class CometExperimentLogger(ExperimentLogger):
def __init__(self, exp_name, online=True, **kwargs):
super(CometExperimentLogger, self).__init__(exp_name, **kwargs)
if online:
self.comet = Experiment(project_name=exp_name, **kwargs)
else:
self.comet = OfflineExperiment(project_name=exp_name, **kwargs)
def log_metric(self, tag, value, step, **kwargs):
self.comet.log_metric(tag, value, step=step, **kwargs)
def log_image(self, tag, img, step, **kwargs):
self.comet.log_image(img, name=tag, step=step, **kwargs)
def log_plt(self, tag, plt, step, **kwargs):
self.comet.log_figure(figure=plt, figure_name=tag, step=step, **kwargs)
def log_text(self, tag, text, **kwargs):
self.comet.log_text(text, **kwargs)
def log_parameters(self, params, **kwargs):
self.comet.log_parameters(params, **kwargs)
def start_epoch(self, **kwargs):
super(CometExperimentLogger, self).start_epoch()
def end_epoch(self, **kwargs):
super(CometExperimentLogger, self).end_epoch()
self.comet.log_epoch_end(self.epoch, **kwargs)
def end_experiment(self):
self.comet.end()
verbose = 10,
n_jobs = 2,
n_points = 2,
scoring = 'accuracy',
)
checkpoint_callback = skopt.callbacks.CheckpointSaver(f'D:\\FINKI\\8_dps\\Project\\MODELS\\skopt_checkpoints\\{EXPERIMENT_ID}.pkl')
hyperparameters_optimizer.fit(X_train, y_train, callback = [checkpoint_callback])
skopt.dump(hyperparameters_optimizer, f'saved_models\\{EXPERIMENT_ID}.pkl')
y_pred = hyperparameters_optimizer.best_estimator_.predict(X_test)
for i in range(len(hyperparameters_optimizer.cv_results_['params'])):
exp = OfflineExperiment(
api_key = 'A8Lg71j9LtIrsv0deBA0DVGcR',
project_name = ALGORITHM,
workspace = "8_dps",
auto_output_logging = 'native',
offline_directory = f'D:\\FINKI\\8_dps\\Project\\MODELS\\comet_ml_offline_experiments\\{EXPERIMENT_ID}'
)
exp.set_name(f'{EXPERIMENT_ID}_{i + 1}')
exp.add_tags([DS, SEGMENTS_LENGTH, ])
for k, v in hyperparameters_optimizer.cv_results_.items():
if k == "params": exp.log_parameters(dict(v[i]))
else: exp.log_metric(k, v[i])
exp.end()
class Logger:
def __init__(self, send_logs, tags, parameters, experiment=None):
self.stations = 5
self.send_logs = send_logs
if self.send_logs:
if experiment is None:
json_loc = glob.glob("./**/comet_token.json")[0]
with open(json_loc, "r") as f:
kwargs = json.load(f)
self.experiment = OfflineExperiment(**kwargs)
else:
self.experiment = experiment
self.sent_mb = 0
self.speed_window = deque(maxlen=100)
self.step_time = None
self.current_speed = 0
if self.send_logs:
if tags is not None:
self.experiment.add_tags(tags)
if parameters is not None:
self.experiment.log_parameters(parameters)
def begin_logging(self, episode_count, steps_per_ep, sigma, theta, step_time):
self.step_time = step_time
if self.send_logs:
self.experiment.log_parameter("Episode count", episode_count)
self.experiment.log_parameter("Steps per episode", steps_per_ep)
self.experiment.log_parameter("theta", theta)
self.experiment.log_parameter("sigma", sigma)
def log_round(self, states, reward, cumulative_reward, info, loss, observations, step):
self.experiment.log_histogram_3d(states, name="Observations", step=step)
info = [[j for j in i.split("|")] for i in info]
