def load_trained_model(model_name, weights_path, num_classes):
if model_name == 'segnet':
model = SegNet(num_classes)
checkpoint = torch.load(weights_path, map_location='cpu')
model.load_state_dict(checkpoint['state_dict'])
else:
raise AssertionError('model not available')
return model
def main():
train_loader = DataLoader(dataset=VaeDataset('train'), batch_size=batch_size, shuffle=True,
pin_memory=True, drop_last=True)
val_loader = DataLoader(dataset=VaeDataset('valid'), batch_size=batch_size, shuffle=False,
pin_memory=True, drop_last=True)
# Create SegNet model
label_nbr = 3
model = SegNet(label_nbr)
if torch.cuda.device_count() > 1:
print("Let's use", torch.cuda.device_count(), "GPUs!")
# dim = 0 [40, xxx] -> [10, ...], [10, ...], [10, ...], [10, ...] on 4 GPUs
model = nn.DataParallel(model)
# Use appropriate device
model = model.to(device)
# print(model)
# define the optimizer
# optimizer = optim.LBFGS(model.parameters(), lr=0.8)
optimizer = optim.Adam(model.parameters(), lr=lr)
best_loss = 100000
epochs_since_improvement = 0
# Epochs
for epoch in range(start_epoch, epochs):
# Decay learning rate if there is no improvement for 8 consecutive epochs, and terminate training after 20
if epochs_since_improvement == 20:
break
if epochs_since_improvement > 0 and epochs_since_improvement % 8 == 0:
adjust_learning_rate(optimizer, 0.8)
# One epoch's training
train(epoch, train_loader, model, optimizer)
# One epoch's validation
val_loss = valid(val_loader, model)
print('\n * LOSS - {loss:.3f}\n'.format(loss=val_loss))
# Check if there was an improvement
is_best = val_loss < best_loss
best_loss = min(best_loss, val_loss)
if not is_best:
epochs_since_improvement += 1
print("\nEpochs since last improvement: %d\n" % (epochs_since_improvement,))
else:
epochs_since_improvement = 0
# Save checkpoint
save_checkpoint(epoch, model, optimizer, val_loss, is_best)
def trainCNN(modelName='resnet'):
# More hyperparameters
dataset = ImageDataset()
dataset_labels = dataset.get_all_labels()
num_classes = len(dataset_labels)
if modelName == 'resnet':
model = resnet_dropout_18(num_classes=num_classes, p=cnnDropout)
elif modelName == 'inception':
model = Inception3(num_classes=num_classes, aux_logits=False)
elif modelName == 'segnet':
# TODO: Figure out how dims need to be changed based off of NYU dataset
model = SegNet(input_channels=3,
output_channels=1,
pretrained_vgg=True)
else:
raise Exception("Please select one of \'resnet\' or \'inception\' or "
"\'segnet\'")
if torch.cuda.is_available():
if multiGPU:
model = nn.DataParallel(model)
model = model.cuda()
optimizer = optim.Adam(model.parameters(), lr=cnnLr)
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer,
'min',
patience=2)
# setup the device for running
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = model.to(device)
model.eval()
return model
def main(args):
num_classes = 1
size = [192, 192] # size of images
thresh = 0.5
if args.out_dir:
os.makedirs(args.out_dir, exist_ok=True)
in_ = eddl.Input([3, size[0], size[1]])
out = SegNet(in_, num_classes)
out_sigm = eddl.Sigmoid(out)
net = eddl.Model([in_], [out_sigm])
eddl.build(net, eddl.adam(0.0001), ["cross_entropy"],
["mean_squared_error"],
eddl.CS_GPU([1]) if args.gpu else eddl.CS_CPU())
eddl.summary(net)
eddl.setlogfile(net, "skin_lesion_segmentation")
training_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(size),
ecvl.AugMirror(0.5),
ecvl.AugFlip(0.5),
ecvl.AugRotate([-180, 180]),
ecvl.AugAdditivePoissonNoise([0, 10]),
ecvl.AugGammaContrast([0.5, 1.5]),
ecvl.AugGaussianBlur([0, 0.8]),
ecvl.AugCoarseDropout([0, 0.3], [0.02, 0.05], 0.5)
])
validation_augs = ecvl.SequentialAugmentationContainer(
[ecvl.AugResizeDim(size)])
dataset_augs = ecvl.DatasetAugmentations(
[training_augs, validation_augs, None])
print("Reading dataset")
d = ecvl.DLDataset(args.in_ds, args.batch_size, dataset_augs)
x = Tensor([args.batch_size, d.n_channels_, size[0], size[1]])
y = Tensor([args.batch_size, d.n_channels_gt_, size[0], size[1]])
num_samples_train = len(d.GetSplit())
num_batches_train = num_samples_train // args.batch_size
d.SetSplit(ecvl.SplitType.validation)
num_samples_validation = len(d.GetSplit())
num_batches_validation = num_samples_validation // args.batch_size
indices = list(range(args.batch_size))
evaluator = utils.Evaluator()
print("Starting training")
for e in range(args.epochs):
print("Epoch {:d}/{:d} - Training".format(e + 1, args.epochs),
flush=True)
d.SetSplit(ecvl.SplitType.training)
eddl.reset_loss(net)
s = d.GetSplit()
random.shuffle(s)
d.split_.training_ = s
d.ResetAllBatches()
for b in range(num_batches_train):
print("Epoch {:d}/{:d} (batch {:d}/{:d}) - ".format(
e + 1, args.epochs, b + 1, num_batches_train),
end="",
flush=True)
d.LoadBatch(x, y)
x.div_(255.0)
y.div_(255.0)
tx, ty = [x], [y]
eddl.train_batch(net, tx, ty, indices)
eddl.print_loss(net, b)
print()
print("Saving weights")
eddl.save(net, "isic_segmentation_checkpoint_epoch_%s.bin" % e, "bin")
d.SetSplit(ecvl.SplitType.validation)
evaluator.ResetEval()
print("Epoch %d/%d - Evaluation" % (e + 1, args.epochs), flush=True)
for b in range(num_batches_validation):
n = 0
print("Epoch {:d}/{:d} (batch {:d}/{:d}) ".format(
e + 1, args.epochs, b + 1, num_batches_validation),
end="",
flush=True)
d.LoadBatch(x, y)
x.div_(255.0)
y.div_(255.0)
eddl.forward(net, [x])
output = eddl.getOutput(out_sigm)
for k in range(args.batch_size):
img = output.select([str(k)])
gt = y.select([str(k)])
img_np = np.array(img, copy=False)
gt_np = np.array(gt, copy=False)
iou = evaluator.BinaryIoU(img_np, gt_np, thresh=thresh)
print("- IoU: %.6g " % iou, end="", flush=True)
if args.out_dir:
# C++ BinaryIoU modifies image as a side effect
img_np[img_np >= thresh] = 1
img_np[img_np < thresh] = 0
img_t = ecvl.TensorToView(img)
img_t.colortype_ = ecvl.ColorType.GRAY
img_t.channels_ = "xyc"
img.mult_(255.)
