├── LICENCE ├── README.md ├── datasets.py ├── datasplits ├── cub │ └── train_val_test_split.txt └── lfw-funneled │ ├── test.txt │ ├── train.txt │ └── val.txt ├── example_load_pretrained.py ├── imgs ├── redo.png ├── redo_lfwxflowers.png └── redo_samples.png ├── models.py └── train.py /LICENCE: -------------------------------------------------------------------------------- 1 | Attribution-NonCommercial 4.0 International 2 | 3 | ======================================================================= 4 | 5 | Creative Commons Corporation ("Creative Commons") is not a law firm and 6 | does not provide legal services or legal advice. Distribution of 7 | Creative Commons public licenses does not create a lawyer-client or 8 | other relationship. Creative Commons makes its licenses and related 9 | information available on an "as-is" basis. Creative Commons gives no 10 | warranties regarding its licenses, any material licensed under their 11 | terms and conditions, or any related information. Creative Commons 12 | disclaims all liability for damages resulting from their use to the 13 | fullest extent possible. 14 | 15 | Using Creative Commons Public Licenses 16 | 17 | Creative Commons public licenses provide a standard set of terms and 18 | conditions that creators and other rights holders may use to share 19 | original works of authorship and other material subject to copyright 20 | and certain other rights specified in the public license below. The 21 | following considerations are for informational purposes only, are not 22 | exhaustive, and do not form part of our licenses. 23 | 24 | Considerations for licensors: Our public licenses are 25 | intended for use by those authorized to give the public 26 | permission to use material in ways otherwise restricted by 27 | copyright and certain other rights. Our licenses are 28 | irrevocable. Licensors should read and understand the terms 29 | and conditions of the license they choose before applying it. 30 | Licensors should also secure all rights necessary before 31 | applying our licenses so that the public can reuse the 32 | material as expected. Licensors should clearly mark any 33 | material not subject to the license. This includes other CC- 34 | licensed material, or material used under an exception or 35 | limitation to copyright. More considerations for licensors: 36 | wiki.creativecommons.org/Considerations_for_licensors 37 | 38 | Considerations for the public: By using one of our public 39 | licenses, a licensor grants the public permission to use the 40 | licensed material under specified terms and conditions. If 41 | the licensor's permission is not necessary for any reason--for 42 | example, because of any applicable exception or limitation to 43 | copyright--then that use is not regulated by the license. Our 44 | licenses grant only permissions under copyright and certain 45 | other rights that a licensor has authority to grant. Use of 46 | the licensed material may still be restricted for other 47 | reasons, including because others have copyright or other 48 | rights in the material. A licensor may make special requests, 49 | such as asking that all changes be marked or described. 50 | Although not required by our licenses, you are encouraged to 51 | respect those requests where reasonable. More_considerations 52 | for the public: 53 | wiki.creativecommons.org/Considerations_for_licensees 54 | 55 | ======================================================================= 56 | 57 | Creative Commons Attribution-NonCommercial 4.0 International Public 58 | License 59 | 60 | By exercising the Licensed Rights (defined below), You accept and agree 61 | to be bound by the terms and conditions of this Creative Commons 62 | Attribution-NonCommercial 4.0 International Public License ("Public 63 | License"). To the extent this Public License may be interpreted as a 64 | contract, You are granted the Licensed Rights in consideration of Your 65 | acceptance of these terms and conditions, and the Licensor grants You 66 | such rights in consideration of benefits the Licensor receives from 67 | making the Licensed Material available under these terms and 68 | conditions. 69 | 70 | Section 1 -- Definitions. 71 | 72 | a. Adapted Material means material subject to Copyright and Similar 73 | Rights that is derived from or based upon the Licensed Material 74 | and in which the Licensed Material is translated, altered, 75 | arranged, transformed, or otherwise modified in a manner requiring 76 | permission under the Copyright and Similar Rights held by the 77 | Licensor. For purposes of this Public License, where the Licensed 78 | Material is a musical work, performance, or sound recording, 79 | Adapted Material is always produced where the Licensed Material is 80 | synched in timed relation with a moving image. 81 | 82 | b. Adapter's License means the license You apply to Your Copyright 83 | and Similar Rights in Your contributions to Adapted Material in 84 | accordance with the terms and conditions of this Public License. 85 | 86 | c. Copyright and Similar Rights means copyright and/or similar rights 87 | closely related to copyright including, without limitation, 88 | performance, broadcast, sound recording, and Sui Generis Database 89 | Rights, without regard to how the rights are labeled or 90 | categorized. For purposes of this Public License, the rights 91 | specified in Section 2(b)(1)-(2) are not Copyright and Similar 92 | Rights. 93 | d. Effective Technological Measures means those measures that, in the 94 | absence of proper authority, may not be circumvented under laws 95 | fulfilling obligations under Article 11 of the WIPO Copyright 96 | Treaty adopted on December 20, 1996, and/or similar international 97 | agreements. 98 | 99 | e. Exceptions and Limitations means fair use, fair dealing, and/or 100 | any other exception or limitation to Copyright and Similar Rights 101 | that applies to Your use of the Licensed Material. 102 | 103 | f. Licensed Material means the artistic or literary work, database, 104 | or other material to which the Licensor applied this Public 105 | License. 106 | 107 | g. Licensed Rights means the rights granted to You subject to the 108 | terms and conditions of this Public License, which are limited to 109 | all Copyright and Similar Rights that apply to Your use of the 110 | Licensed Material and that the Licensor has authority to license. 111 | 112 | h. Licensor means the individual(s) or entity(ies) granting rights 113 | under this Public License. 114 | 115 | i. NonCommercial means not primarily intended for or directed towards 116 | commercial advantage or monetary compensation. For purposes of 117 | this Public License, the exchange of the Licensed Material for 118 | other material subject to Copyright and Similar Rights by digital 119 | file-sharing or similar means is NonCommercial provided there is 120 | no payment of monetary compensation in connection with the 121 | exchange. 122 | 123 | j. Share means to provide material to the public by any means or 124 | process that requires permission under the Licensed Rights, such 125 | as reproduction, public display, public performance, distribution, 126 | dissemination, communication, or importation, and to make material 127 | available to the public including in ways that members of the 128 | public may access the material from a place and at a time 129 | individually chosen by them. 130 | 131 | k. Sui Generis Database Rights means rights other than copyright 132 | resulting from Directive 96/9/EC of the European Parliament and of 133 | the Council of 11 March 1996 on the legal protection of databases, 134 | as amended and/or succeeded, as well as other essentially 135 | equivalent rights anywhere in the world. 136 | 137 | l. You means the individual or entity exercising the Licensed Rights 138 | under this Public License. Your has a corresponding meaning. 139 | 140 | Section 2 -- Scope. 141 | 142 | a. License grant. 143 | 144 | 1. Subject to the terms and conditions of this Public License, 145 | the Licensor hereby grants You a worldwide, royalty-free, 146 | non-sublicensable, non-exclusive, irrevocable license to 147 | exercise the Licensed Rights in the Licensed Material to: 148 | 149 | a. reproduce and Share the Licensed Material, in whole or 150 | in part, for NonCommercial purposes only; and 151 | 152 | b. produce, reproduce, and Share Adapted Material for 153 | NonCommercial purposes only. 154 | 155 | 2. Exceptions and Limitations. For the avoidance of doubt, where 156 | Exceptions and Limitations apply to Your use, this Public 157 | License does not apply, and You do not need to comply with 158 | its terms and conditions. 159 | 160 | 3. Term. The term of this Public License is specified in Section 161 | 6(a). 162 | 163 | 4. Media and formats; technical modifications allowed. The 164 | Licensor authorizes You to exercise the Licensed Rights in 165 | all media and formats whether now known or hereafter created, 166 | and to make technical modifications necessary to do so. The 167 | Licensor waives and/or agrees not to assert any right or 168 | authority to forbid You from making technical modifications 169 | necessary to exercise the Licensed Rights, including 170 | technical modifications necessary to circumvent Effective 171 | Technological Measures. For purposes of this Public License, 172 | simply making modifications authorized by this Section 2(a) 173 | (4) never produces Adapted Material. 174 | 175 | 5. Downstream recipients. 176 | 177 | a. Offer from the Licensor -- Licensed Material. Every 178 | recipient of the Licensed Material automatically 179 | receives an offer from the Licensor to exercise the 180 | Licensed Rights under the terms and conditions of this 181 | Public License. 182 | 183 | b. No downstream restrictions. You may not offer or impose 184 | any additional or different terms or conditions on, or 185 | apply any Effective Technological Measures to, the 186 | Licensed Material if doing so restricts exercise of the 187 | Licensed Rights by any recipient of the Licensed 188 | Material. 189 | 190 | 6. No endorsement. Nothing in this Public License constitutes or 191 | may be construed as permission to assert or imply that You 192 | are, or that Your use of the Licensed Material is, connected 193 | with, or sponsored, endorsed, or granted official status by, 194 | the Licensor or others designated to receive attribution as 195 | provided in Section 3(a)(1)(A)(i). 