def cotrain(model_names, data, save_paths, iter_step=1, train_ratio=0.2):
"""
cotrain model:
params:
model_names: model names such as ['resnet50','densenet121']
data: dataset include train and untrain data
save_paths: paths for storing models
iter_step: maximum iteration steps
train_ratio: labeled data ratio
"""
assert iter_step >= 1
assert len(model_names) == 2 and len(save_paths) == 2
train_data, untrain_data = dp.split_dataset(data.trainval, train_ratio)
data_dir = data.images_dir
for step in range(iter_step):
pred_probs = []
add_ids = []
for view in range(2):
model = mu.train(model_names[view],
train_data,
data_dir,
data.num_trainval_ids,
epochs=50)
data_params = mu.get_params_by_name(model_names[view])
pred_probs.append(
mu.predict_prob(model, untrain_data, data_dir, data_params))
add_ids.append(dp.sel_idx(pred_probs[view], data.train))
torch.save(model.state_dict(),
save_paths[view] + '.cotrain.epoch%d' % (step + 1))
mu.evaluate(model, data, params=data_params)
pred_y = np.argmax(sum(pred_probs), axis=1)
add_id = sum(add_ids)
train_data, untrain_data = dp.update_train_untrain(
add_id, train_data, untrain_data, pred_y)
save_pth = os.path.join(config.logs_dir, config.model_name,
'%s' % (args.checkpoint))
if os.path.exists(save_pth) is not True:
raise ValueError('wrong model pth')
checkpoint = load_checkpoint(save_pth)
state_dict = {
k: v
for k, v in checkpoint['state_dict'].items()
if k in model.state_dict().keys()
}
model.load_state_dict(state_dict)
else:
model = mu.train(data.trainval, data.images_dir, config)
save_checkpoint(
{
'state_dict': model.state_dict(),
'epoch': 0,
'train_data': data.trainval
},
False,
fpath=os.path.join(config.logs_dir, config.model_name,
'full_supervised'))
mu.evaluate(model, data, config)
if args.evaluate is True:
train_data = checkpoint['train_data']
weight = [w for (_, _, _, w) in train_data]
print(np.median(weight))
print(np.mean(weight))
def spaco(configs,
data,
iter_steps=1,
gamma=0,
train_ratio=0.2,
regularizer='hard',
device='cuda:0'):
"""
self-paced co-training model implementation based on Pytroch
params:
model_names: model names for spaco, such as ['resnet50','densenet121']
data: dataset for spaco model
save_pathts: save paths for two models
iter_step: iteration round for spaco
gamma: spaco hyperparameter
train_ratio: initiate training dataset ratio
"""
num_view = len(configs)
train_data, untrain_data = dp.split_dataset(data.trainval, train_ratio,
args.seed)
data_dir = data.images_dir
query_gallery = list(set(data.query) | set(data.gallery))
save_dir = os.path.join('logs', 'parallel_spaco', regularizer,
'seed_%d' % args.seed)
###########
# initiate classifier to get preidctions
###########
add_ratio = 0.5
pred_probs = []
sel_ids = []
weights = []
features = []
start_step = 0
for view in range(num_view):
net = models.create(configs[view].model_name,
num_features=configs[view].num_features,
dropout=configs[view].dropout,
num_classes=configs[view].num_classes).to(device)
mu.train(net, train_data, data_dir, configs[view], device)
pred_probs.append(mu.predict_prob(net, untrain_data, data_dir, configs[view], device))
predictions = mu.predict_prob(net, data.trainval, data_dir, configs[view], device)
mAP = mu.evaluate(net, data, configs[view], device)
save_checkpoint(
{
'state_dict': net.state_dict(),
'epoch': 0,
'train_data': train_data,
'trainval': data.trainval,
'predictions': predictions,
'performance': mAP
},
False,
fpath=os.path.join(save_dir, '%s.epoch0' % (configs[view].model_name)))
pred_y = np.argmax(sum(pred_probs), axis=1)
# initiate weights for unlabled examples
for view in range(num_view):