# orig_img
orig_img = x.select([str(k)])
orig_img.mult_(255.)
orig_img_t = ecvl.TensorToImage(orig_img)
orig_img_t.colortype_ = ecvl.ColorType.BGR
orig_img_t.channels_ = "xyc"
tmp, labels = ecvl.Image.empty(), ecvl.Image.empty()
ecvl.CopyImage(img_t, tmp, ecvl.DataType.uint8)
ecvl.ConnectedComponentsLabeling(tmp, labels)
ecvl.CopyImage(labels, tmp, ecvl.DataType.uint8)
contours = ecvl.FindContours(tmp)
ecvl.CopyImage(orig_img_t, tmp, ecvl.DataType.uint8)
tmp_np = np.array(tmp, copy=False)
for cseq in contours:
for c in cseq:
tmp_np[c[0], c[1], 0] = 0
tmp_np[c[0], c[1], 1] = 0
tmp_np[c[0], c[1], 2] = 255
filename = d.samples_[d.GetSplit()[n]].location_[0]
head, tail = os.path.splitext(os.path.basename(filename))
bname = "%s.png" % head
output_fn = os.path.join(args.out_dir, bname)
ecvl.ImWrite(output_fn, tmp)
if e == 0:
gt_t = ecvl.TensorToView(gt)
gt_t.colortype_ = ecvl.ColorType.GRAY
gt_t.channels_ = "xyc"
gt.mult_(255.)
gt_filename = d.samples_[d.GetSplit()[n]].label_path_
gt_fn = os.path.join(args.out_dir,
os.path.basename(gt_filename))
ecvl.ImWrite(gt_fn, gt_t)
n += 1
print()
print("MIoU: %.6g" % evaluator.MeanMetric())
def main(args):
num_classes = 1
size = [192, 192] # size of images
thresh = 0.5
if args.out_dir:
os.makedirs(args.out_dir, exist_ok=True)
in_ = eddl.Input([3, size[0], size[1]])
out = SegNet(in_, num_classes)
out_sigm = eddl.Sigmoid(out)
net = eddl.Model([in_], [out_sigm])
eddl.build(net, eddl.adam(0.0001), ["cross_entropy"],
["mean_squared_error"],
eddl.CS_GPU([1]) if args.gpu else eddl.CS_CPU())
eddl.summary(net)
eddl.setlogfile(net, "skin_lesion_segmentation_inference")
if not os.path.exists(args.ckpts):
raise RuntimeError('Checkpoint "{}" not found'.format(args.ckpts))
eddl.load(net, args.ckpts, "bin")
training_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(size),
])
test_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(size),
])
dataset_augs = ecvl.DatasetAugmentations([training_augs, None, test_augs])
print("Reading dataset")
d = ecvl.DLDataset(args.in_ds, args.batch_size, dataset_augs)
x = Tensor([args.batch_size, d.n_channels_, size[0], size[1]])
y = Tensor([args.batch_size, d.n_channels_gt_, size[0], size[1]])
print("Testing")
d.SetSplit(ecvl.SplitType.test)
num_samples_test = len(d.GetSplit())
num_batches_test = num_samples_test // args.batch_size
evaluator = utils.Evaluator()
evaluator.ResetEval()
for b in range(num_batches_test):
n = 0
print("Batch {:d}/{:d} ".format(b + 1, num_batches_test),
end="",
flush=True)
d.LoadBatch(x, y)
x.div_(255.0)
y.div_(255.0)
eddl.forward(net, [x])
output = eddl.getOutput(out_sigm)
for k in range(args.batch_size):
img = output.select([str(k)])
gt = y.select([str(k)])
img_np, gt_np = np.array(img, copy=False), np.array(gt, copy=False)
iou = evaluator.BinaryIoU(img_np, gt_np, thresh=thresh)
print("- IoU: %.6g " % iou, end="", flush=True)
if args.out_dir:
# C++ BinaryIoU modifies image as a side effect
img_np[img_np >= thresh] = 1
img_np[img_np < thresh] = 0
img_t = ecvl.TensorToView(img)
img_t.colortype_ = ecvl.ColorType.GRAY
img_t.channels_ = "xyc"
img.mult_(255.)