196 | 197 | b. Other rights. 198 | 199 | 1. Moral rights, such as the right of integrity, are not 200 | licensed under this Public License, nor are publicity, 201 | privacy, and/or other similar personality rights; however, to 202 | the extent possible, the Licensor waives and/or agrees not to 203 | assert any such rights held by the Licensor to the limited 204 | extent necessary to allow You to exercise the Licensed 205 | Rights, but not otherwise. 206 | 207 | 2. Patent and trademark rights are not licensed under this 208 | Public License. 209 | 210 | 3. To the extent possible, the Licensor waives any right to 211 | collect royalties from You for the exercise of the Licensed 212 | Rights, whether directly or through a collecting society 213 | under any voluntary or waivable statutory or compulsory 214 | licensing scheme. In all other cases the Licensor expressly 215 | reserves any right to collect such royalties, including when 216 | the Licensed Material is used other than for NonCommercial 217 | purposes. 218 | 219 | Section 3 -- License Conditions. 220 | 221 | Your exercise of the Licensed Rights is expressly made subject to the 222 | following conditions. 223 | 224 | a. Attribution. 225 | 226 | 1. If You Share the Licensed Material (including in modified 227 | form), You must: 228 | 229 | a. retain the following if it is supplied by the Licensor 230 | with the Licensed Material: 231 | 232 | i. identification of the creator(s) of the Licensed 233 | Material and any others designated to receive 234 | attribution, in any reasonable manner requested by 235 | the Licensor (including by pseudonym if 236 | designated); 237 | 238 | ii. a copyright notice; 239 | 240 | iii. a notice that refers to this Public License; 241 | 242 | iv. a notice that refers to the disclaimer of 243 | warranties; 244 | 245 | v. a URI or hyperlink to the Licensed Material to the 246 | extent reasonably practicable; 247 | 248 | b. indicate if You modified the Licensed Material and 249 | retain an indication of any previous modifications; and 250 | 251 | c. indicate the Licensed Material is licensed under this 252 | Public License, and include the text of, or the URI or 253 | hyperlink to, this Public License. 254 | 255 | 2. You may satisfy the conditions in Section 3(a)(1) in any 256 | reasonable manner based on the medium, means, and context in 257 | which You Share the Licensed Material. For example, it may be 258 | reasonable to satisfy the conditions by providing a URI or 259 | hyperlink to a resource that includes the required 260 | information. 261 | 262 | 3. If requested by the Licensor, You must remove any of the 263 | information required by Section 3(a)(1)(A) to the extent 264 | reasonably practicable. 265 | 266 | 4. If You Share Adapted Material You produce, the Adapter's 267 | License You apply must not prevent recipients of the Adapted 268 | Material from complying with this Public License. 269 | 270 | Section 4 -- Sui Generis Database Rights. 271 | 272 | Where the Licensed Rights include Sui Generis Database Rights that 273 | apply to Your use of the Licensed Material: 274 | 275 | a. for the avoidance of doubt, Section 2(a)(1) grants You the right 276 | to extract, reuse, reproduce, and Share all or a substantial 277 | portion of the contents of the database for NonCommercial purposes 278 | only; 279 | 280 | b. if You include all or a substantial portion of the database 281 | contents in a database in which You have Sui Generis Database 282 | Rights, then the database in which You have Sui Generis Database 283 | Rights (but not its individual contents) is Adapted Material; and 284 | 285 | c. You must comply with the conditions in Section 3(a) if You Share 286 | all or a substantial portion of the contents of the database. 287 | 288 | For the avoidance of doubt, this Section 4 supplements and does not 289 | replace Your obligations under this Public License where the Licensed 290 | Rights include other Copyright and Similar Rights. 291 | 292 | Section 5 -- Disclaimer of Warranties and Limitation of Liability. 293 | 294 | a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE 295 | EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS 296 | AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF 297 | ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS, 298 | IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION, 299 | WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR 300 | PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS, 301 | ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT 302 | KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT 303 | ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU. 304 | 305 | b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE 306 | TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION, 307 | NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT, 308 | INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES, 309 | COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR 310 | USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN 311 | ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR 312 | DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR 313 | IN PART, THIS LIMITATION MAY NOT APPLY TO YOU. 314 | 315 | c. The disclaimer of warranties and limitation of liability provided 316 | above shall be interpreted in a manner that, to the extent 317 | possible, most closely approximates an absolute disclaimer and 318 | waiver of all liability. 319 | 320 | Section 6 -- Term and Termination. 321 | 322 | a. This Public License applies for the term of the Copyright and 323 | Similar Rights licensed here. However, if You fail to comply with 324 | this Public License, then Your rights under this Public License 325 | terminate automatically. 326 | 327 | b. Where Your right to use the Licensed Material has terminated under 328 | Section 6(a), it reinstates: 329 | 330 | 1. automatically as of the date the violation is cured, provided 331 | it is cured within 30 days of Your discovery of the 332 | violation; or 333 | 334 | 2. upon express reinstatement by the Licensor. 335 | 336 | For the avoidance of doubt, this Section 6(b) does not affect any 337 | right the Licensor may have to seek remedies for Your violations 338 | of this Public License. 339 | 340 | c. For the avoidance of doubt, the Licensor may also offer the 341 | Licensed Material under separate terms or conditions or stop 342 | distributing the Licensed Material at any time; however, doing so 343 | will not terminate this Public License. 344 | 345 | d. Sections 1, 5, 6, 7, and 8 survive termination of this Public 346 | License. 347 | 348 | Section 7 -- Other Terms and Conditions. 349 | 350 | a. The Licensor shall not be bound by any additional or different 351 | terms or conditions communicated by You unless expressly agreed. 352 | 353 | b. Any arrangements, understandings, or agreements regarding the 354 | Licensed Material not stated herein are separate from and 355 | independent of the terms and conditions of this Public License. 356 | 357 | Section 8 -- Interpretation. 358 | 359 | a. For the avoidance of doubt, this Public License does not, and 360 | shall not be interpreted to, reduce, limit, restrict, or impose 361 | conditions on any use of the Licensed Material that could lawfully 362 | be made without permission under this Public License. 363 | 364 | b. To the extent possible, if any provision of this Public License is 365 | deemed unenforceable, it shall be automatically reformed to the 366 | minimum extent necessary to make it enforceable. If the provision 367 | cannot be reformed, it shall be severed from this Public License 368 | without affecting the enforceability of the remaining terms and 369 | conditions. 370 | 371 | c. No term or condition of this Public License will be waived and no 372 | failure to comply consented to unless expressly agreed to by the 373 | Licensor. 374 | 375 | d. Nothing in this Public License constitutes or may be interpreted 376 | as a limitation upon, or waiver of, any privileges and immunities 377 | that apply to the Licensor or You, including from the legal 378 | processes of any jurisdiction or authority. 379 | 380 | ======================================================================= 381 | 382 | Creative Commons is not a party to its public 383 | licenses. Notwithstanding, Creative Commons may elect to apply one of 384 | its public licenses to material it publishes and in those instances 385 | will be considered the “Licensor.” The text of the Creative Commons 386 | public licenses is dedicated to the public domain under the CC0 Public 387 | Domain Dedication. Except for the limited purpose of indicating that 388 | material is shared under a Creative Commons public license or as 389 | otherwise permitted by the Creative Commons policies published at 390 | creativecommons.org/policies, Creative Commons does not authorize the 391 | use of the trademark "Creative Commons" or any other trademark or logo 392 | of Creative Commons without its prior written consent including, 393 | without limitation, in connection with any unauthorized modifications 394 | to any of its public licenses or any other arrangements, 395 | understandings, or agreements concerning use of licensed material. For 396 | the avoidance of doubt, this paragraph does not form part of the 397 | public licenses. 398 | 399 | Creative Commons may be contacted at creativecommons.org. 400 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # ReDO: Unsupervised Object Segmentation by Redrawing 2 | 3 | Code for paper [Unsupervised Object Segmentation by Redrawing](https://papers.nips.cc/paper/9434-unsupervised-object-segmentation-by-redrawing) \[[Preprint](https://arxiv.org/abs/1905.13539)\] by Mickaël Chen, Thierry Artières and Ludovic Denoyer. Presented as poster at NeurIPS 2019, Vancouver. 4 | 5 | ![redo](https://github.com/mickaelChen/ReDO/blob/master/imgs/redo.png) 6 | 7 | We discover meaningful segmentation masks by redrawing regions of the images independently. 8 | 9 | ## Table of Contents 10 | 11 | - [Random samples](#random-samples) 12 | * Samples for Flowers, LFW, CUB and toy dataset 13 | * A more diverse dataset with two classes 14 | - [Datasets instructions](#datasets-instructions) 15 | * Flowers 16 | * CUB 17 | * LFW 18 | - [Usage](#usage) 19 | * Pretrained models 20 | * Training ReDO 21 | 22 | ## Random samples 23 | 24 | ### Samples for Flowers, LFW, CUB and toy dataset 25 | ![samples](https://github.com/mickaelChen/ReDO/blob/master/imgs/redo_samples.png) 26 | 27 | ### A more diverse dataset with two classes 28 | 29 | During the rebuttal process, we were asked to demonstrate that ReDO can work when the dataset contains multiple classes. 