def init_data(parser, verb_orders):
dataset_train = CSVDataset(train_file=parser.train_file, class_list=parser.classes_file, verb_info= verb_orders, is_training=True,
transform=transforms.Compose([Normalizer(), Augmenter(), Resizer(True)]))
if parser.val_file is None:
dataset_val = None
print('No validation annotations provided.')
else:
dataset_val = CSVDataset(train_file=parser.val_file, class_list=parser.classes_file, verb_info= verb_orders, is_training=False,
transform=transforms.Compose([Normalizer(), Resizer(False)]))
sampler = AspectRatioBasedSampler(dataset_train, batch_size=parser.batch_size, drop_last=True)
dataloader_train = DataLoader(dataset_train, num_workers=64, collate_fn=collater, batch_sampler=sampler)
if dataset_val is not None:
sampler_val = AspectRatioBasedSampler(dataset_val, batch_size=parser.batch_size, drop_last=True)
dataloader_val = DataLoader(dataset_val, num_workers=64, collate_fn=collater, batch_sampler=sampler_val)
return dataloader_train, dataset_train, dataloader_val, dataset_val
def main(args=None):
parser = argparse.ArgumentParser(
description='Simple training script for training a RetinaNet network.')
parser.add_argument('--dataset',
default='coco',
help='Dataset type, must be one of csv or coco.')
parser.add_argument(
'--coco_path',
default='/home/hao.wyh/jupyter/黑边/smart_reverse_label/coco/',
help='Path to COCO directory')
#parser.add_argument('--coco_path', default='/home/hao.wyh/jupyter/黑边/评估任务/3k_imgs/coco/', help='Path to COCO directory')
parser.add_argument('--csv_classes',
help='Path to file containing class list (see readme)')
parser.add_argument(
'--csv_val',
help=
'Path to file containing validation annotations (optional, see readme)'
)
parser.add_argument('--model', help='Path to model (.pt) file.')
parser = parser.parse_args(args)
if parser.dataset == 'coco':
dataset_val = CocoDataset(parser.coco_path,
set_name='val2017',
transform=transforms.Compose(
[Normalizer(), Resizer()]))
else:
raise ValueError(
'Dataset type not understood (must be csv or coco), exiting.')
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=1,
drop_last=False)
dataloader_val = DataLoader(dataset_val,
num_workers=1,
collate_fn=collater,
batch_sampler=sampler_val)
retinanet = torch.load(parser.model)
use_gpu = True
if use_gpu:
retinanet = retinanet.cuda()
retinanet.eval()
coco_eval.evaluate_coco(dataset_val, retinanet)
def main(args=None):
parser = argparse.ArgumentParser(description='Simple training script for training a RetinaNet network.')
parser.add_argument('--csv_classes', help='Path to file containing class list (see readme)')
parser.add_argument('--csv_val', help='Path to file containing validation annotations (optional, see readme)')
parser.add_argument('--model', help='Path to model (.pt) file.')
parser = parser.parse_args(args)
dataset_val = CSVDataset(train_file=parser.csv_val, class_list=parser.csv_classes, transform=transforms.Compose([Normalizer(), Resizer()]), is_visualizing=True)
sampler_val = AspectRatioBasedSampler(dataset_val, batch_size=1, drop_last=False)
dataloader_val = DataLoader(dataset_val, num_workers=1, collate_fn=collater, batch_sampler=sampler_val)
retinanet = model.resnet50(num_classes=dataset_val.num_classes(), pretrained=True)
retinanet.load_state_dict(torch.load(parser.model))
use_gpu = True
if use_gpu:
retinanet = retinanet.cuda()
retinanet.eval()
scores_for_rnn = {}
for idx, data in enumerate(dataloader_val):
print(idx)
with torch.no_grad():
img_name = data['img_name'][0]
scale = data['scale'][0]
scores, transformed_anchors = retinanet(data['img'].cuda().float(), return_all_scores=True)
transformed_anchors /= scale
scores, transformed_anchors = scores.cpu(), transformed_anchors.cpu()
scores = [[scores[i,j].item() for j in range(scores.size(1))] for i in range(scores.size(0))]
transformed_anchors = [[transformed_anchors[i,j].item() for j in range(transformed_anchors.size(1))] for i in range(transformed_anchors.size(0))]
curr = {'scores': scores, 'bboxes': transformed_anchors}
scores_for_rnn[img_name] = curr
with open('detections.json', 'w') as f:
json.dump(scores_for_rnn, f)
def main(args=None):
parser = argparse.ArgumentParser(description='Simple training script for training a RetinaNet network.')
parser.add_argument('--dataset', help='Dataset type, must be one of csv or coco.')
parser.add_argument('--coco_path', help='Path to COCO directory')
parser.add_argument('--csv_classes', help='Path to file containing class list (see readme)')
parser.add_argument('--csv_val', help='Path to file containing validation annotations (optional, see readme)')
parser.add_argument('--score_threshold', help='Score above which boxes are kept',default=0.5)
parser.add_argument('--nms_threshold', help='Score above which boxes are kept',default=0.5)
parser.add_argument('--model', help='Path to model (.pt) file.')
parser = parser.parse_args(args)
if parser.dataset == 'coco':
dataset_val = CocoDataset(parser.coco_path, set_name='val2017', transform=transforms.Compose([Normalizer(), Resizer()]))
elif parser.dataset == 'csv':
dataset_val = CSVDataset(train_file=parser.csv_val, class_list=parser.csv_classes, transform=transforms.Compose([Normalizer(), Resizer()]))
else:
raise ValueError('Dataset type not understood (must be csv or coco), exiting.')
sampler_val = AspectRatioBasedSampler(dataset_val, batch_size=1, drop_last=False)
dataloader_val = DataLoader(dataset_val, num_workers=0, collate_fn=collater, batch_sampler=sampler_val,shuffle=False)
retinanet = torch.load(parser.model)
score_threshold = float(parser.score_threshold)
nms_threshold = float(parser.score_threshold)
use_gpu = True
f = open('mAPs.txt','w')
writer = csv.writer(f,delimiter = ",")
if use_gpu:
retinanet = retinanet.cuda()
retinanet.eval()
thresholds = np.array([0.1 + 0.05*n for n in range(10)])
for nms_threshold in thresholds:
for score_threshold in thresholds:
mAPs = csv_eval.evaluate(dataset_val, retinanet,iou_threshold=0.5,score_threshold=score_threshold,nms_threshold = nms_threshold)
maps=np.mean([ap[0] for ap in mAPs.values()])
writer.writerow([score_threshold,nms_threshold,maps])
def get_training_dataloader(self,
set_name='train'
): # this can be used for entire sets
with redirect_stdout(None):
self.training_dataset = CocoDataset(root_dir=self.root_dir,
set_name=set_name,
transform=None)
[min_w, min_h] = self.get_min_size(self.training_dataset)
self.training_dataset.transform = transforms.Compose(
[Normalizer(), Augmenter(), Resizer()])
# RandomCropOrScale(min_w, min_h)])
# training_dataset = self.get_dataset(set_name=set_name)
sampler_train = AspectRatioBasedSampler(self.training_dataset,
batch_size=self.batch_size,
shuffle=True)
self.training_dataloader = DataLoader(dataset=self.training_dataset,
num_workers=self.workers,
collate_fn=collater,
batch_sampler=sampler_train,
pin_memory=True)
self.print_data_statistics(data_loader=self.training_dataloader,
set_type='Training')
def get_validation_dataloader(self,
sub_dir=None,
sort=False,
set_name='val'):
with redirect_stdout(None):
self.validation_dataset = CocoDataset(
root_dir=self.root_dir,
set_name=set_name,
sub_dir=sub_dir,
transform=transforms.Compose([Normalizer(),
Resizer()]),
categories=self.categories,
sort=sort)
# validation_dataset = self.get_dataset(set_name=set_name, sub_dir=sub_dir)
sampler_val = AspectRatioBasedSampler(self.validation_dataset,
batch_size=1,
shuffle=False)
self.validation_dataloader = DataLoader(self.validation_dataset,
num_workers=self.workers,
collate_fn=collater,
batch_sampler=sampler_val,
pin_memory=True)
self.print_data_statistics(data_loader=self.validation_dataloader,
set_type='Validation')
def main(args=None):
#def main(epoch):
parser = argparse.ArgumentParser(description='Simple training script for training a RetinaNet network.')
parser.add_argument('--dataset', help='Dataset type, must be one of csv or coco.')
parser.add_argument('--coco_path', help='Path to COCO directory')
parser.add_argument('--csv_train', help='Path to file containing training annotations (see readme)')
parser.add_argument('--csv_classes', help='Path to file containing class list (see readme)')
parser.add_argument('--csv_val', help='Path to file containing validation annotations (optional, see readme)')
parser.add_argument('--depth', help='Resnet depth, must be one of 18, 34, 50, 101, 152', type=int, default=50)
parser.add_argument('--epochs', help='Number of epochs', type=int, default=100)
#parser.add_argument('--resume', '-r', action='store_true', help='resume from checkpoint')
parser.add_argument('--start-epoch', default=0, type=int, help='manual epoch number (useful on restarts)')
parser.add_argument('--resume', default='', type=str, metavar='PATH', help='path to latest checkpoint (default: none)')
parser = parser.parse_args(args)
#args = parser.parse_args()
#parser = parser.parse_args(epoch)
# Create the data loaders
if parser.dataset == 'coco':
if parser.coco_path is None:
raise ValueError('Must provide --coco_path when training on COCO,')
dataset_train = CocoDataset(parser.coco_path, set_name='train2017', transform=transforms.Compose([Normalizer(), Augmenter(), Resizer()]))
dataset_val = CocoDataset(parser.coco_path, set_name='val2017', transform=transforms.Compose([Normalizer(), Resizer()]))
elif parser.dataset == 'csv':
if parser.csv_train is None:
raise ValueError('Must provide --csv_train when training on COCO,')
if parser.csv_classes is None:
raise ValueError('Must provide --csv_classes when training on COCO,')
dataset_train = CSVDataset(train_file=parser.csv_train, class_list=parser.csv_classes, transform=transforms.Compose([Normalizer(), Augmenter(), Resizer()]))
if parser.csv_val is None:
dataset_val = None
print('No validation annotations provided.')
else:
dataset_val = CSVDataset(train_file=parser.csv_val, class_list=parser.csv_classes, transform=transforms.Compose([Normalizer(), Resizer()]))
else:
raise ValueError('Dataset type not understood (must be csv or coco), exiting.')
sampler = AspectRatioBasedSampler(dataset_train, batch_size=4, drop_last=False)
dataloader_train = DataLoader(dataset_train, num_workers=3, collate_fn=collater, batch_sampler=sampler)
if dataset_val is not None:
sampler_val = AspectRatioBasedSampler(dataset_val, batch_size=1, drop_last=False)
dataloader_val = DataLoader(dataset_val, num_workers=3, collate_fn=collater, batch_sampler=sampler_val)
# Create the model
if parser.depth == 18:
retinanet = model.resnet18(num_classes=dataset_train.num_classes(), pretrained=True)
elif parser.depth == 34:
retinanet = model.resnet34(num_classes=dataset_train.num_classes(), pretrained=True)
elif parser.depth == 50:
retinanet = model.resnet50(num_classes=dataset_train.num_classes(), pretrained=True)
elif parser.depth == 101:
retinanet = model.resnet101(num_classes=dataset_train.num_classes(), pretrained=True)
elif parser.depth == 152:
retinanet = model.resnet152(num_classes=dataset_train.num_classes(), pretrained=True)
else:
raise ValueError('Unsupported model depth, must be one of 18, 34, 50, 101, 152')
use_gpu = True
if use_gpu:
retinanet = retinanet.cuda()
#retinanet().load_state_dict(torch.load('/users/wenchi/ghwwc/Pytorch-retinanet-master/resnet50-19c8e357.pth'))
#if True:
#print('==> Resuming from checkpoint..')
#checkpoint = torch.load('/users/wenchi/ghwwc/Pytorch-retinanet-master/coco_retinanet_2.pt')
#retinanet().load_state_dict(checkpoint)
#best_loss = checkpoint['loss']
#start_epoch = checkpoint['epoch']
retinanet = torch.nn.DataParallel(retinanet).cuda()
retinanet.training = True
#optimizer = optim.Adam(retinanet.parameters(), lr=1e-5)
optimizer = optim.SGD(retinanet.parameters(), lr=1e-5)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, patience=3, verbose=True)
loss_hist = collections.deque(maxlen=500)
retinanet.train()
#retinanet.freeze_bn() #for train from a middle state
retinanet.module.freeze_bn() #for train from the very beginning
print('Num training images: {}'.format(len(dataset_train)))
for epoch_num in range(parser.start_epoch, parser.epochs):
if parser.resume:
if os.path.isfile(parser.resume):
print("=>loading checkpoint '{}'".format(parser.resume))
checkpoint = torch.load(parser.resume)
print(parser.start_epoch)
#parser.start_epoch = checkpoint['epoch']
#retinanet.load_state_dict(checkpoint['state_dict'])
retinanet=checkpoint
#retinanet.load_state_dict(checkpoint)
print(retinanet)
#optimizer.load_state_dict(checkpoint)
print("=> loaded checkpoint '{}' (epoch {})".format(parser.resume, checkpoint))
else:
print("=> no checkpoint found at '{}'".format(parser.resume))
retinanet.train()
retinanet.freeze_bn()
#retinanet.module.freeze_bn()
if parser.dataset == 'coco':
print('Evaluating dataset')
coco_eval.evaluate_coco(dataset_val, retinanet)
elif parser.dataset == 'csv' and parser.csv_val is not None:
print('Evaluating dataset')
mAP = csv_eval.evaluate(dataset_val, retinanet)
epoch_loss = []
for iter_num, data in enumerate(dataloader_train):
try:
optimizer.zero_grad()
classification_loss, regression_loss = retinanet([data['img'].cuda().float(), data['annot'].cuda()])
classification_loss = classification_loss.mean()
regression_loss = regression_loss.mean()
loss = classification_loss + regression_loss
if bool(loss == 0):
continue
loss.backward()
torch.nn.utils.clip_grad_norm_(retinanet.parameters(), 0.1)
optimizer.step()
loss_hist.append(float(loss))
epoch_loss.append(float(loss))
print('Epoch: {} | Iteration: {} | Classification loss: {:1.5f} | Regression loss: {:1.5f} | Running loss: {:1.5f}'.format(epoch_num, iter_num, float(classification_loss), float(regression_loss), np.mean(loss_hist)))
del classification_loss
del regression_loss
except Exception as e:
print(e)
continue
if parser.dataset == 'coco':
print('Evaluating dataset')
coco_eval.evaluate_coco(dataset_val, retinanet)
elif parser.dataset == 'csv' and parser.csv_val is not None:
print('Evaluating dataset')
mAP = csv_eval.evaluate(dataset_val, retinanet)
scheduler.step(np.mean(epoch_loss))
#torch.save(retinanet.module, '{}_retinanet_101_{}.pt'.format(parser.dataset, epoch_num))
torch.save(retinanet, '{}_retinanet_dilation_experiment1_{}.pt'.format(parser.dataset, epoch_num))
name = '{}_retinanet_dilation_experiment1_{}.pt'.format(parser.dataset, epoch_num)
parser.resume = '/users/wenchi/ghwwc/pytorch-retinanet-master_new/name'
retinanet.eval()
torch.save(retinanet, 'model_final_dilation_experiment1.pt'.format(epoch_num))
def main(args=None):
parser = argparse.ArgumentParser(
description='Simple training script for training a RetinaNet network.')
