomCrop(out_len=220500)
])
self.spec_transforms = torchvision.transforms.Compose(
[torchvision.transforms.ToTensor()])
def get_dataloader():
# TODO(xwd): Adaptive normalization by some large image.
# E.g. In medical image processing, WSI image is very large and different to ordinary images.
value_scale = 255
mean = [0.485, 0.456, 0.406]
mean = [item * value_scale for item in mean]
std = [0.229, 0.224, 0.225]
std = [item * value_scale for item in std]
train_transform = transform.Compose([
transform.RandomScale([cfg['scale_min'], cfg['scale_max']]),
transform.RandomRotate([cfg['rotate_min'], cfg['rotate_max']],
padding=mean,
ignore_label=cfg['ignore_label']),
transform.RandomGaussianBlur(),
transform.RandomHorizontallyFlip(),
transform.RandomCrop([cfg['train_h'], cfg['train_w']],
crop_type='rand',
padding=mean,
ignore_label=cfg['ignore_label']),
transform.ToTensor(),
transform.Normalize(mean=mean, std=std)
])
train_data = cityscapes.Cityscapes(cfg['data_path'],
split='train',
transform=train_transform)
# Use data sampler to make sure each GPU loads specific parts of dataset to avoid data reduntant.
train_sampler = DistributedSampler(train_data)
train_loader = DataLoader(train_data,
batch_size=cfg['batch_size'] //
cfg['world_size'],
shuffle=(train_sampler is None),
num_workers=4,
pin_memory=True,
sampler=train_sampler,
drop_last=True)
return train_loader, train_sampler
def __init__(self, train=True):
self.root = './data/US8K/audio/'
self.train = train
self.file_paths = [] #only includes the name of the fold and name of the file, like: 'fold2/4201-3-0-0.wav'
if train:
for f in config.train_folds:
file_names = os.listdir(self.root + 'fold' + str(f) + '/' )
for name in file_names:
if name.split('.')[-1] == 'wav':
self.file_paths.append('fold' + str(f) + '/' + name)
else:
file_names = os.listdir(self.root + 'fold' + str(config.test_fold[0]) + '/' )
for name in file_names:
if name.split('.')[-1] == 'wav':
self.file_paths.append('fold' + str(config.test_fold[0]) + '/' + name)
if self.train:
self.wave_transforms = torchvision.transforms.Compose([ transforms.ToTensor1D(),
transforms.RandomScale(max_scale = 1.25),
transforms.RandomPadding(out_len = 176400),
transforms.RandomCrop(out_len = 176400)])
self.spec_transforms = torchvision.transforms.Compose([torchvision.transforms.ToTensor(),
transforms.FrequencyMask(max_width = config.freq_masks_width, numbers = config.freq_masks),
transforms.TimeMask(max_width = config.time_masks_width, numbers = config.time_masks)])
else: #for test
self.wave_transforms = torchvision.transforms.Compose([ transforms.ToTensor1D(),
transforms.RandomPadding(out_len = 176400),
transforms.RandomCrop(out_len = 176400)])
self.spec_transforms = torchvision.transforms.Compose([torchvision.transforms.ToTensor() ])
from experiment_builder import ExperimentBuilder
from utils.arg_extractor import get_args
import utils.transforms as trans
from model.deeplab import DeepLab
import matplotlib.pyplot as plt
from tools import prediction
from utils.metrics import Evaluator
args = get_args()
rng = np.random.RandomState(seed=args.seed)
torch.manual_seed(seed=args.seed)
transform_train = trans.Compose([
trans.RandomHorizontalFlip(),
#trans.FixScale((args.crop_size,args.crop_size)),
trans.RandomScale((0.5, 2.0)),
#trans.FixScale(args.crop_size),
trans.RandomCrop(args.crop_size),
trans.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
trans.ToTensor(),
])
transform_val = trans.Compose([
#trans.FixScale((args.crop_size,args.crop_size)),
trans.FixScale(args.crop_size),
trans.CenterCrop(args.crop_size),
trans.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
trans.ToTensor(),
])
if (args.aug == True):
voc_train = VOCSegmentation(root='./data',