30 | We build a new dataset by combining LFW and Flowers images (without labels). This new dataset has more variability, 31 | contains different types of objects, and display a more obvious correlation between the object and the background. 32 | We trained ReDO without further hyperparameter tuning (not optimal), and obtained a reasonable accuracy of 0.856 and IoU of 0.691. 33 | ![lfw + flowers](https://github.com/mickaelChen/ReDO/blob/master/imgs/redo_lfwxflowers.png) 34 | 35 | ## Datasets instructions 36 | 37 | ### Flowers 38 | 1. Download and extract: *Dataset*, *Segmentations*, and *data splits* from http://www.robots.ox.ac.uk/~vgg/data/flowers/102/ 39 | 2. The obtained *jpg* folder, *segmin* folder and *setid.mat* file should be placed in the same data root folder. 40 | 41 | ### CUB 42 | 1. Download and extract *Images* and *Segmentations* from http://www.vision.caltech.edu/visipedia/CUB-200-2011.html 43 | 2. Place the *segmentations* folder in the *CUB_200_2011/CUB_200_2011* subfolder. 44 | 3. Place the *train_val_test_split.txt* file from this repo in the *CUB_200_2011/CUB_200_2011* subfolder. 45 | 4. dataroot should be set to the *CUB_200_2011/CUB_200_2011* subfolder. 46 | 47 | ### LFW 48 | 1. Download and extract the *funneled images* from http://vis-www.cs.umass.edu/lfw/ 49 | 2. Download and extract the *ground truth images* from http://vis-www.cs.umass.edu/lfw/part_labels/ 50 | 3. Place the obtained *lfw_funneled* and *parts_lfw_funneled_gt_images* folders in the same data root folder. 51 | 4. Also place the *train.txt*, *val.txt* and *test.txt* files from the repo in this data root folder. 52 | 53 | 54 | ## Usage 55 | 56 | Tested on python3.7 with pytorch 1.0.1 57 | 58 | ### Load pretrained models 59 | Weights pretrained on Flowers, LFW, and CUB datasets can be downloaded from [google drive](https://drive.google.com/drive/folders/1hUb2iOTJAbWw1NotWGAsEt4ASomhOwbh). 60 | 61 | - *dataset_nets_state.tar.gz*: pretrained weights for all 4 networks used during training in a single file. 62 | 63 | The weights for the individual networks are also available, for instance if you only need to segment and/or redraw: 64 | 65 | - *dataset_netM_state.tar.gz*: pretrained weights for mask extractor only. Enough if interested only in segmentation. 66 | - *dataset_netX_state.tar.gz*: pretrained weights for region generators. Used to redraw objects. 67 | - *dataset_netD_state.tar.gz*: pretrained weights for discriminator. 68 | - *dataset_netZ_state.tar.gz*: pretrained weights for the network that infer the latent code z from image. 69 | 70 | *.tar.gz* archives have to be uncompressed first to recover the *.pth* files containing the weights. 71 | 72 | Provided example script needs at least netM and netX and is used as follows: 73 | 74 | If using *dataset_nets_state.pth* on GPU cuda device 0 75 | 76 | ``` 77 | python example_load_pretrained.py --statePath path_to_nets_state.pth --dataroot path_to_data --device cuda:0 78 | ``` 79 | 80 | If using *dataset_netX_state.pth* and *dataset_netM_state.pth* on cpu: 81 | ``` 82 | python example_load_pretrained.py --statePathX path_to_netX_state.pth --statePathM path_to_netM_state.pth --dataroot path_to_data --device cpu 83 | ``` 84 | 85 | 86 | ### Training from scratch 87 | 88 | Examples: 89 | 90 | ``` 91 | python train.py --dataset flowers --nfX 32 --useSelfAttG --useSelfAttD --outf path_to_output_folder --dataroot path_to_data_folder --clean 92 | ``` 93 | ``` 94 | python train.py --dataset lfw --useSelfAttG --useSelfAttD --outf path_to_output_folder --dataroot path_to_data_folder --clean 95 | ``` 96 | 97 | Some clarifications about the training process and the collapse issue: 98 | 99 | As mentionned in the paper, the model can collapse with one region taking the whole image. 100 | This happens early in the training (at about 3-5k iterations) in some runs (about 3.5 out of 10 in my experiments). 101 | In this case, it is possible to restart training automatically using option --autoRestart .1 (for instance). 102 | 103 | After these early stages, training should be stable. 104 | I stop training in the 20k~40k range, but the model gets unstable again if you train for too long. 105 | -------------------------------------------------------------------------------- /datasets.py: -------------------------------------------------------------------------------- 1 | import os 2 | import random 3 | 4 | import numpy as np 5 | from scipy import io 6 | from PIL import Image 7 | 8 | import torch 9 | import torchvision 10 | import torchvision.transforms as transforms 11 | 12 | class CUBDataset(torch.utils.data.Dataset): 13 | def __init__(self, dataPath, sets='train', transform=transforms.ToTensor()): 14 | super(CUBDataset, self).__init__() 15 | splits = np.loadtxt(os.path.join(dataPath, "train_val_test_split.txt"), int) 16 | self.files = np.loadtxt(os.path.join(dataPath, "images.txt"), str)[:,1] 17 | if sets == 'train': 18 | self.files = self.files[splits[:,1] == 0] 19 | elif sets == 'val': 20 | self.files = self.files[splits[:,1] == 1] 21 | else: 22 | self.files = self.files[splits[:,1] == 2] 23 | self.transform = transform 24 | self.datapath = dataPath 25 | def __len__(self): 26 | return len(self.files) 27 | def __getitem__(self, idx): 28 | filename = self.files[idx] 29 | img = self.transform(Image.open(os.path.join(self.datapath, "images", filename))) 30 | if img.size(0) == 1: 31 | img = img.expand(3, img.size(1), img.size(2)) 32 | seg = self.transform(Image.open(os.path.join(self.datapath, "segmentations", filename[:-3] + 'png'))) 33 | if seg.size(0) != 1: 34 | seg = seg[:1] 35 | seg = (seg > .5).float() 36 | return img * 2 - 1, seg 37 | 38 | class FlowersDataset(torch.utils.data.Dataset): 39 | def __init__(self, dataPath, sets='train', transform=transforms.ToTensor()): 40 | super(FlowersDataset, self).__init__() 41 | self.files = io.loadmat(os.path.join(dataPath, "setid.mat")) 42 | if sets == 'train': 43 | self.files = self.files.get('tstid')[0] 44 | elif sets == 'val': 45 | self.files = self.files.get('valid')[0] 46 | else: 47 | self.files = self.files.get('trnid')[0] 48 | self.transform = transform 49 | self.datapath = dataPath 50 | def __len__(self): 51 | return len(self.files) 52 | def __getitem__(self, idx): 53 | imgname = "image_%05d.jpg" % self.files[idx] 54 | segname = "segmim_%05d.jpg" % self.files[idx] 55 | img = self.transform(Image.open(os.path.join(self.datapath, "jpg", imgname))) 56 | seg = np.array(Image.open(os.path.join(self.datapath, "segmim", segname))) 57 | seg = 1 - ((seg[:,:,0:1] == 0) + (seg[:,:,1:2] == 0) + (seg[:,:,2:3] == 254)) 58 | seg = (seg * 255).astype('uint8').repeat(3,axis=2) 59 | seg = self.transform(Image.fromarray(seg))[:1] 60 | return img * 2 - 1, seg 61 | 62 | class LFWDataset(torch.utils.data.Dataset): 63 | def __init__(self, dataPath, sets='train', transform=transforms.ToTensor()): 64 | super(LFWDataset, self).__init__() 65 | with open(os.path.join(dataPath,sets+'.txt'), 'r') as f: 66 | self.files = np.array([l[:-1].split() for l in f.readlines()]) 67 | self.transform = transform 68 | self.datapath = dataPath 69 | self.sets = sets 70 | def __len__(self): 71 | return len(self.files) 72 | def __getitem__(self, idx): 73 | img = Image.open(os.path.join(self.datapath, 74 | "lfw_funneled", 75 | self.files[idx,0], 76 | self.files[idx,1]+'.jpg')) 77 | img = self.transform(img) 78 | if self.sets == 'test' or self.sets == 'val': 79 | seg = Image.open(os.path.join(self.datapath, 80 | "parts_lfw_funneled_gt_images", 81 | self.files[idx,1]+'.ppm')) 82 | seg = self.transform(seg) 83 | seg = 1 - seg[2:] 84 | else: 85 | seg = img[:1] 86 | if img.size(0) == 1: 87 | img = img.expand(3, img.size(1), img.size(2)) 88 | return img * 2 - 1, seg 89 | 90 | class CMNISTDataset(torch.utils.data.Dataset): 91 | def __init__(self, dataPath, sets='train', transform=transforms.ToTensor()): 92 | super(CMNISTDataset, self).__init__() 93 | self.mnist = torchvision.datasets.MNIST(dataPath, 94 | train=(sets=='train'), 95 | download=True, 96 | transform=transforms.Compose([transforms.Resize(28+28, Image.NEAREST), 97 | transforms.ToTensor(),])) 98 | self.mnist0 = iter(self.mnist) 99 | self.mnist1 = iter(self.mnist) 100 | self.sets = sets 101 | def __len__(self): 102 | return 1000 # arbitrary number for eval 103 | def __getitem__(self, idx): 104 | background = torch.randint(2, (3,1,1)).float().repeat(1,128,128) 105 | background = torch.FloatTensor(3,1,1).uniform_(.33,.66).repeat(1,128,128) 106 | background[0] = background[1] 107 | color0 = torch.FloatTensor(3,1,1) 108 | color0.uniform_(0,.33) 109 | color0[1] = color0[2] 110 | color1 = torch.FloatTensor(3,1,1) 111 | color1.uniform_(.66,1) 112 | color1[0] = color1[2] 113 | try: 114 | obj0, label0 = next(self.mnist0) 115 | except: 116 | self.mnist0 = iter(self.mnist) 117 | obj0, label0 = next(self.mnist0) 118 | while label0 % 2 != 0: 119 | try: 120 | obj0, label0 = next(self.mnist0) 121 | except: 122 | self.mnist0 = iter(self.mnist) 123 | obj0, label0 = next(self.mnist0) 124 | obj0 = (obj0 > .5).float() 125 | obj0 = obj0.repeat(3,1,1) 126 | try: 127 | obj1, label1 = next(self.mnist1) 128 | except: 129 | self.mnist1 = iter(self.mnist) 130 | obj1, label1 = next(self.mnist1) 131 | while label1 % 2 != 1: 132 | try: 133 | obj1, label1 = next(self.mnist1) 134 | except: 135 | self.mnist1 = iter(self.mnist) 136 | obj1, label1 = next(self.mnist1) 137 | obj1 = (obj1 > .5).float() 138 | obj1 = obj1.repeat(3,1,1) 139 | bg = background.clone() 140 | px0 = random.randint(0,bg.size(1)-obj0.size(1)-1) 141 | py0 = random.randint(0,bg.size(2)-obj0.size(2)-1) 142 | px1 = random.randint(0,bg.size(1)-obj1.size(1)-1) 143 | py1 = random.randint(0,bg.size(2)-obj1.size(2)-1) 144 | seg = torch.zeros(3,128,128) 145 | seg[2].fill_(1) 146 | order = random.randint(0,1) 147 | if order == 0: 148 | bg[:,px0:px0+obj0.size(1),py0:py0+obj0.size(2)] = (bg[:,px0:px0+obj0.size(1),py0:py0+obj0.size(2)] * (1-obj0)) + obj0 * color0 149 | bg[:,px1:px1+obj1.size(1),py1:py1+obj1.size(2)] = (bg[:,px1:px1+obj1.size(1),py1:py1+obj1.size(2)] * (1-obj1)) + obj1 * color1 150 | seg[:,px0:px0+obj0.size(1),py0:py0+obj0.size(2)] = seg[:,px0:px0+obj0.size(1),py0:py0+obj0.size(2)] * (1-obj0) 151 | seg[0,px0:px0+obj0.size(1),py0:py0+obj0.size(2)] = seg[0,px0:px0+obj0.size(1),py0:py0+obj0.size(2)] * (1-obj0[0]) + obj0[0] 152 | seg[:,px1:px1+obj1.size(1),py1:py1+obj1.size(2)] = seg[:,px1:px1+obj1.size(1),py1:py1+obj1.size(2)] * (1-obj1) 153 | seg[1,px1:px1+obj1.size(1),py1:py1+obj1.size(2)] = seg[1,px1:px1+obj1.size(1),py1:py1+obj1.size(2)] * (1-obj1[0]) + obj1[0] 154 | else: 155 | bg[:,px1:px1+obj1.size(1),py1:py1+obj1.size(2)] = (bg[:,px1:px1+obj1.size(1),py1:py1+obj1.size(2)] * (1-obj1)) + obj1 * color1 156 | bg[:,px0:px0+obj0.size(1),py0:py0+obj0.size(2)] = (bg[:,px0:px0+obj0.size(1),py0:py0+obj0.size(2)] * (1-obj0)) + obj0 * color0 157 | seg[:,px1:px1+obj1.size(1),py1:py1+obj1.size(2)] = seg[:,px1:px1+obj1.size(1),py1:py1+obj1.size(2)] * (1-obj1) 158 | seg[1,px1:px1+obj1.size(1),py1:py1+obj1.size(2)] = seg[1,px1:px1+obj1.size(1),py1:py1+obj1.size(2)] * (1-obj1[0]) + obj1[0] 159 | seg[:,px0:px0+obj0.size(1),py0:py0+obj0.size(2)] = seg[:,px0:px0+obj0.size(1),py0:py0+obj0.size(2)] * (1-obj0) 160 | seg[0,px0:px0+obj0.size(1),py0:py0+obj0.size(2)] = seg[0,px0:px0+obj0.size(1),py0:py0+obj0.size(2)] * (1-obj0[0]) + obj0[0] 161 | return bg * 2 - 1, seg 162 | -------------------------------------------------------------------------------- /datasplits/lfw-funneled/test.txt: -------------------------------------------------------------------------------- 1 | AJ_Cook AJ_Cook_0001 2 | Abdel_Nasser_Assidi Abdel_Nasser_Assidi_0001 3 | Abdel_Nasser_Assidi Abdel_Nasser_Assidi_0002 4 | Abdoulaye_Wade Abdoulaye_Wade_0004 5 | Abdul_Rahman Abdul_Rahman_0001 6 | Abdullah Abdullah_0001 7 | Abdullah Abdullah_0002 8 | Abdullah Abdullah_0003 9 | Abdullah Abdullah_0004 10 | Abdullah_Nasseef Abdullah_Nasseef_0001 11 | Abdullah_al-Attiyah Abdullah_al-Attiyah_0001 12 | Abdullah_al-Attiyah Abdullah_al-Attiyah_0002 13 | Abdullah_al-Attiyah Abdullah_al-Attiyah_0003 14 | Abel_Pacheco Abel_Pacheco_0001 15 | Abel_Pacheco Abel_Pacheco_0003 16 | Abel_Pacheco Abel_Pacheco_0004 17 | Adam_Sandler Adam_Sandler_0001 18 | Adam_Sandler Adam_Sandler_0002 19 | Adam_Sandler Adam_Sandler_0003 20 | Adam_Sandler Adam_Sandler_0004 21 | Adrian_Nastase Adrian_Nastase_0002 22 | Afton_Smith Afton_Smith_0001 23 | Ahmed_Chalabi Ahmed_Chalabi_0001 24 | Ahmed_Chalabi Ahmed_Chalabi_0002 25 | Ahmed_Chalabi Ahmed_Chalabi_0004 26 | Ai_Sugiyama Ai_Sugiyama_0002 27 | Ai_Sugiyama Ai_Sugiyama_0004 28 | Aicha_El_Ouafi Aicha_El_Ouafi_0001 29 | Aicha_El_Ouafi Aicha_El_Ouafi_0002 30 | Aicha_El_Ouafi Aicha_El_Ouafi_0003 31 | Aidan_Quinn Aidan_Quinn_0001 32 | Ainsworth_Dyer Ainsworth_Dyer_0001 33 | Aiysha_Smith Aiysha_Smith_0001 34 | Akbar_Al_Baker Akbar_Al_Baker_0001 35 | Al_Gore Al_Gore_0001 36 | Al_Gore Al_Gore_0003 37 | Al_Gore Al_Gore_0006 38 | Alan_Trammell Alan_Trammell_0001 39 | Alberto_Acosta Alberto_Acosta_0001 40 | Alberto_Fujimori Alberto_Fujimori_0001 41 | Alberto_Fujimori Alberto_Fujimori_0002 42 | Alberto_Ruiz_Gallardon Alberto_Ruiz_Gallardon_0001 43 | Alberto_Ruiz_Gallardon Alberto_Ruiz_Gallardon_0002 44 | Albrecht_Mentz Albrecht_Mentz_0001 45 | Albrecht_Mentz Albrecht_Mentz_0002 46 | Aldo_Paredes Aldo_Paredes_0001 47 | Alec_Baldwin Alec_Baldwin_0001 48 | Alec_Baldwin Alec_Baldwin_0002 49 | Alec_Baldwin Alec_Baldwin_0003 50 | Alec_Baldwin Alec_Baldwin_0004 51 | Alejandro_Lopez Alejandro_Lopez_0001 52 | Alejandro_Toledo Alejandro_Toledo_0020 53 | Alejandro_Toledo Alejandro_Toledo_0038 54 | Alex_Barros Alex_Barros_0001 55 | Alex_Barros Alex_Barros_0002 56 | Alex_Holmes Alex_Holmes_0001 57 | Alex_Sink Alex_Sink_0002 58 | Alex_Sink Alex_Sink_0003 59 | Alex_Wallau Alex_Wallau_0001 60 | Alexa_Loren Alexa_Loren_0001 61 | Alexander_Downer Alexander_Downer_0001 62 | Alexander_Lukashenko Alexander_Lukashenko_0001 63 | Alexandre_Vinokourov Alexandre_Vinokourov_0001 64 | Alfredo_Moreno Alfredo_Moreno_0001 65 | Alice_Fisher Alice_Fisher_0001 66 | Alice_Fisher Alice_Fisher_0002 67 | Alicia_Silverstone Alicia_Silverstone_0001 68 | Alicia_Silverstone Alicia_Silverstone_0002 69 | Alimzhan_Tokhtakhounov Alimzhan_Tokhtakhounov_0001 70 | Alimzhan_Tokhtakhounov Alimzhan_Tokhtakhounov_0002 71 | Alina_Kabaeva Alina_Kabaeva_0001 72 | Allan_Houston Allan_Houston_0001 73 | Allen_Iverson Allen_Iverson_0001 74 | Ally_Sheedy Ally_Sheedy_0001 75 | Alvaro_Noboa Alvaro_Noboa_0001 76 | Alvaro_Noboa Alvaro_Noboa_0002 77 | Alvaro_Noboa Alvaro_Noboa_0003 78 | Alvaro_Silva_Calderon Alvaro_Silva_Calderon_0003 79 | Alvaro_Silva_Calderon Alvaro_Silva_Calderon_0004 80 | Aly_Wagner Aly_Wagner_0001 81 | Amelia_Vega Amelia_Vega_0002 82 | Amelia_Vega Amelia_Vega_0004 83 | Amelia_Vega Amelia_Vega_0005 84 | Amelia_Vega Amelia_Vega_0006 85 | Amelia_Vega Amelia_Vega_0007 86 | Amer_al-Saadi Amer_al-Saadi_0001 87 | Amer_al-Saadi Amer_al-Saadi_0002 88 | Amy_Smart Amy_Smart_0001 89 | Ana_Guevara Ana_Guevara_0001 90 | Ana_Guevara Ana_Guevara_0002 91 | Ana_Guevara Ana_Guevara_0003 92 | Ana_Guevara Ana_Guevara_0005 93 | Ana_Guevara Ana_Guevara_0006 94 | Anastasia_Myskina Anastasia_Myskina_0001 95 | Anastasia_Myskina Anastasia_Myskina_0002 96 | Anastasia_Myskina Anastasia_Myskina_0003 97 | Anders_Fogh_Rasmussen Anders_Fogh_Rasmussen_0001 98 | Anders_Fogh_Rasmussen Anders_Fogh_Rasmussen_0002 99 | Anders_Fogh_Rasmussen Anders_Fogh_Rasmussen_0003 100 | Anders_Fogh_Rasmussen Anders_Fogh_Rasmussen_0004 101 | Andres_Manuel_Lopez_Obrador Andres_Manuel_Lopez_Obrador_0001 102 | Andres_Pastrana Andres_Pastrana_0001 103 | Andrew_Bunner Andrew_Bunner_0001 104 | Andrew_Weissmann Andrew_Weissmann_0001 105 | Andrew_Weissmann Andrew_Weissmann_0003 106 | Andy_Dick Andy_Dick_0001 107 | Andy_Madikians Andy_Madikians_0001 108 | Andy_Wisecarver Andy_Wisecarver_0001 109 | Angel_Maza Angel_Maza_0001 110 | Angela_Bassett Angela_Bassett_0002 111 | Angela_Bassett Angela_Bassett_0006 112 | Angelo_Genova Angelo_Genova_0001 113 | Anibal_Ibarra Anibal_Ibarra_0001 114 | Anibal_Ibarra Anibal_Ibarra_0002 115 | Anibal_Ibarra Anibal_Ibarra_0003 116 | Anjum_Hussain Anjum_Hussain_0001 117 | Anna_Kournikova Anna_Kournikova_0005 118 | Anna_Kournikova Anna_Kournikova_0009 119 | Anne_Heche Anne_Heche_0001 120 | Anne_ONeil Anne_ONeil_0001 121 | Annette_Bening Annette_Bening_0001 122 | Annette_Bening Annette_Bening_0002 123 | Anthony_Hopkins Anthony_Hopkins_0001 124 | Anthony_Hopkins Anthony_Hopkins_0002 125 | Anthony_Scott_Miller Anthony_Scott_Miller_0001 126 | Arminio_Fraga Arminio_Fraga_0002 127 | Arminio_Fraga Arminio_Fraga_0006 128 | Arnoldo_Aleman Arnoldo_Aleman_0001 129 | Arnoldo_Aleman Arnoldo_Aleman_0002 130 | Arnoldo_Aleman Arnoldo_Aleman_0003 131 | Arnoldo_Aleman Arnoldo_Aleman_0004 132 | Arsinee_Khanjian Arsinee_Khanjian_0001 133 | Art_Hoffmann Art_Hoffmann_0001 134 | Art_Hoffmann Art_Hoffmann_0002 135 | Asa_Hutchinson Asa_Hutchinson_0001 136 | Asa_Hutchinson Asa_Hutchinson_0002 137 | Asif_Hanif Asif_Hanif_0001 138 | Atsushi_Sato Atsushi_Sato_0001 139 | Augusto_Roa_Bastos Augusto_Roa_Bastos_0001 140 | Augusto_Roa_Bastos Augusto_Roa_Bastos_0002 141 | Azra_Akin Azra_Akin_0001 142 | Azra_Akin Azra_Akin_0004 143 | BJ_Habibie BJ_Habibie_0001 144 | Baburam_Bhattari Baburam_Bhattari_0001 145 | Barbara_Bodine Barbara_Bodine_0001 146 | Barbara_Boxer Barbara_Boxer_0001 147 | Barbra_Streisand Barbra_Streisand_0001 148 | Barbra_Streisand Barbra_Streisand_0002 149 | Barbra_Streisand Barbra_Streisand_0003 150 | Barry_Bonds Barry_Bonds_0001 151 | Barry_Ford Barry_Ford_0001 152 | Ben_Braun Ben_Braun_0001 153 | Ben_Chandler Ben_Chandler_0001 154 | Ben_Lee Ben_Lee_0001 155 | Ben_Wallace Ben_Wallace_0001 156 | Benjamin_Bratt Benjamin_Bratt_0001 157 | Bernard_Law Bernard_Law_0001 158 | Bernard_Law Bernard_Law_0002 159 | Bernard_Law Bernard_Law_0003 160 | Bernard_Law Bernard_Law_0005 161 | Bernard_Lord Bernard_Lord_0002 162 | Bernardo_Segura Bernardo_Segura_0001 163 | Bernardo_Segura Bernardo_Segura_0002 164 | Beth_Jones Beth_Jones_0001 165 | Beth_Jones Beth_Jones_0002 166 | Betty_Garrison Betty_Garrison_0001 167 | Bijan_Darvish Bijan_Darvish_0001 168 | Bijan_Darvish Bijan_Darvish_0003 169 | Bijan_Namdar_Zangeneh Bijan_Namdar_Zangeneh_0001 170 | Bijan_Namdar_Zangeneh Bijan_Namdar_Zangeneh_0002 171 | Bill_Belichick Bill_Belichick_0001 172 | Bill_Belichick Bill_Belichick_0002 173 | Bill_Bradley Bill_Bradley_0001 174 | Bill_Parcells Bill_Parcells_0002 175 | Bill_Richardson Bill_Richardson_0001 176 | Bill_Simon Bill_Simon_0004 177 | Bill_Simon Bill_Simon_0005 178 | Bill_Simon Bill_Simon_0013 179 | Bill_Simon Bill_Simon_0015 180 | Billy_Graham Billy_Graham_0001 181 | Billy_Graham Billy_Graham_0002 182 | Binyamin_Ben-Eliezer Binyamin_Ben-Eliezer_0002 183 | Binyamin_Ben-Eliezer Binyamin_Ben-Eliezer_0003 184 | Binyamin_Ben-Eliezer Binyamin_Ben-Eliezer_0005 185 | Binyamin_Ben-Eliezer Binyamin_Ben-Eliezer_0006 186 | Binyamin_Ben-Eliezer Binyamin_Ben-Eliezer_0007 187 | Bo_Ryan Bo_Ryan_0001 188 | Bo_Ryan Bo_Ryan_0002 189 | Bob_Alper Bob_Alper_0001 190 | Bob_Beauprez Bob_Beauprez_0001 191 | Bob_Beauprez Bob_Beauprez_0002 192 | Bob_Bowlsby Bob_Bowlsby_0001 193 | Bob_Geldof Bob_Geldof_0001 194 | Bob_Geldof Bob_Geldof_0002 195 | Bob_Huggins Bob_Huggins_0001 196 | Bob_Huggins Bob_Huggins_0002 197 | Boris_Becker Boris_Becker_0002 198 | Boris_Henry Boris_Henry_0001 199 | Brad_Brownell Brad_Brownell_0001 200 | Brad_Gushue Brad_Gushue_0001 201 | Brad_Johnson Brad_Johnson_0003 202 | Brad_Wilk Brad_Wilk_0001 203 | Brandon_Hammond Brandon_Hammond_0001 204 | Brendan_Stai Brendan_Stai_0001 205 | Brian_Grazier Brian_Grazier_0001 206 | Brian_Gregory Brian_Gregory_0001 207 | Brian_Pavlich Brian_Pavlich_0001 208 | Brian_Schneider Brian_Schneider_0001 209 | Brian_Van_Dusen Brian_Van_Dusen_0001 210 | Brittany_Snow Brittany_Snow_0001 211 | Brooke_Gordon Brooke_Gordon_0001 212 | Brooke_Shields Brooke_Shields_0001 213 | Brooke_Shields Brooke_Shields_0002 214 | Bruce_Springsteen Bruce_Springsteen_0002 215 | Bruce_Van_De_Velde Bruce_Van_De_Velde_0001 216 | Bruce_Van_De_Velde Bruce_Van_De_Velde_0002 217 | Bruce_Weber Bruce_Weber_0001 218 | Bruce_Weber Bruce_Weber_0002 219 | Buzz_Hargrove Buzz_Hargrove_0001 220 | Cabas Cabas_0001 221 | Cameron_Diaz Cameron_Diaz_0001 222 | Cameron_Diaz Cameron_Diaz_0003 223 | Cameron_Diaz Cameron_Diaz_0004 224 | Camryn_Manheim Camryn_Manheim_0001 225 | Carin_Koch Carin_Koch_0001 226 | Carlos_Alberto_Parreira Carlos_Alberto_Parreira_0001 227 | Carlos_Barra Carlos_Barra_0001 228 | Carlos_Menem Carlos_Menem_0001 229 | Carlos_Menem Carlos_Menem_0003 230 | Carlos_Menem Carlos_Menem_0006 231 | Carlos_Menem Carlos_Menem_0012 232 | Carlos_Paternina Carlos_Paternina_0001 233 | Carlos_Queiroz