From 4fe1ab02a42764f83ff0ee687dad35e698dd8e81 Mon Sep 17 00:00:00 2001
From: Mbaey <1092460929@qq.com>
Date: Thu, 13 Oct 2022 15:48:10 +0800
Subject: [PATCH 1/2] =?UTF-8?q?=E5=90=88=E5=B9=B6commit?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
---
.../FFHQ_ID2978_for_Pytorch/.keep | 0
.../FFHQ_ID2978_for_Pytorch/LICENSE | 201 ++++++++++++++
.../FFHQ_ID2978_for_Pytorch/data_loader.py | 48 ++++
.../FFHQ_ID2978_for_Pytorch/deeplab.py | 261 ++++++++++++++++++
.../FFHQ_ID2978_for_Pytorch/readme.md | 43 +++
.../FFHQ_ID2978_for_Pytorch/requirements.txt | 5 +
.../FFHQ_ID2978_for_Pytorch/run_deeplab.py | 85 ++++++
.../FFHQ_ID2978_for_Pytorch/utils.py | 100 +++++++
8 files changed, 743 insertions(+)
create mode 100644 PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/.keep
create mode 100644 PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/LICENSE
create mode 100644 PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/data_loader.py
create mode 100644 PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/deeplab.py
create mode 100644 PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/readme.md
create mode 100644 PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/requirements.txt
create mode 100644 PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/run_deeplab.py
create mode 100644 PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/utils.py
diff --git a/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/.keep b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/.keep
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/LICENSE b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/LICENSE
new file mode 100644
index 0000000000..261eeb9e9f
--- /dev/null
+++ b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/LICENSE
@@ -0,0 +1,201 @@
+ Apache License
+ Version 2.0, January 2004
+ http://www.apache.org/licenses/
+
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+ 1. Definitions.
+
+ "License" shall mean the terms and conditions for use, reproduction,
+ and distribution as defined by Sections 1 through 9 of this document.
+
+ "Licensor" shall mean the copyright owner or entity authorized by
+ the copyright owner that is granting the License.
+
+ "Legal Entity" shall mean the union of the acting entity and all
+ other entities that control, are controlled by, or are under common
+ control with that entity. For the purposes of this definition,
+ "control" means (i) the power, direct or indirect, to cause the
+ direction or management of such entity, whether by contract or
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
+ outstanding shares, or (iii) beneficial ownership of such entity.
+
+ "You" (or "Your") shall mean an individual or Legal Entity
+ exercising permissions granted by this License.
+
+ "Source" form shall mean the preferred form for making modifications,
+ including but not limited to software source code, documentation
+ source, and configuration files.
+
+ "Object" form shall mean any form resulting from mechanical
+ transformation or translation of a Source form, including but
+ not limited to compiled object code, generated documentation,
+ and conversions to other media types.
+
+ "Work" shall mean the work of authorship, whether in Source or
+ Object form, made available under the License, as indicated by a
+ copyright notice that is included in or attached to the work
+ (an example is provided in the Appendix below).
+
+ "Derivative Works" shall mean any work, whether in Source or Object
+ form, that is based on (or derived from) the Work and for which the
+ editorial revisions, annotations, elaborations, or other modifications
+ represent, as a whole, an original work of authorship. For the purposes
+ of this License, Derivative Works shall not include works that remain
+ separable from, or merely link (or bind by name) to the interfaces of,
+ the Work and Derivative Works thereof.
+
+ "Contribution" shall mean any work of authorship, including
+ the original version of the Work and any modifications or additions
+ to that Work or Derivative Works thereof, that is intentionally
+ submitted to Licensor for inclusion in the Work by the copyright owner
+ or by an individual or Legal Entity authorized to submit on behalf of
+ the copyright owner. For the purposes of this definition, "submitted"
+ means any form of electronic, verbal, or written communication sent
+ to the Licensor or its representatives, including but not limited to
+ communication on electronic mailing lists, source code control systems,
+ and issue tracking systems that are managed by, or on behalf of, the
+ Licensor for the purpose of discussing and improving the Work, but
+ excluding communication that is conspicuously marked or otherwise
+ designated in writing by the copyright owner as "Not a Contribution."
+
+ "Contributor" shall mean Licensor and any individual or Legal Entity
+ on behalf of whom a Contribution has been received by Licensor and
+ subsequently incorporated within the Work.