# orig_img
orig_img = x.select([str(k)])
orig_img.mult_(255.)
orig_img_t = ecvl.TensorToImage(orig_img)
orig_img_t.colortype_ = ecvl.ColorType.BGR
orig_img_t.channels_ = "xyc"
tmp, labels = ecvl.Image.empty(), ecvl.Image.empty()
ecvl.CopyImage(img_t, tmp, ecvl.DataType.uint8)
ecvl.ConnectedComponentsLabeling(tmp, labels)
ecvl.CopyImage(labels, tmp, ecvl.DataType.uint8)
contours = ecvl.FindContours(tmp)
ecvl.CopyImage(orig_img_t, tmp, ecvl.DataType.uint8)
tmp_np = np.array(tmp, copy=False)
for cseq in contours:
for c in cseq:
tmp_np[c[0], c[1], 0] = 0
tmp_np[c[0], c[1], 1] = 0
tmp_np[c[0], c[1], 2] = 255
filename = d.samples_[d.GetSplit()[n]].location_[0]
head, tail = os.path.splitext(os.path.basename(filename))
bname = "%s.png" % head
output_fn = os.path.join(args.out_dir, bname)
ecvl.ImWrite(output_fn, tmp)
gt_t = ecvl.TensorToView(gt)
gt_t.colortype_ = ecvl.ColorType.GRAY
gt_t.channels_ = "xyc"
gt.mult_(255.)
gt_filename = d.samples_[d.GetSplit()[n]].label_path_
gt_fn = os.path.join(args.out_dir,
os.path.basename(gt_filename))
ecvl.ImWrite(gt_fn, gt_t)
n += 1
print()
print("MIoU: %.6g" % evaluator.MeanMetric())
# cv_dataset = DatasetFromjpg('./VOC2012/', mold='val', transforms=transformations, output_size=(320,320),predct=True)
# test_loader = DataLoader(dataset=cv_dataset, batch_size=10, shuffle=True, num_workers=2)
# cv_dataset = CamVidDataset('./CamVid/', mold='test', transforms=transformations, output_size=(352, 480), predct=True)
cv_dataset = DatasetFrombaidu('./baidu/',
mold='val',
transforms=transformations,
output_size=(720, 720),
predct=True)
# cv_loader = DataLoader(dataset=cv_dataset, batch_size=1, shuffle=False, num_workers=8, drop_last=True)
# 定义预测函数
# print(cv_dataset.datalen)
# cm = np.array(COLORMAP).astype('uint8')
# cm = np.array(CamVid_colours).astype('uint8')
n_class = 9
net = SegNet(num_classes=9)
# net=SegNet(num_classes=12)
net.cuda()
net.eval()
dir = './checkpoints/baiduSegNet5.pth'
state = t.load(dir)
net.load_state_dict(state['net'])
test_data, test_label = cv_dataset[1]
print(test_data.size())
# out=net(Variable(test_data.unsqueeze(0)).cuda())
# print(out.data.size())
# pred = out.max(1)[1].squeeze().cpu().data.numpy()
# print(pred.shape)
pil_img = to_pil(out_img)
return pil_img
if __name__ == '__main__':
single_sample = True
outputdir = os.path.dirname(os.path.abspath(__file__))
os.chdir(outputdir)
use_gpu = torch.cuda.is_available()
own_net = SegNet(3, 12) #OwnSegNet(3)
loaders, w_class, class_encoding, sets = dataloader.get_data_loaders(
camvid_dataset, 1, 1, 1, single_sample=single_sample)
trainloader, valloader, testloader = loaders
test_set, val_set, train_set = sets
for i, key in enumerate(class_encoding.keys()):
print("{} \t {}".format(i, key))
optimizer = optim.SGD(own_net.parameters(),
lr=1e-3,
weight_decay=5e-4,
momentum=0.9)
# Evaluation metric
def main():
net = SegNet(num_classes=num_classes).cuda()
if len(train_args['snapshot']) == 0:
curr_epoch = 0
else:
print 'training resumes from ' + train_args['snapshot']
net.load_state_dict(
torch.load(
os.path.join(ckpt_path, exp_name, train_args['snapshot'])))
split_snapshot = train_args['snapshot'].split('_')
curr_epoch = int(split_snapshot[1])
train_record['best_val_loss'] = float(split_snapshot[3])
train_record['corr_mean_iu'] = float(split_snapshot[6])
train_record['corr_epoch'] = curr_epoch
net.train()
mean_std = ([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
train_simul_transform = simul_transforms.Compose([
simul_transforms.Scale(int(train_args['input_size'][0] / 0.875)),
simul_transforms.RandomCrop(train_args['input_size']),
simul_transforms.RandomHorizontallyFlip()
])
val_simul_transform = simul_transforms.Compose([
simul_transforms.Scale(int(train_args['input_size'][0] / 0.875)),
simul_transforms.CenterCrop(train_args['input_size'])
])
img_transform = standard_transforms.Compose([
standard_transforms.ToTensor(),
standard_transforms.Normalize(*mean_std)
])
target_transform = standard_transforms.Compose([
expanded_transforms.MaskToTensor(),
expanded_transforms.ChangeLabel(ignored_label, num_classes - 1)
])
restore_transform = standard_transforms.Compose([
expanded_transforms.DeNormalize(*mean_std),
standard_transforms.ToPILImage()
])
train_set = CityScapes('train',
simul_transform=train_simul_transform,
transform=img_transform,
target_transform=target_transform)
train_loader = DataLoader(train_set,
batch_size=train_args['batch_size'],
num_workers=16,
shuffle=True)
val_set = CityScapes('val',
simul_transform=val_simul_transform,
transform=img_transform,
target_transform=target_transform)
val_loader = DataLoader(val_set,
batch_size=val_args['batch_size'],
num_workers=16,
shuffle=False)
weight = torch.ones(num_classes)
weight[num_classes - 1] = 0
criterion = CrossEntropyLoss2d(weight).cuda()
# don't use weight_decay for bias
optimizer = optim.SGD([{
'params': [
param for name, param in net.named_parameters()
if name[-4:] == 'bias' and 'dec' in name
],
'lr':
2 * train_args['new_lr']
}, {
'params': [
param for name, param in net.named_parameters()
if name[-4:] != 'bias' and 'dec' in name
],
'lr':
train_args['new_lr'],
'weight_decay':
train_args['weight_decay']
}, {
'params': [
param for name, param in net.named_parameters()
if name[-4:] == 'bias' and 'dec' not in name
],
'lr':
2 * train_args['pretrained_lr']
}, {
'params': [
param for name, param in net.named_parameters()
if name[-4:] != 'bias' and 'dec' not in name
],
'lr':
train_args['pretrained_lr'],
'weight_decay':
train_args['weight_decay']
}],
momentum=0.9,
nesterov=True)
if len(train_args['snapshot']) > 0:
optimizer.load_state_dict(
torch.load(
os.path.join(ckpt_path, exp_name,
'opt_' + train_args['snapshot'])))
optimizer.param_groups[0]['lr'] = 2 * train_args['new_lr']
optimizer.param_groups[1]['lr'] = train_args['new_lr']
optimizer.param_groups[2]['lr'] = 2 * train_args['pretrained_lr']
optimizer.param_groups[3]['lr'] = train_args['pretrained_lr']
if not os.path.exists(ckpt_path):
os.mkdir(ckpt_path)
if not os.path.exists(os.path.join(ckpt_path, exp_name)):
os.mkdir(os.path.join(ckpt_path, exp_name))
for epoch in range(curr_epoch, train_args['epoch_num']):
train(train_loader, net, criterion, optimizer, epoch)
validate(val_loader, net, criterion, optimizer, epoch,
restore_transform)
def main():
Dataset = './SDOBenchmark-data-full/'
train_set = SDODataset(Dataset, mode='train')
test_set = SDODataset(Dataset, mode='test')
train_loader = DataLoader(train_set,
batch_size=batch_size,
shuffle=True,
pin_memory=True,
drop_last=True)
val_loader = DataLoader(test_set,
batch_size=batch_size,
shuffle=False,
pin_memory=True,
drop_last=True)
# Create SegNet model
label_nbr = 1
model = SegNet(label_nbr, in_channels=1)
if torch.cuda.device_count() > 1:
print("Let's use", torch.cuda.device_count(), "GPUs!")
model = nn.DataParallel(model)
# Use appropriate device
model = model.to(device)
optimizer = optim.Adam(model.parameters(), lr=lr)
best_loss = 100000
epochs_since_improvement = 0
state, start_epoch = load_checkpoint(mode='autoencoder')
if start_epoch != 0:
print("Load from checkpoint epoch: ", start_epoch - 1)
model = state['model']
model = model.to(device)
optimizer = state['optimizer']
# Epochs
for epoch in range(start_epoch, epochs):
# Decay learning rate if there is no improvement for 8 consecutive epochs, and terminate training after 20
if epochs_since_improvement == 20:
break
if epochs_since_improvement > 0 and epochs_since_improvement % 8 == 0:
adjust_learning_rate(optimizer, 0.8)
# One epoch's training
train_loss = train(epoch, train_loader, model, optimizer)
# One epoch's validation
val_loss = valid(val_loader, model)
print('\n * LOSS - {loss:.3f}\n'.format(loss=val_loss))
# Check if there was an improvement
is_best = val_loss < best_loss
best_loss = min(best_loss, val_loss)
if not is_best:
epochs_since_improvement += 1
print("\nEpochs since last improvement: %d\n" %
(epochs_since_improvement, ))
else:
epochs_since_improvement = 0
# Save checkpoint
save_checkpoint(epoch,
model,
optimizer,
val_loss,
is_best,
mode='autoencoder',
train_loss=train_loss)
print('train finished')
root.mkdir(exist_ok=True, parents=True)
num_classes = 3
channels=list(map(int, args.channels.split(','))) #5
input_channels=len(channels)
print('channels:',channels,'len',input_channels)
if args.model == 'UNet11':
model = UNet11(num_classes=num_classes, input_channels=input_channels)
elif args.model == 'UNet':
model = UNet(num_classes=num_classes, input_channels=input_channels)
elif args.model == 'AlbuNet34':
model = AlbuNet34(num_classes=num_classes, num_input_channels=input_channels, pretrained=False)
elif args.model == 'SegNet':
model = SegNet(num_classes=num_classes, num_input_channels=input_channels, pretrained=False)
elif args.model == 'DeepLabV3':
model = deeplabv3_resnet101(pretrained=False, progress=True, num_classes=num_classes)
#model = models.segmentation.deeplabv3_resnet101(pretrained=False, progress=True, num_classes=num_classes)
elif args.model == 'FCN':
model = fcn_resnet101(pretrained=False, progress=True, num_classes=num_classes)
else:
model = UNet11(num_classes=num_classes, input_channels=input_channels)
if torch.cuda.is_available():
if args.device_ids:#
device_ids = list(map(int, args.device_ids.split(',')))
else:
device_ids = None
#model = nn.DataParallel(model, device_ids=device_ids).cuda()
images = sample_test[0].to(device)
trueMasks = sample_test[1].to(device)
predMasks = model(images)
plt.figure()
predTensor = (torch.exp(predMasks[0, 0, :, :]).detach().cpu())
plt.imshow((predTensor / torch.max(predTensor)) * 255, cmap='gray')
pilTrans = transforms.ToPILImage()
pilImg = pilTrans((predTensor / torch.max(predTensor)) * 255)
pilArray = np.array(pilImg)
pilArray = (pilArray > 127)
im = Image.fromarray(pilArray)
im.save(self.predMaskPath + '/' + str(i_test) + '.tif')
print((predTensor / torch.max(predTensor)) * 255)
mBatchDice = torch.mean(Loss(trueMasks, predMasks).dice_coeff())
print(mBatchDice.item())
if __name__ == "__main__":
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = SegNet(1, 1).to(device)
# model = torchvision.models.segmentation.deeplabv3_resnet101(pretrained=False, num_classes=1)
modelName = model.__class__.__name__
checkpoint = torch.load(test().checkpointsPath + '/' + modelName + '/' +
test().modelWeight)
model.load_state_dict(checkpoint['model_state_dict'])
model = model.to(device)
test().main(model, device)
print('Training size = {}'.format(len(trainset)))
# Dataloaders
trainloader = DataLoader(trainset, batch_size=args.batch, pin_memory=True)
# Model
if args.model == 'unet':
if args.multitask:
model = MultiTaskUNet(3, 1, R=5)
else:
model = UNet(3, 1)
elif args.model == 'segnet':
if args.multitask:
model = MultiTaskSegNet(3, 1, R=5)
else:
model = SegNet(3, 1)
else:
raise ValueError('unknown model {}'.format(args.model))
if torch.cuda.is_available():
print('CUDA available -> Transfering to CUDA')
device = torch.device('cuda')
else:
device = torch.device('cpu')
print('CUDA unavailable')
model = model.to(device)
os.makedirs(args.destination, exist_ok=True)
basename = os.path.join(args.destination,
args.model if args.name is None else args.name)
def main():
parser = argparse.ArgumentParser()
arg = parser.add_argument
arg('--device-ids',
type=str,
default='0',
help='For example 0,1 to run on two GPUs')
arg('--fold-out', type=int, default='0', help='fold train-val test')
arg('--fold-in', type=int, default='0', help='fold train val')
arg('--percent', type=float, default=1, help='percent of data')
arg('--root', default='runs/debug', help='checkpoint root')
arg('--batch-size', type=int, default=4, help='HR:4,VHR:8')
arg('--limit', type=int, default=10000, help='number of images in epoch')
arg('--n-epochs', type=int, default=40)
arg('--lr', type=float, default=1e-3)
arg('--model',
type=str,
default='UNet11',
choices=['UNet11', 'UNet', 'AlbuNet34', 'SegNet'])
arg('--dataset-path',
type=str,
default='data_VHR',
help='main file,in which the dataset is: data_VHR or data_HR')
arg('--dataset-file',
type=str,
default='VHR',
help='resolution of the dataset VHR,HR')
#arg('--out-file', type=str, default='VHR', help='the file in which save the outputs')
arg('--train-val-file',
type=str,
default='train_val_850',
help='name of the train-val file VHR:train_val_850 or train_val_HR')
arg('--test-file',
type=str,
default='test_850',
help='name of the test file VHR:test_850 or HR:test_HR')
args = parser.parse_args()
root = Path(args.root)
root.mkdir(exist_ok=True, parents=True)
num_classes = 1
input_channels = 4
if args.model == 'UNet11':
model = UNet11(num_classes=num_classes, input_channels=input_channels)
elif args.model == 'UNet':
model = UNet(num_classes=num_classes, input_channels=input_channels)
elif args.model == 'AlbuNet34':
model = AlbuNet34(num_classes=num_classes,
num_input_channels=input_channels,
pretrained=False)
elif args.model == 'SegNet':
model = SegNet(num_classes=num_classes,
num_input_channels=input_channels,
pretrained=False)
else:
model = UNet11(num_classes=num_classes, input_channels=input_channels)
if torch.cuda.is_available():
if args.device_ids: #
device_ids = list(map(int, args.device_ids.split(',')))
else:
device_ids = None
model = nn.DataParallel(model, device_ids=device_ids).cuda()
cudnn.benchmark = True
####################Change the files_names ######################################
out_path = Path(('logs_{}/mapping/').format(args.dataset_file))
name_file = '_' + str(int(
args.percent * 100)) + '_percent_' + args.dataset_file
data_all = 'data' ##file with all the data
data_path = Path(args.dataset_path)
print("data_path:", data_path)
#################################################################################
# Nested cross validation K-fold train test
#train_val_file_names, test_file_names = get_split_out(data_path,data_all,args.fold_out)
#################################################################################
#eWe are consider the same test in all the cases
train_val_file_names = np.array(
sorted(
glob.glob(
str(data_path / args.train_val_file / 'images') + "/*.npy")))
test_file_names = np.array(
sorted(
glob.glob(str(data_path / args.test_file / 'images') + "/*.npy")))
if args.percent != 1:
extra, train_val_file_names = percent_split(train_val_file_names,
args.percent)
#################################################################################
train_file_names, val_file_names = get_split_in(train_val_file_names,
args.fold_in)
np.save(
str(
os.path.join(
out_path, "train_files{}_{}_fold{}_{}.npy".format(
name_file, args.model, args.fold_out, args.fold_in))),
train_file_names)
np.save(
str(
os.path.join(
out_path,
"val_files{}_{}_fold{}_{}.npy".format(name_file, args.model,
args.fold_out,
args.fold_in))),
val_file_names)
print('num train = {}, num_val = {}'.format(len(train_file_names),
len(val_file_names)))
def make_loader(file_names,
shuffle=False,
transform=None,
mode='train',
batch_size=4,
limit=None):
return DataLoader(dataset=WaterDataset(file_names,
transform=transform,
mode=mode,
limit=limit),
shuffle=shuffle,
batch_size=batch_size,
pin_memory=torch.cuda.is_available())
max_values, mean_values, std_values = meanstd(train_file_names,
val_file_names,
test_file_names,
str(data_path),
input_channels) #_60
print(max_values, mean_values, std_values)
if (args.dataset_file == 'VHR'):
train_transform = DualCompose([
CenterCrop(512),
HorizontalFlip(),
VerticalFlip(),
Rotate(),
ImageOnly(Normalize(mean=mean_values, std=std_values))
])
val_transform = DualCompose([
CenterCrop(512),
ImageOnly(Normalize(mean=mean_values, std=std_values))
])
max_values = 3521
train_loader = make_loader(train_file_names,
shuffle=True,
transform=train_transform,
mode='train',
batch_size=args.batch_size) #4 batch_size
valid_loader = make_loader(val_file_names,
transform=val_transform,
batch_size=args.batch_size,
mode="train")
if (args.dataset_file == 'HR'):
train_transform = DualCompose([
CenterCrop(64),
HorizontalFlip(),
VerticalFlip(),
Rotate(),
ImageOnly(Normalize2(mean=mean_values, std=std_values))
])
val_transform = DualCompose([
CenterCrop(64),
ImageOnly(Normalize2(mean=mean_values, std=std_values))
])
train_loader = make_loader(train_file_names,
shuffle=True,
transform=train_transform,
mode='train',
batch_size=args.batch_size) #8 batch_size
valid_loader = make_loader(val_file_names,
transform=val_transform,
mode="train",
batch_size=args.batch_size // 2)
#albunet 34 with only 3 batch_size
dataloaders = {'train': train_loader, 'val': valid_loader}
dataloaders_sizes = {x: len(dataloaders[x]) for x in dataloaders.keys()}
root.joinpath(('params_{}.json').format(args.dataset_file)).write_text(
json.dumps(vars(args), indent=True, sort_keys=True))
optimizer_ft = optim.Adam(model.parameters(), lr=args.lr) #
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft,
step_size=20,
gamma=0.1)
utilsTrain.train_model(dataset_file=args.dataset_file,
name_file=name_file,
model=model,
optimizer=optimizer_ft,
scheduler=exp_lr_scheduler,
dataloaders=dataloaders,
fold_out=args.fold_out,
fold_in=args.fold_in,
name_model=args.model,
num_epochs=args.n_epochs)
torch.save(
model.module.state_dict(),
(str(out_path) + '/model{}_{}_foldout{}_foldin{}_{}epochs').format(
name_file, args.model, args.fold_out, args.fold_in, args.n_epochs))
print(args.model)
find_metrics(train_file_names=train_file_names,
val_file_names=val_file_names,
test_file_names=test_file_names,
max_values=max_values,
mean_values=mean_values,
std_values=std_values,
model=model,
fold_out=args.fold_out,
fold_in=args.fold_in,
name_model=args.model,
epochs=args.n_epochs,
out_file=args.dataset_file,
dataset_file=args.dataset_file,
name_file=name_file)
def main():
training_batch_size = 8
validation_batch_size = 8
epoch_num = 200
iter_freq_print_training_log = 50
lr = 1e-4
net = SegNet(pretrained=True, num_classes=num_classes).cuda()
curr_epoch = 0
# net = FCN8VGG(pretrained=False, num_classes=num_classes).cuda()
# snapshot = 'epoch_41_validation_loss_2.1533_mean_iu_0.5225.pth'
# net.load_state_dict(torch.load(os.path.join(ckpt_path, snapshot)))
# split_res = snapshot.split('_')
# curr_epoch = int(split_res[1])
net.train()
mean_std = ([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
train_simultaneous_transform = SimultaneousCompose([
SimultaneousRandomHorizontallyFlip(),
SimultaneousRandomScale((0.9, 1.1)),
SimultaneousRandomCrop((300, 500))
])
train_transform = transforms.Compose([
RandomGaussianBlur(),
transforms.ToTensor(),
transforms.Normalize(*mean_std)
])
val_simultaneous_transform = SimultaneousCompose(
[SimultaneousScale((300, 500))])
val_transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize(*mean_std)])
restore = transforms.Compose(
[DeNormalize(*mean_std),
transforms.ToPILImage()])
train_set = VOC(train_path,
simultaneous_transform=train_simultaneous_transform,
transform=train_transform,
target_transform=MaskToTensor())
train_loader = DataLoader(train_set,
batch_size=training_batch_size,
num_workers=8,
shuffle=True)
val_set = VOC(val_path,
simultaneous_transform=val_simultaneous_transform,
transform=val_transform,
target_transform=MaskToTensor())
val_loader = DataLoader(val_set,
batch_size=validation_batch_size,
num_workers=8)
criterion = CrossEntropyLoss2d(ignored_label=ignored_label)
optimizer = optim.SGD([{
'params': [
param
for name, param in net.named_parameters() if name[-4:] == 'bias'
]
}, {
'params': [
param
for name, param in net.named_parameters() if name[-4:] != 'bias'
],
'weight_decay':
5e-4
}],
lr=lr,
momentum=0.9,
nesterov=True)
if not os.path.exists(ckpt_path):
os.mkdir(ckpt_path)
best = [1e9, -1, -1] # [best_val_loss, best_mean_iu, best_epoch]
for epoch in range(curr_epoch, epoch_num):
train(train_loader, net, criterion, optimizer, epoch,
iter_freq_print_training_log)
if (epoch + 1) % 20 == 0:
lr /= 3
adjust_lr(optimizer, lr)
validate(epoch, val_loader, net, criterion, restore, best)
plt.show()
# logging.basicConfig(level=logging.DEBUG)
# morphSnake(imagesArray, center_of_mass, dia/2, 200).example_lakes()
# logging.info("Done.")
# plt.show()
# if i_train > 0:
# break
#
# break
if __name__ == "__main__":
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model1 = SegNet(1, 1).to(device)
modelName1 = model1.__class__.__name__
model2 = torchvision.models.segmentation.deeplabv3_resnet101(
pretrained=False, num_classes=1)
model2 = model2.to(device)
modelName2 = model2.__class__.__name__
model3 = UNet(1, 1).to(device)
modelName3 = model3.__class__.__name__
model1_checkpoint = torch.load(
train().checkpointsPath + '/' + modelName1 + '/' +
'2019-08-30 13:21:52.559302_epoch-5_dice-0.4743926368317377.pth')
model2_checkpoint = torch.load(
train().checkpointsPath + '/' + modelName2 + '/' +
'2019-08-22 08:37:06.839794_epoch-1_dice-0.4479589270841744.pth')
model3_checkpoint = torch.load(
def main():
parser = argparse.ArgumentParser()
arg = parser.add_argument
arg('--device-ids', type=str, default='0', help='For example 0,1 to run on two GPUs')
arg('--fold-out', type=int, help='fold train test', default=0)
arg('--fold-in', type=int, help='fold train val', default=0)
arg('--percent', type=float, help='percent of data', default=1)
arg('--root', default='runs/debug', help='checkpoint root')
arg('--batch-size', type=int, default=4)
arg('--limit', type=int, default=10000, help='number of images in epoch')
arg('--n-epochs', type=int, default=40)
arg('--n-steps', type=int, default=200)
arg('--lr', type=float, default=0.003)
arg('--modelVHR', type=str, default='UNet11', choices=['UNet11','UNet','AlbuNet34','SegNet'])
arg('--dataset-path-HR', type=str, default='data_HR', help='ain path of the HR dataset')
arg('--model-path-HR', type=str, default='logs_HR/mapping/model_40epoch_HR_UNet11.pth', help='path of the model of HR')
arg('--dataset-path-VHR', type=str, default='data_VHR', help='ain path of the VHR dataset')
arg('--name-file-HR', type=str, default='_HR', help='name file of HR dataset')
arg('--dataset-file', type=str, default='VHR', help='main dataset resolution,depend of this correspond a specific crop' )
arg('--out-file', type=str, default='seq', help='the file in which save the outputs')
arg('--train-val-file-HR', type=str, default='train_val_HR', help='name of the train-val file' )
arg('--test-file-HR', type=str, default='test_HR', help='name of the test file' )
arg('--train-val-file-VHR', type=str, default='train_val_850', help='name of the train-val file' )
arg('--test-file-VHR', type=str, default='test_850', help='name of the test file' )
args = parser.parse_args()
root = Path(args.root)
root.mkdir(exist_ok=True, parents=True)
num_classes = 1
input_channels=4
if args.modelVHR == 'UNet11':
model_VHR = UNet11(num_classes=num_classes, input_channels=input_channels)
elif args.modelVHR == 'UNet':
model_VHR = UNet(num_classes=num_classes, input_channels=input_channels)
elif args.modelVHR == 'AlbuNet34':
model_VHR =AlbuNet34(num_classes=num_classes, num_input_channels=input_channels, pretrained=False)
elif args.modelVHR == 'SegNet':
model_VHR = SegNet(num_classes=num_classes, num_input_channels=input_channels, pretrained=False)
else:
model_VHR = UNet11(num_classes=num_classes, input_channels=4)
if torch.cuda.is_available():
if args.device_ids:#
device_ids = list(map(int, args.device_ids.split(',')))
else:
device_ids = None
model_VHR = nn.DataParallel(model_VHR, device_ids=device_ids).cuda()
cudnn.benchmark = True
out_path = Path(('logs_{}/mapping/').format(args.out_file))
#Data-paths:--------------------------VHr-------------------------------------
data_path_VHR = Path(args.dataset_path_VHR)
print("data_path:",data_path_VHR)
name_file_VHR = '_'+ str(int(args.percent*100))+'_percent_'+args.out_file
data_all='data'
##--------------------------------------
############################
# NEstes cross validation K-fold train test
##train_val_file_names, test_file_names_HR = get_split_out(data_path_HR,data_all,args.fold_out)
############################
############################ Cross validation
train_val_file_names=np.array(sorted(glob.glob(str((data_path_VHR/args.train_val_file_VHR/'images'))+ "/*.npy")))
test_file_names_VHR = np.array(sorted(glob.glob(str((data_path_VHR/args.test_file_VHR/'images')) + "/*.npy")))
if args.percent !=1:
extra, train_val_file_names= percent_split(train_val_file_names, args.percent)
train_file_VHR_lab,val_file_VHR_lab = get_split_in(train_val_file_names,args.fold_in)
np.save(str(os.path.join(out_path,"train_files{}_{}_fold{}_{}.npy".format(name_file_VHR, args.modelVHR, args.fold_out, args.fold_in))), train_file_VHR_lab)
np.save(str(os.path.join(out_path,"val_files{}_{}_fold{}_{}.npy". format(name_file_VHR, args.modelVHR, args.fold_out, args.fold_in))), val_file_VHR_lab)
#Data-paths:--------------------------unlabeled VHR-------------------------------------
train_path_VHR_unlab= data_path_VHR/'unlabel'/'train'/'images'
val_path_VHR_unlab = data_path_VHR/'unlabel'/'val'/'images'
train_file_VHR_unlab = np.array(sorted(list(train_path_VHR_unlab.glob('*.npy'))))
val_file_VHR_unlab = np.array(sorted(list(val_path_VHR_unlab.glob('*.npy'))))
print('num train_lab = {}, num_val_lab = {}'.format(len(train_file_VHR_lab), len(val_file_VHR_lab)))
print('num train_unlab = {}, num_val_unlab = {}'.format(len(train_file_VHR_unlab), len(val_file_VHR_unlab)))
max_values_VHR, mean_values_VHR, std_values_VHR=meanstd(train_file_VHR_lab, val_file_VHR_lab,test_file_names_VHR,str(data_path_VHR),input_channels)
def make_loader(file_names, shuffle=False, transform=None,mode='train',batch_size=4, limit=None):
return DataLoader(
dataset=WaterDataset(file_names, transform=transform,mode=mode, limit=limit),
shuffle=shuffle,
batch_size=batch_size,
pin_memory=torch.cuda.is_available()
)
#transformations ---------------------------------------------------------------------------
train_transform_VHR = DualCompose([
CenterCrop(512),
HorizontalFlip(),
VerticalFlip(),
Rotate(),
ImageOnly(Normalize(mean=mean_values_VHR,std= std_values_VHR))
])
val_transform_VHR = DualCompose([
CenterCrop(512),
ImageOnly(Normalize(mean=mean_values_VHR, std=std_values_VHR))
])
#-------------------------------------------------------------------
mean_values_HR=(0.11952524, 0.1264638 , 0.13479991, 0.15017026)
std_values_HR=(0.08844988, 0.07304429, 0.06740904, 0.11003125)
train_transform_VHR_unlab = DualCompose([
CenterCrop(512),
HorizontalFlip(),
VerticalFlip(),
Rotate(),
ImageOnly(Normalize(mean=mean_values_HR,std= std_values_HR))
])
val_transform_VHR_unlab = DualCompose([
CenterCrop(512),
ImageOnly(Normalize(mean=mean_values_HR, std=std_values_HR))
])
######################## DATA-LOADERS ###########################################################49
train_loader_VHR_lab = make_loader(train_file_VHR_lab, shuffle=True, transform=train_transform_VHR , batch_size = 2, mode = "train")
valid_loader_VHR_lab = make_loader(val_file_VHR_lab, transform=val_transform_VHR, batch_size = 4, mode = "train")
train_loader_VHR_unlab = make_loader(train_file_VHR_unlab, shuffle=True, transform=train_transform_VHR, batch_size = 4, mode = "unlb_train")
valid_loader_VHR_unlab = make_loader(val_file_VHR_unlab, transform=val_transform_VHR, batch_size = 2, mode = "unlb_val")
dataloaders_VHR_lab= {
'train': train_loader_VHR_lab, 'val': valid_loader_VHR_lab
}
dataloaders_VHR_unlab= {
'train': train_loader_VHR_unlab, 'val': valid_loader_VHR_unlab
}
#----------------------------------------------
root.joinpath(('params_{}.json').format(args.out_file)).write_text(
json.dumps(vars(args), indent=True, sort_keys=True))
# Observe that all parameters are being optimized
optimizer_ft = optim.Adam(model_VHR.parameters(), lr= args.lr)
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=20, gamma=0.1)
#--------------------------model HR-------------------------------------
PATH_HR= args.model_path_HR
#Initialise the model
model_HR = UNet11(num_classes=num_classes)
model_HR.cuda()
model_HR.load_state_dict(torch.load(PATH_HR))
#---------------------------------------------------------------
model_VHR= utilsTrain_seq.train_model(
out_file=args.out_file,
name_file_VHR=name_file_VHR,
model_HR=model_HR,
model_VHR=model_VHR,
optimizer=optimizer_ft,
scheduler=exp_lr_scheduler,
dataloaders_VHR_lab=dataloaders_VHR_lab,
dataloaders_VHR_unlab=dataloaders_VHR_unlab,
fold_out=args.fold_out,
fold_in=args.fold_in,
name_model_VHR=args.modelVHR,
n_steps=args.n_steps,
num_epochs=args.n_epochs
)
torch.save(model_VHR.module.state_dict(), (str(out_path)+'/model{}_{}_foldout{}_foldin{}_{}epochs.pth').format(args.n_epochs,name_file_VHR,args.modelVHR, args.fold_out,args.fold_in,args.n_epochs))
print(args.modelVHR)
max_values_all_VHR=3521
find_metrics(train_file_names=train_file_VHR_lab,
val_file_names=val_file_VHR_lab,
test_file_names=test_file_names_VHR,
max_values=max_values_all_VHR,
mean_values=mean_values_VHR,
std_values=std_values_VHR,
model=model_VHR,
fold_out=args.fold_out,
fold_in=args.fold_in,
name_model=args.modelVHR,
epochs=args.n_epochs,
out_file=args.out_file,
dataset_file=args.dataset_file,
name_file=name_file_VHR)
loss = criterion(output, target)
train_losses.append(loss.item())
loss.backward()
optimizer.step()
return train_losses
if __name__ == '__main__':
train_loader = DataLoader(CamVid11('CamVid/', split='train'),
batch_size=5,
shuffle=True)
val_loader = DataLoader(CamVid11('CamVid/', split='val'),
batch_size=1,
shuffle=True)
net = SegNet(3, 12)
net.apply(init_weights)
# Initialize encoder weights from VGG16 pre-trained on ImageNet
vgg16 = models.vgg16(pretrained=True)
layers = [
layer for layer in vgg16.features.children()
if isinstance(layer, nn.Conv2d)
]
start = 0
for i in range(net.encoder.block_count):
end = start + net.encoder.blocks[i].layer_count
net.encoder.blocks[i].initialize_from_layers(layers[start:end])
start = end
