diff --git a/LICENSE-FID b/LICENSE-FID new file mode 100755 index 00000000..261eeb9e --- /dev/null +++ b/LICENSE-FID @@ -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/calc_inception.py b/calc_inception.py old mode 100644 new mode 100755 index e35d350a..a027d0ed --- a/calc_inception.py +++ b/calc_inception.py @@ -11,6 +11,7 @@ import numpy as np from tqdm import tqdm +from inception import InceptionV3 from dataset import MultiResolutionDataset @@ -48,9 +49,10 @@ def forward(self, x): def load_patched_inception_v3(): - inception = inception_v3(pretrained=True) - inception_feat = Inception3Feature() - inception_feat.load_state_dict(inception.state_dict()) + # inception = inception_v3(pretrained=True) + # inception_feat = Inception3Feature() + # inception_feat.load_state_dict(inception.state_dict()) + inception_feat = InceptionV3([3], normalize_input=False) return inception_feat @@ -63,7 +65,7 @@ def extract_features(loader, inception, device): for img in pbar: img = img.to(device) - feature = inception(img) + feature = inception(img)[0].view(img.shape[0], -1) feature_list.append(feature.to('cpu')) features = torch.cat(feature_list, 0) diff --git a/fid.py b/fid.py old mode 100644 new mode 100755 index c7dc430c..5324c187 --- a/fid.py +++ b/fid.py @@ -22,7 +22,7 @@ def extract_feature_from_samples( for batch in tqdm(batch_sizes): latent = torch.randn(batch, 512, device=device) img, _ = g([latent], truncation=truncation, truncation_latent=truncation_latent) - feat = inception(img) + feat = inception(img)[0].view(img.shape[0], -1) features.append(feat.to('cpu')) features = torch.cat(features, 0) diff --git a/inception.py b/inception.py new file mode 100755 index 00000000..f3afed81 --- /dev/null +++ b/inception.py @@ -0,0 +1,310 @@ +import torch +import torch.nn as nn +import torch.nn.functional as F +from torchvision import models + +try: + from torchvision.models.utils import load_state_dict_from_url +except ImportError: + from torch.utils.model_zoo import load_url as load_state_dict_from_url + +# Inception weights ported to Pytorch from +# http://download.tensorflow.org/models/image/imagenet/inception-2015-12-05.tgz +FID_WEIGHTS_URL = 'https://github.com/mseitzer/pytorch-fid/releases/download/fid_weights/pt_inception-2015-12-05-6726825d.pth' + + +class InceptionV3(nn.Module): + """Pretrained InceptionV3 network returning feature maps""" + + # Index of default block of inception to return, + # corresponds to output of final average pooling + DEFAULT_BLOCK_INDEX = 3 + + # Maps feature dimensionality to their output blocks indices + BLOCK_INDEX_BY_DIM = { + 64: 0, # First max pooling features + 192: 1, # Second max pooling featurs + 768: 2, # Pre-aux classifier features + 2048: 3 # Final average pooling features + } + + def __init__(self, + output_blocks=[DEFAULT_BLOCK_INDEX], + resize_input=True, + normalize_input=True, + requires_grad=False, + use_fid_inception=True): + """Build pretrained InceptionV3 + + Parameters + ---------- + output_blocks : list of int + Indices of blocks to return features of. Possible values are: + - 0: corresponds to output of first max pooling + - 1: corresponds to output of second max pooling + - 2: corresponds to output which is fed to aux classifier + - 3: corresponds to output of final average pooling + resize_input : bool + If true, bilinearly resizes input to width and height 299 before + feeding input to model. As the network without fully connected + layers is fully convolutional, it should be able to handle inputs + of arbitrary size, so resizing might not be strictly needed + normalize_input : bool + If true, scales the input from range (0, 1) to the range the + pretrained Inception network expects, namely (-1, 1) + requires_grad : bool + If true, parameters of the model require gradients. Possibly useful + for finetuning the network + use_fid_inception : bool + If true, uses the pretrained Inception model used in Tensorflow's + FID implementation. If false, uses the pretrained Inception model + available in torchvision. The FID Inception model has different + weights and a slightly different structure from torchvision's + Inception model. If you want to compute FID scores, you are + strongly advised to set this parameter to true to get comparable + results. + """ + super(InceptionV3, self).