def train(opt):
params = Params(f'projects/{opt.project}.yml')
params.num_gpus = 4
# opt.log_path = 'C:/Users/giang/Desktop/result_temp/'
if params.num_gpus == 0:
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
if torch.cuda.is_available():
torch.cuda.manual_seed(42)
else:
torch.manual_seed(42)
opt.saved_path = opt.saved_path + f'/{params.project_name}/'
opt.log_path = opt.log_path + f'/{params.project_name}/tensorboard/'
os.makedirs(opt.log_path, exist_ok=True)
os.makedirs(opt.saved_path, exist_ok=True)
training_params = {
'batch_size': opt.batch_size,
'shuffle': True,
'drop_last': True,
'collate_fn': collater,
'num_workers': opt.num_workers
}
val_params = {
'batch_size': opt.batch_size * 4,
'shuffle': False,
'drop_last': True,
'collate_fn': collater,
'num_workers': opt.num_workers
}
input_sizes = [512, 640, 768, 896, 1024, 1280, 1280, 1536, 1536]
# root_train = 'D:/Etri_tracking_data/Etri_full/train_1024/'
# side_train = 'D:/Etri_tracking_data/Etri_full/train_Sejin_1024/'
# ground_truth_train = 'D:/Etri_tracking_data/Etri_full/train_1024.txt'
root_train = '/home/../../data3/giangData/train_1024/'
side_train = '/home/../../data3/giangData/train_Sejin_1024/'
ground_truth_train = '/home/../../data3/giangData/train_1024.txt'
training_set = TobyCustom(root_dir=root_train, side_dir = side_train, \
annot_path = ground_truth_train, \
transform=ComposeAlb([Flip_X(), \
Flip_Y(), \
Equalize(), \
Brightness(), \
Constrast(), \
Resizer(input_sizes[opt.compound_coef], num_channels=3), \
Normalizer(mean = [0.485, 0.456, 0.406], std = [0.229, 0.224, 0.225])]))
training_generator = DataLoader(training_set, **training_params)
# root_val = 'D:/Etri_tracking_data/Etri_full/val_1024/'
# side_val = 'D:/Etri_tracking_data/Etri_full/val_Sejin_1024/'
# ground_truth_val = 'D:/Etri_tracking_data/Etri_full/val_1024.txt'
root_val = '/home/../../data3/giangData/val_1024/'
side_val = '/home/../../data3/giangData/val_Sejin_1024/'
ground_truth_val = '/home/../../data3/giangData/val_1024.txt'
val_set = TobyCustom(root_dir=root_val, side_dir = side_val, \
annot_path = ground_truth_val, \
transform=ComposeAlb([Resizer(input_sizes[opt.compound_coef], num_channels=3),
Normalizer(mean = [0.485, 0.456, 0.406], std = [0.229, 0.224, 0.225])]))
val_generator = DataLoader(val_set, **val_params)
model = EfficientDetBackbone(num_classes=len(params.obj_list),
compound_coef=opt.compound_coef,
ratios=eval(params.anchors_ratios),
scales=eval(params.anchors_scales))
from efficientdet.model import Classifier
# model.backbone_net.model._conv_stem.conv = nn.Conv2d(4, 48, kernel_size=(3, 3), stride=(2, 2), bias=False)
# model.classifier.header.pointwise_conv.conv = nn.Conv2d(224, 9, kernel_size=(1, 1), stride=(1, 1))
model.classifier = Classifier(
in_channels=model.fpn_num_filters[opt.compound_coef],
num_anchors=model.num_anchors,
num_classes=1,
num_layers=model.box_class_repeats[opt.compound_coef],
pyramid_levels=model.pyramid_levels[opt.compound_coef])
# opt.load_weights = 'C:/Users/giang/Desktop/efficientdet-d4_107_15228_6.1788892433756875.pth'
opt.load_weights = './../result_3channel_21/save/coco/efficientdet-d4_21_3000.pth'
# block'
# for EfficientNetB5, please test again with B4
# load last weights
if opt.load_weights is not None:
if opt.load_weights.endswith('.pth'):
weights_path = opt.load_weights
else:
weights_path = get_last_weights(opt.saved_path)
try:
last_step = int(
os.path.basename(weights_path).split('_')[-1].split('.')[0])
except:
last_step = 0
try:
ret = model.load_state_dict(torch.load(weights_path), strict=False)
except RuntimeError as e:
print(f'[Warning] Ignoring {e}')
print(
'[Warning] Don\'t panic if you see this, this might be because you load a pretrained weights with different number of classes. The rest of the weights should be loaded already.'
