From 2acef4bdaea588adee3098a057a395937dff4e6a Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期一, 08 一月 2024 16:51:42 +0800
Subject: [PATCH] json stamp_sents for websocket-server
---
funasr/train/trainer.py | 35 +++++++++++++++++++++++------------
1 files changed, 23 insertions(+), 12 deletions(-)
diff --git a/funasr/train/trainer.py b/funasr/train/trainer.py
index 4f83ace..a5069d0 100644
--- a/funasr/train/trainer.py
+++ b/funasr/train/trainer.py
@@ -26,7 +26,6 @@
import torch
import torch.nn
import torch.optim
-from typeguard import check_argument_types
from funasr.iterators.abs_iter_factory import AbsIterFactory
from funasr.main_funcs.average_nbest_models import average_nbest_models
@@ -44,6 +43,7 @@
from funasr.train.reporter import Reporter
from funasr.train.reporter import SubReporter
from funasr.utils.build_dataclass import build_dataclass
+from funasr.utils.kwargs2args import kwargs2args
if torch.distributed.is_available():
from torch.distributed import ReduceOp
@@ -126,7 +126,6 @@
@classmethod
def build_options(cls, args: argparse.Namespace) -> TrainerOptions:
"""Build options consumed by train(), eval()"""
- assert check_argument_types()
return build_dataclass(TrainerOptions, args)
@classmethod
@@ -187,7 +186,6 @@
distributed_option: DistributedOption,
) -> None:
"""Perform training. This method performs the main process of training."""
- assert check_argument_types()
# NOTE(kamo): Don't check the type more strictly as far trainer_options
assert is_dataclass(trainer_options), type(trainer_options)
assert len(optimizers) == len(schedulers), (len(optimizers), len(schedulers))
@@ -280,14 +278,11 @@
for iepoch in range(start_epoch, trainer_options.max_epoch + 1):
if iepoch != start_epoch:
logging.info(
- "{}/{}epoch started. Estimated time to finish: {}".format(
+ "{}/{}epoch started. Estimated time to finish: {} hours".format(
iepoch,
trainer_options.max_epoch,
- humanfriendly.format_timespan(
- (time.perf_counter() - start_time)
- / (iepoch - start_epoch)
- * (trainer_options.max_epoch - iepoch + 1)
- ),
+ (time.perf_counter() - start_time) / 3600.0 / (iepoch - start_epoch) * (
+ trainer_options.max_epoch - iepoch + 1),
)
)
else:
@@ -371,7 +366,7 @@
],
"scaler": scaler.state_dict() if scaler is not None else None,
"ema_model": model.encoder.ema.model.state_dict()
- if hasattr(model.encoder, "ema") and model.encoder.ema is not None else None,
+ if hasattr(model, "encoder") and hasattr(model.encoder, "ema") and model.encoder.ema is not None else None,
},
buffer,
)
@@ -550,7 +545,6 @@
options: TrainerOptions,
distributed_option: DistributedOption,
) -> Tuple[bool, bool]:
- assert check_argument_types()
grad_noise = options.grad_noise
accum_grad = options.accum_grad
@@ -619,6 +613,24 @@
if no_forward_run:
all_steps_are_invalid = False
continue
+
+ if iiter == 1 and summary_writer is not None:
+ try:
+ args = kwargs2args(model.forward, batch)
+ except (ValueError, TypeError):
+ logging.warning(
+ "inpect.signature() is failed for the model. "
+ "The graph can't be added for tensorboard."
+ )
+ else:
+ try:
+ summary_writer.add_graph(model, args, use_strict_trace=False)
+ except Exception:
+ logging.warning(
+ "summary_writer.add_graph() is failed for the model. "
+ "The graph can't be added for tensorboard."
+ )
+ del args
with autocast(scaler is not None):
with reporter.measure_time("forward_time"):
@@ -826,7 +838,6 @@
options: TrainerOptions,
distributed_option: DistributedOption,
) -> None:
- assert check_argument_types()
ngpu = options.ngpu
no_forward_run = options.no_forward_run
distributed = distributed_option.distributed
--
Gitblit v1.9.1