__init__() + + self.resize_input = resize_input + self.normalize_input = normalize_input + self.output_blocks = sorted(output_blocks) + self.last_needed_block = max(output_blocks) + + assert self.last_needed_block <= 3, \ + 'Last possible output block index is 3' + + self.blocks = nn.ModuleList() + + if use_fid_inception: + inception = fid_inception_v3() + else: + inception = models.inception_v3(pretrained=True) + + # Block 0: input to maxpool1 + block0 = [ + inception.Conv2d_1a_3x3, + inception.Conv2d_2a_3x3, + inception.Conv2d_2b_3x3, + nn.MaxPool2d(kernel_size=3, stride=2) + ] + self.blocks.append(nn.Sequential(*block0)) + + # Block 1: maxpool1 to maxpool2 + if self.last_needed_block >= 1: + block1 = [ + inception.Conv2d_3b_1x1, + inception.Conv2d_4a_3x3, + nn.MaxPool2d(kernel_size=3, stride=2) + ] + self.blocks.append(nn.Sequential(*block1)) + + # Block 2: maxpool2 to aux classifier + if self.last_needed_block >= 2: + block2 = [ + inception.Mixed_5b, + inception.Mixed_5c, + inception.Mixed_5d, + inception.Mixed_6a, + inception.Mixed_6b, + inception.Mixed_6c, + inception.Mixed_6d, + inception.Mixed_6e, + ] + self.blocks.append(nn.Sequential(*block2)) + + # Block 3: aux classifier to final avgpool + if self.last_needed_block >= 3: + block3 = [ + inception.Mixed_7a, + inception.Mixed_7b, + inception.Mixed_7c, + nn.AdaptiveAvgPool2d(output_size=(1, 1)) + ] + self.blocks.append(nn.Sequential(*block3)) + + for param in self.parameters(): + param.requires_grad = requires_grad + + def forward(self, inp): + """Get Inception feature maps + + Parameters + ---------- + inp : torch.autograd.Variable + Input tensor of shape Bx3xHxW. Values are expected to be in + range (0, 1) + + Returns + ------- + List of torch.autograd.Variable, corresponding to the selected output + block, sorted ascending by index + """ + outp = [] + x = inp + + if self.resize_input: + x = F.interpolate(x, + size=(299, 299), + mode='bilinear', + align_corners=False) + + if self.normalize_input: + x = 2 * x - 1 # Scale from range (0, 1) to range (-1, 1) + + for idx, block in enumerate(self.blocks): + x = block(x) + if idx in self.output_blocks: + outp.append(x) + + if idx == self.last_needed_block: + break + + return outp + + +def fid_inception_v3(): + """Build pretrained Inception model for FID computation + + The Inception model for FID computation uses a different set of weights + and has a slightly different structure than torchvision's Inception. + + This method first constructs torchvision's Inception and then patches the + necessary parts that are different in the FID Inception model. + """ + inception = models.inception_v3(num_classes=1008, + aux_logits=False, + pretrained=False) + inception.Mixed_5b = FIDInceptionA(192, pool_features=32) + inception.Mixed_5c = FIDInceptionA(256, pool_features=64) + inception.Mixed_5d = FIDInceptionA(288, pool_features=64) + inception.Mixed_6b = FIDInceptionC(768, channels_7x7=128) + inception.Mixed_6c = FIDInceptionC(768, channels_7x7=160) + inception.Mixed_6d = FIDInceptionC(768, channels_7x7=160) + inception.Mixed_6e = FIDInceptionC(768, channels_7x7=192) + inception.Mixed_7b = FIDInceptionE_1(1280) + inception.Mixed_7c = FIDInceptionE_2(2048) + + state_dict = load_state_dict_from_url(FID_WEIGHTS_URL, progress=True) + inception.load_state_dict(state_dict) + return inception + + +class FIDInceptionA(models.inception.InceptionA): + """InceptionA block patched for FID computation""" + def __init__(self, in_channels, pool_features): + super(FIDInceptionA, self).