parser.add_argument('--coco_path',
help='Path to COCO directory',
type=str,
default='./data/coco')
parser.add_argument(
'--depth',
help='Resnet depth, must be one of 18, 34, 50, 101, 152',
type=int,
default=50)
parser.add_argument('--checkpoint',
help='The path to the checkpoint.',
type=str,
default=None)
parser.add_argument('--epochs',
help='Number of epochs',
type=int,
default=100)
parser.add_argument('--batch_size',
help='Number of batch',
type=int,
default=16)
parser.add_argument('--gpu_ids',
help='Gpu parallel',
type=str,
default='1, 2')
parser = parser.parse_args(args)
# Create the data lodaders
dataset_train = CocoDataset(parser.coco_path,
set_name='train2017',
transform=transforms.Compose(
[Normalizer(),
Augmenter(),
Resizer()]))
dataset_val = CocoDataset(parser.coco_path,
set_name='val2017',
transform=transforms.Compose(
[Normalizer(), Resizer()]))
sampler = AspectRatioBasedSampler(dataset_train,
batch_size=4,
drop_last=False)
dataloader_train = DataLoader(dataset_train,
num_workers=16,
collate_fn=collater,
batch_sampler=sampler)
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=1,
drop_last=False)
dataloader_val = DataLoader(dataset_val,
num_workers=3,
collate_fn=collater,
batch_sampler=sampler_val)
# Create the model
if parser.depth == 18:
retinanet = model.resnet18(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 34:
retinanet = model.resnet34(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 50:
retinanet = model.resnet50(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 101:
retinanet = model.resnet101(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 152:
retinanet = model.resnet152(num_classes=dataset_train.num_classes(),
pretrained=True)
else:
raise ValueError(
'Unsupported model depth, must be one of 18, 34, 50, 101, 152')
use_gpu = True
if use_gpu:
retinanet = retinanet.cuda()
gpu_ids = parser.gpu_ids.split(',')
device = torch.device("cuda:" + gpu_ids[0])
torch.cuda.set_device(device)
gpu_ids = list(map(int, gpu_ids))
retinanet = torch.nn.DataParallel(retinanet, device_ids=gpu_ids).to(device)
if parser.checkpoint:
pretrained = torch.load(parser.checkpoint).state_dict()
retinanet.module.load_state_dict(pretrained)
# add tensorboard to record train log
retinanet.training = True
writer = SummaryWriter('./log')
# writer.add_graph(retinanet, input_to_model=[images, labels])
retinanet.training = True
optimizer = optim.Adam(retinanet.parameters(), lr=1e-5)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer,
patience=3,
verbose=True)
loss_hist = collections.deque(maxlen=500)
retinanet.train()
retinanet.module.freeze_bn()
print('Num training images: {}'.format(len(dataset_train)))
for epoch_num in range(parser.epochs):
retinanet.train()
retinanet.module.freeze_bn()
epoch_loss = []
for iter_num, data in enumerate(dataloader_train):
try:
optimizer.zero_grad()
classification_loss, regression_loss = retinanet(
[data['img'].to(device), data['ann'].to(device)])
classification_loss = classification_loss.mean()
regression_loss = regression_loss.mean()
loss = classification_loss + regression_loss
if bool(loss == 0):
continue
loss.backward()
torch.nn.utils.clip_grad_norm_(retinanet.parameters(), 0.1)
optimizer.step()
loss_hist.append(float(loss))
writer.add_scalar('Loss/train', loss, iter_num)
writer.add_scalar('Loss/reg_loss', regression_loss, iter_num)
writer.add_scalar('Loss/cls_loss', classification_loss,
iter_num)
epoch_loss.append(float(loss))
if (iter_num + 1) % 1000 == 0:
print('Save model')
torch.save(
retinanet.module,
'COCO_retinanet_epoch{}_iter{}.pt'.format(
epoch_num, iter_num))
print(
'Epoch: {} | Iteration: {} | Classification loss: {:1.5f} | Regression loss: {:1.5f} | Running loss: {:1.5f}'
.format(epoch_num, iter_num, float(classification_loss),
float(regression_loss), np.mean(loss_hist)))
del classification_loss
del regression_loss
except Exception as e:
print(e)
continue
print('Evaluating dataset')
coco_eval.evaluate_coco(dataset_val, retinanet, writer)
scheduler.step(np.mean(epoch_loss))
torch.save(retinanet.module, 'COCO_retinanet_{}.pt'.format(epoch_num))
retinanet.eval()
torch.save(retinanet, 'model_final.pt'.format(epoch_num))
def train(args):
train_csv = args.train_csv
test_csv = args.test_csv
labels_csv = args.labels_csv
model_type = args.model_type
epochs = int(args.epochs)
batch_size = int(args.batch_size)
dataset_train = CSVDataset(train_file=train_csv,
class_list=labels_csv,
transform=transforms.Compose(
[Normalizer(),
Augmenter(),
Resizer()]))
dataset_val = CSVDataset(train_file=test_csv,
class_list=labels_csv,
transform=transforms.Compose(
[Normalizer(), Resizer()]))
sampler = AspectRatioBasedSampler(dataset_train,
batch_size=batch_size,
drop_last=False)
dataloader_train = DataLoader(dataset_train,
num_workers=3,
collate_fn=collater,
batch_sampler=sampler)
retinanet = RetinaNet_efficientnet_b4(
num_classes=dataset_train.num_classes(), model_type=model_type)
use_gpu = True
if use_gpu:
retinanet = retinanet.cuda()
retinanet = torch.nn.DataParallel(retinanet).cuda()
retinanet.training = True
optimizer = optim.Adam(retinanet.parameters(), lr=1e-5)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer,
patience=3,
verbose=True)
loss_hist = collections.deque(maxlen=500)
retinanet.train()
retinanet.module.freeze_bn()
print('Num training images: {}'.format(len(dataset_train)))
for epoch_num in range(epochs):
retinanet.train()
retinanet.module.freeze_bn()
epoch_loss = []
for iter_num, data in enumerate(dataloader_train):
try:
optimizer.zero_grad()
classification_loss, regression_loss = retinanet(
[data['img'].cuda().float(), data['annot']])
classification_loss = classification_loss.mean()
regression_loss = regression_loss.mean()
loss = classification_loss + regression_loss
if bool(loss == 0):
continue
loss.backward()
torch.nn.utils.clip_grad_norm_(retinanet.parameters(), 0.1)
optimizer.step()
loss_hist.append(float(loss))
epoch_loss.append(float(loss))
print(
'Epoch: {} | Iteration: {} | Classification loss: {:1.5f} | Regression loss: {:1.5f} | Running loss: {:1.5f}'
.format(epoch_num, iter_num, float(classification_loss),
float(regression_loss), np.mean(loss_hist)))
del classification_loss
del regression_loss
except Exception as e:
print(e)
continue
mAP, MAP = evaluate(dataset_val, retinanet)
scheduler.step(np.mean(epoch_loss))
torch.save(
retinanet.module,
'{}_retinanet_{}_map{}.pt'.format("EfficientNet" + model_type,
epoch_num, MAP))
retinanet.eval()
torch.save(retinanet, 'model_final.pt'.format(epoch_num))
def main(args=None):
parser = argparse.ArgumentParser(
description='Simple training script for training a RetinaNet network.')
parser.add_argument('--dataset',
help='Dataset type, must be one of csv or coco.')
parser.add_argument('--coco_path', help='Path to COCO directory')
parser.add_argument(
'--csv_train',
help='Path to file containing training annotations (see readme)')
parser.add_argument('--csv_classes',
help='Path to file containing class list (see readme)')
parser.add_argument(
'--csv_val',
help=
'Path to file containing validation annotations (optional, see readme)'
)
parser.add_argument(
'--depth',
help='Resnet depth, must be one of 18, 34, 50, 101, 152',
type=int,
default=50)
parser.add_argument('--epochs',
help='Number of epochs',
type=int,
default=100)
parser = parser.parse_args(args)
# Create the data loaders
if parser.dataset == 'coco':
if parser.coco_path is None:
raise ValueError('Must provide --coco_path when training on COCO,')
dataset_train = CocoDataset(parser.coco_path,
set_name='train2017',
transform=transforms.Compose(
[Normalizer(),
Augmenter(),
Resizer()]))
dataset_val = CocoDataset(parser.coco_path,
set_name='val2017',
transform=transforms.Compose(
[Normalizer(), Resizer()]))
elif parser.dataset == 'csv':
if parser.csv_train is None:
raise ValueError('Must provide --csv_train when training on COCO,')
if parser.csv_classes is None:
raise ValueError(
'Must provide --csv_classes when training on COCO,')
dataset_train = CSVDataset(train_file=parser.csv_train,
class_list=parser.csv_classes,
transform=transforms.Compose(
[Normalizer(),
Augmenter(),
Resizer()]))
if parser.csv_val is None:
dataset_val = None
print('No validation annotations provided.')
else:
dataset_val = CSVDataset(train_file=parser.csv_val,
class_list=parser.csv_classes,
transform=transforms.Compose(
[Normalizer(),
Resizer()]))
else:
raise ValueError(
'Dataset type not understood (must be csv or coco), exiting.')
sampler = AspectRatioBasedSampler(dataset_train,
batch_size=2,
drop_last=False)
dataloader_train = DataLoader(dataset_train,
num_workers=3,
collate_fn=collater,
batch_sampler=sampler)
if dataset_val is not None:
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=1,
drop_last=False)
dataloader_val = DataLoader(dataset_val,
num_workers=3,
collate_fn=collater,
batch_sampler=sampler_val)
# Create the model
if parser.depth == 18:
retinanet = model.resnet18(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 34:
retinanet = model.resnet34(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 50:
retinanet = model.resnet50(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 101:
retinanet = model.resnet101(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 152:
retinanet = model.resnet152(num_classes=dataset_train.num_classes(),
pretrained=True)
else:
raise ValueError(
'Unsupported model depth, must be one of 18, 34, 50, 101, 152')
use_gpu = True
if use_gpu:
retinanet = retinanet.cuda()
retinanet = torch.nn.DataParallel(retinanet).cuda()
retinanet.training = True
optimizer = optim.Adam(retinanet.parameters(), lr=1e-5)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer,
patience=3,
verbose=True)
loss_hist = collections.deque(maxlen=500)
retinanet.train()
retinanet.module.freeze_bn()
print('Num training images: {}'.format(len(dataset_train)))
for epoch_num in range(parser.epochs):
retinanet.train()
retinanet.module.freeze_bn()
epoch_loss = []
for iter_num, data in enumerate(dataloader_train):
try:
optimizer.zero_grad()
classification_loss, regression_loss = retinanet(
[data['img'].cuda().float(), data['annot']])
classification_loss = classification_loss.mean()
regression_loss = regression_loss.mean()
loss = classification_loss + regression_loss
if bool(loss == 0):
continue
loss.backward()
torch.nn.utils.clip_grad_norm_(retinanet.parameters(), 0.1)
optimizer.step()
loss_hist.append(float(loss))
epoch_loss.append(float(loss))
print(
'Epoch: {} | Iteration: {} | Classification loss: {:1.5f} | Regression loss: {:1.5f} | Running loss: {:1.5f}'
.format(epoch_num, iter_num, float(classification_loss),
float(regression_loss), np.mean(loss_hist)))
del classification_loss
del regression_loss
except Exception as e:
print(e)
continue
if parser.dataset == 'coco':
print('Evaluating dataset')
coco_eval.evaluate_coco(dataset_val, retinanet)
elif parser.dataset == 'csv' and parser.csv_val is not None:
print('Evaluating dataset')
mAP = csv_eval.evaluate(dataset_val, retinanet)
scheduler.step(np.mean(epoch_loss))
torch.save(
retinanet.module,
'{}_retinanet_dilation_{}.pt'.format(parser.dataset, epoch_num))
retinanet.eval()
torch.save(retinanet, 'model_final_dilation.pt'.format(epoch_num))
epoch_max = 100
batch_size = 1
dataset_train = CocoDataset(data_root_dir,
set_name='train2017',
transform=transforms.Compose(
[Normalizer(),
Augmenter(),
Resizer()]))
dataset_val = CocoDataset(data_root_dir,
set_name='val2017',
transform=transforms.Compose(
[Normalizer(), Resizer()]))
sampler = AspectRatioBasedSampler(dataset_train,
batch_size=batch_size,
drop_last=True)
train_data_loader = DataLoader(dataset_train,
num_workers=8,
collate_fn=collater,
batch_sampler=sampler)
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=batch_size,
drop_last=True)
val_data_loader = DataLoader(dataset_val,
num_workers=8,
collate_fn=collater,
batch_sampler=sampler_val)
# 以使用retinanet_50为例，测试获取数据是否成功
retinanet = model.retinanet_50(dataset_train.num_classes(),
def main(args=None):
parser = argparse.ArgumentParser(description='Simple testing script for RetinaNet network.')
parser.add_argument('--dataset', help='Dataset type, must be one of csv or coco.',default = "csv")
parser.add_argument('--coco_path', help='Path to COCO directory')
parser.add_argument('--csv_classes', help='Path to file containing class list (see readme)',default="binary_class.csv")
parser.add_argument('--csv_val', help='Path to file containing validation annotations (optional, see readme)')
parser.add_argument('--csv_box_annot', help='Path to file containing predicted box annotations ')
parser.add_argument('--depth', help='Resnet depth, must be one of 18, 34, 50, 101, 152', type=int, default=18)
parser.add_argument('--epochs', help='Number of epochs', type=int, default=500)
parser.add_argument('--model', help='Path of .pt file with trained model',default = 'esposallescsv_retinanet_0.pt')
parser.add_argument('--model_out', help='Path of .pt file with trained model to save',default = 'trained')
parser.add_argument('--score_threshold', help='Score above which boxes are kept',default=0.15)
parser.add_argument('--nms_threshold', help='Score above which boxes are kept',default=0.2)
parser.add_argument('--max_epochs_no_improvement', help='Max epochs without improvement',default=100)
parser.add_argument('--max_boxes', help='Max boxes to be fed to recognition',default=50)
parser.add_argument('--seg_level', help='Line or word, to choose anchor aspect ratio',default='line')
parser.add_argument('--htr_gt_box',help='Train recognition branch with box gt (for debugging)',default=False)
parser = parser.parse_args(args)
# Create the data loaders
if parser.dataset == 'csv':
if parser.csv_classes is None:
raise ValueError('Must provide --csv_classes when training on COCO,')
if parser.csv_val is None:
dataset_val = None
print('No validation annotations provided.')
else:
dataset_val = CSVDataset(train_file=parser.csv_val, class_list=parser.csv_classes, transform=transforms.Compose([Normalizer(), Resizer()]))
if parser.csv_box_annot is not None:
box_annot_data = CSVDataset(train_file=parser.csv_box_annot, class_list=parser.csv_classes, transform=transforms.Compose([Normalizer(), Resizer()]))
else:
box_annot_data = None
else:
raise ValueError('Dataset type not understood (must be csv or coco), exiting.')
