Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix structure infos conflict in static return_list mode #43291

Merged
merged 3 commits into from
Jun 10, 2022
Merged

fix structure infos conflict in static return_list mode #43291

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fe139ac
fix structure infos conflict in static return_list mode. test=develop
heavengate Jun 7, 2022
7f10b50
merge develop. test=develop
heavengate Jun 7, 2022
2c83065
fix format. test=develop
heavengate Jun 8, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 10 additions & 10 deletions python/paddle/fluid/dataloader/dataloader_iter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -276,12 +276,12 @@ def __next__(self):
data = self._reader.read_next_list()
for i in range(len(data)):
data[i] = data[i]._move_to_list()
data = [
_restore_batch(d, s) for d, s in zip(
data, self._structure_infos[:len(self._places)])
structs = [
self._structure_infos.pop(0)
for _ in range(len(self._places))
]
self._structure_infos = self._structure_infos[
len(self._places):]
data = [_restore_batch(d, s) \
for d, s in zip(data, structs)]
# static graph organized data on multi-device with list, if
# place number is 1, there is only 1 device, extra the data
# from list for devices to be compatible with dygraph mode
Expand Down Expand Up @@ -750,12 +750,12 @@ def __next__(self):
data = self._reader.read_next_list()
for i in range(len(data)):
data[i] = data[i]._move_to_list()
data = [
_restore_batch(d, s) for d, s in zip(
data, self._structure_infos[:len(self._places)])
structs = [
self._structure_infos.pop(0)
for _ in range(len(self._places))
]
self._structure_infos = self._structure_infos[
len(self._places):]
data = [_restore_batch(d, s) \
for d, s in zip(data, structs)]
# static graph organized data on multi-device with list, if
# place number is 1, there is only 1 device, extra the data
# from list for devices to be compatible with dygraph mode
Expand Down
15 changes: 11 additions & 4 deletions python/paddle/fluid/tests/unittests/test_multiprocess_dataloader_static.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
import multiprocessing
import numpy as np

import paddle
import paddle.fluid as fluid
from paddle.io import Dataset, BatchSampler, DataLoader

Expand Down Expand Up @@ -182,7 +183,7 @@ def test_main(self):

class TestStaticDataLoaderReturnList(unittest.TestCase):

def test_single_place(self):
def run_single_place(self, num_workers):
scope = fluid.Scope()
image = fluid.data(name='image',
shape=[None, IMAGE_SIZE],
Expand All @@ -192,7 +193,7 @@ def test_single_place(self):
dataset = RandomDataset(SAMPLE_NUM, CLASS_NUM)
dataloader = DataLoader(dataset,
feed_list=[image, label],
num_workers=0,
num_workers=num_workers,
batch_size=BATCH_SIZE,
drop_last=True,
return_list=True)
Expand All @@ -203,7 +204,7 @@ def test_single_place(self):
assert not isinstance(d[0], list)
assert not isinstance(d[1], list)

def test_multi_place(self):
def run_multi_place(self, num_workers):
scope = fluid.Scope()
image = fluid.data(name='image',
shape=[None, IMAGE_SIZE],
Expand All @@ -213,7 +214,7 @@ def test_multi_place(self):
dataset = RandomDataset(SAMPLE_NUM, CLASS_NUM)
dataloader = DataLoader(dataset,
feed_list=[image, label],
num_workers=0,
num_workers=num_workers,
batch_size=BATCH_SIZE,
places=[fluid.CPUPlace()] * 2,
drop_last=True,
Expand All @@ -225,6 +226,12 @@ def test_multi_place(self):
assert isinstance(d[0], list)
assert isinstance(d[1], list)

def test_main(self):
paddle.enable_static()
for num_workers in [0, 2]:
self.run_single_place(num_workers)
self.run_multi_place(num_workers)


class RandomBatchedDataset(Dataset):

Expand Down