def loadWarmUpState(filename):
print(' load pre-trained model file: {}'.format(filename))
warmup_resume_file = get_resume_file(filename)
tmp = torch.load(warmup_resume_file)
if tmp is not None:
state = tmp['state']
state_keys = list(state.keys())
for i, key in enumerate(state_keys):
if "feature." in key: # and '.7.' not in key:
newkey = key.replace("feature.", "")
state[newkey] = state.pop(key)
else:
state.pop(key)
else:
raise ValueError('No warm_up file')
return state
test_few_shot_params = dict(n_way=params.test_n_way,
n_support=params.n_shot)
val_datamgr = SetDataManager(image_size,
n_query=n_query,
**test_few_shot_params)
val_loader = val_datamgr.get_data_loader(val_file, aug=False)
model = LFTNet(params, tf_path=params.tf_dir)
model.cuda()
# resume training
start_epoch = params.start_epoch
stop_epoch = params.stop_epoch
if params.resume != '':
resume_file = get_resume_file(
'%s/checkpoints/%s' % (params.save_dir, params.resume),
params.resume_epoch)
if resume_file is not None:
start_epoch = model.resume(resume_file)
print(' resume the training with at {} epoch (model file {})'.
format(start_epoch, params.resume))
else:
raise ValueError('No resume file')
# load pre-trained feature encoder
else:
if params.warmup == 'gg3b0':
raise Exception(
'Must provide pre-trained feature-encoder file using --warmup option!'
)
model.model.feature.load_state_dict(load_warmup_state(
'%s/checkpoints/%s' % (params.save_dir, params.warmup),
tf_path=params.tf_dir,
**train_few_shot_params)
else:
raise ValueError('Unknown method')
model = model.cuda()
max_acc = 0
total_it = 0
start_epoch = params.start_epoch
stop_epoch = params.stop_epoch
if params.method not in ['baseline', 'baseline++']:
stop_epoch = params.stop_epoch * model.batch_size
# resume/warmup or not
if params.resume != '':
resume_file = get_resume_file('%s/checkpoints/%s' %
(params.save_dir, params.resume))
if resume_file is not None:
print(' load resume file: {}'.format(params.resume))
tmp = torch.load(resume_file)
max_acc = tmp['max_acc']
total_it = tmp['total_it']
start_epoch = tmp['epoch'] + 1
model.load_state_dict(tmp['state'])
model.optimizer.load_state_dict(tmp['optimizer'])
else:
raise ValueError('No resume file')
elif params.warmup != 'gg3b0':
warmup_resume_file = get_resume_file('%s/checkpoints/%s' %
(params.save_dir, params.warmup))
if warmup_resume_file is not None:
print(' load pretrained file: {}'.format(params.warmup))