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 conv module bug #5245

Merged
merged 20 commits into from
Jun 21, 2021
Merged

Fix conv module bug #5245

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
20 commits
Select commit Hold shift + click to select a range
249d020
fix bert backward bug
BBuf Jun 8, 2021
72c3ec6
Merge branch 'master' of https://github.com/Oneflow-Inc/oneflow
BBuf Jun 9, 2021
aef184f
fix argwhere module bug
BBuf Jun 9, 2021
9274a82
Merge branch 'master' of https://github.com/Oneflow-Inc/oneflow
BBuf Jun 10, 2021
16cd4dd
align dropout module with torch
BBuf Jun 10, 2021
18b70d7
fix conflict
BBuf Jun 10, 2021
5c3e5fe
Merge branch 'master' of https://github.com/Oneflow-Inc/oneflow
BBuf Jun 13, 2021
7281b0e
Merge branch 'master' of https://github.com/Oneflow-Inc/oneflow
BBuf Jun 15, 2021
6842fa1
Merge branch 'master' of https://github.com/Oneflow-Inc/oneflow
BBuf Jun 17, 2021
0190aa0
fix acosh ci bug
BBuf Jun 17, 2021
2c3779f
fix conflict
BBuf Jun 18, 2021
3e0c27a
Merge branch 'master' of https://github.com/Oneflow-Inc/oneflow
BBuf Jun 18, 2021
e452c81
Merge branch 'master' of https://github.com/Oneflow-Inc/oneflow
BBuf Jun 18, 2021
00d33ce
Merge branch 'master' of https://github.com/Oneflow-Inc/oneflow
BBuf Jun 20, 2021
c10bbdf
fix conv group large input channel error
BBuf Jun 21, 2021
8782d3a
Merge branch 'master' into fix_conv_module_bug
BBuf Jun 21, 2021
c188793
Merge branch 'master' into fix_conv_module_bug
oneflow-ci-bot Jun 21, 2021
064408a
Merge branch 'master' into fix_conv_module_bug
oneflow-ci-bot Jun 21, 2021
93191b1
Merge branch 'master' into fix_conv_module_bug
oneflow-ci-bot Jun 21, 2021
e532d51
Merge branch 'master' into fix_conv_module_bug
oneflow-ci-bot Jun 21, 2021
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
13 changes: 12 additions & 1 deletion oneflow/python/nn/modules/conv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -221,6 +221,7 @@ def __init__(
self.weight = flow.nn.Parameter(
flow.Tensor(out_channels, in_channels // groups, *kernel_size)
)
self.out_channel_groups = out_channels // groups
self.bias = None
self._bias_add_op = None
if bias:
Expand Down Expand Up @@ -280,7 +281,17 @@ def forward(self, x):
out_list = []
for i in range(len(in_split_list)):
out_list.append(
self._cpu_op(in_split_list[i], self.weight[i : i + 1, :, :, :])[0]
self._cpu_op(
in_split_list[i],
self.weight[
i
* self.out_channel_groups : (i + 1)
* self.out_channel_groups,
:,
:,
:,
],
)[0]
)
res = flow.experimental.cat(out_list, dim=in_channel_axis)
else:
Expand Down
285 changes: 285 additions & 0 deletions oneflow/python/test/modules/test_conv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,8 +14,12 @@
limitations under the License.
"""
import unittest
from collections import OrderedDict

import numpy as np

import oneflow.experimental as flow
from test_util import GenArgList

test_conv2d_weight = np.array(
[
Expand Down Expand Up @@ -1202,6 +1206,278 @@ def _test_conv2d_backward(
)


def _test_conv2d_large_in_channel(test_case, device):
np_arr = np.array(
[
[
[
[
0.6206631238581714,
-1.1225329393404626,
0.8407155480700242,
-0.6845162855236345,
],
[
-0.5186484633906412,
0.10420735184519186,
-0.1711568947473012,
0.5168640476046483,
],
[
-0.12429464919764661,
0.050277779246134253,
-1.0144501797426606,
-2.184600444658526,
],
[
0.28918126931309923,
-0.822872663244595,
0.44019150436683663,
-1.0247720130825562,
],
],
[
[
0.7786504412818226,
-0.7501839068078657,
-0.8187283189941765,
-1.1116653569170698,
],
[
0.18085524152316743,
-1.3461349607476678,
1.142505437476448,
-0.000649619704040145,
],
[
0.03160672782674317,
-0.006318157449953413,
1.2218487782604377,
0.15903027907930234,
],
[
1.5857011815642381,
0.6656477116332891,
-0.04036621813223574,
-0.3427168687988546,
],
],
[
[
-1.1774346070102524,
1.6195241269303395,
-0.36185552303441965,
-1.1382193113192487,
],
[
0.08061907334568702,
1.5025447613238763,
-1.1591348706634745,
1.6449050139676873,
],
[
1.1539915649822392,
-2.414624939646017,
0.3056063774849572,
1.1920089257083162,
],
[
0.7623012858982319,
-0.01685314742940813,
-1.096666898224702,
-0.4406476137098582,
],
],
[
[
0.9383797282214235,
-1.1075876842796508,
-0.4420913825139058,
-1.0736097610655628,
],
[
-0.3101376466546291,
1.6578227745160954,
-0.6225454278031398,
0.6831188620748697,
],
[
0.00743800968372913,
-0.8089158949698473,
2.08084287836801,
0.721204366332351,
],
[
0.5694701823297723,
0.031519314469744895,
-0.5041680957766629,
-0.4738588233094669,
],
],
]
]
)
input = flow.Tensor(
np_arr, dtype=flow.float32, device=flow.device(device), requires_grad=True
)
weight = np.array(
[
[
[
[0.06456436216831207, -0.10852358490228653, -0.21638715267181396],
[-0.2279110550880432, 0.1476770043373108, 0.19457484781742096],
[0.05026858672499657, 0.10818571597337723, 0.02056501805782318],
],
[
[0.205095112323761, 0.1488947868347168, -0.2344113141298294],
[0.1684819906949997, -0.21986986696720123, 0.1082606166601181],
[-0.1528974026441574, 0.17120417952537537, 0.01954500749707222],
],
],
[
[
[-0.09441672265529633, -0.03644559532403946, -0.22235223650932312],
[-0.1771145612001419, 0.08043312281370163, 0.06938580423593521],
[0.054393064230680466, -0.05483492836356163, 0.23438701033592224],
],
[
[0.22666795551776886, 0.0874653309583664, 0.07092718034982681],
[0.08883464336395264, -0.052362944930791855, -0.1720171570777893],
[0.10441060364246368, 0.011952142231166363, -0.0894528403878212],
],
],
]
)
m = flow.nn.Conv2d(4, 2, 3, groups=2, bias=False)
m.weight = flow.nn.Parameter(flow.Tensor(weight), requires_grad=True)
m = m.to(device)
output = m(input)
np_out = [
[
[
[0.7666134238243103, -0.3961866497993469],
[-0.656266987323761, -1.1613956689834595],
],
[
[0.3077264130115509, -0.42817503213882446],
[-0.5761325359344482, 0.1300736665725708],
],
]
]
test_case.assertTrue(np.allclose(output.numpy(), np_out, 1e-6, 1e-6))
output = output.sum()
output.backward()
np_grad = [
[
[
[
0.06456436216831207,
-0.04395922273397446,
-0.3249107301235199,
-0.21638715267181396,
],
[
-0.16334669291973114,
-0.12419328093528748,
0.017341122031211853,
-0.021812304854393005,
],
[
-0.17764246463775635,
0.07822024822235107,
0.47100257873535156,
0.21513986587524414,
],
[
0.05026858672499657,
0.1584542989730835,
0.128750741481781,
0.02056501805782318,
],
],
[
[
0.205095112323761,
0.3539898991584778,
-0.08551652729511261,
-0.2344113141298294,
],
[
0.3735771179199219,
0.30260205268859863,
-0.19712577760219574,
-0.1261506974697113,
],
[
0.015584588050842285,
-0.03308109939098358,
0.07913993299007416,
0.12780562043190002,
],
[
-0.1528974026441574,
0.018306776881217957,
0.1907491832971573,
0.01954500749707222,
],
],
[
[
-0.09441672265529633,
-0.13086232542991638,
-0.258797824382782,
-0.22235223650932312,
],
[
-0.27153128385543823,
-0.22754377126693726,
-0.10897888988256454,
-0.1529664397239685,
],
[
-0.12272149324417114,
-0.09712330251932144,
0.32937100529670715,
0.30377280712127686,
],
[
0.054393064230680466,
-0.00044186413288116455,
0.1795520782470703,
0.23438701033592224,
],
],
[
[
0.22666795551776886,
0.31413328647613525,
0.1583925187587738,
0.07092718034982681,
],
[
0.3155025839805603,
0.35060498118400574,
-0.06598758697509766,
-0.1010899767279625,
],
[
0.19324524700641632,
0.1528344452381134,
-0.301880806684494,
-0.2614699900150299,
],
[
0.10441060364246368,
0.11636274307966232,
-0.07750070095062256,
-0.0894528403878212,
],
],
]
]
test_case.assertTrue(np.allclose(input.grad.numpy(), np_grad, 1e-6, 1e-6))


@unittest.skipIf(
not flow.unittest.env.eager_execution_enabled(),
".numpy() doesn't work in lazy mode",
Expand Down Expand Up @@ -1401,6 +1677,15 @@ def test_conv2d_dilation_backward(test_case):
device=device,
)

def test_large_channel_group_conv(test_case):
arg_dict = OrderedDict()
arg_dict["test_fun"] = [
_test_conv2d_large_in_channel,
]
arg_dict["device"] = ["cuda", "cpu"]
for arg in GenArgList(arg_dict):
arg[0](test_case, *arg[1:])


if __name__ == "__main__":
unittest.main()