)
print(
f'[Info] loaded weights: {os.path.basename(weights_path)}, resuming checkpoint from step: {last_step}'
)
else:
last_step = 0
print('[Info] initializing weights...')
init_weights(model)
'''
============================================
Modify model
'''
# from efficientdet.model import Classifier
# model.backbone_net.model._conv_stem.conv = nn.Conv2d(4, 48, kernel_size=(3, 3), stride=(2, 2), bias=False)
# model.classifier.header.pointwise_conv.conv = nn.Conv2d(224, 9, kernel_size=(1, 1), stride=(1, 1))
# model.classifier = Classifier(in_channels=model.fpn_num_filters[opt.compound_coef], num_anchors=model.num_anchors,
# num_classes=1,
# num_layers=model.box_class_repeats[opt.compound_coef],
# pyramid_levels=model.pyramid_levels[opt.compound_coef])
'''
=============================================
'''
# freeze backbone if train head_only
if opt.head_only:
def freeze_backbone(m):
classname = m.__class__.__name__
for ntl in ['EfficientNet', 'BiFPN']:
if ntl in classname:
for param in m.parameters():
param.requires_grad = False
model.apply(freeze_backbone)
print('[Info] freezed backbone')
# https://github.com/vacancy/Synchronized-BatchNorm-PyTorch
# apply sync_bn when using multiple gpu and batch_size per gpu is lower than 4
# useful when gpu memory is limited.
# because when bn is disable, the training will be very unstable or slow to converge,
# apply sync_bn can solve it,
# by packing all mini-batch across all gpus as one batch and normalize, then send it back to all gpus.
# but it would also slow down the training by a little bit.
if params.num_gpus > 1 and opt.batch_size // params.num_gpus < 4:
model.apply(replace_w_sync_bn)
use_sync_bn = True
else:
use_sync_bn = False
writer = SummaryWriter(
opt.log_path +
f'/{datetime.datetime.now().strftime("%Y%m%d-%H%M%S")}/')
# warp the model with loss function, to reduce the memory usage on gpu0 and speedup
model = ModelWithLoss(model, debug=opt.debug)
if params.num_gpus > 0:
model = model.cuda()
if params.num_gpus > 1:
model = CustomDataParallel(model, params.num_gpus)
if use_sync_bn:
patch_replication_callback(model)
if opt.optim == 'adamw':
optimizer = torch.optim.AdamW(model.parameters(), opt.lr)
else:
optimizer = torch.optim.SGD(model.parameters(),
opt.lr,
momentum=0.9,
nesterov=True)
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer,
patience=3,
verbose=True)
epoch = 0
best_loss = 1e5
best_epoch = 0
step = max(0, last_step)
model.train()
num_iter_per_epoch = len(training_generator)
try:
for epoch in range(opt.num_epochs):
last_epoch = step // num_iter_per_epoch
if epoch < last_epoch:
continue
epoch_loss = []
progress_bar = tqdm(training_generator)
for iter, data in enumerate(progress_bar):
if iter < step - last_epoch * num_iter_per_epoch:
progress_bar.update()
continue
try:
imgs = data['img']
annot = data['annot']
image_path = data['image_path']
# print(image_path)
if params.num_gpus == 1:
# if only one gpu, just send it to cuda:0
# elif multiple gpus, send it to multiple gpus in CustomDataParallel, not here
imgs = imgs.cuda()
annot = annot.cuda()
optimizer.zero_grad()
cls_loss, reg_loss = model(imgs,
annot,
obj_list=params.obj_list)
cls_loss = cls_loss.mean()
reg_loss = reg_loss.mean()
loss = cls_loss + reg_loss
if loss == 0 or not torch.isfinite(loss):
continue
loss.backward()
# torch.nn.utils.clip_grad_norm_(model.parameters(), 0.1)
optimizer.step()
epoch_loss.append(float(loss))
progress_bar.set_description(
'Step: {}. Epoch: {}/{}. Iteration: {}/{}. Cls loss: {:.5f}. Reg loss: {:.5f}. Total loss: {:.5f}'
.format(step, epoch, opt.num_epochs, iter + 1,
num_iter_per_epoch, cls_loss.item(),
reg_loss.item(), loss.item()))
writer.add_scalars('Loss', {'train': loss}, step)
writer.add_scalars('Regression_loss', {'train': reg_loss},
step)
writer.add_scalars('Classfication_loss',
{'train': cls_loss}, step)
# log learning_rate
current_lr = optimizer.param_groups[0]['lr']
writer.add_scalar('learning_rate', current_lr, step)
step += 1
if step % opt.save_interval == 0 and step > 0:
save_checkpoint(
model,
f'efficientdet-d{opt.compound_coef}_{epoch}_{step}.pth'
)
print('checkpoint...')
except Exception as e:
print('[Error]', traceback.format_exc())
print(e)
continue
scheduler.step(np.mean(epoch_loss))
if epoch % opt.val_interval == 0:
model.eval()
loss_regression_ls = []
loss_classification_ls = []
for iter, data in enumerate(val_generator):
with torch.no_grad():
imgs = data['img']
annot = data['annot']
if params.num_gpus == 1:
imgs = imgs.cuda()
annot = annot.cuda()
cls_loss, reg_loss = model(imgs,
annot,
obj_list=params.obj_list)
cls_loss = cls_loss.mean()
reg_loss = reg_loss.mean()
loss = cls_loss + reg_loss
if loss == 0 or not torch.isfinite(loss):
continue
loss_classification_ls.append(cls_loss.item())
loss_regression_ls.append(reg_loss.item())
cls_loss = np.mean(loss_classification_ls)
reg_loss = np.mean(loss_regression_ls)
loss = cls_loss + reg_loss
print(
'Val. Epoch: {}/{}. Classification loss: {:1.5f}. Regression loss: {:1.5f}. Total loss: {:1.5f}'
.format(epoch, opt.num_epochs, cls_loss, reg_loss, loss))
writer.add_scalars('Loss', {'val': loss}, step)
writer.add_scalars('Regression_loss', {'val': reg_loss}, step)
writer.add_scalars('Classfication_loss', {'val': cls_loss},
step)
print('\n')
if loss + opt.es_min_delta < best_loss:
best_loss = loss
best_epoch = epoch
save_loss = round(loss, 4)
save_checkpoint(
model,
f'efficientdet-d{opt.compound_coef}_{epoch}_{step}_{loss}.pth'
)
model.train()
# Early stopping
if epoch - best_epoch > opt.es_patience > 0:
print(
'[Info] Stop training at epoch {}. The lowest loss achieved is {}'
.format(epoch, best_loss))
break
except KeyboardInterrupt:
save_checkpoint(
model, f'efficientdet-d{opt.compound_coef}_{epoch}_{step}.pth')
writer.close()
writer.close()
compound_coef] if force_input_size is None else force_input_size
model = EfficientDetBackbone(num_classes=len(params.obj_list),
compound_coef=4,
ratios=eval(params.anchors_ratios),
scales=eval(params.anchors_scales))
# print(model)
# weights_path = './weights/efficientdet-d4.pth'
weights_path = 'C:/Users/giang/Desktop/efficientdet-d4_24_3500.pth'
# model.load_state_dict(torch.load(weights_path, map_location = 'cpu'), strict=False)
from efficientdet.model import Classifier
# model.backbone_net.model._conv_stem.conv = nn.Conv2d(4, 48, kernel_size=(3, 3), stride=(2, 2), bias=False)
# model.classifier.header.pointwise_conv.conv = nn.Conv2d(224, 9, kernel_size=(1, 1), stride=(1, 1))
model.classifier = Classifier(in_channels=model.fpn_num_filters[4],
num_anchors=model.num_anchors,
num_classes=1,
num_layers=model.box_class_repeats[4],
pyramid_levels=model.pyramid_levels[4])
model.load_state_dict(torch.load(weights_path), strict=False)
# model.load_state_dict(torch.load(f'weights/efficientdet-d{compound_coef}.pth', map_location='cpu'))
model.requires_grad_(False)
model.eval()
# model.train(False)
if use_cuda:
model = model.cuda()
if use_float16:
model = model.half()
params.num_gpus = 1
if params.num_gpus == 0:
