def load_model_from_config(pretrained_root):
model_path = os.path.join(pretrained_root, 'checkpoints', 'best', 'best_model.pt')
json_path = os.path.join(pretrained_root, 'logs', 'config.json')
with open(json_path, 'r') as f:
model_config = Munch.fromDict(json.load(f))
# Weird required hack to fix groupings (None is added to start during model training).
if 'groupings' in model_config.model and model_config.model.groupings[0] is -1:
model_config.model.groupings = model_config.model.groupings[1:]
model = get_model(model_config)
model.load_state_dict(torch.load(model_path))
return model, model_config
def main(opt):
exp_dir = opt['model']['exp_path']
model_path = os.path.join(exp_dir, 'checkpoints', 'best', 'best_model.pt')
with open(os.path.join(exp_dir, 'logs', 'config.json'), 'r') as f:
model_config = Munch.fromDict(json.load(f))
# Weird required hack to fix groupings (None is added to start during model training)
if 'groupings' in model_config.model and model_config.model.groupings[0] is -1:
model_config.model.groupings = model_config.model.groupings[1:]
model_config.cuda = opt['cuda']
model_config.data.cuda = opt['cuda']
model = get_model(model_config)
model.load_state_dict(torch.load(model_path))
if opt['cuda']:
print('Using CUDA')
model.cuda()
def on_sample(state):
if opt['cuda']:
state['sample'] = [x.cuda() for x in state['sample']]
def on_forward(state):
state['model'].add_to_meters(state)
data = load_data(model_config)
# Change the model to use ortho layers by copying the base weights
model = convert_model_from_bjorck(model, model_config)
# model.model.project_network_weights(Munch.fromDict({'type': 'l_inf_projected'}))
# Instantiate the trainer.
trainer = Trainer()
trainer.hooks['on_sample'] = on_sample
trainer.hooks['on_forward'] = on_forward
print('TESTING')
state = trainer.test(model, data['test'])
for tag, meter in state['model'].meters.items():
print(tag, meter.value())
logit_margins = check_logit_margins(model, data['test'])
print(logit_margins.min().item(), logit_margins.max().item(), logit_margins.mean().item())
plt.hist(logit_margins.detach().cpu().numpy())
plt.show()
def load_model_hack(pretrained_root):
model_path = os.path.join(pretrained_root, 'checkpoints', 'best',
'best_model.pt')
json_path = os.path.join(pretrained_root, 'logs', 'config.json')
with open(json_path, 'r') as f:
model_config = Munch.fromDict(json.load(f))
if 'groupings' in model_config.model and model_config.model.groupings[
0] is -1:
model_config.model.groupings = model_config.model.groupings[1:]
from lnets.models import get_model
model = get_model(model_config)
state_dict = torch.load(model_path)['state_dict'][0]
for (a, b) in zip(model.model.model.state_dict(), state_dict):
model.model.model.state_dict()[a].copy_(state_dict[b])
return model, model_config
def main(opt):
# if not os.path.isdir(opt['output_root']):
# os.makedirs(opt['output_root'])
exp_dir = opt['model']['exp_path']
model_path = os.path.join(exp_dir, 'checkpoints', 'best', 'best_model.pt')
with open(os.path.join(exp_dir, 'logs', 'config.json'), 'r') as f:
model_config = Munch.fromDict(json.load(f))
# Weird required hack to fix groupings (None is added to start during model training)
if 'groupings' in model_config.model and model_config.model.groupings[
0] is -1:
model_config.model.groupings = model_config.model.groupings[1:]
model_config.model.linear.bjorck_iters = 20
model_config.cuda = opt['cuda']
model = get_model(model_config)
model.load_state_dict(torch.load(model_path))
if opt['cuda']:
print('Using CUDA')
model.cuda()
data = load_data(model_config)
# Change the model to use ortho layers by copying the base weights
model = convert_model_from_bjorck(model, model_config)
model.eval()
rates = []
thresholds = np.linspace(0.0, 1.0, 50, endpoint=True)
for t in thresholds:
undead_rate = get_undead_rate(model,
data['test'],
threshold=t,
cuda=opt['cuda'])
rates.append(undead_rate)
plt.plot(thresholds, np.array(rates))
plt.show()
np.save('undead_rates', rates)
print(undead_rate)
def main(opt):
if not os.path.isdir(opt['output_root']):
os.makedirs(opt['output_root'])
exp_dir = opt['model']['exp_path']
model_path = os.path.join(exp_dir, 'checkpoints', 'best', 'best_model.pt')
with open(os.path.join(exp_dir, 'logs', 'config.json'), 'r') as f:
model_config = Munch.fromDict(json.load(f))
# Weird required hack to fix groupings (None is added to start during model training)
if 'groupings' in model_config.model and model_config.model.groupings[
0] is -1:
model_config.model.groupings = model_config.model.groupings[1:]
model = get_model(model_config)
model.load_state_dict(torch.load(model_path))
if opt['data']['cuda']:
print('Using CUDA')
model.cuda()
model_config.data.cuda = opt['data']['cuda']
data = load_data(model_config)
# Change the model to use ortho layers by copying the base weights
bjorck_iters = 50
model = convert_model_to_bjorck(model, model_config)
for m in model.modules():
if isinstance(m, BjorckLinear):
m.config.model.linear.bjorck_iter = bjorck_iters
model_config.output_root = opt['output_root']
model_config.optim.lr_schedule.lr_init = 1e-5
model_config.optim.epochs = 5
model = train(model, data, model_config)