Carlos_Queiroz_0001 234 | Carlos_Ruiz Carlos_Ruiz_0001 235 | Carlos_Ruiz Carlos_Ruiz_0002 236 | Carlos_Ruiz Carlos_Ruiz_0003 237 | Carlos_Salinas Carlos_Salinas_0001 238 | Carlos_Vives Carlos_Vives_0001 239 | Carlos_Vives Carlos_Vives_0002 240 | Carlos_Vives Carlos_Vives_0003 241 | Carly_Fiorina Carly_Fiorina_0001 242 | Carly_Fiorina Carly_Fiorina_0002 243 | Carly_Fiorina Carly_Fiorina_0003 244 | Carolina_Kluft Carolina_Kluft_0001 245 | Carolina_Kluft Carolina_Kluft_0003 246 | Caroline_Kennedy Caroline_Kennedy_0001 247 | Caroline_Kennedy Caroline_Kennedy_0003 248 | Carson_Palmer Carson_Palmer_0002 249 | Carson_Palmer Carson_Palmer_0004 250 | Cate_Blanchett Cate_Blanchett_0002 251 | Cate_Blanchett Cate_Blanchett_0003 252 | Cate_Blanchett Cate_Blanchett_0004 253 | Catherine_Deneuve Catherine_Deneuve_0002 254 | Catherine_Deneuve Catherine_Deneuve_0005 255 | Cathryn_Crawford Cathryn_Crawford_0001 256 | Catriona_Le_May_Doan Catriona_Le_May_Doan_0001 257 | Cesar_Gaviria Cesar_Gaviria_0002 258 | Cesar_Gaviria Cesar_Gaviria_0004 259 | Cesar_Gaviria Cesar_Gaviria_0005 260 | Cesar_Gaviria Cesar_Gaviria_0006 261 | Cesar_Gaviria Cesar_Gaviria_0007 262 | Cesar_Gaviria Cesar_Gaviria_0008 263 | Chadha_Gurinder Chadha_Gurinder_0001 264 | Chakib_Khelil Chakib_Khelil_0001 265 | Chan_Choi Chan_Choi_0001 266 | Charles_Chandler_IV Charles_Chandler_IV_0001 267 | Charles_Grassley Charles_Grassley_0001 268 | Charles_Grassley Charles_Grassley_0002 269 | Charles_Lebois Charles_Lebois_0001 270 | Charles_Moose Charles_Moose_0001 271 | Charles_Moose Charles_Moose_0003 272 | Charles_Moose Charles_Moose_0004 273 | Charles_Moose Charles_Moose_0010 274 | Charles_Moose Charles_Moose_0011 275 | Charles_Schumer Charles_Schumer_0001 276 | Charles_Schumer Charles_Schumer_0002 277 | Charlotte_Rampling Charlotte_Rampling_0001 278 | Charlotte_Rampling Charlotte_Rampling_0002 279 | Cheryl_Tiegs Cheryl_Tiegs_0001 280 | Chip_Knight Chip_Knight_0001 281 | Choi_Sung-hong Choi_Sung-hong_0001 282 | Choi_Sung-hong Choi_Sung-hong_0003 283 | Choi_Sung-hong Choi_Sung-hong_0004 284 | Chris_Neil Chris_Neil_0001 285 | Chris_Reitsma Chris_Reitsma_0001 286 | Chris_Tucker Chris_Tucker_0001 287 | Chris_Tucker Chris_Tucker_0002 288 | Christian_Lirette Christian_Lirette_0001 289 | Christian_Malcolm Christian_Malcolm_0001 290 | Christopher_Conyers Christopher_Conyers_0001 291 | Christopher_Patten Christopher_Patten_0001 292 | Christopher_Patten Christopher_Patten_0002 293 | Christopher_Walken Christopher_Walken_0001 294 | Christopher_Walken Christopher_Walken_0002 295 | Christopher_Walken Christopher_Walken_0004 296 | Chuck_Yeager Chuck_Yeager_0001 297 | Chuck_Yeager Chuck_Yeager_0002 298 | Cindy_Klassen Cindy_Klassen_0001 299 | Cindy_Margolis Cindy_Margolis_0001 300 | Cindy_Margolis Cindy_Margolis_0002 301 | Cindy_Moll Cindy_Moll_0001 302 | Cindy_Zagorski Cindy_Zagorski_0001 303 | Ciro_Gomes Ciro_Gomes_0002 304 | Ciro_Gomes Ciro_Gomes_0003 305 | Ciro_Gomes Ciro_Gomes_0004 306 | Claire_Hentzen Claire_Hentzen_0001 307 | Claire_Hentzen Claire_Hentzen_0002 308 | Clara_Harris Clara_Harris_0001 309 | Clara_Harris Clara_Harris_0002 310 | Clara_Harris Clara_Harris_0004 311 | Claudia_Schiffer Claudia_Schiffer_0001 312 | Claudia_Schiffer Claudia_Schiffer_0003 313 | Claudine_Farrell Claudine_Farrell_0001 314 | Cliff_Ellis Cliff_Ellis_0001 315 | Clifford_Robinson Clifford_Robinson_0001 316 | Clive_Lloyd Clive_Lloyd_0001 317 | Cole_Chapman Cole_Chapman_0001 318 | Colin_Phillips Colin_Phillips_0001 319 | Colleen_Donovan Colleen_Donovan_0001 320 | Conan_OBrien Conan_OBrien_0001 321 | Conan_OBrien Conan_OBrien_0002 322 | Constance_Marie Constance_Marie_0002 323 | Constance_Marie Constance_Marie_0003 324 | Coretta_Scott_King Coretta_Scott_King_0001 325 | Coretta_Scott_King Coretta_Scott_King_0002 326 | Coretta_Scott_King Coretta_Scott_King_0003 327 | Corinne_Coman Corinne_Coman_0001 328 | Corinne_Coman Corinne_Coman_0002 329 | Crispin_Glover Crispin_Glover_0001 330 | Cristian_Barros Cristian_Barros_0001 331 | Cristiano_da_Matta Cristiano_da_Matta_0001 332 | Cuba_Gooding_Jr Cuba_Gooding_Jr_0001 333 | Curt_Weldon Curt_Weldon_0001 334 | DAngelo_Jimenez DAngelo_Jimenez_0001 335 | Dale_Bosworth Dale_Bosworth_0001 336 | Dale_Earnhardt_Jr Dale_Earnhardt_Jr_0001 337 | Dale_Earnhardt_Jr Dale_Earnhardt_Jr_0002 338 | Dale_Earnhardt_Jr Dale_Earnhardt_Jr_0003 339 | Damon_van_Dam Damon_van_Dam_0001 340 | Damon_van_Dam Damon_van_Dam_0002 341 | Dan_Boyle Dan_Boyle_0001 342 | Dan_Duquette Dan_Duquette_0001 343 | Dan_Morales Dan_Morales_0001 344 | Dan_Morales Dan_Morales_0002 345 | Dan_Morales Dan_Morales_0003 346 | Dan_Quayle Dan_Quayle_0001 347 | Dana_Vollmer Dana_Vollmer_0001 348 | Daniel_Chin Daniel_Chin_0001 349 | Daniel_Day-Lewis Daniel_Day-Lewis_0001 350 | Daniel_Day-Lewis Daniel_Day-Lewis_0002 351 | Daniel_Day-Lewis Daniel_Day-Lewis_0003 352 | Daniel_Rouse Daniel_Rouse_0001 353 | Darko_Milicic Darko_Milicic_0001 354 | Darrell_Porter Darrell_Porter_0001 355 | Darrell_Porter Darrell_Porter_0002 356 | Dave_Matthews Dave_Matthews_0001 357 | Dave_McNally Dave_McNally_0001 358 | Dave_Tucker Dave_Tucker_0001 359 | Dave_Williams Dave_Williams_0001 360 | David_Anderson David_Anderson_0001 361 | David_Anderson David_Anderson_0002 362 | David_Anderson David_Anderson_0004 363 | David_Anderson David_Anderson_0005 364 | David_Ballantyne David_Ballantyne_0001 365 | David_Beckham David_Beckham_0004 366 | David_Beckham David_Beckham_0005 367 | David_Beckham David_Beckham_0008 368 | David_Beckham David_Beckham_0010 369 | David_Beckham David_Beckham_0017 370 | David_Beckham David_Beckham_0024 371 | David_Canary David_Canary_0001 372 | David_Caruso David_Caruso_0001 373 | David_Caruso David_Caruso_0002 374 | David_Coulthard David_Coulthard_0001 375 | David_Coulthard David_Coulthard_0002 376 | David_Dewhurst David_Dewhurst_0001 377 | David_Dodge David_Dodge_0001 378 | David_Dodge David_Dodge_0002 379 | David_Gest David_Gest_0001 380 | David_Hilt David_Hilt_0001 381 | David_Hyde_Pierce David_Hyde_Pierce_0003 382 | David_Hyde_Pierce David_Hyde_Pierce_0004 383 | David_Nalbandian David_Nalbandian_0004 384 | David_Nalbandian David_Nalbandian_0009 385 | David_Nalbandian David_Nalbandian_0013 386 | David_Sibleyk David_Sibleyk_0001 387 | David_Spade David_Spade_0001 388 | David_Spade David_Spade_0002 389 | David_Suazo David_Suazo_0001 390 | David_Wells David_Wells_0001 391 | David_Wells David_Wells_0002 392 | David_Wells David_Wells_0005 393 | David_Wells David_Wells_0007 394 | Dean_Barkley Dean_Barkley_0001 395 | Dean_Barkley Dean_Barkley_0002 396 | Dean_Barkley Dean_Barkley_0003 397 | Dean_Barkley Dean_Barkley_0004 398 | Debbie_Reynolds Debbie_Reynolds_0001 399 | Debbie_Reynolds Debbie_Reynolds_0003 400 | Debra_Brown Debra_Brown_0001 401 | Debra_Brown Debra_Brown_0002 402 | Debra_Yang Debra_Yang_0001 403 | Deena_Burnett Deena_Burnett_0001 404 | Denise_Locke Denise_Locke_0001 405 | Dennis_Kucinich Dennis_Kucinich_0002 406 | Dennis_Kucinich Dennis_Kucinich_0005 407 | Dennis_Kucinich Dennis_Kucinich_0006 408 | Dennis_Kucinich Dennis_Kucinich_0007 409 | Dennis_Oswald Dennis_Oswald_0001 410 | Dereck_Whittenburg Dereck_Whittenburg_0001 411 | Desiree_Lemosi Desiree_Lemosi_0001 412 | Desiree_Lemosi Desiree_Lemosi_0002 413 | Diana_Silvius Diana_Silvius_0001 414 | Diana_Taurasi Diana_Taurasi_0002 415 | Dick_Cheney Dick_Cheney_0001 416 | Dick_Cheney Dick_Cheney_0011 417 | Dick_Cheney Dick_Cheney_0014 418 | Dick_Smothers Dick_Smothers_0001 419 | Dimitar_Berbatov Dimitar_Berbatov_0001 420 | Dionyssis_Georgiadis Dionyssis_Georgiadis_0001 421 | Dita_Von_Tesse Dita_Von_Tesse_0001 422 | Doc_Rivers Doc_Rivers_0001 423 | Dolly_Parton Dolly_Parton_0001 424 | Dolly_Parton Dolly_Parton_0002 425 | Donald_Evans Donald_Evans_0001 426 | Donald_Evans Donald_Evans_0002 427 | Donald_Hays Donald_Hays_0001 428 | Donna_Ralston Donna_Ralston_0001 429 | Donny_Osmond Donny_Osmond_0001 430 | Doris_Roberts Doris_Roberts_0001 431 | Doris_Roberts Doris_Roberts_0002 432 | Drew_Barrymore Drew_Barrymore_0001 433 | Drew_Barrymore Drew_Barrymore_0002 434 | Duane_Lee_Chapman Duane_Lee_Chapman_0001 435 | Duane_Lee_Chapman Duane_Lee_Chapman_0002 436 | Duncan_Fletcher Duncan_Fletcher_0001 437 | Dwayne_Johnson Dwayne_Johnson_0001 438 | Dwayne_Johnson Dwayne_Johnson_0002 439 | Dwayne_Wade Dwayne_Wade_0001 440 | Earl_Campbell Earl_Campbell_0001 441 | Ed_Smart Ed_Smart_0003 442 | Eddie_Fenech_Adami Eddie_Fenech_Adami_0001 443 | Eddie_Lewis Eddie_Lewis_0001 444 | Eddy_Merckx Eddy_Merckx_0001 445 | Eddy_Merckx Eddy_Merckx_0002 446 | Edmund_Stoiber Edmund_Stoiber_0002 447 | Edmund_Stoiber Edmund_Stoiber_0003 448 | Edmund_Stoiber Edmund_Stoiber_0005 449 | Eduard_Shevardnadze Eduard_Shevardnadze_0001 450 | Eduard_Shevardnadze Eduard_Shevardnadze_0003 451 | Eduard_Shevardnadze Eduard_Shevardnadze_0004 452 | Eduardo_Chillida Eduardo_Chillida_0001 453 | Edward_Burns Edward_Burns_0001 454 | Edward_Kennedy Edward_Kennedy_0001 455 | Edward_Kennedy Edward_Kennedy_0002 456 | Edward_Said Edward_Said_0001 457 | Edward_Said Edward_Said_0002 458 | Eglis_Yaima_Cruz Eglis_Yaima_Cruz_0001 459 | Eileen_Spina Eileen_Spina_0001 460 | Ekke_Hard_Forberg Ekke_Hard_Forberg_0001 461 | Elena_Bereznaya Elena_Bereznaya_0001 462 | Elizabeth_Shue Elizabeth_Shue_0001 463 | Elizabeth_Shue Elizabeth_Shue_0002 464 | Elizabeth_Taylor Elizabeth_Taylor_0001 465 | Ellen_Engleman Ellen_Engleman_0001 466 | Elodie_Bouchez Elodie_Bouchez_0001 467 | Emanuel_Ginobili Emanuel_Ginobili_0001 468 | Emanuel_Ginobili Emanuel_Ginobili_0002 469 | Emanuel_Ginobili Emanuel_Ginobili_0004 470 | Emanuel_Ginobili Emanuel_Ginobili_0005 471 | Emile_Lahoud Emile_Lahoud_0001 472 | Emile_Lahoud Emile_Lahoud_0002 473 | Emily_Mortimer Emily_Mortimer_0001 474 | Emily_Robison Emily_Robison_0001 475 | Emily_Robison Emily_Robison_0002 476 | Emmanuel_Milingo Emmanuel_Milingo_0001 477 | Emmanuelle_Beart Emmanuelle_Beart_0001 478 | Emmanuelle_Beart Emmanuelle_Beart_0002 479 | Emmanuelle_Beart Emmanuelle_Beart_0003 480 | Emmanuelle_Jagodsinski Emmanuelle_Jagodsinski_0001 481 | Emmy_Rossum Emmy_Rossum_0001 482 | Enrique_Bolanos Enrique_Bolanos_0001 483 | Enrique_Bolanos Enrique_Bolanos_0002 484 | Enrique_Bolanos Enrique_Bolanos_0004 485 | Enrique_Bolanos Enrique_Bolanos_0005 486 | Enrique_Medina_Gomez Enrique_Medina_Gomez_0001 487 | Eric_Christian_Olsen Eric_Christian_Olsen_0001 488 | Eric_Lloyd Eric_Lloyd_0001 489 | Eric_Robert_Rudolph Eric_Robert_Rudolph_0001 490 | Eric_Rosser Eric_Rosser_0001 491 | Eric_Rosser Eric_Rosser_0002 492 | Eric_Taino