def __init__(self,
weights,
num_class=21,
network='efficientdet-d0',
size_image=(512, 512)):
super(Detect, self).__init__()
self.weights = weights
self.size_image = size_image
self.device = torch.device(
"cuda:0" if torch.cuda.is_available() else 'cpu')
self.transform = get_augumentation(phase='test')
self.show_transform = get_augumentation(phase='show')
if (self.weights is not None):
print('Load pretrained Model')
checkpoint = torch.load(self.weights,
map_location=lambda storage, loc: storage)
num_class = checkpoint['num_class']
network = checkpoint['network']
self.model = EfficientDet(num_classes=num_class,
network=network,
is_training=False,
threshold=args.threshold,
iou_threshold=args.iou_threshold)
if (self.weights is not None):
state_dict = checkpoint['state_dict']
self.model.load_state_dict(state_dict)
if use_cuda:
self.model = self.model.cuda()
self.model.eval()
def __init__(self,
weights,
num_class=21,
network='efficientdet-d0',
size_image=(512, 512)):
super(Detect, self).__init__()
self.weights = weights
self.size_image = size_image
self.device = torch.device(
"cuda:0" if torch.cuda.is_available() else 'cpu')
self.transform = get_augumentation(phase='test')
if (self.weights is not None):
print('Load pretrained Model')
checkpoint = torch.load(self.weights,
map_location=lambda storage, loc: storage)
params = checkpoint['parser']
num_class = params.num_class
network = params.network
# self.model = EfficientDet(num_classes=num_class,
# network=network,
# W_bifpn=EFFICIENTDET[network]['W_bifpn'],
# D_bifpn=EFFICIENTDET[network]['D_bifpn'],
# D_class=EFFICIENTDET[network]['D_class'],
# is_training=False
# )
self.model = EfficientDetBiFPN(num_classes=20, D_bifpn=2, W_bifpn=64)
if (self.weights is not None):
state_dict = checkpoint['state_dict']
self.model.load_state_dict(state_dict)
if torch.cuda.is_available():
self.model = self.model.cuda()
self.model.eval()
def __init__(self,
weights,
num_class=21,
network='efficientdet-d1',
size_image=(512, 512)):
super(Detect, self).__init__()
self.weights = weights
self.size_image = size_image
self.device = torch.device(
"cuda:0" if torch.cuda.is_available() else 'cpu')
self.transform = get_augumentation(phase='test',
width=size_image[0],
height=size_image[1])
if (self.weights is not None):
print('Load pretrained Model')
checkpoint = torch.load(self.weights,
map_location=lambda storage, loc: storage)
num_class = checkpoint['num_class']
network = checkpoint['network']
self.model = EfficientDet(num_classes=num_class,
network=network,
W_bifpn=EFFICIENTDET[network]['W_bifpn'],
D_bifpn=EFFICIENTDET[network]['D_bifpn'],
D_class=EFFICIENTDET[network]['D_class'],
is_training=False,
threshold=0.055)
if (self.weights is not None):
state_dict = checkpoint['state_dict']
self.model.load_state_dict(state_dict)
self.model = self.model.cuda()
self.model.eval()
def __init__(self, weights, num_class=21):
super(Detect, self).__init__()
self.weights = weights
self.device = torch.device(
"cuda:0" if torch.cuda.is_available() else 'cpu')
self.transform = get_augumentation(phase='test')
self.show_transform = get_augumentation(phase='show')
self.model = EfficientDet(num_classes=num_class, is_training=False)
# self.model = torch.nn.DataParallel(self.model, device_ids=[0, 1])
self.model = self.model.cuda()
if (self.weights is not None):
print('Load pretrained Model')
state = torch.load(self.weights,
map_location=lambda storage, loc: storage)
state_dict = state['state_dict']
num_class = state['num_class']
self.model.load_state_dict(state_dict)
self.model.eval()
def main_worker(gpu, ngpus_per_node, args):
args.gpu = gpu
if args.gpu is not None:
print("Use GPU: {} for training".format(args.gpu))
if args.distributed:
if args.dist_url == "env://" and args.rank == -1:
# args.rank = int(os.environ["RANK"])
args.rank = 1
if args.multiprocessing_distributed:
# For multiprocessing distributed training, rank needs to be the
# global rank among all the processes
args.rank = args.rank * ngpus_per_node + gpu
dist.init_process_group(backend=args.dist_backend,
init_method=args.dist_url,
world_size=args.world_size,
rank=args.rank)
checkpoint = []
if (args.resume is not None):
if os.path.isfile(args.resume):
print("=> loading checkpoint '{}'".format(args.resume))
if args.gpu is None:
checkpoint = torch.load(args.resume)
else:
# Map model to be loaded to specified single gpu.
loc = 'cuda:{}'.format(args.gpu)
checkpoint = torch.load(args.resume, map_location=loc)
params = checkpoint['parser']
args.num_class = params.num_class
args.network = params.network
args.start_epoch = params.start_epoch + 1
del params
model = EfficientDet(num_classes=args.num_class,
network=args.network,
W_bifpn=EFFICIENTDET[args.network]['W_bifpn'],
D_bifpn=EFFICIENTDET[args.network]['D_bifpn'],
D_class=EFFICIENTDET[args.network]['D_class'],
gpu=args.gpu)
if (args.resume is not None):
model.load_state_dict(checkpoint['state_dict'])
del checkpoint
if args.distributed:
# For multiprocessing distributed, DistributedDataParallel constructor
# should always set the single device scope, otherwise,
# DistributedDataParallel will use all available devices.
if args.gpu is not None:
torch.cuda.set_device(args.gpu)
model.cuda(args.gpu)
# When using a single GPU per process and per
# DistributedDataParallel, we need to divide the batch size
# ourselves based on the total number of GPUs we have
args.batch_size = int(args.batch_size / ngpus_per_node)
args.workers = int(
(args.workers + ngpus_per_node - 1) / ngpus_per_node)
model = torch.nn.parallel.DistributedDataParallel(
model, device_ids=[args.gpu], find_unused_parameters=True)
print('Run with DistributedDataParallel with divice_ids....')
else:
model.cuda()
# DistributedDataParallel will divide and allocate batch_size to all
# available GPUs if device_ids are not set
model = torch.nn.parallel.DistributedDataParallel(model)
print('Run with DistributedDataParallel without device_ids....')
elif args.gpu is not None:
torch.cuda.set_device(args.gpu)
model = model.cuda(args.gpu)
else:
print('Run with DataParallel ....')
model = torch.nn.DataParallel(model).cuda()
# Training dataset
train_dataset = []
if (args.dataset == 'VOC'):
# train_dataset = VOCDetection(root=args.dataset_root,
# transform=get_augumentation(phase='train', width=EFFICIENTDET[args.network]['input_size'], height=EFFICIENTDET[args.network]['input_size']))
train_dataset = VOCDetection(root=args.dataset_root,
transform=transforms.Compose([
Normalizer(),
Augmenter(),
Resizer()
]))
elif (args.dataset == 'COCO'):
train_dataset = CocoDataset(
root_dir=args.dataset_root,
set_name='train2017',
transform=get_augumentation(
phase='train',
width=EFFICIENTDET[args.network]['input_size'],
height=EFFICIENTDET[args.network]['input_size']))
# train_loader = DataLoader(train_dataset,
# batch_size=args.batch_size,
# num_workers=args.workers,
# shuffle=True,
# collate_fn=detection_collate,
# pin_memory=True)
train_loader = DataLoader(train_dataset,
batch_size=args.batch_size,
num_workers=args.workers,
shuffle=True,
collate_fn=collater,
pin_memory=True)
# define loss function (criterion) , optimizer, scheduler
optimizer = optim.AdamW(model.parameters(), lr=args.lr)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer,
patience=3,
verbose=True)
cudnn.benchmark = True
for epoch in range(args.start_epoch, args.num_epoch):
train(train_loader, model, scheduler, optimizer, epoch, args)
state = {
'epoch': epoch,
'parser': args,
'state_dict': get_state_dict(model)
}
torch.save(
state,
'./weights/checkpoint_{}_{}_{}.pth'.format(args.dataset,
args.network, epoch))
def main_worker(gpu, ngpus_per_node, args):
args.gpu = gpu
if args.gpu is not None:
print("Use GPU: {} for training".format(args.gpu))
if args.distributed:
if args.dist_url == "env://" and args.rank == -1:
# args.rank = int(os.environ["RANK"])
args.rank = 1
if args.multiprocessing_distributed:
# For multiprocessing distributed training, rank needs to be the
# global rank among all the processes
args.rank = args.rank * ngpus_per_node + gpu
dist.init_process_group(
backend=args.dist_backend,
init_method=args.dist_url,
world_size=args.world_size,
rank=args.rank)
# args.num_class = train_dataset.num_classes()
print('dataset:', args.dataset)
print('network:', args.network)
print('num_epoch:', args.num_epoch)
print('batch_size:', args.batch_size)
print('lr_choice:', args.lr_choice)
print('lr:', args.lr)
print('lr_fn:', args.lr_fn)
print('image_size:', args.image_size)
print('workers:', args.workers)
print('num_class:', args.num_class)
print('save_folder:', args.save_folder)
print('limit:', args.limit)
if args.dataset == 'h5':
train_dataset = H5CoCoDataset('{}/train_small.hdf5'.format(args.dataset_root), 'train_small')
valid_dataset = H5CoCoDataset('{}/test.hdf5'.format(args.dataset_root), 'test')
else:
train_dataset = CocoDataset(args.dataset_root, set_name='train_small',
# transform=transforms.Compose([Normalizer(), Augmenter(), Resizer(args.image_size)]),
transform=get_augumentation('train'),
limit_len=args.limit[0])
valid_dataset = CocoDataset(args.dataset_root, set_name='test',
# transform=transforms.Compose([Normalizer(), Resizer(args.image_size)]),
transform=get_augumentation('test'),
limit_len=args.limit[1])
print('train_dataset:', len(train_dataset))
print('valid_dataset:', len(valid_dataset))
steps_pre_epoch = len(train_dataset) // args.batch_size
print('steps_pre_epoch:', steps_pre_epoch)
train_loader = DataLoader(train_dataset,
batch_size=args.batch_size,
num_workers=args.workers,
shuffle=True,
collate_fn=detection_collate,
pin_memory=True)
valid_loader = DataLoader(valid_dataset,
batch_size=1,
num_workers=args.workers,
shuffle=False,
collate_fn=detection_collate,
pin_memory=True)
checkpoint = []
if(args.resume is not None):
if os.path.isfile(args.resume):
print("=> loading checkpoint '{}'".format(args.resume))
if args.gpu is None:
checkpoint = torch.load(args.resume)
else:
# Map model to be loaded to specified single gpu.
loc = 'cuda:{}'.format(args.gpu)
checkpoint = torch.load(args.resume, map_location=loc)
params = checkpoint['parser']
args.num_class = params.num_class
args.network = params.network
args.start_epoch = checkpoint['epoch'] + 1
del params
model = EfficientDet(num_classes=args.num_class,
network=args.network,
W_bifpn=EFFICIENTDET[args.network]['W_bifpn'],
D_bifpn=EFFICIENTDET[args.network]['D_bifpn'],
D_class=EFFICIENTDET[args.network]['D_class']
)
if(args.resume is not None):
model.load_state_dict(checkpoint['state_dict'])
del checkpoint
if args.distributed:
# For multiprocessing distributed, DistributedDataParallel constructor
# should always set the single device scope, otherwise,
# DistributedDataParallel will use all available devices.
if args.gpu is not None:
torch.cuda.set_device(args.gpu)
model.cuda(args.gpu)
# When using a single GPU per process and per
# DistributedDataParallel, we need to divide the batch size
# ourselves based on the total number of GPUs we have
args.batch_size = int(args.batch_size / ngpus_per_node)
args.workers = int((args.workers + ngpus_per_node - 1) / ngpus_per_node)
model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[args.gpu], find_unused_parameters=True)
print('Run with DistributedDataParallel with divice_ids....')