if dataset_val is not None:
sampler_val = AspectRatioBasedSampler(dataset_val, batch_size=1, drop_last=False)
dataloader_val = DataLoader(dataset_val, num_workers=0, collate_fn=collater, batch_sampler=sampler_val)
if box_annot_data is not None:
sampler_val = AspectRatioBasedSampler(box_annot_data, batch_size=1, drop_last=False)
dataloader_box_annot = DataLoader(box_annot_data, num_workers=0, collate_fn=collater, batch_sampler=sampler_val)
else:
dataloader_box_annot = dataloader_val
if not os.path.exists('trained_models'):
os.mkdir('trained_models')
# Create the model
alphabet=dataset_val.alphabet
if os.path.exists(parser.model):
retinanet = torch.load(parser.model)
else:
if parser.depth == 18:
retinanet = model.resnet18(num_classes=dataset_val.num_classes(), pretrained=True,max_boxes=int(parser.max_boxes),score_threshold=float(parser.score_threshold),seg_level=parser.seg_level,alphabet=alphabet)
elif parser.depth == 34:
retinanet = model.resnet34(num_classes=dataset_train.num_classes(), pretrained=True)
elif parser.depth == 50:
retinanet = model.resnet50(num_classes=dataset_train.num_classes(), pretrained=True)
elif parser.depth == 101:
retinanet = model.resnet101(num_classes=dataset_train.num_classes(), pretrained=True)
elif parser.depth == 152:
retinanet = model.resnet152(num_classes=dataset_train.num_classes(), pretrained=True)
else:
raise ValueError('Unsupported model depth, must be one of 18, 34, 50, 101, 152')
use_gpu = True
if use_gpu:
retinanet = retinanet.cuda()
retinanet = torch.nn.DataParallel(retinanet).cuda()
#retinanet = torch.load('../Documents/TRAINED_MODELS/pytorch-retinanet/esposallescsv_retinanet_99.pt')
#print "LOADED pretrained MODEL\n\n"
optimizer = optim.Adam(retinanet.parameters(), lr=1e-4)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, patience=4, verbose=True)
loss_hist = collections.deque(maxlen=500)
ctc = CTCLoss()
retinanet.module.freeze_bn()
best_cer = 1000
epochs_no_improvement=0
cers=[]
retinanet.eval()
retinanet.module.epochs_only_det = 0
#retinanet.module.htr_gt_box = False
retinanet.training=False
if parser.score_threshold is not None:
retinanet.module.score_threshold = float(parser.score_threshold)
'''if parser.dataset == 'csv' and parser.csv_val is not None:
print('Evaluating dataset')
'''
mAP = csv_eval.evaluate(dataset_val, retinanet,score_threshold=retinanet.module.score_threshold)
aps = []
for k,v in mAP.items():
aps.append(v[0])
print ("VALID mAP:",np.mean(aps))
print("score th",retinanet.module.score_threshold)
for idx,data in enumerate(dataloader_box_annot):
print("Eval CER on validation set:",idx,"/",len(dataloader_box_annot),"\r")
if box_annot_data:
image_name = box_annot_data.image_names[idx].split('/')[-1].split('.')[-2]
else:
image_name = dataset_val.image_names[idx].split('/')[-1].split('.')[-2]
#generate_pagexml(image_name,data,retinanet,parser.score_threshold,parser.nms_threshold,dataset_val)
text_gt_path="/".join(dataset_val.image_names[idx].split('/')[:-1])
text_gt = os.path.join(text_gt_path,image_name+'.txt')
f =open(text_gt,'r')
text_gt_lines=f.readlines()[0]
transcript_pred = get_transcript(image_name,data,retinanet,retinanet.module.score_threshold,float(parser.nms_threshold),dataset_val,alphabet)
cers.append(float(editdistance.eval(transcript_pred,text_gt_lines))/len(text_gt_lines))
print("GT",text_gt_lines)
print("PREDS SAMPLE:",transcript_pred)
print("VALID CER:",np.mean(cers),"best CER",best_cer)
print("GT",text_gt_lines)
print("PREDS SAMPLE:",transcript_pred)
print("VALID CER:",np.mean(cers),"best CER",best_cer)
def main(args=None):
parser = argparse.ArgumentParser(description='Simple training script for training a RetinaNet network.')
parser.add_argument('--dataset', help='Dataset type, must be one of csv or coco.')
parser.add_argument('--coco_path', help='Path to COCO directory')
parser.add_argument('--csv_classes', help='Path to file containing class list (see readme)')
parser.add_argument('--csv_val', help='Path to file containing validation annotations (optional, see readme)')
parser.add_argument('--model', help='Path to model (.pt) file.')
parser = parser.parse_args(args)
if parser.dataset == 'coco':
dataset_val = CocoDataset(parser.coco_path, set_name='val2017',
transform=transforms.Compose([Normalizer(), Resizer()]))
elif parser.dataset == 'csv':
dataset_val = CSVDataset(train_file=parser.csv_train, class_list=parser.csv_classes,
transform=transforms.Compose([Normalizer(), Resizer()]))
else:
raise ValueError('Dataset type not understood (must be csv or coco), exiting.')
sampler_val = AspectRatioBasedSampler(dataset_val, batch_size=1, drop_last=False)
dataloader_val = DataLoader(dataset_val, num_workers=1, collate_fn=collater, batch_sampler=sampler_val)
retinanet = torch.load(parser.model)
use_gpu = True
if use_gpu:
retinanet = retinanet.cuda()
retinanet.eval()
unnormalize = UnNormalizer()
def draw_caption(image, box, caption):
b = np.array(box).astype(int)
cv2.putText(image, caption, (b[0], b[1] - 10), cv2.FONT_HERSHEY_PLAIN, 1, (0, 0, 0), 2)
cv2.putText(image, caption, (b[0], b[1] - 10), cv2.FONT_HERSHEY_PLAIN, 1, (255, 255, 255), 1)
for idx, data in enumerate(dataloader_val):
with torch.no_grad():
st = time.time()
scores, classification, transformed_anchors = retinanet(data['img'].cuda().float())
print('Elapsed time: {}'.format(time.time() - st))
idxs = np.where(scores > 0.5)
img = np.array(255 * unnormalize(data['img'][0, :, :, :])).copy()
img[img < 0] = 0
img[img > 255] = 255
img = np.transpose(img, (1, 2, 0))
img = cv2.cvtColor(img.astype(np.uint8), cv2.COLOR_BGR2RGB)
for j in range(idxs[0].shape[0]):
bbox = transformed_anchors[idxs[0][j], :]
x1 = int(bbox[0])
y1 = int(bbox[1])
x2 = int(bbox[2])
y2 = int(bbox[3])
label_name = dataset_val.labels[int(classification[idxs[0][j]])]
draw_caption(img, (x1, y1, x2, y2), label_name)
cv2.rectangle(img, (x1, y1), (x2, y2), color=(0, 0, 255), thickness=2)
print(label_name)
cv2.imshow('img', img)
cv2.waitKey(0)
def main(args=None):
parser = argparse.ArgumentParser(
description='Simple training script for training a CTracker network.')
parser.add_argument('--dataset',
default='csv',
type=str,
help='Dataset type, must be one of csv or coco.')
parser.add_argument('--model_dir',
default='./ctracker/',
type=str,
help='Path to save the model.')
parser.add_argument(
'--root_path',
default='/Dataset/Tracking/MOT17/',
type=str,
help='Path of the directory containing both label and images')
parser.add_argument(
'--csv_train',
default='train_annots.csv',
type=str,
help='Path to file containing training annotations (see readme)')
parser.add_argument('--csv_classes',
default='train_labels.csv',
type=str,
help='Path to file containing class list (see readme)')
parser.add_argument(
'--depth',
help='Resnet depth, must be one of 18, 34, 50, 101, 152',
type=int,
default=50)
parser.add_argument('--epochs',
help='Number of epochs',
type=int,
default=100)
parser.add_argument('--print_freq',
help='Print frequency',
type=int,
default=100)
parser.add_argument(
'--save_every',
help='Save a checkpoint of model at given interval of epochs',
type=int,
default=5)
parser = parser.parse_args(args)
print(parser)
print(parser.model_dir)
if not os.path.exists(parser.model_dir):
os.makedirs(parser.model_dir)
# Create the data loaders
if parser.dataset == 'csv':
if (parser.csv_train is None) or (parser.csv_train == ''):
raise ValueError('Must provide --csv_train when training on COCO,')
if (parser.csv_classes is None) or (parser.csv_classes == ''):
raise ValueError(
'Must provide --csv_classes when training on COCO,')
dataset_train = CSVDataset(parser.root_path, train_file=os.path.join(parser.root_path, parser.csv_train), class_list=os.path.join(parser.root_path, parser.csv_classes), \
transform=transforms.Compose([RandomSampleCrop(), PhotometricDistort(), Augmenter(), Normalizer()]))#transforms.Compose([Normalizer(), Augmenter(), Resizer()]))
else:
raise ValueError(
'Dataset type not understood (must be csv or coco), exiting.')
# sampler = AspectRatioBasedSampler(dataset_train, batch_size=2, drop_last=False)
sampler = AspectRatioBasedSampler(dataset_train,
batch_size=8,
drop_last=False)
dataloader_train = DataLoader(dataset_train,
num_workers=32,
collate_fn=collater,
batch_sampler=sampler)
# Create the model
if parser.depth == 18:
retinanet = model.resnet18(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 34:
retinanet = model.resnet34(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 50:
retinanet = model.resnet50(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 101:
retinanet = model.resnet101(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 152:
retinanet = model.resnet152(num_classes=dataset_train.num_classes(),
pretrained=True)
else:
raise ValueError(
'Unsupported model depth, must be one of 18, 34, 50, 101, 152')
use_gpu = True
if use_gpu:
retinanet = retinanet.cuda()
retinanet = torch.nn.DataParallel(retinanet).cuda()
retinanet.training = True
# optimizer = optim.Adam(retinanet.parameters(), lr=1e-5)
optimizer = optim.Adam(retinanet.parameters(), lr=5e-5)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer,
patience=3,
verbose=True)
loss_hist = collections.deque(maxlen=500)
retinanet.train()
retinanet.module.freeze_bn()
print('Num training images: {}'.format(len(dataset_train)))
total_iter = 0
for epoch_num in range(parser.epochs):
retinanet.train()
retinanet.module.freeze_bn()
epoch_loss = []
for iter_num, data in enumerate(dataloader_train):
try:
total_iter = total_iter + 1
optimizer.zero_grad()
(classification_loss, regression_loss), reid_loss = retinanet([
data['img'].cuda().float(), data['annot'],
data['img_next'].cuda().float(), data['annot_next']
])
classification_loss = classification_loss.mean()
regression_loss = regression_loss.mean()
reid_loss = reid_loss.mean()
# loss = classification_loss + regression_loss + track_classification_losses
loss = classification_loss + regression_loss + reid_loss
if bool(loss == 0):
continue
loss.backward()
torch.nn.utils.clip_grad_norm_(retinanet.parameters(), 0.1)
optimizer.step()
loss_hist.append(float(loss))
epoch_loss.append(float(loss))
# print frequency default=100 or e.g. --print_freq 500
if total_iter % parser.print_freq == 0:
print(
'Epoch: {} | Iter: {} | Cls loss: {:1.5f} | Reid loss: {:1.5f} | Reg loss: {:1.5f} | Running loss: {:1.5f}'
.format(epoch_num, iter_num,
float(classification_loss), float(reid_loss),
float(regression_loss), np.mean(loss_hist)))
except Exception as e:
print(e)
continue
scheduler.step(np.mean(epoch_loss))
# Save a checkpoint of model at given interval of epochs e.g. --save_every 10
if epoch_num % parser.save_every == 0:
torch.save(
retinanet,
os.path.join(parser.model_dir,
"weights_epoch_" + str(epoch_num) + ".pt"))
retinanet.eval()
torch.save(retinanet, os.path.join(parser.model_dir, 'model_final.pt'))
run_from_train(parser.model_dir, parser.root_path)
def main(args=None):
"""
In current implementation, if test csv is provided, we use that as validation set and combine the val and train csv's
as the csv for training.
If train_all_labeled_data flag is use, then we combine all 3 (if test is provided) for training and use a prespecified learning rate step schedule.
"""
parser = argparse.ArgumentParser(
description='Simple training script for training a RetinaNet network.')
parser.add_argument(
'--csv_train',
help='Path to file containing training annotations (see readme)')
parser.add_argument('--csv_classes',
help='Path to file containing class list (see readme)')
parser.add_argument(
'--csv_val',
help=
'Path to file containing validation annotations (optional, see readme)',
default=None)
parser.add_argument(
'--csv_test',
help=
'Path to file containing test annotations (optional, if provided, train & val will be combined for training and test will be used for evaluation)',
default=None)
parser.add_argument('--lr', type=float, default=2e-5)
parser.add_argument(
'--depth',
help='Resnet depth, must be one of 18, 34, 50, 101, 152',
type=int,
default=101)
parser.add_argument('--epochs',
help='Number of epochs',
type=int,
default=25)
parser.add_argument('--model_output_dir', type=str, default='models')
parser.add_argument(
'--train_all_labeled_data',
help=
'Combine train, val, and test into 1 training set. Will use prespecified learning rate scheduler steps',
action='store_true')
parser.add_argument('--resnet-backbone-normalization',
choices=['batch_norm', 'group_norm'],
type=str,
default='batch_norm')
parser = parser.parse_args(args)
print('Learning Rate: {}'.format(parser.lr))
print("Normalization: ", parser.resnet_backbone_normalization)
# Create folder - will raise error if folder exists
assert (os.path.exists(parser.model_output_dir) == False)
os.mkdir(parser.model_output_dir)
if parser.csv_train is None:
raise ValueError('Must provide --csv_train when training,')
if parser.csv_classes is None:
raise ValueError('Must provide --csv_classes when training,')
if not parser.csv_val and parser.csv_test:
raise ValueError(
"Cannot specify test set without specifying validation set")
if parser.train_all_labeled_data:
csv_paths = [parser.csv_train, parser.csv_val, parser.csv_test]
train_csv = []
for path in csv_paths:
if isinstance(path, str):
train_csv.append(path)
val_csv = None
else:
if parser.csv_train and parser.csv_val and parser.csv_test:
train_csv = [parser.csv_train, parser.csv_val
] # Combine train and val sets for training
val_csv = parser.csv_test
else:
train_csv = parser.csv_train
val_csv = parser.csv_val
print('loading train data')
print(train_csv)
dataset_train = CSVDataset(train_file=train_csv,
class_list=parser.csv_classes,
transform=transforms.Compose(
[Normalizer(),
Augmenter(),
Resizer()]))
print(dataset_train.__len__())
if val_csv is None:
dataset_val = None
print('No validation annotations provided.')
