def CrossEntropyLoss(self, logit, target):
n, c, h, w = logit.size()
criterion = nn.CrossEntropyLoss(weight=self.weight, ignore_index=self.ignore_index,
size_average=self.size_average)
if self.cuda and len(self.args.gpu_ids) > 1:
criterion = DataParallelCriterion(criterion)
if self.cuda and len(self.args.gpu_ids) < 2:
criterion = criterion.cuda()
loss = criterion(logit, target.long())
if self.batch_average:
loss /= n
return loss
if config.model_type=='LSTM':
model = LSTMLM(input_size=len(vocab),
embedding_size=config.embedding_size,
hidden_size=config.hidden_size,
output_size=len(vocab),
n_layers=config.n_layers,
dropout_p=config.dropout_p)
elif config.model_type=='BiLSTM':
model = BiLSTMLM(input_size=len(vocab),
embedding_size=config.embedding_size,
hidden_size=config.hidden_size,
output_size=len(vocab),
n_layers=config.n_layers,
dropout_p=config.dropout_p)
loss_fn = nn.NLLLoss(ignore_index=vocab.stoi[vocab.pad_token])
optimizer = optim.Adam(model.parameters())
if config.cuda:
if config.multi_gpu:
from parallel import DataParallelModel, DataParallelCriterion
model = DataParallelModel(model).cuda()
loss_fn = DataParallelCriterion(loss_fn).cuda()
else:
model = model.cuda()
loss_fn = loss_fn.cuda()
print('=========MODEL=========\n',model)
# Train
for epoch in range(1, config.epochs+1):
train()
def main_tr(args, crossVal):
dataLoad = ld.LoadData(args.data_dir, args.classes)
data = dataLoad.processData(crossVal, args.data_name)
# load the model
model = net.MiniSeg(args.classes, aux=True)
if not osp.isdir(osp.join(args.savedir + '_mod' + str(args.max_epochs))):
os.mkdir(args.savedir + '_mod' + str(args.max_epochs))
if not osp.isdir(
osp.join(args.savedir + '_mod' + str(args.max_epochs),
args.data_name)):
os.mkdir(
osp.join(args.savedir + '_mod' + str(args.max_epochs),
args.data_name))
saveDir = args.savedir + '_mod' + str(
args.max_epochs) + '/' + args.data_name + '/' + args.model_name
# create the directory if not exist
if not osp.exists(saveDir):
os.mkdir(saveDir)
if args.gpu and torch.cuda.device_count() > 1:
#model = torch.nn.DataParallel(model)
model = DataParallelModel(model)
if args.gpu:
model = model.cuda()
total_paramters = sum([np.prod(p.size()) for p in model.parameters()])
print('Total network parameters: ' + str(total_paramters))
# define optimization criteria
weight = torch.from_numpy(
data['classWeights']) # convert the numpy array to torch
if args.gpu:
weight = weight.cuda()
criteria = CrossEntropyLoss2d(weight, args.ignore_label) #weight
if args.gpu and torch.cuda.device_count() > 1:
criteria = DataParallelCriterion(criteria)
if args.gpu:
criteria = criteria.cuda()
# compose the data with transforms
trainDataset_main = myTransforms.Compose([
myTransforms.Normalize(mean=data['mean'], std=data['std']),
myTransforms.Scale(args.width, args.height),
myTransforms.RandomCropResize(int(32. / 1024. * args.width)),
myTransforms.RandomFlip(),
myTransforms.ToTensor()
])
trainDataset_scale1 = myTransforms.Compose([
myTransforms.Normalize(mean=data['mean'], std=data['std']),
myTransforms.Scale(int(args.width * 1.5), int(args.height * 1.5)),
myTransforms.RandomCropResize(int(100. / 1024. * args.width)),
myTransforms.RandomFlip(),
myTransforms.ToTensor()
])
trainDataset_scale2 = myTransforms.Compose([
myTransforms.Normalize(mean=data['mean'], std=data['std']),
myTransforms.Scale(int(args.width * 1.25), int(args.height * 1.25)),
myTransforms.RandomCropResize(int(100. / 1024. * args.width)),
myTransforms.RandomFlip(),
myTransforms.ToTensor()
])
trainDataset_scale3 = myTransforms.Compose([
myTransforms.Normalize(mean=data['mean'], std=data['std']),
myTransforms.Scale(int(args.width * 0.75), int(args.height * 0.75)),
myTransforms.RandomCropResize(int(32. / 1024. * args.width)),
myTransforms.RandomFlip(),
myTransforms.ToTensor()
])
valDataset = myTransforms.Compose([
myTransforms.Normalize(mean=data['mean'], std=data['std']),
myTransforms.Scale(args.width, args.height),
myTransforms.ToTensor()
])
# since we training from scratch, we create data loaders at different scales
# so that we can generate more augmented data and prevent the network from overfitting
trainLoader = torch.utils.data.DataLoader(myDataLoader.Dataset(
data['trainIm'], data['trainAnnot'], transform=trainDataset_main),
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers,
pin_memory=True,
drop_last=True)
trainLoader_scale1 = torch.utils.data.DataLoader(
myDataLoader.Dataset(data['trainIm'],
data['trainAnnot'],
transform=trainDataset_scale1),
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers,
pin_memory=True,
drop_last=True)
trainLoader_scale2 = torch.utils.data.DataLoader(
myDataLoader.Dataset(data['trainIm'],
data['trainAnnot'],
transform=trainDataset_scale2),
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers,
pin_memory=True,
drop_last=True)
trainLoader_scale3 = torch.utils.data.DataLoader(
myDataLoader.Dataset(data['trainIm'],
data['trainAnnot'],
transform=trainDataset_scale3),
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers,
pin_memory=True,
drop_last=True)
valLoader = torch.utils.data.DataLoader(myDataLoader.Dataset(
data['valIm'], data['valAnnot'], transform=valDataset),
batch_size=args.batch_size,
shuffle=False,
num_workers=args.num_workers,
pin_memory=True)
max_batches = len(trainLoader) + len(trainLoader_scale1) + len(
trainLoader_scale2) + len(trainLoader_scale3)
if args.gpu:
cudnn.benchmark = True
start_epoch = 0
if args.pretrained is not None:
state_dict = torch.load(args.pretrained)
new_keys = []
new_values = []
for idx, key in enumerate(state_dict.keys()):
if 'pred' not in key:
new_keys.append(key)
new_values.append(list(state_dict.values())[idx])
new_dict = OrderedDict(list(zip(new_keys, new_values)))
model.load_state_dict(new_dict, strict=False)
print('pretrained model loaded')
if args.resume is not None:
if osp.isfile(args.resume):
print("=> loading checkpoint '{}'".format(args.resume))
checkpoint = torch.load(args.resume)
start_epoch = checkpoint['epoch']
args.lr = checkpoint['lr']
model.load_state_dict(checkpoint['state_dict'])
print("=> loaded checkpoint '{}' (epoch {})".format(
args.resume, checkpoint['epoch']))
else:
print("=> no checkpoint found at '{}'".format(args.resume))
log_file = osp.join(saveDir, 'trainValLog_' + args.model_name + '.txt')
if osp.isfile(log_file):
logger = open(log_file, 'a')
else:
logger = open(log_file, 'w')
logger.write("Parameters: %s" % (str(total_paramters)))
logger.write("\n%s\t%s\t\t%s\t%s\t%s\t%s\tlr" %
('CrossVal', 'Epoch', 'Loss(Tr)', 'Loss(val)',
'mIOU (tr)', 'mIOU (val)'))
logger.flush()
optimizer = torch.optim.Adam(model.parameters(),
args.lr, (0.9, 0.999),
eps=1e-08,
weight_decay=1e-4)
maxmIOU = 0
maxEpoch = 0
print(args.model_name + '-CrossVal: ' + str(crossVal + 1))
for epoch in range(start_epoch, args.max_epochs):
# train for one epoch
cur_iter = 0
train(args, trainLoader_scale1, model, criteria, optimizer, epoch,
max_batches, cur_iter)
cur_iter += len(trainLoader_scale1)
train(args, trainLoader_scale2, model, criteria, optimizer, epoch,
max_batches, cur_iter)
cur_iter += len(trainLoader_scale2)
train(args, trainLoader_scale3, model, criteria, optimizer, epoch,
max_batches, cur_iter)
cur_iter += len(trainLoader_scale3)
lossTr, overall_acc_tr, per_class_acc_tr, per_class_iu_tr, mIOU_tr, lr = \
train(args, trainLoader, model, criteria, optimizer, epoch, max_batches, cur_iter)
# evaluate on validation set
lossVal, overall_acc_val, per_class_acc_val, per_class_iu_val, mIOU_val = \
val(args, valLoader, model, criteria)
torch.save(
{
'epoch': epoch + 1,
'arch': str(model),
'state_dict': model.state_dict(),
'optimizer': optimizer.state_dict(),
'lossTr': lossTr,
'lossVal': lossVal,
'iouTr': mIOU_tr,
'iouVal': mIOU_val,
'lr': lr
},
osp.join(
saveDir, 'checkpoint_' + args.model_name + '_crossVal' +
str(crossVal + 1) + '.pth.tar'))
# save the model also
model_file_name = osp.join(
saveDir, 'model_' + args.model_name + '_crossVal' +
str(crossVal + 1) + '_' + str(epoch + 1) + '.pth')
torch.save(model.state_dict(), model_file_name)
logger.write(
"\n%d\t\t%d\t\t%.4f\t\t%.4f\t\t%.4f\t\t%.4f\t\t%.7f" %
(crossVal + 1, epoch + 1, lossTr, lossVal, mIOU_tr, mIOU_val, lr))
logger.flush()
print("\nEpoch No. %d:\tTrain Loss = %.4f\tVal Loss = %.4f\t mIOU(tr) = %.4f\t mIOU(val) = %.4f\n" \
% (epoch + 1, lossTr, lossVal, mIOU_tr, mIOU_val))
if mIOU_val >= maxmIOU:
maxmIOU = mIOU_val
maxEpoch = epoch + 1
torch.cuda.empty_cache()
logger.flush()
logger.close()
return maxEpoch, maxmIOU