Eric_Taino_0001 493 | Erin_Brockovich Erin_Brockovich_0001 494 | Erskine_Bowles Erskine_Bowles_0001 495 | Estella_Warren Estella_Warren_0001 496 | Eunice_Barber Eunice_Barber_0001 497 | Eunice_Barber Eunice_Barber_0002 498 | Eva_Dimas Eva_Dimas_0001 499 | Eva_Dimas Eva_Dimas_0002 500 | Evander_Holyfield Evander_Holyfield_0001 501 | Evander_Holyfield Evander_Holyfield_0002 502 | Farida_Ragoonanan Farida_Ragoonanan_0001 503 | Farouk_al-Sharaa Farouk_al-Sharaa_0001 504 | Farouk_al-Sharaa Farouk_al-Sharaa_0002 505 | Farouk_al-Sharaa Farouk_al-Sharaa_0003 506 | Federico_Trillo Federico_Trillo_0001 507 | Federico_Trillo Federico_Trillo_0003 508 | Fernando_Gonzalez Fernando_Gonzalez_0002 509 | Fernando_Gonzalez Fernando_Gonzalez_0004 510 | Fernando_Gonzalez Fernando_Gonzalez_0006 511 | Fernando_Gonzalez Fernando_Gonzalez_0007 512 | Fernando_Henrique_Cardoso Fernando_Henrique_Cardoso_0001 513 | Fernando_Henrique_Cardoso Fernando_Henrique_Cardoso_0003 514 | Fernando_Henrique_Cardoso Fernando_Henrique_Cardoso_0005 515 | Fernando_Hierro Fernando_Hierro_0001 516 | Filippo_Volandri Filippo_Volandri_0001 517 | Flavia_Delaroli Flavia_Delaroli_0001 518 | Flavia_Delaroli Flavia_Delaroli_0002 519 | Florencia_Kirchner Florencia_Kirchner_0001 520 | Francis_Ford_Coppola Francis_Ford_Coppola_0001 521 | Francis_Ford_Coppola Francis_Ford_Coppola_0002 522 | Francis_George Francis_George_0001 523 | Francis_Mer Francis_Mer_0001 524 | Francisco_Flores Francisco_Flores_0003 525 | Francisco_Flores Francisco_Flores_0004 526 | Francois_Botha Francois_Botha_0001 527 | Frank_Coraci Frank_Coraci_0001 528 | Frank_Hilldrup Frank_Hilldrup_0001 529 | Frank_Solich Frank_Solich_0001 530 | Frank_Solich Frank_Solich_0002 531 | Frank_Solich Frank_Solich_0003 532 | Frank_Solich Frank_Solich_0004 533 | Frank_Solich Frank_Solich_0005 534 | Franz_Muentefering Franz_Muentefering_0001 535 | Franz_Muentefering Franz_Muentefering_0002 536 | Franz_Muentefering Franz_Muentefering_0003 537 | Franz_Muentefering Franz_Muentefering_0004 538 | Fred_Eckhard Fred_Eckhard_0002 539 | Fred_Huff Fred_Huff_0001 540 | Freda_Black Freda_Black_0001 541 | Gabriel_Valdes Gabriel_Valdes_0001 542 | Gabriel_Valdes Gabriel_Valdes_0002 543 | Garry_Alejano Garry_Alejano_0001 544 | Garry_Kasparov Garry_Kasparov_0001 545 | Garry_Kasparov Garry_Kasparov_0002 546 | Gary_Bald Gary_Bald_0001 547 | Gary_Condit Gary_Condit_0001 548 | Gary_Forsee Gary_Forsee_0001 549 | Gary_Forsee Gary_Forsee_0002 550 | Geno_Auriemma Geno_Auriemma_0001 551 | Geoff_Dixon Geoff_Dixon_0001 552 | George_Clooney George_Clooney_0002 553 | George_Clooney George_Clooney_0003 554 | George_Clooney George_Clooney_0005 555 | George_Clooney George_Clooney_0007 556 | George_Clooney George_Clooney_0008 557 | George_Clooney George_Clooney_0009 558 | George_Galloway George_Galloway_0001 559 | George_Galloway George_Galloway_0004 560 | George_Gregan George_Gregan_0001 561 | George_HW_Bush George_HW_Bush_0001 562 | George_HW_Bush George_HW_Bush_0003 563 | George_HW_Bush George_HW_Bush_0005 564 | George_HW_Bush George_HW_Bush_0009 565 | George_HW_Bush George_HW_Bush_0010 566 | George_HW_Bush George_HW_Bush_0013 567 | George_Lopez George_Lopez_0001 568 | George_Lopez George_Lopez_0004 569 | George_Pataki George_Pataki_0001 570 | George_Pataki George_Pataki_0002 571 | George_Pataki George_Pataki_0005 572 | George_Roy_Hill George_Roy_Hill_0001 573 | George_Roy_Hill George_Roy_Hill_0002 574 | George_Voinovich George_Voinovich_0001 575 | George_Voinovich George_Voinovich_0002 576 | George_Voinovich George_Voinovich_0003 577 | George_W_Bush George_W_Bush_0353 578 | George_W_Bush George_W_Bush_0407 579 | Gerald_Ford Gerald_Ford_0001 580 | Geraldo_Rivera Geraldo_Rivera_0001 581 | Gerard_Butler Gerard_Butler_0001 582 | Gerry_Parsky Gerry_Parsky_0001 583 | Gerry_Parsky Gerry_Parsky_0002 584 | Gian_Marco Gian_Marco_0002 585 | Gian_Marco Gian_Marco_0003 586 | Gianna_Angelopoulos-Daskalaki Gianna_Angelopoulos-Daskalaki_0001 587 | Gil_de_Ferran Gil_de_Ferran_0002 588 | Gil_de_Ferran Gil_de_Ferran_0003 589 | Gilberto_Simoni Gilberto_Simoni_0001 590 | Gilles_Panizzi Gilles_Panizzi_0001 591 | Gillian_Anderson Gillian_Anderson_0001 592 | Gina_Torres Gina_Torres_0001 593 | Gisele_Bundchen Gisele_Bundchen_0001 594 | Gisele_Bundchen Gisele_Bundchen_0002 595 | Gloria_Allred Gloria_Allred_0001 596 | Gloria_Allred Gloria_Allred_0002 597 | Gloria_Trevi Gloria_Trevi_0001 598 | Gloria_Trevi Gloria_Trevi_0002 599 | Gloria_Trevi Gloria_Trevi_0003 600 | Gloria_Trevi Gloria_Trevi_0004 601 | Goldie_Hawn Goldie_Hawn_0002 602 | Goldie_Hawn Goldie_Hawn_0006 603 | Gonzalo_Barrientos Gonzalo_Barrientos_0001 604 | Gonzalo_Sanchez_de_Lozada Gonzalo_Sanchez_de_Lozada_0003 605 | Gonzalo_Sanchez_de_Lozada Gonzalo_Sanchez_de_Lozada_0004 606 | Gonzalo_Sanchez_de_Lozada Gonzalo_Sanchez_de_Lozada_0007 607 | Gonzalo_Sanchez_de_Lozada Gonzalo_Sanchez_de_Lozada_0008 608 | Gonzalo_Sanchez_de_Lozada Gonzalo_Sanchez_de_Lozada_0010 609 | Goran_Persson Goran_Persson_0001 610 | Goran_Persson Goran_Persson_0002 611 | Gordana_Grubin Gordana_Grubin_0001 612 | Gordon_Cooper Gordon_Cooper_0001 613 | Grady_Little Grady_Little_0001 614 | Graeme_Smith Graeme_Smith_0001 615 | Graham_Bentley Graham_Bentley_0001 616 | Greg_Owen Greg_Owen_0001 617 | Gregg_Berhalter Gregg_Berhalter_0001 618 | Gregg_Popovich Gregg_Popovich_0003 619 | Gregg_Popovich Gregg_Popovich_0004 620 | Gregorio_Rosal Gregorio_Rosal_0001 621 | Guennadi_Chipouline Guennadi_Chipouline_0001 622 | Guido_Westerwelle Guido_Westerwelle_0002 623 | Guillaume_Depardieu Guillaume_Depardieu_0001 624 | Guillermo_Coria Guillermo_Coria_0019 625 | Guillermo_Coria Guillermo_Coria_0027 626 | Guillermo_Coria Guillermo_Coria_0029 627 | Guus_Hiddink Guus_Hiddink_0001 628 | Habib_Rizieq Habib_Rizieq_0001 629 | Habib_Rizieq Habib_Rizieq_0004 630 | Habib_Rizieq Habib_Rizieq_0005 631 | Hadley_Bilger Hadley_Bilger_0001 632 | Hal_Gehman Hal_Gehman_0001 633 | Hal_Gehman Hal_Gehman_0003 634 | Hal_Sutton Hal_Sutton_0002 635 | Halle_Berry Halle_Berry_0007 636 | Halle_Berry Halle_Berry_0010 637 | Halle_Berry Halle_Berry_0014 638 | Halle_Berry Halle_Berry_0016 639 | Ham_Pong-sil Ham_Pong-sil_0001 640 | Hama_Arba_Diallo Hama_Arba_Diallo_0001 641 | Hamad_Bin_Jassim Hamad_Bin_Jassim_0001 642 | Hamid_Efendi Hamid_Efendi_0001 643 | Hamid_Karzai Hamid_Karzai_0001 644 | Hamid_Karzai Hamid_Karzai_0002 645 | Hamzah_Haz Hamzah_Haz_0001 646 | Hamzah_Haz Hamzah_Haz_0002 647 | Hans_Blix Hans_Blix_0003 648 | Hans_Blix Hans_Blix_0006 649 | Hans_Blix Hans_Blix_0014 650 | Hans_Blix Hans_Blix_0027 651 | Hans_Blix Hans_Blix_0036 652 | Harrison_Ford Harrison_Ford_0007 653 | Hashim_Thaci Hashim_Thaci_0001 654 | Hashim_Thaci Hashim_Thaci_0002 655 | Hassanal_Bolkiah Hassanal_Bolkiah_0001 656 | Heather_Willson Heather_Willson_0001 657 | Hedayat_Amin_Arsala Hedayat_Amin_Arsala_0001 658 | Helmut_Panke Helmut_Panke_0001 659 | Helo_Pinheiro Helo_Pinheiro_0001 660 | Henrique_Meirelles Henrique_Meirelles_0001 661 | Henrique_Meirelles Henrique_Meirelles_0002 662 | Herb_Ritts Herb_Ritts_0001 663 | Hermes_Gamonal Hermes_Gamonal_0001 664 | Herta_Daeubler-Gmelin Herta_Daeubler-Gmelin_0001 665 | Herta_Daeubler-Gmelin Herta_Daeubler-Gmelin_0002 666 | Hilary_Duff Hilary_Duff_0001 667 | Hilary_Duff Hilary_Duff_0002 668 | Hilary_Duff Hilary_Duff_0003 669 | Hillary_Clinton Hillary_Clinton_0001 670 | Hillary_Clinton Hillary_Clinton_0002 671 | Hillary_Clinton Hillary_Clinton_0003 672 | Hillary_Clinton Hillary_Clinton_0008 673 | Hillary_Clinton Hillary_Clinton_0014 674 | Hilmi_Ozkok Hilmi_Ozkok_0001 675 | Hilmi_Ozkok Hilmi_Ozkok_0002 676 | Hipolito_Mejia Hipolito_Mejia_0001 677 | Hipolito_Mejia Hipolito_Mejia_0003 678 | Hiroki_Gomi Hiroki_Gomi_0001 679 | Hisao_Oguchi Hisao_Oguchi_0001 680 | Hisao_Oguchi Hisao_Oguchi_0002 681 | Hitoshi_Tanaka Hitoshi_Tanaka_0001 682 | Holly_Hunter Holly_Hunter_0002 683 | Holly_Hunter Holly_Hunter_0003 684 | Holly_Hunter Holly_Hunter_0004 685 | Holly_Hunter Holly_Hunter_0005 686 | Holly_Hunter Holly_Hunter_0007 687 | Holly_Robinson_Peete Holly_Robinson_Peete_0001 688 | Hootie_Johnson Hootie_Johnson_0001 689 | Hootie_Johnson Hootie_Johnson_0002 690 | Humberto_Coelho Humberto_Coelho_0001 691 | Hung_Wan-ting Hung_Wan-ting_0001 692 | Iain_Anderson Iain_Anderson_0001 693 | Ian_Wilmut Ian_Wilmut_0001 694 | Ibrahim_Jaafari Ibrahim_Jaafari_0001 695 | Ibrahim_Jaafari Ibrahim_Jaafari_0002 696 | Ibrahim_Rugova Ibrahim_Rugova_0001 697 | Igor_Ivanov Igor_Ivanov_0005 698 | Igor_Ivanov Igor_Ivanov_0016 699 | Igor_Trunov Igor_Trunov_0001 700 | Ilan_Ramon Ilan_Ramon_0001 701 | Ilan_Ramon Ilan_Ramon_0003 702 | Inam-ul-Haq Inam-ul-Haq_0001 703 | Inam-ul-Haq Inam-ul-Haq_0002 704 | Inga_Hall Inga_Hall_0001 705 | Intisar_Ajouri Intisar_Ajouri_0001 706 | Intisar_Ajouri Intisar_Ajouri_0002 707 | Intisar_Ajouri Intisar_Ajouri_0003 708 | Ira_Einhorn Ira_Einhorn_0001 709 | Jack_LaLanne Jack_LaLanne_0001 710 | Jack_Straw Jack_Straw_0004 711 | Jack_Straw Jack_Straw_0022 712 | Jacqueline_Obradors Jacqueline_Obradors_0001 713 | Jacqueline_Obradors Jacqueline_Obradors_0002 714 | Jade_Jagger Jade_Jagger_0001 715 | Jafar_Umar_Thalib Jafar_Umar_Thalib_0001 716 | Jakob_Kellenberger Jakob_Kellenberger_0001 717 | James_Baker James_Baker_0001 718 | James_Ballenger James_Ballenger_0001 719 | James_Barksdale James_Barksdale_0001 720 | James_Jones James_Jones_0001 721 | James_Jones James_Jones_0002 722 | James_Parker James_Parker_0001 723 | James_Parker James_Parker_0002 724 | James_Roberts James_Roberts_0001 725 | Jan-Michael_Gambill Jan-Michael_Gambill_0001 726 | Jan-Michael_Gambill Jan-Michael_Gambill_0003 727 | Jane_Russell Jane_Russell_0001 728 | Janet_Leigh Janet_Leigh_0001 729 | Jaouad_Gharib Jaouad_Gharib_0001 730 | Jason_Bentley Jason_Bentley_0001 731 | Jason_Kidd Jason_Kidd_0001 732 | Jason_Kidd Jason_Kidd_0004 733 | Jason_Kidd Jason_Kidd_0005 734 | Jason_Kidd Jason_Kidd_0006 735 | Jason_Kidd Jason_Kidd_0009 736 | Jason_Kidd Jason_Kidd_0010 737 | Jason_Vale Jason_Vale_0001 738 | Jean-Claude_Braquet Jean-Claude_Braquet_0001 739 | Jean-Claude_Braquet Jean-Claude_Braquet_0002 740 | Jean-David_Levitte Jean-David_Levitte_0003 741 | Jean-David_Levitte Jean-David_Levitte_0004 742 | Jean-David_Levitte Jean-David_Levitte_0006 743 | Jean-David_Levitte Jean-David_Levitte_0007 744 | Jean-David_Levitte Jean-David_Levitte_0008 745 | Jean-David_Levitte Jean-David_Levitte_0010 746 | Jean-Francois_Pontal Jean-Francois_Pontal_0001 747 | Jean-Francois_Pontal Jean-Francois_Pontal_0003 748 | Jean_Chretien Jean_Chretien_0003 