+
+ 2. Grant of Copyright License. Subject to the terms and conditions of
+ this License, each Contributor hereby grants to You a perpetual,
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+ copyright license to reproduce, prepare Derivative Works of,
+ publicly display, publicly perform, sublicense, and distribute the
+ Work and such Derivative Works in Source or Object form.
+
+ 3. Grant of Patent License. Subject to the terms and conditions of
+ this License, each Contributor hereby grants to You a perpetual,
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+ (except as stated in this section) patent license to make, have made,
+ use, offer to sell, sell, import, and otherwise transfer the Work,
+ where such license applies only to those patent claims licensable
+ by such Contributor that are necessarily infringed by their
+ Contribution(s) alone or by combination of their Contribution(s)
+ with the Work to which such Contribution(s) was submitted. If You
+ institute patent litigation against any entity (including a
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
+ or a Contribution incorporated within the Work constitutes direct
+ or contributory patent infringement, then any patent licenses
+ granted to You under this License for that Work shall terminate
+ as of the date such litigation is filed.
+
+ 4. Redistribution. You may reproduce and distribute copies of the
+ Work or Derivative Works thereof in any medium, with or without
+ modifications, and in Source or Object form, provided that You
+ meet the following conditions:
+
+ (a) You must give any other recipients of the Work or
+ Derivative Works a copy of this License; and
+
+ (b) You must cause any modified files to carry prominent notices
+ stating that You changed the files; and
+
+ (c) You must retain, in the Source form of any Derivative Works
+ that You distribute, all copyright, patent, trademark, and
+ attribution notices from the Source form of the Work,
+ excluding those notices that do not pertain to any part of
+ the Derivative Works; and
+
+ (d) If the Work includes a "NOTICE" text file as part of its
+ distribution, then any Derivative Works that You distribute must
+ include a readable copy of the attribution notices contained
+ within such NOTICE file, excluding those notices that do not
+ pertain to any part of the Derivative Works, in at least one
+ of the following places: within a NOTICE text file distributed
+ as part of the Derivative Works; within the Source form or
+ documentation, if provided along with the Derivative Works; or,
+ within a display generated by the Derivative Works, if and
+ wherever such third-party notices normally appear. The contents
+ of the NOTICE file are for informational purposes only and
+ do not modify the License. You may add Your own attribution
+ notices within Derivative Works that You distribute, alongside
+ or as an addendum to the NOTICE text from the Work, provided
+ that such additional attribution notices cannot be construed
+ as modifying the License.
+
+ You may add Your own copyright statement to Your modifications and
+ may provide additional or different license terms and conditions
+ for use, reproduction, or distribution of Your modifications, or
+ for any such Derivative Works as a whole, provided Your use,
+ reproduction, and distribution of the Work otherwise complies with
+ the conditions stated in this License.
+
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
+ any Contribution intentionally submitted for inclusion in the Work
+ by You to the Licensor shall be under the terms and conditions of
+ this License, without any additional terms or conditions.
+ Notwithstanding the above, nothing herein shall supersede or modify
+ the terms of any separate license agreement you may have executed
+ with Licensor regarding such Contributions.
+
+ 6. Trademarks. This License does not grant permission to use the trade
+ names, trademarks, service marks, or product names of the Licensor,
+ except as required for reasonable and customary use in describing the
+ origin of the Work and reproducing the content of the NOTICE file.
+
+ 7. Disclaimer of Warranty. Unless required by applicable law or
+ agreed to in writing, Licensor provides the Work (and each
+ Contributor provides its Contributions) on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+ implied, including, without limitation, any warranties or conditions
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+ PARTICULAR PURPOSE. You are solely responsible for determining the
+ appropriateness of using or redistributing the Work and assume any
+ risks associated with Your exercise of permissions under this License.
+
+ 8. Limitation of Liability. In no event and under no legal theory,
+ whether in tort (including negligence), contract, or otherwise,
+ unless required by applicable law (such as deliberate and grossly
+ negligent acts) or agreed to in writing, shall any Contributor be
+ liable to You for damages, including any direct, indirect, special,
+ incidental, or consequential damages of any character arising as a
+ result of this License or out of the use or inability to use the
+ Work (including but not limited to damages for loss of goodwill,
+ work stoppage, computer failure or malfunction, or any and all
+ other commercial damages or losses), even if such Contributor
+ has been advised of the possibility of such damages.
+
+ 9. Accepting Warranty or Additional Liability. While redistributing
+ the Work or Derivative Works thereof, You may choose to offer,
+ and charge a fee for, acceptance of support, warranty, indemnity,
+ or other liability obligations and/or rights consistent with this
+ License. However, in accepting such obligations, You may act only
+ on Your own behalf and on Your sole responsibility, not on behalf
+ of any other Contributor, and only if You agree to indemnify,
+ defend, and hold each Contributor harmless for any liability
+ incurred by, or claims asserted against, such Contributor by reason
+ of your accepting any such warranty or additional liability.
+
+ END OF TERMS AND CONDITIONS
+
+ APPENDIX: How to apply the Apache License to your work.
+
+ To apply the Apache License to your work, attach the following
+ boilerplate notice, with the fields enclosed by brackets "[]"
+ replaced with your own identifying information. (Don't include
+ the brackets!) The text should be enclosed in the appropriate
+ comment syntax for the file format. We also recommend that a
+ file or class name and description of purpose be included on the
+ same "printed page" as the copyright notice for easier
+ identification within third-party archives.
+
+ Copyright [yyyy] [name of copyright owner]
+
+ Licensed under the Apache License, Version 2.0 (the "License");
+ you may not use this file except in compliance with the License.
+ You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
diff --git a/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/data_loader.py b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/data_loader.py
new file mode 100644
index 0000000000..d8420602ec
--- /dev/null
+++ b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/data_loader.py
@@ -0,0 +1,48 @@
+# Copyright 2022 Huawei Technologies Co., Ltd
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+import torch.utils.data as data
+import os
+from PIL import Image
+from utils import preprocess_image
+
+
+class CelebASegmentation(data.Dataset):
+ CLASSES = ['background' ,'skin','nose','eye_g','l_eye','r_eye','l_brow','r_brow','l_ear','r_ear','mouth','u_lip','l_lip','hair','hat','ear_r','neck_l','neck','cloth']
+
+ def __init__(self, root, transform=None, crop_size=None):
+ self.root = root
+ self.transform = transform
+ self.crop_size = crop_size
+
+ self.images = []
+ subdirs = next(os.walk(self.root))[1] #quick trick to get all subdirectories
+ for subdir in subdirs:
+ curr_images = [os.path.join(self.root,subdir,file) for file in os.listdir(os.path.join(self.root,subdir)) if file.endswith('.png')]
+ self.images += curr_images
+
+
+ def __getitem__(self, index):
+ _img = Image.open(self.images[index]).convert('RGB')
+ _img=_img.resize((513,513),Image.BILINEAR)
+ _img = preprocess_image(_img,flip=False,scale=None,crop=(self.crop_size, self.crop_size))
+
+ if self.transform is not None:
+ _img = self.transform(_img)
+
+ return _img
+
+ def __len__(self):
+ return len(self.images)
diff --git a/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/deeplab.py b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/deeplab.py
new file mode 100644
index 0000000000..99afacaf17
--- /dev/null
+++ b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/deeplab.py
@@ -0,0 +1,261 @@
+# Copyright 2022 Huawei Technologies Co., Ltd
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import torch
+import torch.nn as nn
+import math
+import torch.utils.model_zoo as model_zoo
+from torch.nn import functional as F
+
+
+__all__ = ['ResNet', 'resnet50', 'resnet101', 'resnet152']
+
+
+model_urls = {
+ 'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
+ 'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
+ 'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
+}
+
+
+class Conv2d(nn.Conv2d):
+
+ def __init__(self, in_channels, out_channels, kernel_size, stride=1,
+ padding=0, dilation=1, groups=1, bias=True):
+ super(Conv2d, self).__init__(in_channels, out_channels, kernel_size, stride,
+ padding, dilation, groups, bias)
+
+ def forward(self, x):
+ # return super(Conv2d, self).forward(x)
+ weight = self.weight
+ weight_mean = weight.mean(dim=1, keepdim=True).mean(dim=2,
+ keepdim=True).mean(dim=3, keepdim=True)
+ weight = weight - weight_mean
+ std = weight.view(weight.size(0), -1).std(dim=1).view(-1, 1, 1, 1) + 1e-5
+ weight = weight / std.expand_as(weight)
+ return F.conv2d(x, weight, self.bias, self.stride,
+ self.padding, self.dilation, self.groups)
+
+
+class ASPP(nn.Module):
+
+ def __init__(self, C, depth, num_classes, conv=nn.Conv2d, norm=nn.BatchNorm2d, momentum=0.0003, mult=1):
+ super(ASPP, self).__init__()
+ self._C = C
+ self._depth = depth
+ self._num_classes = num_classes
+
+ self.global_pooling = nn.AdaptiveAvgPool2d(1)
+ self.relu = nn.ReLU(inplace=True)
+ self.aspp1 = conv(C, depth, kernel_size=1, stride=1, bias=False)
+ self.aspp2 = conv(C, depth, kernel_size=3, stride=1,
+ dilation=int(6*mult), padding=int(6*mult),
+ bias=False)
+ self.aspp3 = conv(C, depth, kernel_size=3, stride=1,
+ dilation=int(12*mult), padding=int(12*mult),
+ bias=False)
+ self.aspp4 = conv(C, depth, kernel_size=3, stride=1,
+ dilation=int(18*mult), padding=int(18*mult),
+ bias=False)
+ self.aspp5 = conv(C, depth, kernel_size=1, stride=1, bias=False)
+ self.aspp1_bn = norm(depth, momentum)
+ self.aspp2_bn = norm(depth, momentum)
+ self.aspp3_bn = norm(depth, momentum)
+ self.aspp4_bn = norm(depth, momentum)
+ self.aspp5_bn = norm(depth, momentum)
+ self.conv2 = conv(depth * 5, depth, kernel_size=1, stride=1,
+ bias=False)
+ self.bn2 = norm(depth, momentum)
+ self.conv3 = nn.Conv2d(depth, num_classes, kernel_size=1, stride=1)
+
+ def forward(self, x):
+ x1 = self.aspp1(x)
+ x1 = self.aspp1_bn(x1)
+ x1 = self.relu(x1)
+ x2 = self.aspp2(x)
+ x2 = self.aspp2_bn(x2)
+ x2 = self.relu(x2)
+ x3 = self.aspp3(x)
+ x3 = self.aspp3_bn(x3)
+ x3 = self.relu(x3)
+ x4 = self.aspp4(x)
+ x4 = self.aspp4_bn(x4)
+ x4 = self.relu(x4)
+ x5 = self.global_pooling(x)
+ x5 = self.aspp5(x5)
+ x5 = self.aspp5_bn(x5)
+ x5 = self.relu(x5)
+ x5 = nn.Upsample((x.shape[2], x.shape[3]), mode='bilinear',
+ align_corners=True)(x5)
+ x = torch.cat((x1, x2, x3, x4, x5), 1)
+ x = self.conv2(x)
+ x = self.bn2(x)
+ x = self.relu(x)
+ x = self.conv3(x)
+
+ return x
+
+
+class Bottleneck(nn.Module):
+ expansion = 4
+
+ def __init__(self, inplanes, planes, stride=1, downsample=None, dilation=1, conv=None, norm=None):
+ super(Bottleneck, self).__init__()
+ self.conv1 = conv(inplanes, planes, kernel_size=1, bias=False)
+ self.bn1 = norm(planes)
+ self.conv2 = conv(planes, planes, kernel_size=3, stride=stride,
+ dilation=dilation, padding=dilation, bias=False)
+ self.bn2 = norm(planes)
+ self.conv3 = conv(planes, planes * self.expansion, kernel_size=1, bias=False)
+ self.bn3 = norm(planes * self.expansion)
+ self.relu = nn.ReLU(inplace=True)
+ self.downsample = downsample
+ self.stride = stride
+
+ def forward(self, x):
+ residual = x
+
+ out = self.conv1(x)
+ out = self.bn1(out)
+ out = self.relu(out)
+
+ out = self.conv2(out)
+ out = self.bn2(out)
+ out = self.relu(out)
+
+ out = self.conv3(out)
+ out = self.bn3(out)
+
+ if self.downsample is not None:
+ residual = self.downsample(x)
+
+ out += residual
+ out = self.relu(out)
+
+ return out
+
+
+class ResNet(nn.Module):
+
+ def __init__(self, block, layers, num_classes, num_groups=None, weight_std=False, beta=False):
+ self.inplanes = 64
+ self.norm = lambda planes, momentum=0.05: nn.BatchNorm2d(planes, momentum=momentum) if num_groups is None else nn.GroupNorm(num_groups, planes)
+ self.conv = Conv2d if weight_std else nn.Conv2d
+
+ super(ResNet, self).__init__()
+ if not beta:
+ self.conv1 = self.conv(3, 64, kernel_size=7, stride=2, padding=3,
+ bias=False)
+ else:
+ self.conv1 = nn.Sequential(
+ self.conv(3, 64, 3, stride=2, padding=1, bias=False),
+ self.conv(64, 64, 3, stride=1, padding=1, bias=False),
+ self.conv(64, 64, 3, stride=1, padding=1, bias=False))
+ self.bn1 = self.norm(64)
+ self.relu = nn.ReLU(inplace=True)
+ self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
+ self.layer1 = self._make_layer(block, 64, layers[0])
+ self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
+ self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
+ self.layer4 = self._make_layer(block, 512, layers[3], stride=1,
+ dilation=2)
+ self.aspp = ASPP(512 * block.expansion, 256, num_classes, conv=self.conv, norm=self.norm)
+
+ for m in self.modules():
+ if isinstance(m, self.conv):
+ n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
+ m.weight.data.normal_(0, math.sqrt(2. / n))
+ elif isinstance(m, nn.BatchNorm2d) or isinstance(m, nn.GroupNorm):
+ m.weight.data.fill_(1)
+ m.bias.data.zero_()
+
+ def _make_layer(self, block, planes, blocks, stride=1, dilation=1):
+ downsample = None
+ if stride != 1 or dilation != 1 or self.inplanes != planes * block.expansion:
+ downsample = nn.Sequential(
+ self.conv(self.inplanes, planes * block.expansion,
+ kernel_size=1, stride=stride, dilation=max(1, dilation/2), bias=False),
+ self.norm(planes * block.expansion),
+ )
+
+ layers = []
+ layers.append(block(self.inplanes, planes, stride, downsample, dilation=max(1, dilation/2), conv=self.conv, norm=self.norm))
+ self.inplanes = planes * block.expansion
+ for i in range(1, blocks):
+ layers.append(block(self.inplanes, planes, dilation=dilation, conv=self.conv, norm=self.norm))
+
+ return nn.Sequential(*layers)
+
+ def forward(self, x):
+ size = (x.shape[2], x.shape[3])
+ x = self.conv1(x)
+ x = self.bn1(x)
+ x = self.relu(x)
+ x = self.maxpool(x)
+
+ x = self.layer1(x)
+ x = self.layer2(x)
+ x = self.layer3(x)
+ x = self.layer4(x)
+
+ x = self.aspp(x)
+ x = nn.Upsample(size, mode='bilinear', align_corners=True)(x)
+ return x
+
+
+def resnet50(pretrained=False, **kwargs):
+ """Constructs a ResNet-50 model.
+
+ Args:
+ pretrained (bool): If True, returns a model pre-trained on ImageNet
+ """
+ model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
+ if pretrained:
+ model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
+ return model
+
+
+def resnet101(pretrained=False, num_groups=None, weight_std=False, **kwargs):
+ """Constructs a ResNet-101 model.
+
+ Args:
+ pretrained (bool): If True, returns a model pre-trained on ImageNet
+ """
+ model = ResNet(Bottleneck, [3, 4, 23, 3], num_groups=num_groups, weight_std=weight_std, **kwargs)
+ if pretrained:
+ model_dict = model.state_dict()
+ if num_groups and weight_std:
+ pretrained_dict = torch.load('deeplab_model/R-101-GN-WS.pth.tar' , map_location='cpu')
+ overlap_dict = {k[7:]: v for k, v in pretrained_dict.items() if k[7:] in model_dict}
+ assert len(overlap_dict) == 312
+ elif not num_groups and not weight_std:
+ pretrained_dict = model_zoo.load_url(model_urls['resnet101'])
+ overlap_dict = {k: v for k, v in pretrained_dict.items() if k in model_dict}
+ else:
+ raise ValueError('Currently only support BN or GN+WS')
+ model_dict.update(overlap_dict)
+ model.load_state_dict(model_dict)
+ return model
+
+
+def resnet152(pretrained=False, **kwargs):
+ """Constructs a ResNet-152 model.
+
+ Args:
+ pretrained (bool): If True, returns a model pre-trained on ImageNet
+ """
+ model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
+ if pretrained:
+ model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
+ return model
diff --git a/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/readme.md b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/readme.md
new file mode 100644
index 0000000000..1b5653c876
--- /dev/null
+++ b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/readme.md
@@ -0,0 +1,43 @@
+# FFHQ-Aging-Dataset
+- Paper:[[2003.09764] Lifespan Age Transformation Synthesis](https://arxiv.org/abs/2003.09764)
+- Github Code:[royorel/FFHQ-Aging-Dataset: FFHQ-Aging Dataset](https://github.com/royorel/FFHQ-Aging-Dataset)
+
+Face Semantic maps were acquired by training a pytorch implementation of [DeepLabV3](https://github.com/chenxi116/DeepLabv3.pytorch) network on the [CelebAMASK-HQ](https://github.com/switchablenorms/CelebAMask-HQ) dataset.
+
+## Directory structure
+```
+.
+├── data_loader.py # 数据集加载
+├── deeplab_model #存放模型参数，下载的模型请放这里。
+│ ├── deeplab_model.pth
+│ └── R-101-GN-WS.pth.tar
+├── ffhq_aging128×128 #存放数据集，下载的数据集请解压到这里
+├── deeplab.py #deeplap v3模型脚本
+├── readme.md
+├── requirements.txt
+├── run_deeplab.py
+└── utils.py
+```
+## Environment preparation
+- Install Packages
+ - pip install -r requirements.txt
+- Download **FFHQ-Aging-Dataset** & **Deeplab Model** from [original repo](https://github.com/royorel/FFHQ-Aging-Dataset) & [deeplab_model/R-101-GN-WS.pth.tar](https://drive.google.com/uc?id=1oRGgrI4KNdefbWVpw0rRkEP1gbJIRokM) & [deeplab_model/deeplab_model.pth](https://drive.google.com/uc?id=1w2XjDywFr2NjuUWaLQDRktH7VwIfuNlYhttps://drive.google.com/uc?id=1w2XjDywFr2NjuUWaLQDRktH7VwIfuNlY)
+ - The original **FFHQ-dataset** is stored on the [google drive](https://drive.google.com/drive/folders/1u2xu7bSrWxrbUxk-dT-UvEJq8IjdmNTP), By running the [original repo's get_ffhq_aging.sh](https://github.com/royorel/FFHQ-Aging-Dataset/blob/master/get_ffhq_aging.sh) , you can easily get **FFHQ-Aging-Dataset**.
+
+## Run
+
+python3.7 run_deeplab.py
+
+
+> 分割后的图像，放在原图片存放路径里的parsings文件夹下。
+
+> 例如：ffhq_aging128×128\0-2\parsings
+> ffhq_aging128×128\3-6\parsings等
+
+### Runing result
+
+
+
+- 原始图像、GPU分割、NPU分割效果对比如下：
+
调用deeplab模型后，原始图片被分割为：背景、皮肤、鼻子、眼睛等部分。
diff --git a/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/requirements.txt b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/requirements.txt
new file mode 100644
index 0000000000..f116ff3221
--- /dev/null
+++ b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/requirements.txt
@@ -0,0 +1,5 @@
+requests
+numpy
+scipy
+pillow
+pytorch
diff --git a/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/run_deeplab.py b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/run_deeplab.py
new file mode 100644
index 0000000000..41de24d34f
--- /dev/null
+++ b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/run_deeplab.py
@@ -0,0 +1,85 @@
+# Copyright 2022 Huawei Technologies Co., Ltd
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import argparse
+import os
+import datetime
+import numpy as np
+import torch.npu
+import torch
+import torch.nn as nn
+from pdb import set_trace as st
+from PIL import Image
+from torchvision import transforms
+import deeplab
+from data_loader import CelebASegmentation
+
+# resnet_file_spec = dict(file_url='https://drive.google.com/uc?id=1oRGgrI4KNdefbWVpw0rRkEP1gbJIRokM', file_path='deeplab_model/R-101-GN-WS.pth.tar', file_size=178260167, file_md5='aa48cc3d3ba3b7ac357c1489b169eb32')
+# deeplab_file_spec = dict(file_url='https://drive.google.com/uc?id=1w2XjDywFr2NjuUWaLQDRktH7VwIfuNlY', file_path='deeplab_model/deeplab_model.pth', file_size=464446305, file_md5='8e8345b1b9d95e02780f9bed76cc0293')
+
+resolution = 128
+model_fname = 'deeplab_model/deeplab_model.pth'
+dataset_root = "ffhq_aging128x128"
+
+assert torch.npu.is_available()
+assert os.path.isdir(dataset_root)
+
+dataset = CelebASegmentation(dataset_root, crop_size=513)
+print("len(dataset)", len(dataset))
+print("dataset.CLASSES", dataset.CLASSES)
+print("dataset.images[0]", dataset.images[0])
+print("Start time:", datetime.datetime.now())
+
+model = getattr(deeplab, 'resnet101')(
+ pretrained=True,
+ num_classes=len(dataset.CLASSES),
+ num_groups=32,
+ weight_std=True,
+ beta=False)
+
+checkpoint = torch.load(model_fname, map_location='cpu')
+state_dict = {k[7:]: v for k,
+ v in checkpoint['state_dict'].items() if 'tracked' not in k}
+model.load_state_dict(state_dict)
+
+device = "npu"
+# model = model.npu()
+model = model.to(device)
+model.eval()
+
+for i in range(len(dataset)):
+ inputs = dataset[i]
+ # inputs = inputs.npu()
+ inputs = inputs.unsqueeze(0).to(device)
+ # print("inputs-----",inputs.shape)
+ outputs = model(inputs)
+ # print("outputs-----",outputs.shape)
+
+ _, pred = torch.max(outputs, 1)
+ pred = pred.data.cpu().numpy().squeeze().astype(np.uint8)
+ imname = os.path.basename(dataset.images[i])
+ mask_pred = Image.fromarray(pred)
+ mask_pred = mask_pred.resize((resolution, resolution), Image.NEAREST)
+ try:
+ mask_pred.save(dataset.images[i].replace(
+ imname, 'parsings/'+imname[:-4]+'.png'))
+ except FileNotFoundError:
+ os.makedirs(os.path.join(os.path.dirname(
+ dataset.images[i]), 'parsings'))
+ mask_pred.save(dataset.images[i].replace(
+ imname, 'parsings/'+imname[:-4]+'.png'))
+
+ print('processed {0}/{1} images, Time:{2}'.format(i +
+ 1, len(dataset), datetime.datetime.now()))
+ # break
diff --git a/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/utils.py b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/utils.py
new file mode 100644
index 0000000000..e05d7b8e72
--- /dev/null
+++ b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/utils.py
@@ -0,0 +1,100 @@
+# Copyright 2022 Huawei Technologies Co., Ltd
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+import os
+import math
+import html
+import glob
+import uuid
+import random
+import hashlib
+import requests
+import numpy as np
+import torch
+import torchvision.transforms as transforms
+from PIL import Image
+
+
+def preprocess_image(image, flip=False, scale=None, crop=None):
+ if flip:
+ if random.random() < 0.5:
+ image = image.transpose(Image.FLIP_LEFT_RIGHT)
+ if scale:
+ w, h = image.size
+ rand_log_scale = math.log(scale[0], 2) + random.random() * (math.log(scale[1], 2) - math.log(scale[0], 2))
+ random_scale = math.pow(2, rand_log_scale)
+ new_size = (int(round(w * random_scale)), int(round(h * random_scale)))
+ image = image.resize(new_size, Image.ANTIALIAS)
+
+ data_transforms = transforms.Compose([
+ transforms.ToTensor(),
+ transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+ ])
+ image = data_transforms(image)
+
+ return image
+
+
+def download_file(session, file_spec, chunk_size=128, num_attempts=10):
+ file_path = file_spec['file_path']
+ file_url = file_spec['file_url']
+ file_dir = os.path.dirname(file_path)
+ tmp_path = file_path + '.tmp.' + uuid.uuid4().hex
+ if file_dir:
+ os.makedirs(file_dir, exist_ok=True)
+
+ for attempts_left in reversed(range(num_attempts)):
+ data_size = 0
+ try:
+ # Download.
+ data_md5 = hashlib.md5()
+ with session.get(file_url, stream=True) as res:
+ res.raise_for_status()
+ with open(tmp_path, 'wb') as f:
+ for chunk in res.iter_content(chunk_size=chunk_size<<10):
+ f.write(chunk)
+ data_size += len(chunk)
+ data_md5.update(chunk)
+
+ # Validate.
+ if 'file_size' in file_spec and data_size != file_spec['file_size']:
+ raise IOError('Incorrect file size', file_path)
+ if 'file_md5' in file_spec and data_md5.hexdigest() != file_spec['file_md5']:
+ raise IOError('Incorrect file MD5', file_path)
+ break
+
+ except:
+ # Last attempt => raise error.
+ if not attempts_left:
+ raise
+
+ # Handle Google Drive virus checker nag.
+ if data_size > 0 and data_size < 8192:
+ with open(tmp_path, 'rb') as f:
+ data = f.read()
+ links = [html.unescape(link) for link in data.decode('utf-8').split('"') if 'export=download' in link]
+ if len(links) == 1:
+ file_url = requests.compat.urljoin(file_url, links[0])
+ continue
+
+ # Rename temp file to the correct name.
+ os.replace(tmp_path, file_path) # atomic
+
+ # Attempt to clean up any leftover temps.
+ for filename in glob.glob(file_path + '.tmp.*'):
+ try:
+ os.remove(filename)
+ except:
+ pass
--
Gitee
From f9d6ba9357c9990c83ea90b803dc7bcd1aa2493a Mon Sep 17 00:00:00 2001
From: Mbaey <1092460929@qq.com>
Date: Wed, 26 Oct 2022 15:09:20 +0800
Subject: [PATCH 2/2] =?UTF-8?q?=E6=80=A7=E8=83=BD=E8=BE=BE=E6=A0=87?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
---
.../FFHQ_ID2978_for_Pytorch/readme.md | 7 +++++++
.../FFHQ_ID2978_for_Pytorch/run_deeplab.py | 9 ++++++++-
2 files changed, 15 insertions(+), 1 deletion(-)
diff --git a/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/readme.md b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/readme.md
index 1b5653c876..0475466d67 100644
--- a/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/readme.md
+++ b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/readme.md
@@ -41,3 +41,10 @@ python3.7 run_deeplab.py
- 原始图像、GPU分割、NPU分割效果对比如下：
调用deeplab模型后，原始图片被分割为：背景、皮肤、鼻子、眼睛等部分。
+
+### 性能达标
+
+| Name | FPS |
+| ------ | ---- |
+| GPU-1p | 20.9 |
+| NPU-1p | 21.5 |
diff --git a/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/run_deeplab.py b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/run_deeplab.py
index 41de24d34f..a40089791e 100644
--- a/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/run_deeplab.py
+++ b/PyTorch/contrib/cv/semantic_segmentation/FFHQ_ID2978_for_Pytorch/run_deeplab.py
@@ -21,6 +21,7 @@ import torch
import torch.nn as nn
from pdb import set_trace as st
from PIL import Image
+from tqdm import tqdm
from torchvision import transforms
import deeplab
from data_loader import CelebASegmentation
@@ -35,6 +36,12 @@ dataset_root = "ffhq_aging128x128"
assert torch.npu.is_available()
assert os.path.isdir(dataset_root)
+option = {}
+option["ACL_OP_COMPILER_CACHE_MODE"] = "enable" # cache功能启用
+option["ACL_OP_COMPILER_CACHE_DIR"] = "./my_kernel_meta" # cache所在文件夹
+print("option:",option)
+torch.npu.set_option(option)
+
dataset = CelebASegmentation(dataset_root, crop_size=513)
print("len(dataset)", len(dataset))
print("dataset.CLASSES", dataset.CLASSES)
@@ -58,7 +65,7 @@ device = "npu"
model = model.to(device)
model.eval()
-for i in range(len(dataset)):
+for i in tqdm(range(len(dataset))):
inputs = dataset[i]
# inputs = inputs.npu()
inputs = inputs.unsqueeze(0).to(device)
--
Gitee