info = np.mean(np.array(info, dtype=np.float32), axis=0)
try:
round_mb = info[0]
except Exception as e:
print(info)
print(reward)
raise e
self.speed_window.append(round_mb)
self.current_speed = np.mean(np.asarray(self.speed_window)/self.step_time)
self.sent_mb += round_mb
CW = info[1]
CW_ax = info[2]
self.stations = info[3]
fairness = info[4]
if self.send_logs:
self.experiment.log_metric("Round reward", np.mean(reward), step=step)
self.experiment.log_metric("Per-ep reward", np.mean(cumulative_reward), step=step)
self.experiment.log_metric("Megabytes sent", self.sent_mb, step=step)
self.experiment.log_metric("Round megabytes sent", round_mb, step=step)
self.experiment.log_metric("Chosen CW for legacy devices", CW, step=step)
self.experiment.log_metric("Chosen CW for 802.11ax devices", CW_ax, step=step)
self.experiment.log_metric("Station count", self.stations, step=step)
self.experiment.log_metric("Current throughput", self.current_speed, step=step)
self.experiment.log_metric("Fairness index", fairness, step=step)
for i, obs in enumerate(observations):
self.experiment.log_metric(f"Observation {i}", obs, step=step)
self.experiment.log_metrics(loss, step=step)
def log_episode(self, cumulative_reward, speed, step):
if self.send_logs:
self.experiment.log_metric("Cumulative reward", cumulative_reward, step=step)
self.experiment.log_metric("Speed", speed, step=step)
self.sent_mb = 0
self.last_speed = speed
self.speed_window = deque(maxlen=100)
self.current_speed = 0
def end(self):
if self.send_logs:
self.experiment.end()
)
# HTML
write_html(
output_directory + "/index.html",
iterations + 1,
config["image_save_iter"],
"images",
comet_exp=comet_exp,
)
if (iterations + 1) % config["image_display_iter"] == 0:
with torch.no_grad():
image_outputs = trainer.sample(train_display_images_a,
train_display_images_b)
write_2images(image_outputs, display_size, image_directory,
"train_current")
# Save network weights
if (iterations + 1) % config["snapshot_save_iter"] == 0:
trainer.save(checkpoint_directory, iterations)
iterations += 1
if iterations >= max_iter:
sys.exit("Finish training")
comet_exp.end()
subprocess.check_output(
"python -m comet_ml.scripts.upload {}".format(
str(Path(opts.output_path) / (comet_exp.id + ".zip"))),
shell=True,
)
class CometWriter:
def __init__(self,
logger,
project_name: Optional[str] = None,
experiment_name: Optional[str] = None,
api_key: Optional[str] = None,
log_dir: Optional[str] = None,
offline: bool = False,
**kwargs):
if not _COMET_AVAILABLE:
raise ImportError(
"You want to use `comet_ml` logger which is not installed yet,"
" install it with `pip install comet-ml`.")
self.project_name = project_name
self.experiment_name = experiment_name
self.kwargs = kwargs
self.timer = Timer()
if (api_key is not None) and (log_dir is not None):
self.mode = "offline" if offline else "online"
self.api_key = api_key
self.log_dir = log_dir
elif api_key is not None:
self.mode = "online"
self.api_key = api_key
self.log_dir = None
elif log_dir is not None:
self.mode = "offline"
self.log_dir = log_dir
else:
logger.warning(
"CometLogger requires either api_key or save_dir during initialization."
)
if self.mode == "online":
self.experiment = CometExperiment(
api_key=self.api_key,
project_name=self.project_name,
**self.kwargs,
)
else:
self.experiment = CometOfflineExperiment(
offline_directory=self.log_dir,
project_name=self.project_name,
**self.kwargs,
)
if self.experiment_name:
self.experiment.set_name(self.experiment_name)
def set_step(self, step, epoch=None, mode='train') -> None:
self.mode = mode
self.step = step
self.epoch = epoch
if step == 0:
self.timer.reset()
else:
duration = self.timer.check()
self.add_scalar({'steps_per_sec': 1 / duration})
def log_hyperparams(self, params: Dict[str, Any]) -> None:
self.experiment.log_parameters(params)
def log_code(self, file_name=None, folder='models/') -> None:
self.experiment.log_code(file_name=file_name, folder=folder)
def add_scalar(self,
metrics: Dict[str, Union[torch.Tensor, float]],
step: Optional[int] = None,
epoch: Optional[int] = None) -> None:
metrics_renamed = {}
for key, val in metrics.items():
tag = '{}/{}'.format(key, self.mode)
if is_tensor(val):
metrics_renamed[tag] = val.cpu().detach()
else:
metrics_renamed[tag] = val
if epoch is None:
self.experiment.log_metrics(metrics_renamed,
step=self.step,
epoch=self.epoch)
else:
self.experiment.log_metrics(metrics_renamed, epoch=epoch)
def add_plot(self, figure_name, figure):
"""
Primarily for log gate plots
"""
self.experiment.log_figure(figure_name=figure_name, figure=figure)
def add_hist3d(self, hist, name):
"""
Primarily for log gate plots
"""
self.experiment.log_histogram_3d(hist, name=name)
def reset_experiment(self):
self.experiment = None
def finalize(self) -> None:
self.experiment.end()
self.reset_experiment()
class CometLogger(Logger):
def __init__(
self,
batch_size: int,
snapshot_dir: Optional[str] = None,
snapshot_mode: str = "last",
snapshot_gap: int = 1,
exp_set: Optional[str] = None,
use_print_exp: bool = False,
saved_exp: Optional[str] = None,
**kwargs,
):
"""
:param kwargs: passed to comet's Experiment at init.
"""
if use_print_exp:
self.experiment = PrintExperiment()
else:
from comet_ml import Experiment, ExistingExperiment, OfflineExperiment
if saved_exp:
self.experiment = ExistingExperiment(
previous_experiment=saved_exp, **kwargs
)
else:
try:
self.experiment = Experiment(**kwargs)
except ValueError: # no API key
log_dir = Path.home() / "logs"
log_dir.mkdir(exist_ok=True)
self.experiment = OfflineExperiment(offline_directory=str(log_dir))
self.experiment.log_parameter("complete", False)
if exp_set:
self.experiment.log_parameter("exp_set", exp_set)
if snapshot_dir:
snapshot_dir = Path(snapshot_dir) / self.experiment.get_key()
# log_traj_window (int): How many trajectories to hold in deque for computing performance statistics.
self.log_traj_window = 100
self._cum_metrics = {
"n_unsafe_actions": 0,
"constraint_used": 0,
"cum_completed_trajs": 0,
"logging_time": 0,
}
self._new_completed_trajs = 0
self._last_step = 0
self._start_time = self._last_time = time()
self._last_snapshot_upload = 0
self._snaphot_upload_time = 30 * 60
super().__init__(batch_size, snapshot_dir, snapshot_mode, snapshot_gap)
def log_fast(
self,
step: int,
traj_infos: Sequence[Dict[str, float]],
opt_info: Optional[Tuple[Sequence[float], ...]] = None,
test: bool = False,
) -> None:
if not traj_infos:
return
start = time()
self._new_completed_trajs += len(traj_infos)
self._cum_metrics["cum_completed_trajs"] += len(traj_infos)