else:
model.cuda()
# DistributedDataParallel will divide and allocate batch_size to all
# available GPUs if device_ids are not set
model = torch.nn.parallel.DistributedDataParallel(model)
print('Run with DistributedDataParallel without device_ids....')
elif args.gpu is not None:
# print('using gpu:', args.gpu)
torch.cuda.set_device(args.gpu)
model = model.cuda(args.gpu)
else:
model = model.cpu()
# print('Run with DataParallel ....')
model = torch.nn.DataParallel(model).cuda()
if args.lr_choice == 'lr_fn':
lr_now = float(args.lr_fn['LR_START'])
elif args.lr_choice == 'lr_scheduler':
lr_now = args.lr
optimizer = optim.Adam(model.parameters(), lr=lr_now)
# optimizer = optim.AdamW(model.parameters(), lr=args.lr)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, patience=3, factor=0.1, verbose=True)
cudnn.benchmark = True
iteration_loss_path = 'iteration_loss.csv'
if os.path.isfile(iteration_loss_path):
os.remove(iteration_loss_path)
epoch_loss_path = 'epoch_loss.csv'
if os.path.isfile(epoch_loss_path):
os.remove(epoch_loss_path)
eval_train_path = 'eval_train_result.csv'
if os.path.isfile(eval_train_path):
os.remove(eval_train_path)
eval_val_path = 'eval_val_result.csv'
if os.path.isfile(eval_val_path):
os.remove(eval_val_path)
USE_KAGGLE = True if os.environ.get('KAGGLE_KERNEL_RUN_TYPE', False) else False
if USE_KAGGLE:
iteration_loss_path = '/kaggle/working/' + iteration_loss_path
epoch_loss_path = '/kaggle/working/' + epoch_loss_path
eval_val_path = '/kaggle/working/' + eval_val_path
eval_train_path = '/kaggle/working/' + eval_train_path
with open(epoch_loss_path, 'a+') as epoch_loss_file, \
open(iteration_loss_path, 'a+') as iteration_loss_file, \
open(eval_train_path, 'a+') as eval_train_file, \
open(eval_val_path, 'a+') as eval_val_file:
epoch_loss_file.write('epoch_num,mean_epoch_loss\n')
iteration_loss_file.write('epoch_num,iteration,classification_loss,regression_loss,iteration_loss\n')
eval_train_file.write('epoch_num,map50\n')
eval_val_file.write('epoch_num,map50\n')
for epoch in range(args.start_epoch, args.num_epoch):
train(train_loader, model, scheduler, optimizer, epoch, args, epoch_loss_file, iteration_loss_file, steps_pre_epoch)
# test
_model = model.module
_model.eval()
_model.is_training = False
with torch.no_grad():
if args.dataset != 'show':
evaluate_coco(train_dataset, _model, args.dataset, epoch, eval_train_file)
evaluate_coco(valid_dataset, _model, args.dataset, epoch, eval_val_file)
def get_state_dict(model):
if type(model) == torch.nn.DataParallel:
state_dict = model.module.state_dict()
else:
state_dict = model.state_dict()
return state_dict
checkpoint = []
if(args.resume is not None):
resume_path = str(args.resume)
print("Loading checkpoint: {} ...".format(resume_path))
checkpoint = torch.load(args.resume, map_location=lambda storage, loc: storage)
train_dataset = []
if(args.dataset=='VOC'):
train_dataset = VOCDetection(root = args.dataset_root,
transform = get_augumentation(phase='train'))
elif(args.dataset=='COCO'):
train_dataset = COCODetection(root = args.dataset_root,
transform = get_augumentation(phase='train'))
train_dataloader = DataLoader(train_dataset,
batch_size=args.batch_size,
num_workers=args.num_worker,
shuffle=True,
