level14taken’s gists

level14taken / scse.py

Created January 4, 2021 07:46

	class ChannelAttentionGate(nn.Module):
	def __init__(self, channel, reduction=16):
	super(ChannelAttentionGate, self).__init__()
	self.avg_pool = nn.AdaptiveAvgPool2d(1)
	self.fc = nn.Sequential(
	nn.Linear(channel, channel // reduction),
	nn.ReLU(inplace=True),
	nn.Linear(channel // reduction, channel),
	nn.Sigmoid()
	)

level14taken / baseline.py

Last active January 3, 2021 11:02

	#https://www.kaggle.com/c/tgs-salt-identification-challenge/discussion/67693
	class ConvBn2d(nn.Module):
	def __init__(self, in_channels, out_channels, kernel_size=(3,3), stride=(1,1), padding=(1,1)):
	super(ConvBn2d, self).__init__()

	self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=kernel_size, stride=stride, padding=padding, bias=False)
	self.bn = nn.BatchNorm2d(out_channels)

	def forward(self, z):
	x = self.conv(z)

level14taken / metric.py

Last active January 3, 2021 06:50

	#https://www.kaggle.com/c/tgs-salt-identification-challenge/discussion/67693
	def iou_metric(outputs, labels,logits=True):
	outputs,labels= size_correct(outputs,labels)
	outputs= (outputs>0).detach().cpu().numpy() if logits else (outputs>.5).detach().cpu().numpy()
	labels= labels.detach().cpu().numpy()
	batch_size = outputs.shape[0]
	metric = 0.0
	for batch in range(batch_size):
	t, p = labels[batch], outputs[batch]
	true = np.sum(t)

level14taken / train.py

Created December 29, 2020 10:13

	kf = StratifiedKFold(10,shuffle=True,random_state=seed)
	for fold, (trn_idx,val_idx) in enumerate(kf.split(file_list,coverage)):
	print('****************************************************')
	print('***************** fold %d *****************' % fold)
	print('****************************************************')

	file_list_train= [x for i,x in enumerate(file_list) if i in trn_idx]
	file_list_val= [x for i,x in enumerate(file_list) if i in val_idx]
	train = TGSSaltDataset(train_path, file_list_train,augment=transform_train)
	val = TGSSaltDataset(train_path, file_list_val,augment= transform_test)

level14taken / model.py

Last active January 3, 2021 11:07

	class ConvBn2d(nn.Module):
	def __init__(self, in_channels, out_channels, kernel_size=(3,3), stride=(1,1), padding=(1,1)):
	super(ConvBn2d, self).__init__()

	self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=kernel_size, stride=stride, padding=padding, bias=False)
	self.bn = nn.BatchNorm2d(out_channels)

	def forward(self, z):
	x = self.conv(z)
	x = self.bn(x)

level14taken / simpleloss.py

Created December 29, 2020 10:08

	def get_losslv_simple(model,inp):
	no_mask,final=model(inp[0])
	final=final*inp[-1].view(-1,1,1,1)
	mfl=nn.BCEWithLogitsLoss()
	lv=LovaszLoss()
	weights=[.1/2.1,2/2.1]
	loss=[mfl(no_mask.view(-1,1,1,1),inp[-1].view(-1,1,1,1)),lv(final,inp[1])]
	accuracy=acc(no_mask.reshape(-1),inp[-1],center=True)/len(inp[-1])
	loss=sum(x_i*y_i for x_i, y_i in zip(weights, loss))
	return loss,accuracy,final

level14taken / test_loop.py

Created December 29, 2020 10:05

level14taken / train_loop.py

Created December 29, 2020 10:05

	def train_loop_fn(loader):
	model.train()
	loss_,iou_,acc_=0.,0.,0.
	for x ,(image, mask) in enumerate(loader):
	mask=mask.to(device)
	image= image.to(device)
	y_pred = model(image)
	loss = loss_fn(y_pred, mask)
	loss_+= loss.item()
	optimizer.zero_grad()

level14taken / augment.py

Last active December 29, 2020 11:00

	test_transforms=PadIfNeeded(128,128,cv2.BORDER_REPLICATE),
	Normalize(mean=(0,0,0),std=(1,1,1,))])
	transform_train = Compose([
	HorizontalFlip(p=.5),
	Compose([RandomCrop(90,90),
	Resize(101,101)],p=.3),
	OneOf([RandomBrightness(.1),
	RandomContrast(.1),RandomGamma()],p=.2),
	PadIfNeeded(256//2,256//2,cv2.BORDER_REPLICATE),
	Normalize(mean=(0,0,0),std=(1,1,1,))])

level14taken / dataset.py

Last active December 29, 2020 11:00

	class TGSSaltDataset(data.Dataset):
	def __init__(self, root_path, file_list, is_test = False,augment= def_transforms,dpsv=False):
	self.is_test = is_test
	self.root_path = root_path
	self.file_list = file_list
	self.augment= augment
	self.dpsv= dpsv
	def __len__(self):
	return len(self.file_list)

Manoj Guthikonda level14taken