# TODO: do we need to support sum(t[k]) if key in k?
# without that, this doesn't include anything from extra eval samplers
for key in self._cum_metrics:
if key == "cum_completed_trajs":
continue
self._cum_metrics[key] += sum(t.get(key, 0) for t in traj_infos)
self._cum_metrics["logging_time"] += time() - start
def log(
self,
step: int,
traj_infos: Sequence[Dict[str, float]],
opt_info: Optional[Tuple[Sequence[float], ...]] = None,
test: bool = False,
):
self.log_fast(step, traj_infos, opt_info, test)
start = time()
with (self.experiment.test() if test else nullcontext()):
step *= self.batch_size
if opt_info is not None:
# grad norm is left on the GPU for some reason
# https://github.com/astooke/rlpyt/issues/163
self.experiment.log_metrics(
{
k: np.mean(v)
for k, v in opt_info._asdict().items()
if k != "gradNorm"
},
step=step,
)
if traj_infos:
agg_vals = {}
for key in traj_infos[0].keys():
if key in self._cum_metrics:
continue
agg_vals[key] = sum(t[key] for t in traj_infos) / len(traj_infos)
self.experiment.log_metrics(agg_vals, step=step)
if not test:
now = time()
self.experiment.log_metrics(
{
"new_completed_trajs": self._new_completed_trajs,
"steps_per_second": (step - self._last_step)
/ (now - self._last_time),
},
step=step,
)
self._last_time = now
self._last_step = step
self._new_completed_trajs = 0
self.experiment.log_metrics(self._cum_metrics, step=step)
self._cum_metrics["logging_time"] += time() - start
def log_metric(self, name, val):
self.experiment.log_metric(name, val)
def log_parameters(self, parameters):
self.experiment.log_parameters(parameters)
def log_config(self, config):
self.experiment.log_parameter("config", json.dumps(convert_dict(config)))
def upload_snapshot(self):
if self.snapshot_dir:
self.experiment.log_asset(self._previous_snapshot_fname)
def save_itr_params(
self, step: int, params: Dict[str, Any], metric: Optional[float] = None
) -> None:
super().save_itr_params(step, params, metric)
now = time()
if now - self._last_snapshot_upload > self._snaphot_upload_time:
self._last_snapshot_upload = now
self.upload_snapshot()
def shutdown(self, error: bool = False) -> None:
if not error:
self.upload_snapshot()
self.experiment.log_parameter("complete", True)
self.experiment.end()
def run_experiment_iter(i, experiment, train_iter, nExp, agent_list, env,
video, user_seed, experiment_name, log_params, debug,
project_name, sps, sps_es, **kwargs):
"""
Function used to paralelize the run_experiment calculations.
Parameters
----------
i : int
Index of the agent being trained.
Raises
------
NotImplementedError
In case Comet is used, raises this error to signal where user intervention
is required (namely to set the api_key and the workspace).
Returns
-------
rewards : array
An array with the cumulative rewards, where each column corresponds to
an agent (random seed), and each row to a training iteration.
arms : array
An array with the number of agent arms, where each column corresponds
to an agent (random seed), and each row to a training iteration.
agent : Agent
The trained agent.
"""
if debug:
start = time.time()
print("Experiment {0} out of {1}...".format(i + 1, nExp))
if not user_seed:
seed = int.from_bytes(os.urandom(4), 'big')
else:
seed = user_seed
if experiment_name:
raise NotImplementedError(
"Before using Comet, you need to come here and set your API key")
experiment = Experiment(api_key=None,
project_name=project_name,
workspace=None,
display_summary=False,
offline_directory="offline")
experiment.add_tag(experiment_name)
experiment.set_name("{0}_{1}".format(experiment_name, i))