749 | Jean_Chretien Jean_Chretien_0008 750 | Jean_Chretien Jean_Chretien_0022 751 | Jean_Chretien Jean_Chretien_0030 752 | Jean_Chretien Jean_Chretien_0031 753 | Jean_Chretien Jean_Chretien_0050 754 | Jeanette_Stauffer Jeanette_Stauffer_0001 755 | Jeanne_Moreau Jeanne_Moreau_0001 756 | Jeanne_Moreau Jeanne_Moreau_0002 757 | Jeb_Bush Jeb_Bush_0004 758 | Jeb_Bush Jeb_Bush_0012 759 | Jeff_Bzdelik Jeff_Bzdelik_0001 760 | Jeff_Schiffner Jeff_Schiffner_0001 761 | Jeff_Van_Gundy Jeff_Van_Gundy_0001 762 | Jeff_Van_Gundy Jeff_Van_Gundy_0003 763 | Jeff_Weaver Jeff_Weaver_0001 764 | Jeffrey_Archer Jeffrey_Archer_0001 765 | Jeffrey_Archer Jeffrey_Archer_0002 766 | Jeffrey_Scott_Postell Jeffrey_Scott_Postell_0001 767 | Jen_Schefft Jen_Schefft_0001 768 | Jennifer_Aniston Jennifer_Aniston_0005 769 | Jennifer_Aniston Jennifer_Aniston_0013 770 | Jerry_Regier Jerry_Regier_0002 771 | Jerry_Regier Jerry_Regier_0003 772 | Jerry_Sloan Jerry_Sloan_0001 773 | Jessica_Alba Jessica_Alba_0002 774 | Jessica_Lynch Jessica_Lynch_0001 775 | Jessica_Lynch Jessica_Lynch_0002 776 | Jia_Qinglin Jia_Qinglin_0001 777 | Jia_Qinglin Jia_Qinglin_0002 778 | Jim_Carrey Jim_Carrey_0002 779 | Jim_Carrey Jim_Carrey_0003 780 | Jim_Furyk Jim_Furyk_0001 781 | Jim_Furyk Jim_Furyk_0006 782 | Jim_Greenwood Jim_Greenwood_0001 783 | Jim_Thome Jim_Thome_0001 784 | Jim_Wong Jim_Wong_0001 785 | Jimmy_Jimenez Jimmy_Jimenez_0001 786 | Jimmy_Smits Jimmy_Smits_0001 787 | Jo_Dee_Messina Jo_Dee_Messina_0001 788 | Jo_Dee_Messina Jo_Dee_Messina_0002 789 | Joan_Dangerfield Joan_Dangerfield_0001 790 | Joan_Laporta Joan_Laporta_0002 791 | Joan_Laporta Joan_Laporta_0007 792 | Job_Cohen Job_Cohen_0001 793 | Job_Cohen Job_Cohen_0002 794 | Joe_Calzaghe Joe_Calzaghe_0001 795 | Joe_Calzaghe Joe_Calzaghe_0002 796 | Joe_Dumars Joe_Dumars_0001 797 | Joe_Dumars Joe_Dumars_0002 798 | Joe_Lieberman Joe_Lieberman_0011 799 | John_Abizaid John_Abizaid_0003 800 | John_Abizaid John_Abizaid_0009 801 | John_Ashcroft John_Ashcroft_0018 802 | John_Ashcroft John_Ashcroft_0021 803 | John_Ashcroft John_Ashcroft_0025 804 | John_Ashcroft John_Ashcroft_0027 805 | John_Ashcroft John_Ashcroft_0035 806 | John_Ashcroft John_Ashcroft_0053 807 | John_Bond John_Bond_0001 808 | John_Brady John_Brady_0001 809 | John_Daly_Jr John_Daly_Jr_0001 810 | John_Kerry John_Kerry_0001 811 | John_Kerry John_Kerry_0002 812 | John_Kerry John_Kerry_0005 813 | John_Kerry John_Kerry_0014 814 | John_McCormack John_McCormack_0001 815 | John_McCormack John_McCormack_0002 816 | John_Paul_II John_Paul_II_0003 817 | John_Paul_II John_Paul_II_0010 818 | John_Paul_II John_Paul_II_0011 819 | John_Perrota John_Perrota_0001 820 | John_Reilly John_Reilly_0001 821 | John_Rosa John_Rosa_0002 822 | John_Ruiz John_Ruiz_0001 823 | John_Ruiz John_Ruiz_0002 824 | John_Snow John_Snow_0004 825 | John_Snow John_Snow_0008 826 | John_Snow John_Snow_0014 827 | John_Snow John_Snow_0016 828 | John_Snow John_Snow_0017 829 | John_Spencer John_Spencer_0002 830 | John_Starks John_Starks_0001 831 | John_Sweeney John_Sweeney_0001 832 | John_Swofford John_Swofford_0001 833 | John_Swofford John_Swofford_0003 834 | Johnny_Benson Johnny_Benson_0001 835 | Johnny_Tapia Johnny_Tapia_0001 836 | Johnny_Tapia Johnny_Tapia_0003 837 | Jon_Gruden Jon_Gruden_0002 838 | Jon_Gruden Jon_Gruden_0007 839 | Jon_Stewart Jon_Stewart_0001 840 | Jonathan_Mostow Jonathan_Mostow_0001 841 | Jonathan_Mostow Jonathan_Mostow_0002 842 | Jorge_Alberto_Galindo Jorge_Alberto_Galindo_0001 843 | Joschka_Fischer Joschka_Fischer_0014 844 | Joschka_Fischer Joschka_Fischer_0015 845 | Jose_Canseco Jose_Canseco_0001 846 | Jose_Lopez_Beltran Jose_Lopez_Beltran_0001 847 | Jose_Manuel_Durao_Barroso Jose_Manuel_Durao_Barroso_0001 848 | Jose_Manuel_Durao_Barroso Jose_Manuel_Durao_Barroso_0005 849 | Jose_Maria_Aznar Jose_Maria_Aznar_0004 850 | Jose_Maria_Aznar Jose_Maria_Aznar_0018 851 | Jose_Maria_Aznar Jose_Maria_Aznar_0020 852 | Jose_Maria_Aznar Jose_Maria_Aznar_0022 853 | Jose_Miguel_Aleman Jose_Miguel_Aleman_0001 854 | Jose_Santos Jose_Santos_0001 855 | Jose_Sarney Jose_Sarney_0001 856 | Jose_Sarney Jose_Sarney_0002 857 | Jose_Viegas_Filho Jose_Viegas_Filho_0001 858 | Jose_Woldenberg Jose_Woldenberg_0001 859 | Joseph_Biden Joseph_Biden_0001 860 | Joseph_Biden Joseph_Biden_0002 861 | Joseph_Biden Joseph_Biden_0003 862 | Joseph_Biden Joseph_Biden_0005 863 | Joseph_Kabila Joseph_Kabila_0001 864 | Joy_Bryant Joy_Bryant_0001 865 | Joy_Lee_Sadler Joy_Lee_Sadler_0001 866 | Juan_Antonio_Samaranch Juan_Antonio_Samaranch_0001 867 | Juan_Carlos_Ferrero Juan_Carlos_Ferrero_0002 868 | Juan_Carlos_Ferrero Juan_Carlos_Ferrero_0007 869 | Juan_Carlos_Ferrero Juan_Carlos_Ferrero_0009 870 | Juan_Francisco_Palencia Juan_Francisco_Palencia_0001 871 | Juan_Manuel_Marquez Juan_Manuel_Marquez_0001 872 | Juan_Pablo_Montoya Juan_Pablo_Montoya_0003 873 | Juan_Pablo_Montoya Juan_Pablo_Montoya_0005 874 | Judy_Genshaft Judy_Genshaft_0002 875 | Julia_Tymoshenko Julia_Tymoshenko_0002 876 | Julianne_Moore Julianne_Moore_0006 877 | Julianne_Moore Julianne_Moore_0009 878 | Julianne_Moore Julianne_Moore_0012 879 | Julie_Infante Julie_Infante_0001 880 | Julie_Taymor Julie_Taymor_0002 881 | Juliette_Binoche Juliette_Binoche_0001 882 | Juliette_Lewis Juliette_Lewis_0001 883 | Justin_Guarini Justin_Guarini_0001 884 | Justin_Guarini Justin_Guarini_0002 885 | Justin_Guarini Justin_Guarini_0003 886 | Justine_Pasek Justine_Pasek_0005 887 | Kaio_Almeida Kaio_Almeida_0001 888 | Karen_Lynn_Gorney Karen_Lynn_Gorney_0001 889 | Karen_Pereiras Karen_Pereiras_0001 890 | Kate_Hudson Kate_Hudson_0002 891 | Kate_Hudson Kate_Hudson_0004 892 | Kathleen_Glynn Kathleen_Glynn_0001 893 | Kathleen_Glynn Kathleen_Glynn_0002 894 | Kathy_Baker Kathy_Baker_0001 895 | Katie_Harman Katie_Harman_0001 896 | Katie_Harman Katie_Harman_0002 897 | Katie_Harman Katie_Harman_0003 898 | Keanu_Reeves Keanu_Reeves_0002 899 | Keanu_Reeves Keanu_Reeves_0005 900 | Keanu_Reeves Keanu_Reeves_0006 901 | Keanu_Reeves Keanu_Reeves_0012 902 | Keiko_Sofia_Fujimori Keiko_Sofia_Fujimori_0001 903 | Keith_Rodriguez Keith_Rodriguez_0001 904 | Kelli_White Kelli_White_0001 905 | Kelli_White Kelli_White_0002 906 | Kelly_Osbourne Kelly_Osbourne_0001 907 | Ken_Dorsey Ken_Dorsey_0001 908 | Kenneth_Carlsen Kenneth_Carlsen_0001 909 | Kenny_Brack Kenny_Brack_0001 910 | Kent_McCord Kent_McCord_0001 911 | Kent_Rominger Kent_Rominger_0001 912 | Kent_Rominger Kent_Rominger_0002 913 | Kevin_Keegan Kevin_Keegan_0001 914 | Kevin_Spacey Kevin_Spacey_0001 915 | Kevin_Spacey Kevin_Spacey_0002 916 | Kevin_Spacey Kevin_Spacey_0004 917 | Khin_Nyunt Khin_Nyunt_0001 918 | Kieran_Culkin Kieran_Culkin_0001 919 | Kim_Ryong-sung Kim_Ryong-sung_0003 920 | Kim_Ryong-sung Kim_Ryong-sung_0004 921 | Kim_Ryong-sung Kim_Ryong-sung_0009 922 | Kim_Ryong-sung Kim_Ryong-sung_0010 923 | Kimi_Raikkonen Kimi_Raikkonen_0001 924 | Kimi_Raikkonen Kimi_Raikkonen_0002 925 | Kimi_Raikkonen Kimi_Raikkonen_0003 926 | Kirk_Johnson Kirk_Johnson_0001 927 | Kobe_Bryant Kobe_Bryant_0001 928 | Kobe_Bryant Kobe_Bryant_0003 929 | Kong_Quan Kong_Quan_0001 930 | Kostya_Tszyu Kostya_Tszyu_0001 931 | Kristin_Scott_Thomas Kristin_Scott_Thomas_0001 932 | Kurt_Russell Kurt_Russell_0001 933 | Kurt_Russell Kurt_Russell_0002 934 | Kwame_Kilpatrick Kwame_Kilpatrick_0001 935 | Kwon_Yang-sook Kwon_Yang-sook_0003 936 | Kwon_Young-gil Kwon_Young-gil_0001 937 | Larry_Brown Larry_Brown_0001 938 | Larry_Brown Larry_Brown_0002 939 | Larry_Brown Larry_Brown_0003 940 | Larry_Brown Larry_Brown_0006 941 | Larry_Brown Larry_Brown_0007 942 | Larry_Johnson Larry_Johnson_0001 943 | Larry_Johnson Larry_Johnson_0002 944 | Laura_Schlessinger Laura_Schlessinger_0001 945 | Laurence_Tribe Laurence_Tribe_0001 946 | LeAnn_Rimes LeAnn_Rimes_0001 947 | LeAnn_Rimes LeAnn_Rimes_0002 948 | Leandro_Garcia Leandro_Garcia_0001 949 | Lech_Walesa Lech_Walesa_0001 950 | Lech_Walesa Lech_Walesa_0002 951 | Lee_Hoi-chang Lee_Hoi-chang_0001 952 | Lee_Hoi-chang Lee_Hoi-chang_0003 953 | Lee_Nam-shin Lee_Nam-shin_0001 954 | Lee_Soo-hyuck Lee_Soo-hyuck_0001 955 | Lee_Soo-hyuck Lee_Soo-hyuck_0002 956 | Lee_Tae-sik Lee_Tae-sik_0001 957 | Lee_Yeo-jin Lee_Yeo-jin_0001 958 | Lenny_Wilkens Lenny_Wilkens_0002 959 | Lenny_Wilkens Lenny_Wilkens_0003 960 | Leonard_Hamilton Leonard_Hamilton_0001 961 | Leonard_Hamilton Leonard_Hamilton_0002 962 | Leslie_Caldwell Leslie_Caldwell_0002 963 | Lim_Dong-won Lim_Dong-won_0002 964 | Lin_Yung_Hsi Lin_Yung_Hsi_0001 965 | Linda_Dano Linda_Dano_0001 966 | Linda_Lingle Linda_Lingle_0001 967 | Lindsay_Benko Lindsay_Benko_0002 968 | Lisa_Gottsegen Lisa_Gottsegen_0002 969 | Lisa_Ling Lisa_Ling_0001 970 | Lisa_Ling Lisa_Ling_0002 971 | Lisa_Stansfield Lisa_Stansfield_0001 972 | Lisa_Stone Lisa_Stone_0001 973 | Liu_Mingkang Liu_Mingkang_0001 974 | Liu_Mingkang Liu_Mingkang_0002 975 | Lon_Kruger Lon_Kruger_0001 976 | Lon_Kruger Lon_Kruger_0002 977 | Lonnie_Donegan Lonnie_Donegan_0001 978 | Lope_Mendoza Lope_Mendoza_0001 979 | Lou_Piniella Lou_Piniella_0001 980 | Lou_Piniella Lou_Piniella_0003 981 | Lucia_Kenny_Anthony Lucia_Kenny_Anthony_0001 982 | Lucio_Angulo Lucio_Angulo_0001 983 | Lucio_Cecchinello Lucio_Cecchinello_0001 984 | Luis_Fonsi Luis_Fonsi_0001 985 | Luis_Guzman Luis_Guzman_0001 986 | Luiz_Inacio_Lula_da_Silva Luiz_Inacio_Lula_da_Silva_0012 987 | Luiz_Inacio_Lula_da_Silva Luiz_Inacio_Lula_da_Silva_0017 988 | Luiz_Inacio_Lula_da_Silva Luiz_Inacio_Lula_da_Silva_0025 989 | Luiz_Inacio_Lula_da_Silva Luiz_Inacio_Lula_da_Silva_0033 990 | Luiz_Inacio_Lula_da_Silva Luiz_Inacio_Lula_da_Silva_0042 991 | Luke_Ridnour Luke_Ridnour_0001 992 | Lynne_Thigpen Lynne_Thigpen_0001 993 | MC_Hammer MC_Hammer_0001 994 | Mae_Jemison Mae_Jemison_0001 995 | Maha_Habib Maha_Habib_0001 996 | Mahmoud_Al_Zhar Mahmoud_Al_Zhar_0001 997 | Mahmoud_Diyab_al-Ahmed Mahmoud_Diyab_al-Ahmed_0001 998 | Manfred_Reyes_Villa Manfred_Reyes_Villa_0001 999 | Manuel_Llorente Manuel_Llorente_0001 1000 | Manuel_Poggiali Manuel_Poggiali_0001 1001 | Manuel_Poggiali Manuel_Poggiali_0002 1002 | Marc-Andre_Fleury Marc-Andre_Fleury_0001 1003 | Marcelo_Ebrard Marcelo_Ebrard_0002 1004 | Marco_Antonio_Barrera Marco_Antonio_Barrera_0002 1005 | Marcos_Cafu Marcos_Cafu_0001 1006 | Marcos_Milinkovic Marcos_Milinkovic_0001 1007 | Marcus_Gronholm Marcus_Gronholm_0002 1008 | Maria_Soledad_Alvear_Valenzuela Maria_Soledad_Alvear_Valenzuela_0001 1009 | Maria_Soledad_Alvear_Valenzuela Maria_Soledad_Alvear_Valenzuela_0003 1010 | Maria_Soledad_Alvear_Valenzuela Maria_Soledad_Alvear_Valenzuela_0005 1011 | Marie-Reine_Le_Gougne Marie-Reine_Le_Gougne_0001 1012 | Marie-Reine_Le_Gougne Marie-Reine_Le_Gougne_0002 1013 | Marilyn_Monroe Marilyn_Monroe_0001 1014 | Mario_Vasquez_Rana Mario_Vasquez_Rana_0001 1015 | Marion_Barry Marion_Barry_0001 1016 | Mark_Geragos Mark_Geragos_0001 1017 | Mark_Geragos Mark_Geragos_0002 1018 | Mark_Gottfried Mark_Gottfried_0001 1019 | Mark_Gottfried Mark_Gottfried_0003 1020 | Mark_Hamister Mark_Hamister_0001 1021 | Mark_Hamister Mark_Hamister_0002 1022 | Mark_Hurlbert Mark_Hurlbert_0002 1023 | Mark_Hurlbert Mark_Hurlbert_0004 1024 | Mark_Hurlbert Mark_Hurlbert_0005 1025 | Mark_Lazarus Mark_Lazarus_0001 1026 | Mark_Schweiker Mark_Schweiker_0002 1027 | Mark_Swartz Mark_Swartz_0001 1028 | Marlene_Weingartner Marlene_Weingartner_0001 1029 | Marsha_Sharp Marsha_Sharp_0001 1030 | Marsha_Thomason Marsha_Thomason_0001 1031 | Martha_Bowen Martha_Bowen_0001 1032 | Martha_Bowen Martha_Bowen_0002 1033 | Martha_Lucia_Ramirez Martha_Lucia_Ramirez_0002 1034 | Martha_Lucia_Ramirez Martha_Lucia_Ramirez_0003 1035 | Martha_Sahagun_de_Fox Martha_Sahagun_de_Fox_0001 1036 | Martina_Hingis Martina_Hingis_0001 1037 | Martina_Hingis Martina_Hingis_0003 1038 | Marty_Mornhinweg Marty_Mornhinweg_0002 1039 | Marty_Mornhinweg Marty_Mornhinweg_0003 1040 | Masja_Juel Masja_Juel_0001 1041 | Mathias_Reichhold Mathias_Reichhold_0001 1042 | Mathias_Reichhold Mathias_Reichhold_0003 1043 | Mathilda_Karel_Spak Mathilda_Karel_Spak_0001 1044 | Matt_Damon Matt_Damon_0001 1045 | Matt_Damon Matt_Damon_0002 1046 | Matt_Damon Matt_Damon_0003 1047 | Matthew_Perry Matthew_Perry_0003 1048 | Matthew_Perry Matthew_Perry_0005 1049 | Matthew_Perry Matthew_Perry_0007 1050 | Maureen_Fanning Maureen_Fanning_0001 1051 | Maureen_Fanning Maureen_Fanning_0002 1052 | Maurice_Strong Maurice_Strong_0001 1053 | Max_Biaggi Max_Biaggi_0001 1054 | Mehmet_Okur Mehmet_Okur_0001 1055 | Mel_Gibson Mel_Gibson_0001 1056 | Mel_Gibson Mel_Gibson_0002 1057 | Mel_Karmazin Mel_Karmazin_0001 1058 | Mercedes_Amor Mercedes_Amor_0001 1059 | Michael_Ballack Michael_Ballack_0001 1060 | Michael_Ballack Michael_Ballack_0002 1061 | Michael_Ballack Michael_Ballack_0003 1062 | Michael_Caine Michael_Caine_0001 1063 | Michael_Caine Michael_Caine_0002 1064 | Michael_Chiklis Michael_Chiklis_0004 1065 | Michael_Deutsch Michael_Deutsch_0001 1066 | Michael_J_Fox Michael_J_Fox_0001 1067 | Michael_Jordan Michael_Jordan_0001 1068 | Michael_Jordan Michael_Jordan_0003 1069 | Michael_Jordan Michael_Jordan_0004 1070 | Michael_Kors Michael_Kors_0001 1071 | Michael_Powell Michael_Powell_0002 1072 | Michael_Powell Michael_Powell_0004 1073 | Michael_Powell Michael_Powell_0005 1074 | Michael_Schumacher Michael_Schumacher_0003 1075 | Michael_Winterbottom Michael_Winterbottom_0001 1076 | Michael_Winterbottom Michael_Winterbottom_0002 1077 | Michael_Winterbottom Michael_Winterbottom_0003 1078 | Michelle_Branch Michelle_Branch_0002 1079 | Mickey_Loomis Mickey_Loomis_0001 1080 | Mickey_Sherman Mickey_Sherman_0001 1081 | Micky_Arison Micky_Arison_0001 1082 | Micky_Ward Micky_Ward_0001 1083 | Miguel_Estrada Miguel_Estrada_0001 1084 | Mike_Alden Mike_Alden_0001 1085 | Mike_Easley Mike_Easley_0001 1086 | Mike_Farrar Mike_Farrar_0001 1087 | Mike_Holmgren Mike_Holmgren_0001 1088 | Mike_Krzyzewski Mike_Krzyzewski_0002 1089 | Mike_Miller Mike_Miller_0001 1090 | Mike_Miller Mike_Miller_0002 1091 | Mike_Myers Mike_Myers_0003 1092 | Mike_Myers Mike_Myers_0004 1093 | Mike_Myers Mike_Myers_0005 1094 | Mike_Myers Mike_Myers_0007 1095 | Mike_OConnell Mike_OConnell_0001 1096 | Mike_Scioscia Mike_Scioscia_0001 1097 | Mike_Scioscia Mike_Scioscia_0002 1098 | Mike_Szymanczyk Mike_Szymanczyk_0001 1099 | Mike_Tyson Mike_Tyson_0001 1100 | Mike_Tyson Mike_Tyson_0003 1101 | Mikhail_Kalashnikov Mikhail_Kalashnikov_0001 1102 | Mikhail_Khodorkovsky Mikhail_Khodorkovsky_0001 1103 | Mikhail_Shvydkoi Mikhail_Shvydkoi_0001 1104 | Mikhail_Wehbe Mikhail_Wehbe_0001 1105 | Mikhail_Wehbe Mikhail_Wehbe_0004 1106 | Milan_Kucan Milan_Kucan_0001 1107 | Minnie_Driver Minnie_Driver_0001 1108 | Minnie_Driver Minnie_Driver_0002 1109 | Minnie_Mendoza Minnie_Mendoza_0001 1110 | Mira_Sorvino Mira_Sorvino_0001 1111 | Miranda_Otto Miranda_Otto_0001 1112 | Mireille_Jospin-Dandieu Mireille_Jospin-Dandieu_0001 1113 | Mitar_Rasevic Mitar_Rasevic_0001 1114 | Mitoji_Yabunaka Mitoji_Yabunaka_0001 1115 | Mitsou_Gelinas Mitsou_Gelinas_0001 1116 | Mitt_Romney Mitt_Romney_0001 1117 | Mitzi_Gaynor Mitzi_Gaynor_0001 1118 | Mohamed_Seineldin Mohamed_Seineldin_0001 1119 | Mohammed_Ashraf_Hafiz Mohammed_Ashraf_Hafiz_0001 1120 | Molly_Sims Molly_Sims_0001 1121 | Monica_Bellucci Monica_Bellucci_0001 1122 | Monica_Bellucci Monica_Bellucci_0003 1123 | Monica_Seles Monica_Seles_0002 1124 | Monica_Seles Monica_Seles_0003 1125 | Monica_Seles Monica_Seles_0004 1126 | Monique_Garbrecht-Enfeldt Monique_Garbrecht-Enfeldt_0001 1127 | Monique_Garbrecht-Enfeldt Monique_Garbrecht-Enfeldt_0002 1128 | Morgan_Freeman Morgan_Freeman_0002 1129 | Moshe_Katsav Moshe_Katsav_0001 1130 | Moshe_Katsav Moshe_Katsav_0002 1131 | Moshe_Katsav Moshe_Katsav_0003 1132 | Moshe_Katsav Moshe_Katsav_0004 1133 | Muhammad_Saeed_al-Sahhaf Muhammad_Saeed_al-Sahhaf_0005 1134 | Mukesh_Ambani Mukesh_Ambani_0003 1135 | Munir_Akram Munir_Akram_0001 1136 | Munir_Akram Munir_Akram_0002 1137 | Myung_Yang Myung_Yang_0001 1138 | Nabil_Shaath Nabil_Shaath_0001 1139 | Nabil_Shaath Nabil_Shaath_0003 1140 | Nadia_Forte Nadia_Forte_0001 1141 | Najib_al-Salhi Najib_al-Salhi_0001 1142 | Nan_Wang Nan_Wang_0004 1143 | Nancy_Demme Nancy_Demme_0001 1144 | Nancy_Demme Nancy_Demme_0002 1145 | Nancy_Greenlaw Nancy_Greenlaw_0001 1146 | Nancy_Kerrigan Nancy_Kerrigan_0001 1147 | Nancy_Reagan Nancy_Reagan_0001 1148 | Nancy_Reagan Nancy_Reagan_0002 1149 | Nancy_Sinatra Nancy_Sinatra_0001 1150 | Nancy_Sinatra Nancy_Sinatra_0002 1151 | Nanni_Moretti Nanni_Moretti_0001 1152 | Nanni_Moretti Nanni_Moretti_0002 1153 | Natalia_Dmitrieva Natalia_Dmitrieva_0001 1154 | Natalia_Verbeke Natalia_Verbeke_0001 1155 | Natasa_Micic Natasa_Micic_0001 1156 | Natasha_Lyonne Natasha_Lyonne_0001 1157 | Natasha_McElhone Natasha_McElhone_0002 1158 | Natasha_McElhone Natasha_McElhone_0003 1159 | Nate_Hybl Nate_Hybl_0001 1160 | Nathalia_Gillot Nathalia_Gillot_0001 1161 | Nathan_Doudney Nathan_Doudney_0001 1162 | Nathan_Lane Nathan_Lane_0001 1163 | Nathan_Lane Nathan_Lane_0002 1164 | Nathirah_Hussein Nathirah_Hussein_0001 1165 | Nebojsa_Pavkovic Nebojsa_Pavkovic_0001 1166 | Nebojsa_Pavkovic Nebojsa_Pavkovic_0002 1167 | Nicholas_Tse Nicholas_Tse_0002 1168 | Nick_Nolte Nick_Nolte_0001 1169 | Nick_Nolte Nick_Nolte_0004 1170 | Nicolas_Escude Nicolas_Escude_0002 1171 | Nicolas_Kiefer Nicolas_Kiefer_0001 1172 | Nicolas_Lapentti Nicolas_Lapentti_0001 1173 | Nicolas_Lapentti Nicolas_Lapentti_0002 1174 | Nicole_Kidman Nicole_Kidman_0007 1175 | Noel_Niell Noel_Niell_0001 1176 | Nora_Ephron Nora_Ephron_0001 1177 | Norman_Jewison Norman_Jewison_0001 1178 | Norman_Jewison Norman_Jewison_0002 1179 | Normand_Legault Normand_Legault_0001 1180 | Nova_Esther_Guthrie Nova_Esther_Guthrie_0001 1181 | Nursultan_Nazarbayev Nursultan_Nazarbayev_0002 1182 | Octavio_Lara Octavio_Lara_0001 1183 | Olesya_Bonabarenko Olesya_Bonabarenko_0001 1184 | Olesya_Bonabarenko Olesya_Bonabarenko_0002 1185 | Omar_Vizquel Omar_Vizquel_0001 1186 | Orlando_Bloom Orlando_Bloom_0001 1187 | Pamela_Melroy Pamela_Melroy_0001 1188 | Parris_Glendening Parris_Glendening_0001 1189 | Pascal_Lamy Pascal_Lamy_0001 1190 | Pascal_Lamy Pascal_Lamy_0002 1191 | Patricia_Wartusch Patricia_Wartusch_0001 1192 | Patsy_Mink Patsy_Mink_0001 1193 | Paul_Coppin Paul_Coppin_0001 1194 | Paul_Coppin Paul_Coppin_0002 1195 | Paul_Luvera Paul_Luvera_0001 1196 | Paul_McNulty Paul_McNulty_0001 1197 | Paul_McNulty Paul_McNulty_0002 1198 | Paul_Murphy Paul_Murphy_0001 1199 | Paul_Wilson Paul_Wilson_0001 1200 | Paul_Wolfowitz Paul_Wolfowitz_0002 1201 | Paul_Wolfowitz Paul_Wolfowitz_0003 1202 | Paul_Wolfowitz Paul_Wolfowitz_0004 1203 | Paul_Wolfowitz Paul_Wolfowitz_0005 1204 | Paul_Wolfowitz Paul_Wolfowitz_0006 1205 | Paul_Wolfowitz Paul_Wolfowitz_0008 1206 | Pauley_Perrette Pauley_Perrette_0001 1207 | Paulo_Cesar_Pinheiro Paulo_Cesar_Pinheiro_0001 1208 | Paulo_Cesar_Pinheiro Paulo_Cesar_Pinheiro_0002 1209 | Pedro_Velasquez Pedro_Velasquez_0001 1210 | Penelope_Ann_Miller Penelope_Ann_Miller_0001 1211 | Penelope_Taylor Penelope_Taylor_0001 1212 | Perri_Shaw Perri_Shaw_0001 1213 | Pete_Carroll Pete_Carroll_0001 1214 | Pete_Carroll Pete_Carroll_0002 1215 | Peter_Arnett Peter_Arnett_0002 1216 | Peter_Arnett Peter_Arnett_0003 1217 | Peter_Bacanovic Peter_Bacanovic_0001 1218 | Peter_Bacanovic Peter_Bacanovic_0002 1219 | Philippe_Noiret Philippe_Noiret_0001 1220 | Philippe_Noiret Philippe_Noiret_0002 1221 | Piotr_Anderszewski Piotr_Anderszewski_0001 1222 | Platon_Lebedev Platon_Lebedev_0001 1223 | Porter_Goss Porter_Goss_0001 1224 | Prince_Claus Prince_Claus_0001 1225 | Prince_Claus Prince_Claus_0003 1226 | Prince_Felipe Prince_Felipe_0001 1227 | Prince_Harry Prince_Harry_0001 1228 | Prince_Harry Prince_Harry_0002 1229 | Princess_Aiko Princess_Aiko_0001 1230 | Princess_Anne Princess_Anne_0001 1231 | Princess_Anne Princess_Anne_0002 1232 | Princess_Caroline Princess_Caroline_0001 1233 | Princess_Elisabeth Princess_Elisabeth_0002 1234 | Princess_Masako Princess_Masako_0001 1235 | Princess_Masako Princess_Masako_0002 1236 | Pupi_Avati Pupi_Avati_0001 1237 | Qian_Qichen Qian_Qichen_0001 1238 | Queen_Elizabeth_II Queen_Elizabeth_II_0004 1239 | Queen_Elizabeth_II Queen_Elizabeth_II_0005 1240 | Queen_Elizabeth_II Queen_Elizabeth_II_0006 1241 | Queen_Elizabeth_II Queen_Elizabeth_II_0007 1242 | Queen_Elizabeth_II Queen_Elizabeth_II_0011 1243 | Queen_Elizabeth_II Queen_Elizabeth_II_0013 1244 | Queen_Latifah Queen_Latifah_0001 1245 | Queen_Rania Queen_Rania_0004 1246 | Queen_Sofia Queen_Sofia_0001 1247 | Rachel_Wadsworth Rachel_Wadsworth_0001 1248 | Rainer_Schuettler Rainer_Schuettler_0001 1249 | Rainer_Schuettler Rainer_Schuettler_0003 1250 | Rainer_Schuettler Rainer_Schuettler_0004 1251 | Ralph_Nader Ralph_Nader_0001 1252 | Ramon_Cardenas Ramon_Cardenas_0001 1253 | Randall_Tobias Randall_Tobias_0001 1254 | Randy_Ferbey Randy_Ferbey_0001 1255 | Rani_Mukherjee Rani_Mukherjee_0001 1256 | Raoul_Ruiz Raoul_Ruiz_0001 1257 | Raoul_Ruiz Raoul_Ruiz_0003 1258 | Raoul_Ruiz Raoul_Ruiz_0004 1259 | Raquel_Welch Raquel_Welch_0002 1260 | Ratna_Sari_Dewi_Sukarno Ratna_Sari_Dewi_Sukarno_0001 1261 | Ray_Allen Ray_Allen_0002 1262 | Ray_Allen Ray_Allen_0003 1263 | Ray_Lewis Ray_Lewis_0001 1264 | