class TrainingStats(object):
"""Track vital training statistics."""
def __init__(self, model):
# Window size for smoothing tracked values (with median filtering)
self.WIN_SZ = int(20 / cfg.NUM_GPUS)
# Output logging period in SGD iterations
self.LOG_PERIOD = int(20 /cfg.NUM_GPUS)
self.smoothed_losses_and_metrics = {
key: SmoothedValue(self.WIN_SZ)
for key in model.losses + model.metrics
}
self.losses_and_metrics = {
key: 0
for key in model.losses + model.metrics
}
self.smoothed_total_loss = SmoothedValue(self.WIN_SZ)
self.smoothed_mb_qsize = SmoothedValue(self.WIN_SZ)
self.iter_total_loss = np.nan
self.iter_timer = Timer()
self.model = model
def IterTic(self):
self.iter_timer.tic()
def IterToc(self):
return self.iter_timer.toc(average=False)
def ResetIterTimer(self):
self.iter_timer.reset()
def UpdateIterStats(self):
"""Update tracked iteration statistics."""
for k in self.losses_and_metrics.keys():
if k in self.model.losses:
self.losses_and_metrics[k] = nu.sum_multi_gpu_blob(k)
else:
self.losses_and_metrics[k] = nu.average_multi_gpu_blob(k)
for k, v in self.smoothed_losses_and_metrics.items():
v.AddValue(self.losses_and_metrics[k])
self.iter_total_loss = np.sum(
np.array([self.losses_and_metrics[k] for k in self.model.losses])
)
self.smoothed_total_loss.AddValue(self.iter_total_loss)
self.smoothed_mb_qsize.AddValue(
self.model.roi_data_loader._minibatch_queue.qsize()
)
def LogIterStats(self, cur_iter, lr):
"""Log the tracked statistics."""
num_iter_per_epoch = self.model.roi_data_loader.get_num_iter_per_epoch()
if (cur_iter % self.LOG_PERIOD == 0 or
cur_iter == cfg.SOLVER.MAX_ITER * num_iter_per_epoch - 1):
stats = self.GetStats(cur_iter, lr)
log_json_stats(stats)
def GetStats(self, cur_iter, lr):
num_iter_per_epoch = self.model.roi_data_loader.get_num_iter_per_epoch()
eta_seconds = self.iter_timer.average_time * (
cfg.SOLVER.MAX_ITER * num_iter_per_epoch - cur_iter
)
eta = str(datetime.timedelta(seconds=int(eta_seconds)))
mem_stats = c2_py_utils.GetGPUMemoryUsageStats()
mem_usage = np.max(mem_stats['max_by_gpu'][:cfg.NUM_GPUS])
stats = dict(
iter=cur_iter,
lr=float(lr),
time=self.iter_timer.average_time,
loss=self.smoothed_total_loss.GetAverageValue(),
eta=eta,
mb_qsize=int(
np.round(self.smoothed_mb_qsize.GetAverageValue())
),
mem=int(np.ceil(mem_usage / 1024 / 1024))
)
for k, v in self.smoothed_losses_and_metrics.items():
stats[k] = v.GetAverageValue()
return stats
class TrainingStats(object):
"""Track vital training statistics."""
def __init__(self, model):
# Window size for smoothing tracked values (with median filtering)
self.WIN_SZ = int(1280 / cfg.NUM_GPUS)
# Output logging period in SGD iterations
self.LOG_PERIOD = int(1280 / cfg.NUM_GPUS)
self.smoothed_losses_and_metrics = {
key: SmoothedValue(self.WIN_SZ)
for key in model.losses + model.metrics
}
self.losses_and_metrics = {
key: 0
for key in model.losses + model.metrics
}
self.smoothed_total_loss = SmoothedValue(self.WIN_SZ)
self.smoothed_mb_qsize = SmoothedValue(self.WIN_SZ)
self.iter_total_loss = np.nan
self.iter_timer = Timer()
self.model = model
self.mem = dict()
self.mem = None
def IterTic(self):
self.iter_timer.tic()
def IterToc(self):
return self.iter_timer.toc(average=False)
def ResetIterTimer(self):
self.iter_timer.reset()
def UpdateIterStats(self):
"""Update tracked iteration statistics."""