# Sometimes adding the tag fails
log_params["experiment_tag"] = experiment_name
experiment.log_parameters(log_params)
agent = agent_list[i]
if sps_es: # This one overrides sps
rewards, arms, agent = run_sps_es_experiment(agent,
env,
train_iter,
seed=seed,
video=video,
experiment=experiment,
**kwargs)
elif sps:
rewards, arms, agent = run_sps_experiment(agent,
env,
train_iter,
seed=seed,
video=video,
experiment=experiment,
**kwargs)
else:
rewards, arms, agent = run_aql_experiment(agent,
env,
train_iter,
seed=seed,
video=video,
experiment=experiment,
**kwargs)
agent_list[i] = agent
if experiment:
experiment.end()
if debug:
end = time.time()
elapsed = end - start
units = "secs"
if elapsed > 3600:
elapsed /= 3600
units = "hours"
elif elapsed > 60:
elapsed /= 60
units = "mins"
print("Time elapsed: {0:.02f} {1}".format(elapsed, units))
return rewards, arms, agent
def main(args):
print('Pretrain? ', not args.not_pretrain)
print(args.model)
start_time = time.time()
if opt['local_comet_dir']:
comet_exp = OfflineExperiment(api_key="hIXq6lDzWzz24zgKv7RYz6blo",
project_name="selfcifar",
workspace="cinjon",
auto_metric_logging=True,
auto_output_logging=None,
auto_param_logging=False,
offline_directory=opt['local_comet_dir'])
else:
comet_exp = CometExperiment(api_key="hIXq6lDzWzz24zgKv7RYz6blo",
project_name="selfcifar",
workspace="cinjon",
auto_metric_logging=True,
auto_output_logging=None,
auto_param_logging=False)
comet_exp.log_parameters(vars(args))
comet_exp.set_name(args.name)
# Build model
# path = "/misc/kcgscratch1/ChoGroup/resnick/spaceofmotion/zeping/bsn"
linear_cls = NonLinearModel if args.do_nonlinear else LinearModel
if args.model == "amdim":
hparams = load_hparams_from_tags_csv(
'/checkpoint/cinjon/amdim/meta_tags.csv')
# hparams = load_hparams_from_tags_csv(os.path.join(path, "meta_tags.csv"))
model = AMDIMModel(hparams)
if not args.not_pretrain:
# _path = os.path.join(path, "_ckpt_epoch_434.ckpt")
_path = '/checkpoint/cinjon/amdim/_ckpt_epoch_434.ckpt'
model.load_state_dict(torch.load(_path)["state_dict"])
else:
print("AMDIM not loading checkpoint") # Debug
linear_model = linear_cls(AMDIM_OUTPUT_DIM, args.num_classes)
elif args.model == "ccc":
model = CCCModel(None)
if not args.not_pretrain:
# _path = os.path.join(path, "TimeCycleCkpt14.pth")
_path = '/checkpoint/cinjon/spaceofmotion/bsn/TimeCycleCkpt14.pth'
checkpoint = torch.load(_path)
base_dict = {
'.'.join(k.split('.')[1:]): v
for k, v in list(checkpoint['state_dict'].items())
}
model.load_state_dict(base_dict)
else:
print("CCC not loading checkpoint") # Debug
linear_model = linaer_cls(CCC_OUTPUT_DIM,
args.num_classes) #.to(device)
elif args.model == "corrflow":
model = CORRFLOWModel(None)
if not args.not_pretrain:
_path = '/checkpoint/cinjon/spaceofmotion/supercons/corrflow.kineticsmodel.pth'
# _path = os.path.join(path, "corrflow.kineticsmodel.pth")
checkpoint = torch.load(_path)
base_dict = {
'.'.join(k.split('.')[1:]): v
for k, v in list(checkpoint['state_dict'].items())
}
model.load_state_dict(base_dict)
else:
print("CorrFlow not loading checkpoing") # Debug
linear_model = linear_cls(CORRFLOW_OUTPUT_DIM, args.num_classes)
elif args.model == "resnet":
if not args.not_pretrain:
resnet = torchvision.models.resnet50(pretrained=True)
else:
resnet = torchvision.models.resnet50(pretrained=False)
print("ResNet not loading checkpoint") # Debug
modules = list(resnet.children())[:-1]
model = nn.Sequential(*modules)
linear_model = linear_cls(RESNET_OUTPUT_DIM, args.num_classes)
else:
raise Exception("model type has to be amdim, ccc, corrflow or resnet")
if torch.cuda.device_count() > 1:
model = nn.DataParallel(model).to(device)
linear_model = nn.DataParallel(linear_model).to(device)
else:
model = model.to(device)
linear_model = linear_model.to(device)
# model = model.to(device)
# linear_model = linear_model.to(device)
# Freeze model
for p in model.parameters():
p.requires_grad = False
model.eval()
if args.optimizer == "Adam":
optimizer = optim.Adam(linear_model.parameters(),
lr=args.lr,
weight_decay=args.weight_decay)
print("Optimizer: Adam with weight decay: {}".format(
args.weight_decay))
elif args.optimizer == "SGD":
optimizer = optim.SGD(linear_model.parameters(),
lr=args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
print("Optimizer: SGD with weight decay: {} momentum: {}".format(
args.weight_decay, args.momentum))
else:
raise Exception("optimizer should be Adam or SGD")
optimizer.zero_grad()
# Set up log dir
now = datetime.datetime.now()
log_dir = '/checkpoint/cinjon/spaceofmotion/bsn/cifar-%d-weights/%s/%s' % (
args.num_classes, args.model, args.name)
# log_dir = "{}{:%Y%m%dT%H%M}".format(args.model, now)
# log_dir = os.path.join("weights", log_dir)
if not os.path.exists(log_dir):
os.makedirs(log_dir)
print("Saving to {}".format(log_dir))
batch_size = args.batch_size * torch.cuda.device_count()
# CIFAR-10
if args.num_classes == 10:
data_path = ("/private/home/cinjon/cifar-data/cifar-10-batches-py")
_train_dataset = CIFAR_dataset(glob(os.path.join(data_path, "data*")),
args.num_classes, args.model, True)
# _train_acc_dataset = CIFAR_dataset(
# glob(os.path.join(data_path, "data*")),
# args.num_classes,
# args.model,
# False)
train_dataloader = data.DataLoader(_train_dataset,
shuffle=True,
batch_size=batch_size,
num_workers=args.num_workers)
# train_split = int(len(_train_dataset) * 0.8)
# train_dev_split = int(len(_train_dataset) - train_split)
# train_dataset, train_dev_dataset = data.random_split(
# _train_dataset, [train_split, train_dev_split])
# train_acc_dataloader = data.DataLoader(
# train_dataset, shuffle=False, batch_size=batch_size, num_workers=args.num_workers)
# train_dev_acc_dataloader = data.DataLoader(
# train_dev_dataset, shuffle=False, batch_size=batch_size, num_workers=args.num_workers)
# train_dataset = data.Subset(_train_dataset, list(range(train_split)))
# train_dataloader = data.DataLoader(
# train_dataset, shuffle=True, batch_size=batch_size, num_workers=args.num_workers)
# train_acc_dataset = data.Subset(
# _train_acc_dataset, list(range(train_split)))
# train_acc_dataloader = data.DataLoader(
# train_acc_dataset, shuffle=False, batch_size=batch_size, num_workers=args.num_workers)
# train_dev_acc_dataset = data.Subset(
# _train_acc_dataset, list(range(train_split, len(_train_acc_dataset))))
# train_dev_acc_dataloader = data.DataLoader(
# train_dev_acc_dataset, shuffle=False, batch_size=batch_size, num_workers=args.num_workers)
_val_dataset = CIFAR_dataset([os.path.join(data_path, "test_batch")],
args.num_classes, args.model, False)
val_dataloader = data.DataLoader(_val_dataset,
shuffle=False,
batch_size=batch_size,
num_workers=args.num_workers)
# val_split = int(len(_val_dataset) * 0.8)
# val_dev_split = int(len(_val_dataset) - val_split)
# val_dataset, val_dev_dataset = data.random_split(
# _val_dataset, [val_split, val_dev_split])
# val_dataloader = data.DataLoader(
# val_dataset, shuffle=False, batch_size=batch_size, num_workers=args.num_workers)
# val_dev_dataloader = data.DataLoader(
# val_dev_dataset, shuffle=False, batch_size=batch_size, num_workers=args.num_workers)
# CIFAR-100
elif args.num_classes == 100:
data_path = ("/private/home/cinjon/cifar-data/cifar-100-python")
_train_dataset = CIFAR_dataset([os.path.join(data_path, "train")],
args.num_classes, args.model, True)
train_dataloader = data.DataLoader(_train_dataset,
shuffle=True,
batch_size=batch_size)
_val_dataset = CIFAR_dataset([os.path.join(data_path, "test")],
args.num_classes, args.model, False)
val_dataloader = data.DataLoader(_val_dataset,
shuffle=False,
batch_size=batch_size)
else:
raise Exception("num_classes should be 10 or 100")
best_acc = 0.0
best_epoch = 0
# Training
for epoch in range(1, args.epochs + 1):
current_lr = max(3e-4, args.lr *\
math.pow(0.5, math.floor(epoch / args.lr_interval)))
linear_model.train()
if args.optimizer == "Adam":
optimizer = optim.Adam(linear_model.parameters(),
lr=current_lr,
weight_decay=args.weight_decay)
elif args.optimizer == "SGD":
optimizer = optim.SGD(
linear_model.parameters(),
lr=current_lr,
momentum=args.momentum,
weight_decay=args.weight_decay,
)
####################################################
# Train
t = time.time()
train_acc = 0
train_loss_sum = 0.0
for iter, input in enumerate(train_dataloader):
if time.time(
) - start_time > args.time * 3600 - 300 and comet_exp is not None:
comet_exp.end()
sys.exit(-1)
imgs = input[0].to(device)
if args.model != "resnet":
imgs = imgs.unsqueeze(1)
lbls = input[1].flatten().to(device)
# output = model(imgs)
# output = linear_model(output)
output = linear_model(model(imgs))
loss = F.cross_entropy(output, lbls)
train_loss_sum += float(loss.data)
train_acc += int(sum(torch.argmax(output, dim=1) == lbls))
optimizer.zero_grad()
loss.backward()
optimizer.step()
# log_text = "train epoch {}/{}\titer {}/{} loss:{} {:.3f}s/iter"
if iter % 1500 == 0:
log_text = "train epoch {}/{}\titer {}/{} loss:{}"
print(log_text.format(epoch, args.epochs, iter + 1,
len(train_dataloader), loss.data,
time.time() - t),
flush=False)
t = time.time()
train_acc /= len(_train_dataset)
train_loss_sum /= len(train_dataloader)
with comet_exp.train():
comet_exp.log_metrics({
'acc': train_acc,
'loss': train_loss_sum
},
step=(epoch + 1) * len(train_dataloader),
epoch=epoch + 1)
print("train acc epoch {}/{} loss:{} train_acc:{}".format(
epoch, args.epochs, train_loss_sum, train_acc),
flush=True)
#######################################################################
# Train acc
# linear_model.eval()
# train_acc = 0
# train_loss_sum = 0.0
# for iter, input in enumerate(train_acc_dataloader):
# imgs = input[0].to(device)
# if args.model != "resnet":
# imgs = imgs.unsqueeze(1)
# lbls = input[1].flatten().to(device)
#
# # output = model(imgs)
# # output = linear_model(output)
# output = linear_model(model(imgs))
# loss = F.cross_entropy(output, lbls)
# train_loss_sum += float(loss.data)
# train_acc += int(sum(torch.argmax(output, dim=1) == lbls))
#
# print("train acc epoch {}/{}\titer {}/{} loss:{} {:.3f}s/iter".format(
# epoch,
# args.epochs,
# iter+1,
# len(train_acc_dataloader),
# loss.data,
# time.time() - t),
# flush=True)
# t = time.time()
#
#
# train_acc /= len(train_acc_dataset)
# train_loss_sum /= len(train_acc_dataloader)
# print("train acc epoch {}/{} loss:{} train_acc:{}".format(
# epoch, args.epochs, train_loss_sum, train_acc), flush=True)
#######################################################################
# Train dev acc
# # linear_model.eval()
# train_dev_acc = 0
# train_dev_loss_sum = 0.0
# for iter, input in enumerate(train_dev_acc_dataloader):
# imgs = input[0].to(device)
# if args.model != "resnet":
# imgs = imgs.unsqueeze(1)
# lbls = input[1].flatten().to(device)
#
# output = model(imgs)
# output = linear_model(output)
# # output = linear_model(model(imgs))
# loss = F.cross_entropy(output, lbls)
# train_dev_loss_sum += float(loss.data)
# train_dev_acc += int(sum(torch.argmax(output, dim=1) == lbls))
#
# print("train dev acc epoch {}/{}\titer {}/{} loss:{} {:.3f}s/iter".format(
# epoch,
# args.epochs,
# iter+1,
# len(train_dev_acc_dataloader),
# loss.data,
# time.time() - t),
# flush=True)
# t = time.time()
#
# train_dev_acc /= len(train_dev_acc_dataset)
# train_dev_loss_sum /= len(train_dev_acc_dataloader)
# print("train dev epoch {}/{} loss:{} train_dev_acc:{}".format(
# epoch, args.epochs, train_dev_loss_sum, train_dev_acc), flush=True)
#######################################################################
# Val dev
# # linear_model.eval()
# val_dev_acc = 0
# val_dev_loss_sum = 0.0
# for iter, input in enumerate(val_dev_dataloader):
# imgs = input[0].to(device)
# if args.model != "resnet":
# imgs = imgs.unsqueeze(1)
# lbls = input[1].flatten().to(device)
#
# output = model(imgs)
# output = linear_model(output)
# loss = F.cross_entropy(output, lbls)
# val_dev_loss_sum += float(loss.data)
# val_dev_acc += int(sum(torch.argmax(output, dim=1) == lbls))
#
# print("val dev epoch {}/{} iter {}/{} loss:{} {:.3f}s/iter".format(
# epoch,
# args.epochs,
# iter+1,
# len(val_dev_dataloader),
# loss.data,
# time.time() - t),
# flush=True)
# t = time.time()
#
# val_dev_acc /= len(val_dev_dataset)
# val_dev_loss_sum /= len(val_dev_dataloader)
# print("val dev epoch {}/{} loss:{} val_dev_acc:{}".format(
# epoch, args.epochs, val_dev_loss_sum, val_dev_acc), flush=True)
#######################################################################
# Val
linear_model.eval()
val_acc = 0
val_loss_sum = 0.0
for iter, input in enumerate(val_dataloader):
if time.time(
) - start_time > args.time * 3600 - 300 and comet_exp is not None:
comet_exp.end()
sys.exit(-1)
imgs = input[0].to(device)
if args.model != "resnet":
imgs = imgs.unsqueeze(1)
lbls = input[1].flatten().to(device)
output = model(imgs)
output = linear_model(output)
loss = F.cross_entropy(output, lbls)
val_loss_sum += float(loss.data)
val_acc += int(sum(torch.argmax(output, dim=1) == lbls))
# log_text = "val epoch {}/{} iter {}/{} loss:{} {:.3f}s/iter"
if iter % 1500 == 0:
log_text = "val epoch {}/{} iter {}/{} loss:{}"
print(log_text.format(epoch, args.epochs, iter + 1,
len(val_dataloader), loss.data,
time.time() - t),
flush=False)
t = time.time()
val_acc /= len(_val_dataset)
val_loss_sum /= len(val_dataloader)
print("val epoch {}/{} loss:{} val_acc:{}".format(
epoch, args.epochs, val_loss_sum, val_acc))
with comet_exp.test():
comet_exp.log_metrics({
'acc': val_acc,
'loss': val_loss_sum
},
step=(epoch + 1) * len(train_dataloader),
epoch=epoch + 1)
if val_acc > best_acc:
best_acc = val_acc
best_epoch = epoch
linear_save_path = os.path.join(log_dir,
"{}.linear.pth".format(epoch))
model_save_path = os.path.join(log_dir,
"{}.model.pth".format(epoch))
torch.save(linear_model.state_dict(), linear_save_path)
torch.save(model.state_dict(), model_save_path)
# Check bias and variance
print(
"Epoch {} lr {} total: train_loss:{} train_acc:{} val_loss:{} val_acc:{}"
.format(epoch, current_lr, train_loss_sum, train_acc, val_loss_sum,
val_acc),
flush=True)
# print("Epoch {} lr {} total: train_acc:{} train_dev_acc:{} val_dev_acc:{} val_acc:{}".format(
# epoch, current_lr, train_acc, train_dev_acc, val_dev_acc, val_acc), flush=True)
print("The best epoch: {} acc: {}".format(best_epoch, best_acc))