testadmin
/
ParakeetRebeccaRosario
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Adapt the change in save & load

This commit is contained in:
liuyibing01 2020-03-26 09:27:22 +00:00
parent fccbf6d797
commit 618eb31ab4
7 changed files with 49 additions and 68 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
examples/waveflow/README.md
View File

@ -13,8 +13,8 @@ PaddlePaddle dynamic graph implementation of [WaveFlow: A Compact Flow-based Mod
├── synthesis.py # script for speech synthesis
├── train.py # script for model training
├── utils.py # helper functions for e.g., model checkpointing
├── parakeet/models/waveflow/data.py # dataset and dataloader settings for LJSpeech
├── parakeet/models/waveflow/waveflow.py # WaveFlow model high level APIs
├── data.py # dataset and dataloader settings for LJSpeech
├── waveflow.py # WaveFlow model high level APIs
└── parakeet/models/waveflow/waveflow_modules.py # WaveFlow model implementation
```
@ -48,12 +48,12 @@ python -u train.py \
--config=./configs/waveflow_ljspeech.yaml \
--root=./data/LJSpeech-1.1 \
--name=${ModelName} --batch_size=4 \
--parallel=false --use_gpu=true
--use_gpu=true
```
#### Save and Load checkpoints
Our model will save model parameters as checkpoints in `./runs/waveflow/${ModelName}/checkpoint/` every 10000 iterations by default.
Our model will save model parameters as checkpoints in `./runs/waveflow/${ModelName}/checkpoint/` every 10000 iterations by default, where `${ModelName}` is the model name for one single experiment and it could be whatever you like.
The saved checkpoint will have the format of `step-${iteration_number}.pdparams` for model parameters and `step-${iteration_number}.pdopt` for optimizer parameters.
There are three ways to load a checkpoint and resume training (take an example that you want to load a 500000-iteration checkpoint):
@ -68,7 +68,7 @@ export CUDA_VISIBLE_DEVICES=0,1,2,3
python -u -m paddle.distributed.launch train.py \
--config=./configs/waveflow_ljspeech.yaml \
--root=./data/LJSpeech-1.1 \
--name=${ModelName} --parallel=true --use_gpu=true
--name=${ModelName} --use_gpu=true
```
Use `export CUDA_VISIBLE_DEVICES=0,1,2,3` to set the GPUs that you want to use to be visible. Then the `paddle.distributed.launch` module will use these visible GPUs to do data parallel training in multiprocessing mode.

2
examples/waveflow/benchmark.py
View File

@ -23,7 +23,7 @@ from paddle import fluid
import utils
from parakeet.utils import io
from parakeet.models.waveflow import WaveFlow
from waveflow import WaveFlow
def add_options_to_parser(parser):

4
examples/waveflow/synthesis.py
View File

@ -21,9 +21,9 @@ import numpy as np
import paddle.fluid.dygraph as dg
from paddle import fluid
import utils
from parakeet.models.waveflow import WaveFlow
from parakeet.utils import io
import utils
from waveflow import WaveFlow
def add_options_to_parser(parser):

24
examples/waveflow/train.py
View File

@ -26,7 +26,7 @@ from tensorboardX import SummaryWriter
import utils
from parakeet.utils import io
from parakeet.models.waveflow import WaveFlow
from waveflow import WaveFlow
def add_options_to_parser(parser):
@ -40,11 +40,6 @@ def add_options_to_parser(parser):
parser.add_argument(
'--root', type=str, help="root path of the LJSpeech dataset")
parser.add_argument(
'--parallel',
type=utils.str2bool,
default=True,
help="option to use data parallel training")
parser.add_argument(
'--use_gpu',
type=utils.str2bool,
@ -66,11 +61,11 @@ def add_options_to_parser(parser):
def train(config):
use_gpu = config.use_gpu
parallel = config.parallel if use_gpu else False
# Get the rank of the current training process.
rank = dg.parallel.Env().local_rank if parallel else 0
nranks = dg.parallel.Env().nranks if parallel else 1
rank = dg.parallel.Env().local_rank
nranks = dg.parallel.Env().nranks
parallel = nranks > 1
if rank == 0:
# Print the whole config setting.
@ -100,16 +95,7 @@ def train(config):
# Build model.
model = WaveFlow(config, checkpoint_dir, parallel, rank, nranks, tb)
model.build()
# Obtain the current iteration.
if config.checkpoint is None:
if config.iteration is None:
iteration = io.load_latest_checkpoint(checkpoint_dir, rank)
else:
iteration = config.iteration
else:
iteration = int(config.checkpoint.split('/')[-1].split('-')[-1])
iteration = model.build()
while iteration < config.max_iterations:
# Run one single training step.

34
examples/waveflow/waveflow.py
View File

@ -21,11 +21,11 @@ import paddle.fluid.dygraph as dg
from paddle import fluid
from scipy.io.wavfile import write
import utils
from parakeet.utils import io
from parakeet.modules import weight_norm
from .data import LJSpeech
from .waveflow_modules import WaveFlowLoss, WaveFlowModule
from parakeet.models.waveflow import WaveFlowLoss, WaveFlowModule
from data import LJSpeech
import utils
class WaveFlow():
@ -93,13 +93,12 @@ class WaveFlow():
parameter_list=waveflow.parameters())
# Load parameters.
io.load_parameters(
self.checkpoint_dir,
self.rank,
waveflow,
optimizer,
iteration = io.load_parameters(
model=waveflow,
optimizer=optimizer,
checkpoint_dir=self.checkpoint_dir,
iteration=config.iteration,
file_path=config.checkpoint)
checkpoint_path=config.checkpoint)
print("Rank {}: checkpoint loaded.".format(self.rank))
# Data parallelism.
@ -113,13 +112,11 @@ class WaveFlow():
else:
# Load parameters.
io.load_parameters(
self.checkpoint_dir,
self.rank,
waveflow,
iteration = io.load_parameters(
model=waveflow,
checkpoint_dir=self.checkpoint_dir,
iteration=config.iteration,
file_path=config.checkpoint,
dtype=self.dtype)
checkpoint_path=config.checkpoint)
print("Rank {}: checkpoint loaded.".format(self.rank))
for layer in waveflow.sublayers():
@ -128,6 +125,8 @@ class WaveFlow():
self.waveflow = waveflow
return iteration
def train_step(self, iteration):
"""Train the model for one step.
@ -293,6 +292,5 @@ class WaveFlow():
Returns:
None
"""
io.save_latest_parameters(self.checkpoint_dir, iteration,
self.waveflow, self.optimizer)
io.save_latest_checkpoint(self.checkpoint_dir, iteration)
io.save_parameters(self.checkpoint_dir, iteration, self.waveflow,
self.optimizer)

2
parakeet/models/waveflow/__init__.py
View File

@ -12,4 +12,4 @@
# See the License for the specific language governing permissions and
# limitations under the License.
from parakeet.models.waveflow.waveflow import WaveFlow
from parakeet.models.waveflow.waveflow_modules import WaveFlowLoss, WaveFlowModule

39
parakeet/utils/io.py
View File

@ -18,6 +18,7 @@ import time
import ruamel.yaml
import numpy as np
import paddle.fluid.dygraph as dg
from paddle.fluid.framework import convert_np_dtype_to_dtype_ as convert_np_dtype
def is_main_process():
@ -90,8 +91,7 @@ def load_parameters(model,
optimizer=None,
checkpoint_dir=None,
iteration=None,
checkpoint_path=None,
dtype="float32"):
checkpoint_path=None):
"""Load a specific model checkpoint from disk.
Args:
@ -102,40 +102,37 @@ def load_parameters(model,
iteration (int, optional): if specified, load the specific checkpoint,
if not specified, load the latest one. Defaults to None.
checkpoint_path (str, optional): if specified, load the checkpoint
stored in the checkpoint_path. Defaults to None.
dtype (str, optional): precision of the model parameters.
Defaults to float32.
stored in the checkpoint_path and the argument 'checkpoint_dir' will
be ignored. Defaults to None.
Returns:
iteration (int): number of iterations that the loaded checkpoint has
been trained.
"""
if checkpoint_dir is not None and checkpoint_path is not None:
raise ValueError(
"Load from either from (checkpoint_dir and iteration) \n"
"or checkpoint_path. Do not pass both.")
if iteration is not None and checkpoint_dir is None:
raise ValueError(
"When iteration is specified, checkpoint_dir should not be None")
if checkpoint_dir is not None:
if checkpoint_path is not None:
iteration = int(os.path.basename(checkpoint_path).split("-")[-1])
elif checkpoint_dir is not None:
if iteration is None:
iteration = _load_latest_checkpoint(checkpoint_dir)
checkpoint_path = os.path.join(checkpoint_dir,
"step-{}".format(iteration))
if iteration == 0 and not os.path.exists(checkpoint_path):
if iteration == 0:
# if step-0 exist, it is also loaded
return iteration
checkpoint_path = os.path.join(checkpoint_dir,
"step-{}".format(iteration))
else:
# checkpoint is not None
iteration = int(os.path.basename(checkpoint_path).split("-")[-1])
raise ValueError(
"At least one of 'checkpoint_dir' and 'checkpoint_path' should be specified!"
)
local_rank = dg.parallel.Env().local_rank
model_dict, optimizer_dict = dg.load_dygraph(checkpoint_path)
# cast to desired data type
state_dict = model.state_dict()
# cast to desired data type, for mixed-precision training/inference.
for k, v in model_dict.items():
model_dict[k] = v.astype(dtype)
if k in state_dict and convert_np_dtype(v.dtype) != state_dict[
k].dtype:
model_dict[k] = v.astype(state_dict[k].numpy().dtype)
model.set_dict(model_dict)
print("[checkpoint] Rank {}: loaded model from {}.pdparams".format(