for k in self.losses_and_metrics.keys():
self.losses_and_metrics[k] = nu.average_multi_gpu_blob(k)
for k, v in self.smoothed_losses_and_metrics.items():
v.AddValue(self.losses_and_metrics[k])
self.iter_total_loss = np.sum(
np.array([self.losses_and_metrics[k] for k in self.model.losses]))
self.smoothed_total_loss.AddValue(self.iter_total_loss)
self.smoothed_mb_qsize.AddValue(
self.model.roi_data_loader._minibatch_queue.qsize())
if self.mem is not None:
self.GetMem()
def LogIterStats(self, cur_iter, lr):
"""Log the tracked statistics."""
if (cur_iter % self.LOG_PERIOD == 0
or cur_iter == cfg.SOLVER.MAX_ITER - 1):
stats = self.GetStats(cur_iter, lr)
log_json_stats(stats)
if self.mem is not None:
mem_sorted = sorted(self.mem.items(), key=lambda d: d[1])
print(mem_sorted)
def GetStats(self, cur_iter, lr):
eta_seconds = self.iter_timer.average_time * (cfg.SOLVER.MAX_ITER -
cur_iter)
eta = str(datetime.timedelta(seconds=int(eta_seconds)))
mem_stats = c2_py_utils.GetGPUMemoryUsageStats()
mem_usage = np.max(mem_stats['max_by_gpu'][:cfg.NUM_GPUS])
stats = dict(iter=cur_iter,
lr=float(lr),
time=self.iter_timer.average_time,
loss=self.smoothed_total_loss.GetAverageValue(),
eta=eta,
mb_qsize=int(
np.round(self.smoothed_mb_qsize.GetAverageValue())),
mem=int(np.ceil(mem_usage / 1024 / 1024)))
for k, v in self.smoothed_losses_and_metrics.items():
stats[k] = v.GetAverageValue()
return stats
def is_grad(self, b):
name = str(b)
return name.endswith("_grad")
def is_shared(self, b):
name = str(b)
return name.endswith("_shared")
def GetMem(self):
for op_idx in range(len(self.model.net._net.op)):
op = self.model.net._net.op[op_idx]
for b in list(op.output):
if self.is_grad(b):
pass
elif self.is_shared(b):
pass
else:
continue
blob = workspace.FetchBlob(str(b))
if b not in self.mem.keys():
self.mem[str(b)] = 0
self.mem[str(b)] = max(self.mem[str(b)], blob.size)
class TrainingStats(object):
"""Track vital training statistics."""
def __init__(self, model):
# Window size for smoothing tracked values (with median filtering)
self.WIN_SZ = 20
# Output logging period in SGD iterations
self.LOG_PERIOD = 20
self.smoothed_losses_and_metrics = {
key: SmoothedValue(self.WIN_SZ)
for key in model.losses + model.metrics
}
self.losses_and_metrics = {
key: 0
for key in model.losses + model.metrics
}
self.smoothed_total_loss = SmoothedValue(self.WIN_SZ)
self.smoothed_mb_qsize = SmoothedValue(self.WIN_SZ)
self.iter_total_loss = np.nan
self.iter_timer = Timer()
self.model = model
def IterTic(self):
self.iter_timer.tic()
def IterToc(self):
return self.iter_timer.toc(average=False)
def ResetIterTimer(self):
self.iter_timer.reset()
def UpdateIterStats(self):
"""Update tracked iteration statistics."""
for k in self.losses_and_metrics.keys():
if k in self.model.losses:
self.losses_and_metrics[k] = nu.sum_multi_gpu_blob(k)
else:
self.losses_and_metrics[k] = nu.average_multi_gpu_blob(k)
for k, v in self.smoothed_losses_and_metrics.items():
v.AddValue(self.losses_and_metrics[k])
self.iter_total_loss = np.sum(
np.array([self.losses_and_metrics[k] for k in self.model.losses])
)
self.smoothed_total_loss.AddValue(self.iter_total_loss)
self.smoothed_mb_qsize.AddValue(
self.model.roi_data_loader._minibatch_queue.qsize()
)
def LogIterStats(self, cur_iter, lr):
"""Log the tracked statistics."""