else:
dataset_val = CSVDataset(train_file=val_csv,
class_list=parser.csv_classes,
transform=transforms.Compose(
[Normalizer(), Resizer()]))
print('putting data into loader')
sampler = AspectRatioBasedSampler(dataset_train,
batch_size=2,
drop_last=False)
dataloader_train = DataLoader(dataset_train,
num_workers=3,
collate_fn=collater,
batch_sampler=sampler)
if dataset_val is not None:
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=1,
drop_last=False)
dataloader_val = DataLoader(dataset_val,
num_workers=3,
collate_fn=collater,
batch_sampler=sampler_val)
# Create the model
print('creating model')
if parser.depth == 18:
retinanet = model.resnet18(
num_classes=dataset_train.num_classes(),
pretrained=True,
normalization=parser.resnet_backbone_normalization)
elif parser.depth == 34:
retinanet = model.resnet34(
num_classes=dataset_train.num_classes(),
pretrained=True,
normalization=parser.resnet_backbone_normalization)
elif parser.depth == 50:
retinanet = model.resnet50(
num_classes=dataset_train.num_classes(),
pretrained=True,
normalization=parser.resnet_backbone_normalization)
elif parser.depth == 101:
retinanet = model.resnet101(
num_classes=dataset_train.num_classes(),
pretrained=True,
normalization=parser.resnet_backbone_normalization)
elif parser.depth == 152:
retinanet = model.resnet152(
num_classes=dataset_train.num_classes(),
pretrained=True,
normalization=parser.resnet_backbone_normalization)
else:
raise ValueError(
'Unsupported model depth, must be one of 18, 34, 50, 101, 152')
use_gpu = True
if use_gpu:
retinanet = retinanet.cuda()
retinanet = torch.nn.DataParallel(retinanet).cuda()
retinanet.training = True
optimizer = optim.Adam(retinanet.parameters(), lr=parser.lr)
lr_factor = 0.3
if not parser.train_all_labeled_data:
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer,
patience=3,
factor=lr_factor,
verbose=True)
else:
# these milestones are for when using the lung masks - not for unmasked lung data
scheduler = optim.lr_scheduler.MultiStepLR(
optimizer, milestones=[12, 16, 20,
24], gamma=lr_factor) # masked training
#scheduler = optim.lr_scheduler.MultiStepLR(optimizer, milestones=[14, 18, 22, 26], gamma=lr_factor)
loss_hist = collections.deque(maxlen=500)
retinanet.train()
retinanet.module.freeze_bn()
#initialize tensorboard
writer = SummaryWriter(comment=parser.model_output_dir)
# Augmentation
seq = iaa.Sequential([
iaa.Fliplr(0.5),
iaa.Flipud(0.5),
iaa.Affine(scale={
"x": (1.0, 1.2),
"y": (1.0, 1.2)
},
rotate=(-20, 20),
shear=(-4, 4))
],
random_order=True)
def augment(data, seq):
for n, img in enumerate(data['img']):
# imgaug needs dim in format (H, W, C)
image = data['img'][n].permute(1, 2, 0).numpy()
bbs_array = []
for ann in data['annot'][n]:
x1, y1, x2, y2, _ = ann
bbs_array.append(BoundingBox(x1=x1, y1=y1, x2=x2, y2=y2))
bbs = BoundingBoxesOnImage(bbs_array, shape=image.shape)
image_aug, bbs_aug = seq(image=image, bounding_boxes=bbs)
# save augmented image and chage dims to (C, H, W)
data['img'][n] = torch.tensor(image_aug.copy()).permute(2, 0, 1)
# save augmented annotations
for i, bbox in enumerate(bbs_aug.bounding_boxes):
x1, y1, x2, y2 = bbox.x1, bbox.y1, bbox.x2, bbox.y2
obj_class = data['annot'][n][i][-1]
data['annot'][n][i] = torch.tensor([x1, y1, x2, y2, obj_class])
return data
print('Num training images: {}'.format(len(dataset_train)))
dir_training_images = os.path.join(os.getcwd(), writer.log_dir,
'training_images')
os.mkdir(dir_training_images)
best_validation_loss = None
best_validation_map = None
for epoch_num in range(parser.epochs):
writer.add_scalar('Train/LR', optimizer.param_groups[0]['lr'],
epoch_num)
retinanet.train()
retinanet.module.freeze_bn()
epoch_loss = []
for iter_num, data in enumerate(dataloader_train):
try:
optimizer.zero_grad()
data = augment(data, seq)
# save a few training images to see what augmentation looks like
if iter_num % 100 == 0 and epoch_num == 0:
x1, y1, x2, y2, _ = data['annot'][0][0]
fig, ax = plt.subplots(1)
ax.imshow(data['img'][0][1])
rect = patches.Rectangle((x1, y1),
x2 - x1,
y2 - y1,
linewidth=1,
edgecolor='r',
facecolor='none',
alpha=1)
ax.add_patch(rect)
fig.savefig(
os.path.join(dir_training_images,
'{}.png'.format(iter_num)))
plt.close()
classification_loss, regression_loss = retinanet(
[data['img'].cuda().float(), data['annot']])
classification_loss = classification_loss.mean()
regression_loss = regression_loss.mean()
loss = classification_loss + regression_loss
if bool(loss == 0):
continue
loss.backward()
if parser.resnet_backbone_normalization == 'batch_norm':
torch.nn.utils.clip_grad_norm_(
parameters=retinanet.parameters(), max_norm=0.1)
else:
torch.nn.utils.clip_grad_norm_(
parameters=retinanet.parameters(), max_norm=0.01
) # Decrease norm to reduce risk of exploding gradients
optimizer.step()
loss_hist.append(float(loss))
epoch_loss.append(float(loss))
print(
'Epoch: {} | Iteration: {} | Classification loss: {:1.5f} | Regression loss: {:1.5f} | Running loss: {:1.5f}'
.format(epoch_num, iter_num, float(classification_loss),
float(regression_loss), np.mean(loss_hist)))
del classification_loss
del regression_loss
except Exception as e:
print(e)
continue
writer.add_scalar('Train/Loss', np.mean(epoch_loss), epoch_num)
if not parser.train_all_labeled_data:
print('Evaluating Validation Loss...')
with torch.no_grad():
retinanet.train()
val_losses, val_class_losses, val_reg_losses = [], [], []
for val_iter_num, val_data in enumerate(dataloader_val):
try:
val_classification_loss, val_regression_loss = retinanet(
[
val_data['img'].cuda().float(),
val_data['annot']
])
val_losses.append(
float(val_classification_loss) +
float(val_regression_loss))
val_class_losses.append(float(val_classification_loss))
val_reg_losses.append(float(val_regression_loss))
del val_classification_loss, val_regression_loss
except Exception as e:
print(e)
continue
print(
'VALIDATION Epoch: {} | Classification loss: {:1.5f} | Regression loss: {:1.5f} | Total loss: {:1.5f}'
.format(epoch_num, np.mean(val_class_losses),
np.mean(val_reg_losses), np.mean(val_losses)))
# Save model with best validation loss
if best_validation_loss is None:
best_validation_loss = np.mean(val_losses)
if best_validation_loss >= np.mean(val_losses):
best_validation_loss = np.mean(val_losses)
torch.save(
retinanet.module,
parser.model_output_dir + '/best_result_valloss.pt')
writer.add_scalar('Validation/Loss', np.mean(val_losses),
epoch_num)
# Calculate Validation mAP
print('Evaluating validation mAP')
mAP = csv_eval.evaluate(dataset_val, retinanet)
print("Validation mAP: " + str(mAP[0][0]))
if best_validation_map is None:
best_validation_map = mAP[0][0]
elif best_validation_map < mAP[0][0]:
best_validation_map = mAP[0][0]
torch.save(
retinanet.module,
parser.model_output_dir + '/best_result_valmAP.pt')
writer.add_scalar('Validation/mAP', mAP[0][0], epoch_num)
if not parser.train_all_labeled_data:
scheduler.step(np.mean(val_losses))
else:
scheduler.step()
torch.save(
retinanet.module,
parser.model_output_dir + '/retinanet_{}.pt'.format(epoch_num))
retinanet.eval()
torch.save(retinanet, parser.model_output_dir + '/model_final.pt')
def bbox_extraction(file_list='./data/images2.csv'):
weights_path = './models/csv_retinanet_25.pt'
csv_classes = './classes.csv'
dataset_val = CSVDataset(train_file=file_list,
class_list=csv_classes,
transform=transforms.Compose(
[Normalizer(), Resizer()]))
# dataset_val = CSVDataset(train_file=file_list, class_list= csv_classes, transform=transforms.Compose([Normalizer()]))
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=1,
drop_last=False)
dataloader_val = DataLoader(dataset_val,
num_workers=1,
collate_fn=collater,
batch_sampler=sampler_val)
retinanet = model.resnet50(num_classes=dataset_val.num_classes(),
pretrained=False)
retinanet.load_state_dict(torch.load(weights_path))
use_gpu = True
if torch.cuda.is_available():
device = torch.device("cuda")
if use_gpu:
retinanet = retinanet.to(device)
retinanet.eval()
unnormalize = UnNormalizer()
for idx, data in enumerate(dataloader_val):
with torch.no_grad():
scores, classification, transformed_anchors = retinanet(
data['img'].to(device).float())
def get_bbox(classification, transformed_anchors, label=0):
bbox = {}
idx = np.where(classification == label)[0][0]
co_ord = transformed_anchors[idx, :]
bbox['x1'] = int(co_ord[0])
bbox['y1'] = int(co_ord[1])
bbox['x2'] = int(co_ord[2])
bbox['y2'] = int(co_ord[3])
return bbox
scores = scores.cpu().numpy()
classification = classification.cpu().numpy()
transformed_anchors = transformed_anchors.cpu().numpy()
# print('scores:',scores)
# print('classification:', classification)
# print('transformed_anchors', transformed_anchors)
bbox = {}
bbox['neck'] = get_bbox(classification,
transformed_anchors,
label=0)
bbox['stomach'] = get_bbox(classification,
transformed_anchors,
label=1)
# print('neck',bbox['neck'] )
# print('stomach',bbox['stomach'] )
img = np.array(255 * unnormalize(data['img'][0, :, :, :])).copy()
img[img < 0] = 0
img[img > 255] = 255
img = np.transpose(img, (1, 2, 0))
img = cv2.cvtColor(img.astype(np.uint8), cv2.COLOR_BGR2RGB)
cv2.rectangle(img, (bbox['neck']['x1'], bbox['neck']['y1']),
(bbox['neck']['x2'], bbox['neck']['y2']),
color=(0, 0, 255),
thickness=2)
cv2.rectangle(img, (bbox['stomach']['x1'], bbox['stomach']['y1']),
(bbox['stomach']['x2'], bbox['stomach']['y2']),
color=(0, 0, 255),
thickness=2)
# cv2.imshow('img', img)
# cv2.imwrite('./sample_11.jpg',img)
# cv2.waitKey(0)
return bbox
# bbox_extraction()
# if __name__ == '__main__':
# main()
def main(args=None):
parser = argparse.ArgumentParser(
description='Simple training script for training a RetinaNet network.')
parser.add_argument('--dataset',
help='Dataset type, must be one of csv or coco.')
parser.add_argument('--coco_path', help='Path to COCO directory')
parser.add_argument('--csv_classes',
help='Path to file containing class list (see readme)')
parser.add_argument(
'--csv_val',
help=
'Path to file containing validation annotations (optional, see readme)'
)
parser.add_argument('--model', help='Path to model (.pt) file.')
parser = parser.parse_args(args)
if parser.dataset == 'coco':
dataset_val = CocoDataset(parser.coco_path,
set_name='val2017',
transform=transforms.Compose(
[Normalizer(), Resizer()]))
elif parser.dataset == 'csv':
dataset_val = CSVDataset(train_file=parser.csv_val,
class_list=parser.csv_classes,
transform=transforms.Compose(
[Normalizer(), Resizer()]))
else:
raise ValueError(
'Dataset type not understood (must be csv or coco), exiting.')
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=1,
drop_last=False)
dataloader_val = DataLoader(dataset_val,
num_workers=1,
collate_fn=collater,
batch_sampler=sampler_val)
#retinanet = torch.load(parser.model)
retinanet = model.resnet50(num_classes=80, pretrained=True)
retinanet.load_state_dict(torch.load(parser.model))
use_gpu = True
if use_gpu:
retinanet = retinanet.cuda()
retinanet.eval()
if not os.path.isdir("./detection_files"):
os.makedirs("./detection_files")
for idx, data in enumerate(dataloader_val):
with torch.no_grad():
st = time.time()
scores, classification, transformed_anchors = retinanet(
data['img'].cuda().float())
print('Elapsed time: {}'.format(time.time() - st))
idxs = np.where(scores > 0.35)
img_name = data['img_name'].split('.')[0]
with open("./detection_files/" + img_name + '.txt', 'w') as f:
for j in range(idxs[0].shape[0]):
bbox = transformed_anchors[idxs[0][j], :]
x1 = int(bbox[0])
y1 = int(bbox[1])
x2 = int(bbox[2])
y2 = int(bbox[3])
label_name = dataset_val.labels[int(
classification[idxs[0][j]])]
f.write('{},{},{},{},label_name'.format(
x1, y1, x2, y2, label_name))
if j < idxs[0].shape[0] - 1:
f.write('\n')
def main(args=None):
parser = argparse.ArgumentParser(description='Simple training script for training a RetinaNet network.')
parser.add_argument('--dataset',default="csv", help='Dataset type, must be one of csv or coco.')
parser.add_argument('--coco_path',default="/home/mayank-s/PycharmProjects/Datasets/coco",help='Path to COCO directory')
parser.add_argument('--csv_train',default="berkely_ready_to_train_for_retinanet_pytorch.csv", help='Path to file containing training annotations (see readme)')
parser.add_argument('--csv_classes',default="berkely_class.csv", help='Path to file containing class list (see readme)')
parser.add_argument('--csv_val', help='Path to file containing validation annotations (optional, see readme)')
parser.add_argument('--depth', help='Resnet depth, must be one of 18, 34, 50, 101, 152', type=int, default=50)
parser.add_argument('--epochs', help='Number of epochs', type=int, default=200)
# parser.add_argument('--resume', default=0, help='resume from checkpoint')
parser = parser.parse_args(args)
# print(args.resume)
# Create the data loaders
if parser.dataset == 'coco':
if parser.coco_path is None:
raise ValueError('Must provide --coco_path when training on COCO,')
dataset_train = CocoDataset(parser.coco_path, set_name='train2014', transform=transforms.Compose([Normalizer(), Augmenter(), Resizer()]))
dataset_val = CocoDataset(parser.coco_path, set_name='val2014', transform=transforms.Compose([Normalizer(), Resizer()]))
elif parser.dataset == 'csv':
if parser.csv_train is None:
raise ValueError('Must provide --csv_train when training on COCO,')
if parser.csv_classes is None:
raise ValueError('Must provide --csv_classes when training on COCO,')
dataset_train = CSVDataset(train_file=parser.csv_train, class_list=parser.csv_classes, transform=transforms.Compose([Normalizer(), Augmenter(), Resizer()]))
if parser.csv_val is None:
dataset_val = None
print('No validation annotations provided.')
else:
dataset_val = CSVDataset(train_file=parser.csv_val, class_list=parser.csv_classes, transform=transforms.Compose([Normalizer(), Resizer()]))
else:
raise ValueError('Dataset type not understood (must be csv or coco), exiting.')
sampler = AspectRatioBasedSampler(dataset_train, batch_size=4, drop_last=False)
dataloader_train = DataLoader(dataset_train, num_workers=0, collate_fn=collater, batch_sampler=sampler)
if dataset_val is not None:
sampler_val = AspectRatioBasedSampler(dataset_val, batch_size=1, drop_last=False)
dataloader_val = DataLoader(dataset_val, num_workers=3, collate_fn=collater, batch_sampler=sampler_val)
# Create the model
if parser.depth == 18:
retinanet = model.resnet18(num_classes=dataset_train.num_classes(), pretrained=True)
elif parser.depth == 34:
retinanet = model.resnet34(num_classes=dataset_train.num_classes(), pretrained=True)
elif parser.depth == 50:
retinanet = model.resnet50(num_classes=dataset_train.num_classes(), pretrained=True)
elif parser.depth == 101:
retinanet = model.resnet101(num_classes=dataset_train.num_classes(), pretrained=True)
elif parser.depth == 152:
retinanet = model.resnet152(num_classes=dataset_train.num_classes(), pretrained=True)
else:
raise ValueError('Unsupported model depth, must be one of 18, 34, 50, 101, 152')
use_gpu = True
# if use_gpu:
if torch.cuda.is_available():
retinanet = retinanet.cuda()
retinanet = torch.nn.DataParallel(retinanet).cuda()
retinanet.training = True
###################################################################################3
# # args.resume=0
# Resume_model = False
# start_epoch=0
# if Resume_model:
# print('==> Resuming from checkpoint..')
# checkpoint = torch.load('./checkpoint/saved_with_epochs/retina_fpn_1')
# retinanet.load_state_dict(checkpoint['net'])
# best_loss = checkpoint['loss']
# start_epoch = checkpoint['epoch']
# print('Resuming from epoch:{ep} loss:{lp}'.format(ep=start_epoch, lp=best_loss))
#####################################################################################
optimizer = optim.Adam(retinanet.parameters(), lr=1e-5)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, patience=3, verbose=True)
loss_hist = collections.deque(maxlen=500)
retinanet.train()
retinanet.module.freeze_bn()
print('Num training images: {}'.format(len(dataset_train)))
retinanet = torch.load("./checkpoint/retina_fpn_1")
# epoch_num=start_epoch
for epoch_num in range(parser.epochs):
# retinanet.train()retina_fpn_1
# retinanet.module.freeze_bn()
epoch_loss = []
for iter_num, data in enumerate(dataloader_train):
try:
optimizer.zero_grad()
if torch.cuda.is_available():
classification_loss, regression_loss = retinanet([data['img'].cuda().float(), data['annot']])
else:
classification_loss, regression_loss = retinanet([data['img'].float(), data['annot']])
classification_loss = classification_loss.mean()
regression_loss = regression_loss.mean()
loss = classification_loss + regression_loss
if bool(loss == 0):
continue
loss.backward()
torch.nn.utils.clip_grad_norm_(retinanet.parameters(), 0.1)
optimizer.step()
loss_hist.append(float(loss))
epoch_loss.append(float(loss))
print('Epoch: {} | Iteration: {} | Classification loss: {:1.5f} | Regression loss: {:1.5f} | Running loss: {:1.5f}'.format(epoch_num, iter_num, float(classification_loss), float(regression_loss), np.mean(loss_hist)))
del classification_loss
del regression_loss
except Exception as e:
print(e)
continue
# print("Saving model...")
# name = "./checkpoint/retina_fpn_" + str(epoch_num)
# torch.save(retinanet, name)
# ###################################################################333
print('Saving..')
state = {
'net': retinanet.module.state_dict(),
'loss': loss_hist,
'epoch': epoch_num,
}
if not os.path.isdir('checkpoint/saved_with_epochs'):
os.mkdir('checkpoint/saved_with_epochs')
# checkpoint_path="./checkpoint/Ckpt_"+
name = "./checkpoint/saved_with_epochs/retina_fpn_" + str(epoch_num)
torch.save(state, name)
# torch.save(state, './checkpoint/retinanet.pth')
#####################################################################
'''if parser.dataset == 'coco':
def main(args=None):
parser = argparse.ArgumentParser(
description='Simple training script for training a RetinaNet network.')
parser.add_argument('--dataset',
default="csv",
help='Dataset type, must be one of csv or coco.')
parser.add_argument('--coco_path', help='Path to COCO directory')
parser.add_argument(
'--csv_train',
default="./data/train_only.csv",
help='Path to file containing training annotations (see readme)')
parser.add_argument('--csv_classes',
default="./data/classes.csv",
help='Path to file containing class list (see readme)')
parser.add_argument(
'--csv_val',
default="./data/train_only.csv",
help=
'Path to file containing validation annotations (optional, see readme)'
)
parser.add_argument('--voc_train',
default="./data/voc_train",
help='Path to containing images and annAnnotations')
parser.add_argument('--voc_val',
default="./data/bov_train",
help='Path to containing images and annAnnotations')
parser.add_argument(
'--depth',
help='Resnet depth, must be one of 18, 34, 50, 101, 152',
type=int,
default=101)
parser.add_argument('--epochs',
help='Number of epochs',
type=int,
default=40)
parser = parser.parse_args(args)
# Create the data loaders
if parser.dataset == 'coco':
if parser.coco_path is None:
raise ValueError('Must provide --coco_path when training on COCO,')
dataset_train = CocoDataset(parser.coco_path,
set_name='train2017',
transform=transforms.Compose(
[Normalizer(),
Augmenter(),
Resizer()]))
dataset_val = CocoDataset(parser.coco_path,
set_name='val2017',
transform=transforms.Compose(
[Normalizer(), Resizer()]))
elif parser.dataset == 'csv':
if parser.csv_train is None:
raise ValueError('Must provide --csv_train when training on COCO,')
if parser.csv_classes is None:
raise ValueError(
'Must provide --csv_classes when training on COCO,')
dataset_train = CSVDataset(train_file=parser.csv_train,
class_list=parser.csv_classes,
transform=transforms.Compose(
[Normalizer(),
Augmenter(),
Resizer()]))
if parser.csv_val is None:
dataset_val = None
print('No validation annotations provided.')
else:
dataset_val = CSVDataset(train_file=parser.csv_val,
class_list=parser.csv_classes,
transform=transforms.Compose(
[Normalizer(),
Resizer()]))
elif parser.dataset == 'voc':
if parser.voc_train is None:
raise ValueError(
'Must provide --voc_train when training on PASCAL VOC,')
dataset_train = XML_VOCDataset(
img_path=parser.voc_train + 'JPEGImages/',
xml_path=parser.voc_train + 'Annotations/',
class_list=class_list,
transform=transforms.Compose(
[Normalizer(), Augmenter(),
ResizerMultiScale()]))
if parser.voc_val is None:
dataset_val = None
print('No validation annotations provided.')
else:
dataset_val = XML_VOCDataset(
img_path=parser.voc_val + 'JPEGImages/',
xml_path=parser.voc_val + 'Annotations/',
class_list=class_list,
transform=transforms.Compose([Normalizer(),
Resizer()]))
else:
raise ValueError(
'Dataset type not understood (must be csv or coco), exiting.')
sampler = AspectRatioBasedSampler(dataset_train,
batch_size=1,
drop_last=False)
dataloader_train = DataLoader(dataset_train,
num_workers=2,
collate_fn=collater,
batch_sampler=sampler)
if dataset_val is not None:
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=1,
drop_last=False)
dataloader_val = DataLoader(dataset_val,
num_workers=2,
collate_fn=collater,
batch_sampler=sampler_val)
# Create the model
if parser.depth == 18:
retinanet = model.resnet18(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 34:
retinanet = model.resnet34(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 50:
retinanet = model.resnet50(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 101:
retinanet = model.resnet101(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 152:
retinanet = model.resnet152(num_classes=dataset_train.num_classes(),
pretrained=True)
else:
raise ValueError(
'Unsupported model depth, must be one of 18, 34, 50, 101, 152')
use_gpu = True
if use_gpu:
retinanet = retinanet.cuda()
retinanet = torch.nn.DataParallel(retinanet).cuda()
retinanet.training = True
optimizer = optim.Adam(retinanet.parameters(), lr=1e-4)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer,
patience=15,
verbose=True,
mode="max")
#scheduler = optim.lr_scheduler.StepLR(optimizer,8)
loss_hist = collections.deque(maxlen=1024)
retinanet.train()
retinanet.module.freeze_bn()
if not os.path.exists("./logs"):
os.mkdir("./logs")
log_file = open("./logs/log.txt", "w")
print('Num training images: {}'.format(len(dataset_train)))
best_map = 0
print("Training models...")
for epoch_num in range(parser.epochs):
#scheduler.step(epoch_num)
retinanet.train()
retinanet.module.freeze_bn()
epoch_loss = []
for iter_num, data in enumerate(dataloader_train):
#print('iter num is: ', iter_num)
try:
#print(csv_eval.evaluate(dataset_val[:20], retinanet)[0])
#print(type(csv_eval.evaluate(dataset_val, retinanet)))
#print('iter num is: ', iter_num % 10 == 0)
optimizer.zero_grad()
classification_loss, regression_loss = retinanet(
[data['img'].cuda().float(), data['annot']])
classification_loss = classification_loss.mean()
regression_loss = regression_loss.mean()
loss = classification_loss + regression_loss
#print(loss)
if bool(loss == 0):
continue
loss.backward()
torch.nn.utils.clip_grad_norm_(retinanet.parameters(), 0.1)
optimizer.step()
loss_hist.append(float(loss))
epoch_loss.append(float(loss))
if iter_num % 50 == 0:
print(
'Epoch: {} | Iteration: {} | Classification loss: {:1.5f} | Regression loss: {:1.5f} | Running loss: {:1.5f}'
.format(epoch_num, iter_num,
float(classification_loss),
float(regression_loss), np.mean(loss_hist)))
log_file.write(
'Epoch: {} | Iteration: {} | Classification loss: {:1.5f} | Regression loss: {:1.5f} | Running loss: {:1.5f} \n'
.format(epoch_num, iter_num,
float(classification_loss),
float(regression_loss), np.mean(loss_hist)))
del classification_loss
del regression_loss
except Exception as e:
print(e)
continue
if parser.dataset == 'coco':
print('Evaluating dataset')
coco_eval.evaluate_coco(dataset_val, retinanet)
elif parser.dataset == 'csv' and parser.csv_val is not None:
print('Evaluating dataset')
mAP = csv_eval.evaluate(dataset_val, retinanet)
elif parser.dataset == 'voc' and parser.voc_val is not None:
print('Evaluating dataset')
mAP = voc_eval.evaluate(dataset_val, retinanet)
try:
is_best_map = mAP[0][0] > best_map
best_map = max(mAP[0][0], best_map)
except:
pass
if is_best_map:
print("Get better map: ", best_map)
torch.save(retinanet.module,
'./logs/{}_scale15_{}.pt'.format(epoch_num, best_map))
shutil.copyfile(
'./logs/{}_scale15_{}.pt'.format(epoch_num, best_map),
"./best_models/model.pt")
else:
print("Current map: ", best_map)
scheduler.step(best_map)
retinanet.eval()
torch.save(retinanet, './logs/model_final.pt')
def visualize(csv_val, csv_classes, model):
dataset = "csv"
if dataset == 'csv':
dataset_val = CSVDataset(train_file=csv_val,
class_list=csv_classes,
transform=transforms.Compose(
[Normalizer(), Resizer()]))
else:
raise ValueError(
'Dataset type not understood (must be csv or coco), exiting.')
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=1,
drop_last=False)
dataloader_val = DataLoader(dataset_val,
num_workers=1,
collate_fn=collater,
batch_sampler=sampler_val)
retinanet = torch.load(model)
use_gpu = True
if use_gpu:
retinanet = retinanet.cuda()
retinanet.eval()
unnormalize = UnNormalizer()
def draw_caption(image, box, caption):
b = np.array(box).astype(int)
cv2.putText(image, caption, (b[0], b[1] - 10), cv2.FONT_HERSHEY_PLAIN,
1, (0, 0, 0), 2)
cv2.putText(image, caption, (b[0], b[1] - 10), cv2.FONT_HERSHEY_PLAIN,
1, (0, 180, 0), 1)
def draw_caption_original(image, box, caption):
b = np.array(box).astype(int)
#print("b", b)
cv2.putText(image, caption, (b[0], b[3] + 20), cv2.FONT_HERSHEY_PLAIN,
1, (0, 0, 0), 2)
cv2.putText(image, caption, (b[0], b[3] + 20), cv2.FONT_HERSHEY_PLAIN,
1, (0, 0, 180), 1) #B
kaggle_ouput = []
for idx, data in enumerate(dataloader_val):
print(idx)
kaggle_row = []
with torch.no_grad():
st = time.time()
#print("data shape:", data['img'].shape)
scores, classification, transformed_anchors = retinanet(
data['img'].cuda().float())
#print('Elapsed time: {}'.format(time.time()-st))
idxs = np.where(scores > 0.5)
img = np.array(255 * unnormalize(data['img'][0, :, :, :])).copy()
print('Scores', scores)
#print("name", data['name'])
img[img < 0] = 0
img[img > 255] = 255
img = np.transpose(img, (1, 2, 0))
img = cv2.cvtColor(img.astype(np.uint8), cv2.COLOR_BGR2RGB)
kaggle_row.append(get_filename(data['name'][0]))
row = ''
for j in range(idxs[0].shape[0]):
bbox = transformed_anchors[idxs[0][j], :]
x1 = int(bbox[0])
y1 = int(bbox[1])
x2 = int(bbox[2])
y2 = int(bbox[3])
label_name = dataset_val.labels[int(
classification[idxs[0][j]])]
draw_caption(img, (x1, y1, x2, y2), "Predicted opacity")
cv2.rectangle(img, (x1, y1), (x2, y2),
color=(0, 255, 0),
thickness=2)
#print(x1, y1, x2, y2)
if (j == 0):
row = row + str(round(
scores[j].item(), 2)) + " " + str(x1) + ' ' + str(
y1) + ' ' + str(x2 - x1) + ' ' + str(y2 - y1)
pass
else:
row = row + " " + str(round(
scores[j].item(), 2)) + " " + str(x1) + ' ' + str(
y1) + ' ' + str(x2 - x1) + ' ' + str(y2 - y1)
for ann in data['annot']:
for annotation in ann:
#print("Original annot:", ann)
if annotation[0] != -1:
draw_caption_original(img,
(annotation[0], annotation[1],
annotation[2], annotation[3]),
"Real opacity")
cv2.rectangle(img, (annotation[0], annotation[1]),
(annotation[2], annotation[3]),
color=(0, 0, 255),
thickness=2)
pass
cv2.imshow('img', img)
kaggle_row.append(row)
#print(kaggle_row)
#print(idxs)
kaggle_ouput.append(kaggle_row)
cv2.waitKey(0)
import pandas as pd
pd.DataFrame(kaggle_ouput, columns=[
'patientId', 'PredictionString'
]).to_csv("/home/jdmaestre/PycharmProjects/test_kaggle.csv")
def main(args=None):
parser = argparse.ArgumentParser(
description='Simple testing script for RetinaNet network.')
parser.add_argument('--dataset',
help='Dataset type, must be one of csv or coco.',
default="csv")
parser.add_argument('--coco_path', help='Path to COCO directory')
parser.add_argument('--csv_classes',
help='Path to file containing class list (see readme)',
default="binary_class.csv")
parser.add_argument(
'--csv_val',
help=
'Path to file containing validation annotations (optional, see readme)'
)
parser.add_argument(
'--csv_box_annot',
help='Path to file containing predicted box annotations ')
parser.add_argument(
'--depth',
help='Resnet depth, must be one of 18, 34, 50, 101, 152',
type=int,
default=18)
parser.add_argument('--epochs',
help='Number of epochs',
type=int,
default=500)
parser.add_argument('--model',
help='Path of .pt file with trained model',
default='esposallescsv_retinanet_0.pt')
parser.add_argument('--model_out',
help='Path of .pt file with trained model to save',
default='trained')
parser.add_argument('--score_threshold',
help='Score above which boxes are kept',
default=0.15)
parser.add_argument('--nms_threshold',
help='Score above which boxes are kept',
default=0.2)
parser.add_argument('--max_epochs_no_improvement',
help='Max epochs without improvement',
default=100)
parser.add_argument('--max_boxes',
help='Max boxes to be fed to recognition',
default=50)
parser.add_argument('--seg_level',
help='Line or word, to choose anchor aspect ratio',
default='line')
parser.add_argument(
'--htr_gt_box',
help='Train recognition branch with box gt (for debugging)',
default=False)
parser.add_argument(
'--binary_classifier',
help=
'Wether to use classification branch as binary or not, multiclass instead.',
default='False')
parser = parser.parse_args(args)
# Create the data loaders
if parser.dataset == 'csv':
if parser.csv_classes is None:
raise ValueError(
'Must provide --csv_classes when training on COCO,')
if parser.csv_val is None:
dataset_val = None
print('No validation annotations provided.')
else:
dataset_val = CSVDataset(train_file=parser.csv_val,
class_list=parser.csv_classes,
transform=transforms.Compose(
[Normalizer(),
Resizer()]))
if parser.csv_box_annot is not None:
box_annot_data = CSVDataset(train_file=parser.csv_box_annot,
class_list=parser.csv_classes,
transform=transforms.Compose(
[Normalizer(),
Resizer()]))
else:
box_annot_data = None
else:
raise ValueError(
'Dataset type not understood (must be csv or coco), exiting.')
if dataset_val is not None:
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=1,
drop_last=False)
dataloader_val = DataLoader(dataset_val,
num_workers=0,
collate_fn=collater,
batch_sampler=sampler_val)
if box_annot_data is not None:
sampler_val = AspectRatioBasedSampler(box_annot_data,
batch_size=1,
drop_last=False)
dataloader_box_annot = DataLoader(box_annot_data,
num_workers=0,
collate_fn=collater,
batch_sampler=sampler_val)
else:
dataloader_box_annot = dataloader_val
if not os.path.exists('trained_models'):
os.mkdir('trained_models')
# Create the model
alphabet = dataset_val.alphabet
if os.path.exists(parser.model):
retinanet = torch.load(parser.model)
else:
print("Choose an existing saved model path.")
sys.exit()
use_gpu = True
if use_gpu:
retinanet = retinanet.cuda()
retinanet = torch.nn.DataParallel(retinanet).cuda()
#retinanet = torch.load('../Documents/TRAINED_MODELS/pytorch-retinanet/esposallescsv_retinanet_99.pt')
#print "LOADED pretrained MODEL\n\n"
optimizer = optim.Adam(retinanet.parameters(), lr=1e-4)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer,
patience=4,
verbose=True)
loss_hist = collections.deque(maxlen=500)
ctc = CTCLoss()
retinanet.module.freeze_bn()
best_cer = 1000
epochs_no_improvement = 0
cers = []
retinanet.eval()
retinanet.module.epochs_only_det = 0
#retinanet.module.htr_gt_box = False
retinanet.training = False
if parser.score_threshold is not None:
retinanet.module.score_threshold = float(parser.score_threshold)
'''if parser.dataset == 'csv' and parser.csv_val is not None:
print('Evaluating dataset')
'''
mAP, binary_mAP, cer = csv_eval.evaluate(
dataset_val,
retinanet,
score_threshold=retinanet.module.score_threshold)
from torch.utils.data import Dataset, DataLoader
from dataloader import CocoDataset, CSVDataset, collater, Resizer, AspectRatioBasedSampler, Augmenter, UnNormalizer, Normalizer, TXTDataset
from torchvision import datasets, models, transforms
import argparse
import csv_eval
ap = argparse.ArgumentParser(description='Just for eval.')
ap.add_argument('-B', '--ImageNamePath')
ap.add_argument('-A', '--AnnotationPath')
ap.add_argument('-I', '--ImagePath')
args = vars(ap.parse_args())
dataset_val = TXTDataset(ImgNamePth=args['ImageNamePath'],
AnnoPth=args['AnnotationPath'],
ImgPth=args['ImagePath'],
transform=transforms.Compose(
[Normalizer(), Resizer()]))
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=1,
drop_last=False)
dataloader_val = DataLoader(dataset_val,
num_workers=3,
collate_fn=collater,
batch_sampler=sampler_val)
modelpath = os.path.join(os.path.dirname(__file__), 'weights/model.pt')
modelretina = torch.load(modelpath)
modelretina.cuda()
modelretina.eval()
AP = csv_eval.evaluate(dataset_val, modelretina)
map = (AP[0][0] + AP[1][0]) / 2
print("mAp:" + str(map))
def main():
data_type = 'coco'
data_root_dir = '/data/data_coco/'
# model_depth = 50
epoch_max = 100
batch_size = 8
if data_type == 'coco':
dataset_train = CocoDataset(data_root_dir,
set_name='train2017',
transform=transforms.Compose(
[Normalizer(),
Augmenter(),
Resizer()]))
dataset_val = CocoDataset(data_root_dir,
set_name='val2017',
transform=transforms.Compose(
[Normalizer(), Resizer()]))
else:
print('暂不支持')
sampler = AspectRatioBasedSampler(dataset_train,
batch_size=batch_size,
drop_last=True)
loader_train = DataLoader(dataset_train,
num_workers=8,
collate_fn=collater,
batch_sampler=sampler)
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=batch_size,
drop_last=True)
loader_val = DataLoader(dataset_val,
num_workers=8,
collate_fn=collater,
batch_sampler=sampler_val)
retinanet = model.retinanet_50(dataset_train.num_classes(),
pretrained=True)
retinanet = retinanet.cuda()
optimizer = torch.optim.Adam(retinanet.parameters(), lr=1e-4)
# optimizer = torch.optim.SGD(retinanet.parameters(), lr=1e-4, momentum=0.9, weight_decay=5e-4)
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer,
patience=3,
verbose=True,
factor=0.5)
model_pretrain_dir = './model/model_final.pt'
if os.path.exists(model_pretrain_dir):
print('pretrain model exist!')
retinanet = torch.load(model_pretrain_dir)
print('train images num: {}'.format(len(loader_train) * batch_size))
for epoch_num in range(epoch_max):
retinanet.train()
epoch_loss = []
for iter_num, data in enumerate(loader_train):
optimizer.zero_grad()
input_tensor = [data['img'].cuda().float(), data['annot']]
classification_loss, regression_loss = retinanet(input_tensor)
classification_loss = classification_loss.mean()
regression_loss = regression_loss.mean()
loss = classification_loss + regression_loss
epoch_loss.append(float(loss))
if loss.item() == 0:
continue
loss.backward()
optimizer.step()
print(
'Epoch:{}/{} | Iters:{}/{} | C loss:{:.4f} | R loss:{:.4f} | Current loss:{:.4f} | Current LR:{:.7f}'
.format(epoch_num + 1, epoch_max, iter_num + 1,
len(loader_train), float(classification_loss),
float(regression_loss), np.mean(epoch_loss),
optimizer.param_groups[0]['lr']))
del classification_loss
del regression_loss
# 每个epoch 进行验证一次
eval.eval_coco(dataset_val, retinanet)
scheduler.step(np.mean(epoch_loss))
torch.save(
retinanet,
'./model/{}_retinanet_{}.pt'.format(data_type, epoch_num + 1))
retinanet.eval()
torch.save(retinanet, './model/model_final.pt')
def main(args=None):
parser = argparse.ArgumentParser(description='Training script for training a EfficientDet network.')
parser.add_argument('--dataset', help='Dataset type, must be one of csv or coco.')
parser.add_argument('--coco_path', help='Path to COCO directory')
parser.add_argument('--csv_train', help='Path to file containing training annotations (see readme)')
parser.add_argument('--csv_classes', help='Path to file containing class list (see readme)')
parser.add_argument('--csv_val', help='Path to file containing validation annotations (optional, see readme)')
parser.add_argument('--phi', help='EfficientNet scaling coefficient.', type=int, default=0)
parser.add_argument('--batch-size', help='Batch size', type=int, default=8)
parser.add_argument('--epochs', help='Number of epochs', type=int, default=100)
parser = parser.parse_args(args)
# Create the data loaders
if parser.dataset == 'coco':
if parser.coco_path is None:
raise ValueError('Must provide --coco_path when training on COCO,')
dataset_train = CocoDataset(parser.coco_path, set_name='train2017', transform=transforms.Compose([Normalizer(), Augmenter(), Resizer(img_size=512)]))
dataset_val = CocoDataset(parser.coco_path, set_name='val2017', transform=transforms.Compose([Normalizer(), Resizer(img_size=512)]))
elif parser.dataset == 'csv':
if parser.csv_train is None:
raise ValueError('Must provide --csv_train when training on COCO')
if parser.csv_classes is None:
raise ValueError('Must provide --csv_classes when training on COCO')
dataset_train = CSVDataset(train_file=parser.csv_train, class_list=parser.csv_classes, transform=transforms.Compose([Normalizer(), Augmenter(), Resizer()]))
if parser.csv_val is None:
dataset_val = None
print('No validation annotations provided.')
else:
dataset_val = CSVDataset(train_file=parser.csv_val, class_list=parser.csv_classes, transform=transforms.Compose([Normalizer(), Resizer()]))
else:
raise ValueError('Dataset type not understood (must be csv or coco), exiting.')
sampler = AspectRatioBasedSampler(dataset_train, batch_size=parser.batch_size, drop_last=False)
dataloader_train = DataLoader(dataset_train, num_workers=3, collate_fn=collater, batch_sampler=sampler)
if dataset_val is not None:
sampler_val = AspectRatioBasedSampler(dataset_val, batch_size=1, drop_last=False)
dataloader_val = DataLoader(dataset_val, num_workers=3, collate_fn=collater, batch_sampler=sampler_val)
# Create the model
efficientdet = model.efficientdet(num_classes=dataset_train.num_classes(), pretrained=True, phi=parser.phi)
use_gpu = True
if use_gpu:
efficientdet = efficientdet.cuda()
efficientdet = torch.nn.DataParallel(efficientdet).cuda()
efficientdet.training = True
optimizer = optim.Adam(efficientdet.parameters(), lr=1e-5)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, patience=3, verbose=True)
loss_hist = collections.deque(maxlen=500)
efficientdet.train()
efficientdet.module.freeze_bn()
print('Num training images: {}'.format(len(dataset_train)))
for epoch_num in range(parser.epochs):
efficientdet.train()
efficientdet.module.freeze_bn()
epoch_loss = []
print(('\n' + '%10s' * 5) % ('Epoch', 'gpu_mem', 'Loss', 'cls', 'rls'))
pbar = tqdm(enumerate(dataloader_train), total=len(dataloader_train))
for iter_num, data in pbar:
try:
optimizer.zero_grad()
classification_loss, regression_loss = efficientdet([data['img'].cuda().float(), data['annot']])
classification_loss = classification_loss.mean()
regression_loss = regression_loss.mean()
loss = classification_loss + regression_loss
if bool(loss == 0):
continue
loss.backward()
torch.nn.utils.clip_grad_norm_(efficientdet.parameters(), 0.1)
optimizer.step()
loss_hist.append(float(loss))
epoch_loss.append(float(loss))
loss = (loss * iter_num) / (iter_num + 1) # update mean losses
mem = torch.cuda.memory_cached() / 1E9 if torch.cuda.is_available() else 0 # (GB)
s = ('%10s' * 2 + '%10.3g' * 3) % (
'%g/%g' % (epoch_num, parser.epochs - 1), '%.3gG' % mem, np.mean(loss_hist), float(regression_loss), float(classification_loss))
pbar.set_description(s)
del classification_loss
del regression_loss
except Exception as e:
raise(e)
continue
if parser.dataset == 'coco':
print('Evaluating dataset')
coco_eval.evaluate_coco(dataset_val, efficientdet)
elif parser.dataset == 'csv' and parser.csv_val is not None:
print('Evaluating dataset')
mAP = csv_eval.evaluate(dataset_val, efficientdet)
scheduler.step(np.mean(epoch_loss))
torch.save(efficientdet.module, '{}_retinanet_{}.pt'.format(parser.dataset, epoch_num))
efficientdet.eval()
torch.save(efficientdet, 'model_final.pt'.format(epoch_num))
def main(args=None):
parser = argparse.ArgumentParser(
description='Simple training script for training a RetinaNet network.')
parser.add_argument('--dataset',
help='Dataset type, must be one of csv or coco.',
default="csv")
parser.add_argument('--coco_path', help='Path to COCO directory')
parser.add_argument(
'--csv_train',
help='Path to file containing training annotations (see readme)')
parser.add_argument('--csv_classes',
help='Path to file containing class list (see readme)',
default="binary_class.csv")
parser.add_argument(
'--csv_val',
help=
'Path to file containing validation annotations (optional, see readme)'
)
parser.add_argument(
'--depth',
help='Resnet depth, must be one of 18, 34, 50, 101, 152',
type=int,
default=18)
parser.add_argument('--epochs',
help='Number of epochs',
type=int,
default=500)
parser.add_argument('--epochs_only_det',
help='Number of epochs to train detection part',
type=int,
default=1)
parser.add_argument('--max_epochs_no_improvement',
help='Max epochs without improvement',
type=int,
default=100)
parser.add_argument('--pretrained_model',
help='Path of .pt file with pretrained model',
default='esposallescsv_retinanet_0.pt')
parser.add_argument('--model_out',
help='Path of .pt file with trained model to save',
default='trained')
parser.add_argument('--score_threshold',
help='Score above which boxes are kept',
type=float,
default=0.5)
parser.add_argument('--nms_threshold',
help='Score above which boxes are kept',
type=float,
default=0.2)
parser.add_argument('--max_boxes',
help='Max boxes to be fed to recognition',
default=95)
parser.add_argument('--seg_level',
help='[line, word], to choose anchor aspect ratio',
default='word')
parser.add_argument(
'--early_stop_crit',
help='Early stop criterion, detection (map) or transcription (cer)',
default='cer')
parser.add_argument('--max_iters_epoch',
help='Max steps per epoch (for debugging)',
default=1000000)
parser.add_argument('--train_htr',
help='Train recognition or not',
default='True')
parser.add_argument('--train_det',
help='Train detection or not',
default='True')
parser.add_argument(
'--binary_classifier',
help=
'Wether to use classification branch as binary or not, multiclass instead.',
default='False')
parser.add_argument(
'--htr_gt_box',
help='Train recognition branch with box gt (for debugging)',
default='False')
parser.add_argument(
'--ner_branch',
help='Train named entity recognition with separate branch',
default='False')
parser = parser.parse_args(args)
if parser.dataset == 'csv':
if parser.csv_train is None:
raise ValueError('Must provide --csv_train')
dataset_name = parser.csv_train.split("/")[-2]
dataset_train = CSVDataset(train_file=parser.csv_train,
class_list=parser.csv_classes,
transform=transforms.Compose(
[Normalizer(),
Augmenter(),
Resizer()]))
if parser.csv_val is None:
dataset_val = None
print('No validation annotations provided.')
else:
dataset_val = CSVDataset(train_file=parser.csv_val,
class_list=parser.csv_classes,
transform=transforms.Compose(
[Normalizer(),
Resizer()]))
else:
raise ValueError(
'Dataset type not understood (must be csv or coco), exiting.')
# Files for training log
experiment_id = str(time.time()).split('.')[0]
valid_cer_f = open('trained_models/' + parser.model_out + 'log.txt', 'w')
for arg in vars(parser):
if getattr(parser, arg) is not None:
valid_cer_f.write(
str(arg) + ' ' + str(getattr(parser, arg)) + '\n')
current_commit = subprocess.check_output(['git', 'rev-parse', 'HEAD'])
valid_cer_f.write(str(current_commit))
valid_cer_f.write(
"epoch_num cer best cer mAP best mAP time\n")
valid_cer_f.close()
sampler = AspectRatioBasedSampler(dataset_train,
batch_size=1,
drop_last=False)
dataloader_train = DataLoader(dataset_train,
num_workers=3,
collate_fn=collater,
batch_sampler=sampler)
if dataset_val is not None:
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=1,
drop_last=False)
dataloader_val = DataLoader(dataset_val,
num_workers=0,
collate_fn=collater,
batch_sampler=sampler_val)
if not os.path.exists('trained_models'):
os.mkdir('trained_models')
# Create the model
train_htr = parser.train_htr == 'True'
htr_gt_box = parser.htr_gt_box == 'True'
ner_branch = parser.ner_branch == 'True'
binary_classifier = parser.binary_classifier == 'True'
torch.backends.cudnn.benchmark = False
alphabet = dataset_train.alphabet
if os.path.exists(parser.pretrained_model):
retinanet = torch.load(parser.pretrained_model)
retinanet.classificationModel = ClassificationModel(
num_features_in=256,
num_anchors=retinanet.anchors.num_anchors,
num_classes=dataset_train.num_classes())
if ner_branch:
retinanet.nerModel = NERModel(
feature_size=256,
pool_h=retinanet.pool_h,
n_classes=dataset_train.num_classes(),
pool_w=retinanet.pool_w)
else:
if parser.depth == 18:
retinanet = model.resnet18(num_classes=dataset_train.num_classes(),
pretrained=True,
max_boxes=int(parser.max_boxes),
score_threshold=float(
parser.score_threshold),
seg_level=parser.seg_level,
alphabet=alphabet,
train_htr=train_htr,
htr_gt_box=htr_gt_box,
ner_branch=ner_branch,
binary_classifier=binary_classifier)
elif parser.depth == 34:
retinanet = model.resnet34(num_classes=dataset_train.num_classes(),
pretrained=True,
max_boxes=int(parser.max_boxes),
score_threshold=float(
parser.score_threshold),
seg_level=parser.seg_level,
alphabet=alphabet,
train_htr=train_htr,
htr_gt_box=htr_gt_box)
elif parser.depth == 50:
retinanet = model.resnet50(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 101:
retinanet = model.resnet101(
num_classes=dataset_train.num_classes(), pretrained=True)
elif parser.depth == 152:
retinanet = model.resnet152(
num_classes=dataset_train.num_classes(), pretrained=True)
else:
raise ValueError(
'Unsupported model depth, must be one of 18, 34, 50, 101, 152')
use_gpu = True
train_htr = parser.train_htr == 'True'
train_det = parser.train_det == 'True'
retinanet.htr_gt_box = parser.htr_gt_box == 'True'
retinanet.train_htr = train_htr
retinanet.epochs_only_det = parser.epochs_only_det
if use_gpu:
retinanet = retinanet.cuda()
retinanet = torch.nn.DataParallel(retinanet).cuda()
retinanet.training = True
optimizer = optim.Adam(retinanet.parameters(), lr=1e-4)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer,
patience=50,
verbose=True)
loss_hist = collections.deque(maxlen=500)
ctc = CTCLoss()
retinanet.train()
retinanet.module.freeze_bn()
best_cer = 1000
best_map = 0
epochs_no_improvement = 0
verbose_each = 20
optimize_each = 1
objective = 100
best_objective = 10000
print(('Num training images: {}'.format(len(dataset_train))))
for epoch_num in range(parser.epochs):
cers = []
retinanet.training = True
retinanet.train()
retinanet.module.freeze_bn()
epoch_loss = []
for iter_num, data in enumerate(dataloader_train):
if iter_num > int(parser.max_iters_epoch): break
try:
if iter_num % optimize_each == 0:
optimizer.zero_grad()
(classification_loss, regression_loss, ctc_loss,
ner_loss) = retinanet([
data['img'].cuda().float(), data['annot'], ctc, epoch_num
])
classification_loss = classification_loss.mean()
regression_loss = regression_loss.mean()
if train_det:
if train_htr:
loss = ctc_loss + classification_loss + regression_loss + ner_loss
else:
loss = classification_loss + regression_loss + ner_loss
elif train_htr:
loss = ctc_loss
else:
continue
if bool(loss == 0):
continue
loss.backward()
torch.nn.utils.clip_grad_norm_(retinanet.parameters(), 0.1)
if iter_num % verbose_each == 0:
print((
'Epoch: {} | Step: {} |Classification loss: {:1.5f} | Regression loss: {:1.5f} | CTC loss: {:1.5f} | NER loss: {:1.5f} | Running loss: {:1.5f} | Total loss: {:1.5f}\r'
.format(epoch_num, iter_num,
float(classification_loss),
float(regression_loss), float(ctc_loss),
float(ner_loss), np.mean(loss_hist),
float(loss), "\r")))
optimizer.step()
loss_hist.append(float(loss))
epoch_loss.append(float(loss))
torch.cuda.empty_cache()
except Exception as e:
print(e)
continue
if parser.dataset == 'csv' and parser.csv_val is not None and train_det:
print('Evaluating dataset')
mAP, text_mAP, current_cer = csv_eval.evaluate(
dataset_val, retinanet, score_threshold=parser.score_threshold)
#text_mAP,_ = csv_eval_binary_map.evaluate(dataset_val, retinanet,score_threshold=parser.score_threshold)
objective = current_cer * (1 - mAP)
retinanet.eval()
retinanet.training = False
retinanet.score_threshold = float(parser.score_threshold)
'''for idx,data in enumerate(dataloader_val):
if idx>int(parser.max_iters_epoch): break
print("Eval CER on validation set:",idx,"/",len(dataset_val),"\r")
image_name = dataset_val.image_names[idx].split('/')[-1].split('.')[-2]
#generate_pagexml(image_name,data,retinanet,parser.score_threshold,parser.nms_threshold,dataset_val)
text_gt =".".join(dataset_val.image_names[idx].split('.')[:-1])+'.txt'
f =open(text_gt,'r')
text_gt_lines=f.readlines()[0]
transcript_pred = get_transcript(image_name,data,retinanet,float(parser.score_threshold),float(parser.nms_threshold),dataset_val,alphabet)
cers.append(float(editdistance.eval(transcript_pred,text_gt_lines))/len(text_gt_lines))'''
t = str(time.time()).split('.')[0]
valid_cer_f.close()
#print("GT",text_gt_lines)
#print("PREDS SAMPLE:",transcript_pred)
if parser.early_stop_crit == 'cer':
if float(objective) < float(
best_objective): #float(current_cer)<float(best_cer):
best_cer = current_cer
best_objective = objective
epochs_no_improvement = 0
torch.save(
retinanet.module, 'trained_models/' + parser.model_out +
'{}_retinanet.pt'.format(parser.dataset))
else:
epochs_no_improvement += 1
if mAP > best_map:
best_map = mAP
elif parser.early_stop_crit == 'map':
if mAP > best_map:
best_map = mAP
epochs_no_improvement = 0
torch.save(
retinanet.module, 'trained_models/' + parser.model_out +
'{}_retinanet.pt'.format(parser.dataset))
else:
epochs_no_improvement += 1
if float(current_cer) < float(best_cer):
best_cer = current_cer
if train_det:
print(epoch_num, "mAP: ", mAP, " best mAP", best_map)
if train_htr:
print("VALID CER:", current_cer, "best CER", best_cer)
print("Epochs no improvement:", epochs_no_improvement)
valid_cer_f = open('trained_models/' + parser.model_out + 'log.txt',
'a')
valid_cer_f.write(
str(epoch_num) + " " + str(current_cer) + " " + str(best_cer) +
' ' + str(mAP) + ' ' + str(best_map) + ' ' + str(text_mAP) + '\n')
if epochs_no_improvement > 3:
for param_group in optimizer.param_groups:
if param_group['lr'] > 10e-5:
param_group['lr'] *= 0.1
if epochs_no_improvement >= parser.max_epochs_no_improvement:
print("TRAINING FINISHED AT EPOCH", epoch_num, ".")
sys.exit()
scheduler.step(np.mean(epoch_loss))
torch.cuda.empty_cache()
retinanet.eval()
def main(args=None):
parser = argparse.ArgumentParser(
description='Simple training script for training a RetinaNet network.')
parser.add_argument('--dataset',
help='Dataset type, must be one of csv or coco.')
parser.add_argument('--coco_path', help='Path to COCO directory')
parser.add_argument(
'--csv_train',
help='Path to file containing training annotations (see readme)')
parser.add_argument('--csv_classes',
help='Path to file containing class list (see readme)')
parser.add_argument(
'--csv_val',
help=
'Path to file containing validation annotations (optional, see readme)'
)
parser.add_argument(
'--depth',
help='Resnet depth, must be one of 18, 34, 50, 101, 152',
type=int,
default=50)
parser.add_argument('--epochs',
help='Number of epochs',
type=int,
default=100)
parser.add_argument('--optimizer',
help='[SGD | Adam]',
type=str,
default='SGD')
parser.add_argument('--model', help='Path to model (.pt) file.')
parser = parser.parse_args(args)
# Create the data loaders
print("\n[Phase 1]: Creating DataLoader for {} dataset".format(
parser.dataset))
if parser.dataset == 'coco':
if parser.coco_path is None:
raise ValueError('Must provide --coco_path when training on COCO,')
dataset_train = CocoDataset(parser.coco_path,
set_name='train2014',
transform=transforms.Compose(
[Normalizer(),
Augmenter(),
Resizer()]))
dataset_val = CocoDataset(parser.coco_path,
set_name='val2014',
transform=transforms.Compose(
[Normalizer(), Resizer()]))
elif parser.dataset == 'csv':
if parser.csv_train is None:
raise ValueError('Must provide --csv_train when training on COCO,')
if parser.csv_classes is None:
raise ValueError(
'Must provide --csv_classes when training on COCO,')
dataset_train = CSVDataset(train_file=parser.csv_train,
class_list=parser.csv_classes,
transform=transforms.Compose(
[Normalizer(),
Augmenter(),
Resizer()]))
if parser.csv_val is None:
dataset_val = None
print('No validation annotations provided.')
else:
dataset_val = CSVDataset(train_file=parser.csv_val,
class_list=parser.csv_classes,
transform=transforms.Compose(
[Normalizer(),
Resizer()]))
else:
raise ValueError(
'Dataset type not understood (must be csv or coco), exiting.')
sampler = AspectRatioBasedSampler(dataset_train,
batch_size=8,
drop_last=False)
dataloader_train = DataLoader(dataset_train,
num_workers=8,
collate_fn=collater,
batch_sampler=sampler)
if dataset_val is not None:
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=16,
drop_last=False)
dataloader_val = DataLoader(dataset_val,
num_workers=8,
collate_fn=collater,
batch_sampler=sampler_val)
# Create the model
if parser.depth == 18:
retinanet = model.resnet18(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 34:
retinanet = model.resnet34(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 50:
retinanet = model.resnet50(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 101:
retinanet = model.resnet101(num_classes=dataset_train.num_classes(),
pretrained=True)
elif parser.depth == 152:
retinanet = model.resnet152(num_classes=dataset_train.num_classes(),
pretrained=True)
else:
raise ValueError(
'Unsupported model depth, must be one of 18, 34, 50, 101, 152')
print('| Num training images: {}'.format(len(dataset_train)))
print('| Num test images : {}'.format(len(dataset_val)))
print("\n[Phase 2]: Preparing RetinaNet Detection Model...")
use_gpu = torch.cuda.is_available()
if use_gpu:
device = torch.device('cuda')
retinanet = retinanet.to(device)
retinanet = torch.nn.DataParallel(retinanet,
device_ids=range(
torch.cuda.device_count()))
print("| Using %d GPUs for Train/Validation!" % torch.cuda.device_count())
retinanet.training = True
if parser.optimizer == 'Adam':
optimizer = optim.Adam(retinanet.parameters(),
lr=1e-5) # not mentioned
print("| Adam Optimizer with Learning Rate = {}".format(1e-5))
elif parser.optimizer == 'SGD':
optimizer = optim.SGD(retinanet.parameters(),
lr=1e-2,
momentum=0.9,
weight_decay=1e-4)
print("| SGD Optimizer with Learning Rate = {}".format(1e-2))
else:
raise ValueError('Unsupported Optimizer, must be one of [SGD | Adam]')
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer,
patience=3,
verbose=True)
loss_hist = collections.deque(maxlen=500)
retinanet.train()
retinanet.module.freeze_bn(
) # Freeze the BN parameters to ImageNet configuration
# Check if there is a 'checkpoints' path
if not osp.exists('./checkpoints/'):
os.makedirs('./checkpoints/')
print("\n[Phase 3]: Training Model on {} dataset...".format(
parser.dataset))
for epoch_num in range(parser.epochs):
epoch_loss = []
for iter_num, data in enumerate(dataloader_train):
try:
optimizer.zero_grad()
classification_loss, regression_loss = retinanet(
[data['img'].to(device), data['annot']])
classification_loss = classification_loss.mean()
regression_loss = regression_loss.mean()
loss = classification_loss + regression_loss
if bool(loss == 0):
continue
loss.backward()
torch.nn.utils.clip_grad_norm_(retinanet.parameters(), 0.001)
optimizer.step()
loss_hist.append(float(loss))
epoch_loss.append(float(loss))
sys.stdout.write('\r')
sys.stdout.write(
'| Epoch: {} | Iteration: {}/{} | Classification loss: {:1.5f} | Regression loss: {:1.5f} | Running loss: {:1.5f}'
.format(epoch_num + 1, iter_num + 1, len(dataloader_train),
float(classification_loss), float(regression_loss),
np.mean(loss_hist)))
sys.stdout.flush()
del classification_loss
del regression_loss
except Exception as e:
print(e)
continue
print("\n| Saving current best model at epoch {}...".format(epoch_num +
1))
torch.save(
retinanet.state_dict(),
'./checkpoints/{}_retinanet_{}.pt'.format(parser.dataset,
epoch_num + 1))
if parser.dataset == 'coco':
#print('Evaluating dataset')
coco_eval.evaluate_coco(dataset_val, retinanet, device)
elif parser.dataset == 'csv' and parser.csv_val is not None:
#print('Evaluating dataset')
mAP = csv_eval.evaluate(dataset_val, retinanet, device)
scheduler.step(np.mean(epoch_loss))
retinanet.eval()
torch.save(retinanet.state_dict(), './checkpoints/model_final.pt')
def train(img_dir,classes_csv,model_fname=None,resnet_depth=50,epochs=1000,steps=100,train_split=0.8,out_dir ='',out_prefix=''):
if not os.path.exists(out_dir):
os.makedirs(out_dir)
# Create the data loaders
# Get all image fnames in folder
img_list = []
if not isinstance(img_dir, list):
img_dir = [img_dir]
for dir in img_dir:
for file in os.listdir(dir):
if file.endswith(".png"):
img_list.append(dir + file)
randomised_list = random.sample(img_list, len(img_list))
num_train = int(0.8*len(img_list))
train_imgs, val_imgs = randomised_list[:num_train], randomised_list[num_train:]
dataset_train = CustomDataset(img_list=train_imgs, class_list=classes_csv, transform=transforms.Compose([Normalizer(), Augmenter(), Resizer()]))
dataset_val = CustomDataset(img_list=val_imgs, class_list=classes_csv,transform=transforms.Compose([Normalizer(), Resizer()]))
sampler = AspectRatioBasedSampler(dataset_train, batch_size=2, drop_last=False)
dataloader_train = DataLoader(dataset_train, num_workers=3, collate_fn=collater, batch_sampler=sampler)
if dataset_val is not None:
sampler_val = AspectRatioBasedSampler(dataset_val, batch_size=1, drop_last=False)
dataloader_val = DataLoader(dataset_val, num_workers=3, collate_fn=collater, batch_sampler=sampler_val)
# Create the model
if resnet_depth == 18:
retinanet = model.resnet18(num_classes=dataset_train.num_classes(), pretrained=True)
elif resnet_depth == 34:
retinanet = model.resnet34(num_classes=dataset_train.num_classes(), pretrained=True)
elif resnet_depth == 50:
retinanet = model.resnet50(num_classes=dataset_train.num_classes(), pretrained=True)
elif resnet_depth == 101:
retinanet = model.resnet101(num_classes=dataset_train.num_classes(), pretrained=True)
elif resnet_depth == 152:
retinanet = model.resnet152(num_classes=dataset_train.num_classes(), pretrained=True)
else:
raise ValueError('Unsupported model depth, must be one of 18, 34, 50, 101, 152')
# retinanet = torch.load(model_fname)
if use_gpu:
retinanet = retinanet.cuda()
retinanet = torch.nn.DataParallel(retinanet).cuda()
if model_fname is not None:
retinanet.load_state_dict(torch.load(model_fname))
retinanet.training = True
optimizer = optim.Adam(retinanet.parameters(), lr=1e-5)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, patience=3, verbose=True)
loss_hist = collections.deque(maxlen=500)
retinanet.train()
retinanet.module.freeze_bn()
start_time = time.clock()
print('Num training images: {}'.format(len(dataset_train)))
for epoch_num in range(epochs):
retinanet.train()
retinanet.module.freeze_bn()
epoch_loss = []
for iter_num, data in enumerate(dataloader_train):
try:
optimizer.zero_grad()
classification_loss, regression_loss = retinanet([data['img'].cuda().float(), data['annot']])
classification_loss = classification_loss.mean()
regression_loss = regression_loss.mean()
loss = classification_loss + regression_loss
if bool(loss == 0):
continue
loss.backward()
torch.nn.utils.clip_grad_norm_(retinanet.parameters(), 0.1)
optimizer.step()
loss_hist.append(float(loss))
epoch_loss.append(float(loss))
# print('Epoch: {} | Iteration: {} | Classification loss: {:1.5f} | Regression loss: {:1.5f} | Running loss: {:1.5f}'.format(epoch_num, iter_num, float(classification_loss), float(regression_loss), np.mean(loss_hist)))
del classification_loss
del regression_loss
except Exception as e:
print(e)
continue
print('Epoch: {} | Running loss: {:1.5f} | Elapsed Time: {}'.format(epoch_num, np.mean(loss_hist),(time.clock() - start_time)/60))
mAP = csv_eval.evaluate(dataset_val, retinanet)
scheduler.step(np.mean(epoch_loss))
if (epoch_num) % steps == 0:
torch.save(retinanet.module, '{}{}_model_{}.pt'.format(out_dir, out_prefix, epoch_num))
torch.save(retinanet.state_dict(), '{}{}_state_{}.pt'.format(out_dir, out_prefix, epoch_num))
torch.save(retinanet, out_dir + '{}model_final.pt'.format(out_prefix))
torch.save(retinanet.state_dict(), out_dir + '{}state_final_.pt'.format(out_prefix))
if args.csv_val is not None:
dataset_val = CSVDataset(
train_file=args.csv_val,
class_list=args.csv_classes,
transform=transforms.Compose([Normalizer(), Resizer()])
)
else:
dataset_val = None
print('No validation annotations provided.')
dataloader_train = DataLoader(
dataset_train,
num_workers=4,
collate_fn=collater,
batch_sampler=AspectRatioBasedSampler(dataset_train, batch_size=args.batch_size, drop_last=False),
)
if dataset_val is not None:
dataloader_val = DataLoader(
dataset_val,
num_workers=4,
collate_fn=collater,
batch_sampler=AspectRatioBasedSampler(dataset_val, batch_size=1, drop_last=False),
)
# --
# Define model
device_ids = [int(device_id) for device_id in args.device_ids.split(',')]
def main(args=None):
parser = argparse.ArgumentParser(
description='Simple training script for training a RetinaNet network.')
parser.add_argument(
'--csv_train',
help='Path to file containing training annotations (see readme)')
parser.add_argument('--csv_classes',
help='Path to file containing class list (see readme)')
parser.add_argument(
'--csv_val',
help=
'Path to file containing validation annotations (optional, see readme)'
)
parser.add_argument(
'--depth',
help='Resnet depth, must be one of 18, 34, 50, 101, 152',
type=int,
default=50)
parser.add_argument('--epochs',
help='Number of epochs',
type=int,
default=50)
parser.add_argument('--model_name', help='name of the model to save')
parser.add_argument('--pretrained', help='pretrained model name')
parser = parser.parse_args(args)
# Create the data loaders
dataset_train = CSVDataset(train_file=parser.csv_train,
class_list=parser.csv_classes,
transform=transforms.Compose(
[Resizer(),
Augmenter(),
Normalizer()]))
if parser.csv_val is None:
dataset_val = None
print('No validation annotations provided.')
else:
dataset_val = CSVDataset(train_file=parser.csv_val,
class_list=parser.csv_classes,
transform=transforms.Compose(
[Resizer(), Normalizer()]))
sampler = AspectRatioBasedSampler(dataset_train,
batch_size=2,
drop_last=False)
dataloader_train = DataLoader(dataset_train,
num_workers=16,
collate_fn=collater,
batch_sampler=sampler)
#dataloader_train = DataLoader(dataset_train, num_workers=16, collate_fn=collater, batch_size=8, shuffle=True)
if dataset_val is not None:
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=2,
drop_last=False)
dataloader_val = DataLoader(dataset_val,
num_workers=16,
collate_fn=collater,
batch_sampler=sampler_val)
#dataloader_val = DataLoader(dataset_train, num_workers=16, collate_fn=collater, batch_size=8, shuffle=True)
# Create the model_pose_level_attention
if parser.depth == 18:
retinanet = model.resnet18(num_classes=dataset_train.num_classes())
elif parser.depth == 34:
retinanet = model.resnet34(num_classes=dataset_train.num_classes())
elif parser.depth == 50:
retinanet = model.resnet50(num_classes=dataset_train.num_classes())
elif parser.depth == 101:
retinanet = model.resnet101(num_classes=dataset_train.num_classes())
elif parser.depth == 152:
retinanet = model.resnet152(num_classes=dataset_train.num_classes())
else:
raise ValueError(
'Unsupported model depth, must be one of 18, 34, 50, 101, 152')
if ckpt:
retinanet = torch.load('')
print('load ckpt')
else:
retinanet_dict = retinanet.state_dict()
pretrained_dict = torch.load('./weight/' + parser.pretrained)
pretrained_dict = {
k: v
for k, v in pretrained_dict.items() if k in retinanet_dict
}
retinanet_dict.update(pretrained_dict)
retinanet.load_state_dict(retinanet_dict)
print('load pretrained backbone')
print(retinanet)
retinanet = torch.nn.DataParallel(retinanet, device_ids=[0])
retinanet.cuda()
retinanet.training = True
optimizer = optim.Adam(retinanet.parameters(), lr=1e-5)
#optimizer = optim.SGD(retinanet.parameters(), lr=1e-3, momentum=0.9, weight_decay=1e-4)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer,
patience=3,
verbose=True)
#scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=20, gamma=0.1)
loss_hist = collections.deque(maxlen=500)
retinanet.train()
retinanet.module.freeze_bn()
print('Num training images: {}'.format(len(dataset_train)))
f_map = open('./mAP_txt/' + parser.model_name + '.txt', 'a')
writer = SummaryWriter(log_dir='./summary')
iters = 0
for epoch_num in range(0, parser.epochs):
retinanet.train()
retinanet.module.freeze_bn()
epoch_loss = []
#scheduler.step()
for iter_num, data in enumerate(dataloader_train):
iters += 1
optimizer.zero_grad()
classification_loss_f, regression_loss_f, classification_loss_v, regression_loss_v = retinanet(
[
data['img'].cuda().float(), data['annot'], data['vbox'],
data['ignore']
])
classification_loss_f = classification_loss_f.mean()
regression_loss_f = regression_loss_f.mean()
classification_loss_v = classification_loss_v.mean()
regression_loss_v = regression_loss_v.mean()
loss = classification_loss_f + regression_loss_f + classification_loss_v + regression_loss_v
if bool(loss == 0):
continue
loss.backward()
torch.nn.utils.clip_grad_norm_(retinanet.parameters(), 0.1)
optimizer.step()
loss_hist.append(float(loss))
epoch_loss.append(float(loss))
print(
'Epoch: {} | Iteration: {} | Classification loss_f: {:1.5f} | Regression loss_f: {:1.5f} | Classification loss_v {:1.5f} | Regression loss_v {:1.5f} | Running loss: {:1.5f}'
.format(epoch_num, iter_num, float(classification_loss_f),
float(regression_loss_f), float(classification_loss_v),
float(regression_loss_v), np.mean(loss_hist)))
writer.add_scalar('classification_loss_f', classification_loss_f,
iters)
writer.add_scalar('regression_loss_f', regression_loss_f, iters)
writer.add_scalar('classification_loss_v', classification_loss_v,
iters)
writer.add_scalar('regression_loss_v', regression_loss_v, iters)
writer.add_scalar('loss', loss, iters)
if parser.csv_val is not None:
print('Evaluating dataset')
mAP = csv_eval.evaluate(dataset_val, retinanet)
f_map.write('mAP:{}, epoch:{}'.format(mAP[0][0], epoch_num))
f_map.write('\n')
scheduler.step(np.mean(epoch_loss))
torch.save(retinanet.module,
'./ckpt/' + parser.model_name + '_{}.pt'.format(epoch_num))
retinanet.eval()
writer.export_scalars_to_json(
"./summary/' + parser.pretrained + 'all_scalars.json")
f_map.close()
writer.close()
def main(args=None):
parser = argparse.ArgumentParser(
description='Simple training script for training a RetinaNet network.')
parser.add_argument('--dataset',
help='Dataset type, must be one of csv or coco.')
parser.add_argument('--data_path', help='Path to COCO directory')
parser.add_argument('--csv_classes',
help='Path to file containing class list (see readme)')
parser.add_argument(
'--csv_val',
help=
'Path to file containing validation annotations (optional, see readme)'
)
parser.add_argument('--net', help='Network to use', default='fasterrcnn')
parser.add_argument('--model', help='Path to model (.pt) file.')
parser.add_argument(
'--depth',
help='Resnet depth, must be one of 18, 34, 50, 101, 152',
type=int,
default=50)
parser = parser.parse_args(args)
if parser.dataset == 'coco':
raise NotImplementedError()
dataset_val = CocoDataset(parser.data_path,
set_name='val2017',
transform=Compose([Normalizer(),
Resizer()]))
elif parser.dataset == 'openimages':
dataset_val = OidDataset(parser.data_path,
subset='validation',
transform=Compose([ToTensor()]))
elif parser.dataset == 'csv':
raise NotImplementedError()
dataset_val = CSVDataset(train_file=parser.csv_train,
class_list=parser.csv_classes,
transform=Compose([Normalizer(),
Resizer()]))
else:
raise ValueError(
'Dataset type not understood (must be csv or coco), exiting.')
sampler_val = AspectRatioBasedSampler(dataset_val,
batch_size=1,
drop_last=False)
dataloader_val = DataLoader(dataset_val,
num_workers=1,
collate_fn=collate_fn,
batch_sampler=sampler_val)
# Create the model
model = create_detection_model(dataset_val.num_classes(), parser)
checkpoint = torch.load(parser.model,
map_location=lambda storage, loc: storage)
weights = checkpoint['model']
weights = {k.replace('module.', ''): v for k, v in weights.items()}
model.load_state_dict(weights)
if use_gpu:
model = model.cuda()
model.eval()
def draw_caption(image, box, caption):
b = np.array(box).astype(int)
cv2.putText(image, caption, (b[0], b[1] - 10), cv2.FONT_HERSHEY_PLAIN,
1, (0, 0, 0), 2)
cv2.putText(image, caption, (b[0], b[1] - 10), cv2.FONT_HERSHEY_PLAIN,
1, (255, 255, 255), 1)
for idx, data in enumerate(dataloader_val):
with torch.no_grad():
st = time.time()
images, targets = data
# targets = [{k: v.cuda() for k, v in t.items()} for t in targets]
if use_gpu:
input_images = list(image.cuda().float() for image in images)
else:
input_images = list(image.float() for image in images)
# TODO: adapt retinanet output to the one by torchvision 0.3
# scores, classification, transformed_anchors = model(data_img.float())
outputs = model(input_images)
outputs = [{k: v.cpu() for k, v in t.items()} for t in outputs]
output = outputs[0] # take the only batch
scores = output['scores']
classification = output['labels']
transformed_anchors = output['boxes']
# from here, interface to the code already written in the original repo
print('Elapsed time: {}'.format(time.time() - st))
idxs = np.where(scores > thres)
img = np.array(255 * images[0]).copy()
img[img < 0] = 0
img[img > 255] = 255
img = np.transpose(img, (1, 2, 0))
img = cv2.cvtColor(img.astype(np.uint8), cv2.COLOR_BGR2RGB)
'''
# Visualize ground truth bounding boxes
for bbox, label in zip(targets[0]['boxes'], targets[0]['labels']):
# bbox = transformed_anchors[idxs[0][j], :]
x1 = int(bbox[0])
y1 = int(bbox[1])
x2 = int(bbox[2])
y2 = int(bbox[3])
label_name = dataset_val.labels[int(label)]
draw_caption(img, (x1, y1, x2, y2), label_name)
cv2.rectangle(img, (x1, y1), (x2, y2), color=(0, 255, 0), thickness=1)
print('GT: '+label_name)
'''
for j in range(idxs[0].shape[0]):
bbox = transformed_anchors[idxs[0][j], :]
x1 = int(bbox[0])
y1 = int(bbox[1])
x2 = int(bbox[2])
y2 = int(bbox[3])
label_name = dataset_val.labels[int(
classification[idxs[0][j]])]
draw_caption(img, (x1, y1, x2, y2), label_name)
cv2.rectangle(img, (x1, y1), (x2, y2),
color=(0, 0, 255),
thickness=2)
print('Detection: ' + label_name)
cv2.imshow('img', img)
cv2.waitKey(0)