__init__(in_channels, pool_features) + + def forward(self, x): + branch1x1 = self.branch1x1(x) + + branch5x5 = self.branch5x5_1(x) + branch5x5 = self.branch5x5_2(branch5x5) + + branch3x3dbl = self.branch3x3dbl_1(x) + branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl) + branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl) + + # Patch: Tensorflow's average pool does not use the padded zero's in + # its average calculation + branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1, + count_include_pad=False) + branch_pool = self.branch_pool(branch_pool) + + outputs = [branch1x1, branch5x5, branch3x3dbl, branch_pool] + return torch.cat(outputs, 1) + + +class FIDInceptionC(models.inception.InceptionC): + """InceptionC block patched for FID computation""" + def __init__(self, in_channels, channels_7x7): + super(FIDInceptionC, self).__init__(in_channels, channels_7x7) + + def forward(self, x): + branch1x1 = self.branch1x1(x) + + branch7x7 = self.branch7x7_1(x) + branch7x7 = self.branch7x7_2(branch7x7) + branch7x7 = self.branch7x7_3(branch7x7) + + branch7x7dbl = self.branch7x7dbl_1(x) + branch7x7dbl = self.branch7x7dbl_2(branch7x7dbl) + branch7x7dbl = self.branch7x7dbl_3(branch7x7dbl) + branch7x7dbl = self.branch7x7dbl_4(branch7x7dbl) + branch7x7dbl = self.branch7x7dbl_5(branch7x7dbl) + + # Patch: Tensorflow's average pool does not use the padded zero's in + # its average calculation + branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1, + count_include_pad=False) + branch_pool = self.branch_pool(branch_pool) + + outputs = [branch1x1, branch7x7, branch7x7dbl, branch_pool] + return torch.cat(outputs, 1) + + +class FIDInceptionE_1(models.inception.InceptionE): + """First InceptionE block patched for FID computation""" + def __init__(self, in_channels): + super(FIDInceptionE_1, self).__init__(in_channels) + + def forward(self, x): + branch1x1 = self.branch1x1(x) + + branch3x3 = self.branch3x3_1(x) + branch3x3 = [ + self.branch3x3_2a(branch3x3), + self.branch3x3_2b(branch3x3), + ] + branch3x3 = torch.cat(branch3x3, 1) + + branch3x3dbl = self.branch3x3dbl_1(x) + branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl) + branch3x3dbl = [ + self.branch3x3dbl_3a(branch3x3dbl), + self.branch3x3dbl_3b(branch3x3dbl), + ] + branch3x3dbl = torch.cat(branch3x3dbl, 1) + + # Patch: Tensorflow's average pool does not use the padded zero's in + # its average calculation + branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1, + count_include_pad=False) + branch_pool = self.branch_pool(branch_pool) + + outputs = [branch1x1, branch3x3, branch3x3dbl, branch_pool] + return torch.cat(outputs, 1) + + +class FIDInceptionE_2(models.inception.InceptionE): + """Second InceptionE block patched for FID computation""" + def __init__(self, in_channels): + super(FIDInceptionE_2, self).__init__(in_channels) + + def forward(self, x): + branch1x1 = self.branch1x1(x) + + branch3x3 = self.branch3x3_1(x) + branch3x3 = [ + self.branch3x3_2a(branch3x3), + self.branch3x3_2b(branch3x3), + ] + branch3x3 = torch.cat(branch3x3, 1) + + branch3x3dbl = self.branch3x3dbl_1(x) + branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl) + branch3x3dbl = [ + self.branch3x3dbl_3a(branch3x3dbl), + self.branch3x3dbl_3b(branch3x3dbl), + ] + branch3x3dbl = torch.cat(branch3x3dbl, 1) + + # Patch: The FID Inception model uses max pooling instead of average + # pooling. This is likely an error in this specific Inception + # implementation, as other Inception models use average pooling here + # (which matches the description in the paper). + branch_pool = F.max_pool2d(x, kernel_size=3, stride=1, padding=1) + branch_pool = self.branch_pool(branch_pool) + + outputs = [branch1x1, branch3x3, branch3x3dbl, branch_pool] + return torch.cat(outputs, 1) diff --git a/inception_ffhq.pkl b/inception_ffhq.pkl index 6183ab92..0a1b6e52 100644 Binary files a/inception_ffhq.pkl and b/inception_ffhq.pkl differ