if (cur_iter % self.LOG_PERIOD == 0 or
cur_iter == cfg.SOLVER.MAX_ITER - 1):
stats = self.GetStats(cur_iter, lr)
log_json_stats(stats)
def GetStats(self, cur_iter, lr):
eta_seconds = self.iter_timer.average_time * (
cfg.SOLVER.MAX_ITER - cur_iter
)
eta = str(datetime.timedelta(seconds=int(eta_seconds)))
mem_stats = c2_py_utils.GetGPUMemoryUsageStats()
mem_usage = np.max(mem_stats['max_by_gpu'][:cfg.NUM_GPUS])
stats = dict(
iter=cur_iter,
lr=float(lr),
time=self.iter_timer.average_time,
loss=self.smoothed_total_loss.GetMedianValue(),
eta=eta,
mb_qsize=int(
np.round(self.smoothed_mb_qsize.GetMedianValue())
),
mem=int(np.ceil(mem_usage / 1024 / 1024))
)
for k, v in self.smoothed_losses_and_metrics.items():
stats[k] = v.GetMedianValue()
return stats
class TrainingStats(object):
"""Track vital training statistics."""
def __init__(self, model):
# Window size for smoothing tracked values (with median filtering)
self.WIN_SZ = 1
# Output logging period in SGD iterations
self.LOG_PERIOD = 1
self.smoothed_losses_and_metrics = {
key: SmoothedValue(self.WIN_SZ)
for key in model.losses + model.metrics
}
self.losses_and_metrics = {
key: 0
for key in model.losses + model.metrics
}
self.smoothed_total_loss = SmoothedValue(self.WIN_SZ)
self.smoothed_mb_qsize = SmoothedValue(self.WIN_SZ)
self.iter_total_loss = np.nan
self.iter_timer = Timer()
self.model = model
def IterTic(self):
self.iter_timer.tic()
def IterToc(self):
return self.iter_timer.toc(average=False)
def ResetIterTimer(self):
self.iter_timer.reset()
def UpdateIterStats(self):
"""Update tracked iteration statistics."""
for k in self.losses_and_metrics.keys():
if k in self.model.losses:
self.losses_and_metrics[k] = nu.sum_multi_gpu_blob(k)
else:
self.losses_and_metrics[k] = nu.average_multi_gpu_blob(k)
for k, v in self.smoothed_losses_and_metrics.items():
v.AddValue(self.losses_and_metrics[k])
self.iter_total_loss = np.sum(
np.array([self.losses_and_metrics[k] for k in self.model.losses]))
self.smoothed_total_loss.AddValue(self.iter_total_loss)
self.smoothed_mb_qsize.AddValue(
self.model.roi_data_loader._minibatch_queue.qsize())
def LogIterStats(self, cur_iter, lr):
"""Log the tracked statistics."""
if (cur_iter % self.LOG_PERIOD == 0
or cur_iter == cfg.SOLVER.MAX_ITER - 1):
stats = self.GetStats(cur_iter, lr)
log_json_stats(stats)
def GetStats(self, cur_iter, lr):
eta_seconds = self.iter_timer.average_time * (cfg.SOLVER.MAX_ITER -
cur_iter)
eta = str(datetime.timedelta(seconds=int(eta_seconds)))
mem_stats = c2_py_utils.GetGPUMemoryUsageStats()
mem_usage = np.max(mem_stats['max_by_gpu'][:cfg.NUM_GPUS])
stats = dict(
iter=cur_iter,
lr=float(lr),
time=self.iter_timer.average_time,
loss=self.smoothed_total_loss.GetMedianValue(),
eta=eta,
mb_qsize=int(np.round(self.smoothed_mb_qsize.GetMedianValue())),
mem=int(np.ceil(mem_usage / 1024 / 1024)),
)
if cfg.TRAIN.DA_FADE_IN:
stats['da_weight'] = self.model.da_fade_in.get_weight()
if cfg.TRAIN.PADA:
stats[
'avg_pada_weight'] = self.model.class_weight_db.get_avg_pada_weight(
)
stats[
'total_detects'] = self.model.class_weight_db.total_sum_softmax.sum(
) / 2
stats['KL_div'] = self.model.class_weight_db.get_KL_to_init()
stats['accuracy_fg'] = self.model.class_weight_db.fg_acc.get()
stats[
'acc_fg_weighted'] = self.model.class_weight_db.weighted_fg_acc.get(
)
target_dist = self.model.class_weight_db.get_dist()
print('target_dist: {}'.format(list(target_dist)))
class_weights = self.model.class_weight_db.class_weights
print('class_weights: {}'.format(list(class_weights)))
classes = np.array(
dummy_datasets.get_coco_dataset().classes.values(), dtype=str)
for dist in [target_dist, class_weights]:
order = np.argsort(dist)[::-1]
o_target_dist = target_dist[order]
o_classes = classes[order]
cwo = class_weights[order]
print("dist tops: ", end='')
for prob, w, c in list(zip(o_target_dist, cwo, o_classes))[:5]:
print("{}:{:.3f} ({:.3f})".format(c, prob, w), end='; ')
print()
print()
for k, v in self.smoothed_losses_and_metrics.items():
stats[k] = v.GetMedianValue()
# for k,v in stats.items():
# print(k,v)
return stats
class TrainingStats(object):
"""Track vital training statistics."""
def __init__(self, model, tensorflow_board=None):
# Window size for smoothing tracked values (with median filtering)
self.WIN_SZ = 20
# Output logging period in SGD iterations
self.LOG_PERIOD = 20
self.smoothed_losses_and_metrics = {
key: SmoothedValue(self.WIN_SZ)
for key in model.losses + model.metrics
}
self.losses_and_metrics = {
key: 0
for key in model.losses + model.metrics
}
self.smoothed_total_loss = SmoothedValue(self.WIN_SZ)
self.smoothed_mb_qsize = SmoothedValue(self.WIN_SZ)
self.iter_total_loss = np.nan
self.iter_timer = Timer()
self.model = model
self.tblogger = tensorflow_board
self.tb_ignored_keys = ['iter', 'eta', 'mb_qsize', 'mem', 'time']
def IterTic(self):
self.iter_timer.tic()
def IterToc(self):
return self.iter_timer.toc(average=False)
def ResetIterTimer(self):
self.iter_timer.reset()
def UpdateIterStats(self):
"""Update tracked iteration statistics."""
for k in self.losses_and_metrics.keys():
if k in self.model.losses:
self.losses_and_metrics[k] = nu.sum_multi_gpu_blob(k)
else:
self.losses_and_metrics[k] = nu.average_multi_gpu_blob(k)
for k, v in self.smoothed_losses_and_metrics.items():
v.AddValue(self.losses_and_metrics[k])
self.iter_total_loss = np.sum(
np.array([self.losses_and_metrics[k] for k in self.model.losses]))
self.smoothed_total_loss.AddValue(self.iter_total_loss)
self.smoothed_mb_qsize.AddValue(
self.model.roi_data_loader._minibatch_queue.qsize())
def LogIterStats(self, cur_iter, lr):
"""Log the tracked statistics."""
if (cur_iter % self.LOG_PERIOD == 0
or cur_iter == cfg.SOLVER.MAX_ITER - 1):
stats = self.GetStats(cur_iter, lr)
log_json_stats(stats)
if self.tblogger:
self.tb_log_stats(stats, cur_iter)
def tb_log_stats(self, stats, cur_iter):
"""Log the tracked statistics to tensorboard"""
for k in stats:
if k not in self.tb_ignored_keys:
v = stats[k]
if isinstance(v, dict):
self.tb_log_stats(v, cur_iter)
else:
self.tblogger.write_scalars({k: v}, cur_iter)
def GetStats(self, cur_iter, lr):
eta_seconds = self.iter_timer.average_time * (cfg.SOLVER.MAX_ITER -
cur_iter)
eta = str(datetime.timedelta(seconds=int(eta_seconds)))
mem_stats = c2_py_utils.GetGPUMemoryUsageStats()
mem_usage = np.max(mem_stats['max_by_gpu'][:cfg.NUM_GPUS])
stats = dict(iter=cur_iter,
lr=float(lr),
time=self.iter_timer.average_time,
loss=self.smoothed_total_loss.GetMedianValue(),
eta=eta,
mb_qsize=int(
np.round(self.smoothed_mb_qsize.GetMedianValue())),
mem=int(np.ceil(mem_usage / 1024 / 1024)))
for k, v in self.smoothed_losses_and_metrics.items():
stats[k] = v.GetMedianValue()
return stats
class TrainingStats(object):
"""Track vital training statistics."""
def __init__(self, model, writer):
# Window size for smoothing tracked values (with median filtering)
self.WIN_SZ = 20
# Output logging period in SGD iterations
self.LOG_PERIOD = 20
self.smoothed_losses_and_metrics = {
key: SmoothedValue(self.WIN_SZ)
for key in model.losses + model.metrics
}
self.losses_and_metrics = {
key: 0
for key in model.losses + model.metrics
}
self.smoothed_total_loss = SmoothedValue(self.WIN_SZ)
self.smoothed_mb_qsize = SmoothedValue(self.WIN_SZ)
self.iter_total_loss = np.nan
self.iter_timer = Timer()
self.model = model
self.writer = writer
def IterTic(self):
self.iter_timer.tic()
def IterToc(self):
return self.iter_timer.toc(average=False)
def ResetIterTimer(self):
self.iter_timer.reset()
def UpdateIterStats(self, i_iter=0):
"""Update tracked iteration statistics."""
for k in self.losses_and_metrics.keys():
if k in self.model.losses:
self.losses_and_metrics[k] = nu.sum_multi_gpu_blob(k)
else:
self.losses_and_metrics[k] = nu.average_multi_gpu_blob(k)
for k, v in self.smoothed_losses_and_metrics.items():
v.AddValue(self.losses_and_metrics[k])
self.writer.add_scalar(k, self.losses_and_metrics[k], i_iter)
self.iter_total_loss = np.sum(
np.array([self.losses_and_metrics[k] for k in self.model.losses])
)
self.smoothed_total_loss.AddValue(self.iter_total_loss)
# self.smoothed_mb_qsize.AddValue(
# self.model.roi_data_loader._minibatch_queue.qsize()
# )
def LogIterStats(self, cur_iter, lr):
"""Log the tracked statistics."""
if (cur_iter % self.LOG_PERIOD == 0 or
cur_iter == cfg.SOLVER.MAX_ITER - 1):
stats = self.GetStats(cur_iter, lr)
log_json_stats(stats)
def GetStats(self, cur_iter, lr):
eta_seconds = self.iter_timer.average_time * (
cfg.SOLVER.MAX_ITER - cur_iter
)
eta = str(datetime.timedelta(seconds=int(eta_seconds)))
mem_stats = c2_py_utils.GetGPUMemoryUsageStats()
mem_usage = np.max(mem_stats['max_by_gpu'][:cfg.NUM_GPUS])
stats = dict(
iter=cur_iter,
lr=float(lr),
time=self.iter_timer.average_time,
loss=self.smoothed_total_loss.GetMedianValue(),
eta=eta,
# mb_qsize=int(
# np.round(self.smoothed_mb_qsize.GetMedianValue())
# ),
mem=int(np.ceil(mem_usage / 1024 / 1024))
)
for k, v in self.smoothed_losses_and_metrics.items():
stats[k] = v.GetMedianValue()
return stats
def SaveTrainingStates(self, save_file):
save_state = {
key:0 for key in self.smoothed_losses_and_metrics.keys()
}
save_smooth_state = {
key:0 for key in self.smoothed_losses_and_metrics.keys()
}
for k, v in self.smoothed_losses_and_metrics.items():
save_state[k] = v.series
save_smooth_state[k] = v.smooth_series
save_state['total_loss'] = self.smoothed_total_loss.series
save_smooth_state['total_loss'] = self.smoothed_total_loss.series
# print(save_state)
with open(save_file, 'w') as f:
json.dump(save_state, f)
# save smooth state
save_smooth_file = save_file.replace('.json', '_smooth.json')
with open(save_smooth_file, 'w') as f:
json.dump(save_smooth_state, f)