sel_id, weight = dp.get_ids_weights(pred_probs[view], pred_y, train_data,
add_ratio, gamma, regularizer, num_view)
sel_ids.append(sel_id)
weights.append(weight)
# start iterative training
for step in range(start_step, iter_steps):
for view in range(num_view):
# update v_view
sel_ids[view], weights[view] = update_ids_weights(view, pred_probs,
sel_ids, weights,
pred_y, train_data,
add_ratio, gamma,
regularizer)
# update w_view
new_train_data, _ = dp.update_train_untrain(sel_ids[view], train_data,
untrain_data, pred_y,
weights[view])
configs[view].set_training(True)
net = models.create(configs[view].model_name,
num_features=configs[view].num_features,
dropout=configs[view].dropout,
num_classes=configs[view].num_classes).to(device)
mu.train(net, new_train_data, data_dir, configs[view], device)
# update y
pred_probs[view] = mu.predict_prob(net, untrain_data, data_dir,
configs[view], device)
# calculate predict probility on all data
test_acc(net, data.trainval, data_dir, configs[view], device)
# evaluation current model and save it
mAP = mu.evaluate(net, data, configs[view], device)
predictions = mu.predict_prob(net, data.trainval, data_dir,
configs[view], device)
save_checkpoint(
{
'state_dict': net.state_dict(),
'epoch': step + 1,
'train_data': new_train_data,
'trainval': data.trainval,
'predictions': predictions,
'performance': mAP
},
False,
fpath=os.path.join(
save_dir, '%s.epoch%d' % (configs[view].model_name, step + 1)))
if step + 1 == iter_steps:
features += [
mu.get_feature(net, query_gallery, data.images_dir, configs[view], device)
]
add_ratio += 1.2
# pred_y = np.argmax(sum(pred_probs), axis=1)
acc = mu.combine_evaluate(features, data)
print(acc)
def spaco(model_names,
data,
save_paths,
iter_step=1,
gamma=0.3,
train_ratio=0.2):
"""
self-paced co-training model implementation based on Pytroch
params:
model_names: model names for spaco, such as ['resnet50','densenet121']
data: dataset for spaco model
save_pathts: save paths for two models
iter_step: iteration round for spaco
gamma: spaco hyperparameter
train_ratio: initiate training dataset ratio
"""
assert iter_step >= 1
assert len(model_names) == 2 and len(save_paths) == 2
num_view = len(model_names)
train_data, untrain_data = dp.split_dataset(data.trainval, train_ratio)
data_dir = data.images_dir
num_classes = data.num_trainval_ids
###########
# initiate classifier to get preidctions
###########
add_ratio = 0.5
pred_probs = []
add_ids = []
for view in range(num_view):
pred_probs.append(
mu.train_predict(model_names[view], train_data, untrain_data,
num_classes, data_dir))
add_ids.append(dp.sel_idx(pred_probs[view], train_data, add_ratio))
pred_y = np.argmax(sum(pred_probs), axis=1)
for step in range(iter_step):
for view in range(num_view):
# update v_view
ov = add_ids[1 - view]
pred_probs[view][ov, pred_y[ov]] += gamma
add_id = dp.sel_idx(pred_probs[view], train_data, add_ratio)
# update w_view
new_train_data, _ = dp.update_train_untrain(
add_id, train_data, untrain_data, pred_y)
model = mu.train(model_names[view], new_train_data, data_dir,
num_classes)
# update y
data_params = mu.get_params_by_name(model_names[view])
pred_probs[view] = mu.predict_prob(model, untrain_data, data_dir,
data_params)
pred_y = np.argmax(sum(pred_probs), axis=1)
# udpate v_view for next view
add_ratio += 0.5
add_ids[view] = dp.sel_idx(pred_probs[view], train_data, add_ratio)
# evaluation current model and save it
mu.evaluate(model, data, data_params)
torch.save(model.state_dict(),
save_paths[view] + '.spaco.epoch%d' % (step + 1))
def wrap_evaluate(net, data, config, view, mAPs):
mAPs[view] = mu.evaluate(net, data, config, view)