collate_fn=detection_collate,
pin_memory=True)
model = EfficientDet(num_classes = args.num_classes, network = args.network)
if(args.resume is not None):
# num_class = checkpoint['num_classes']
# network = checkpoint['network']
model = EfficientDet(num_classes = 21, network = 'efficientdet-d0')
return state_dict
checkpoint = []
if(args.resume is not None):
resume_path = str(args.resume)
print("Loading checkpoint: {} ...".format(resume_path))
checkpoint = torch.load(
args.resume, map_location=lambda storage, loc: storage)
args.num_class = checkpoint['num_class']
args.network = checkpoint['network']
train_dataset = []
if(args.dataset == 'VOC'):
train_dataset = VOCDetection(root=args.dataset_root,
transform=get_augumentation(phase='train', width=EFFICIENTDET[args.network]['input_size'], height=EFFICIENTDET[args.network]['input_size']))
elif(args.dataset == 'COCO'):
train_dataset = CocoDataset(root_dir=args.dataset_root, set_name='train2017', transform=get_augumentation(
phase='train', width=EFFICIENTDET[args.network]['input_size'], height=EFFICIENTDET[args.network]['input_size']))
train_dataloader = DataLoader(train_dataset,
batch_size=args.batch_size,
num_workers=args.num_worker,
shuffle=True,
collate_fn=detection_collate,
pin_memory=True)
model = EfficientDet(num_classes=args.num_classes,
network=args.network,
W_bifpn=EFFICIENTDET[args.network]['W_bifpn'],
n_gpu_use = 0
if n_gpu_use > n_gpu:
print(
"Warning: The number of GPU\'s configured to use is {}, but only {} are available on this machine.".format(
n_gpu_use, n_gpu))
n_gpu_use = n_gpu
list_ids = device
device = torch.device('cuda:{}'.format(
device[0]) if n_gpu_use > 0 else 'cpu')
return device, list_ids
if (args.dataset == 'VOC'):
valid_dataset = VOCDetection(root=args.dataset_root,
transform=get_augumentation(phase='valid'))
elif (args.dataset == 'COCO'):
valid_dataset = COCODetection(root=args.dataset_root,
transform=get_augumentation(phase='valid'))
valid_dataloader = DataLoader(valid_dataset,
batch_size=1,
num_workers=args.num_worker,
shuffle=False,
collate_fn=detection_collate,
pin_memory=False)
if (args.weights is not None):
resume_path = str(args.weights)
print("Loading checkpoint: {} ...".format(resume_path))
checkpoint = torch.load(
args.weights, map_location=lambda storage, loc: storage)
num_class = checkpoint['num_class']
checkpoint = []
if (args.resume is not None):
resume_path = str(args.resume)
print("Loading checkpoint: {} ...".format(resume_path))
checkpoint = torch.load(args.resume,
map_location=lambda storage, loc: storage)
args.num_classes = checkpoint['num_classes']
args.network = checkpoint['network']
train_dataset = []
if (args.dataset == 'VOC'):
train_dataset = VOCDetection(
root=args.dataset_root,
transform=get_augumentation(
phase='train',
width=EFFICIENTDET[args.network]['input_size'],
height=EFFICIENTDET[args.network]['input_size']))
elif (args.dataset == 'COCO'):
train_dataset = CocoDataset(
root_dir=args.dataset_root,
set_name='train2017',
transform=get_augumentation(
phase='train',
width=EFFICIENTDET[args.network]['input_size'],
height=EFFICIENTDET[args.network]['input_size']))
train_dataloader = DataLoader(train_dataset,
batch_size=args.batch_size,
num_workers=args.num_worker,
shuffle=True,
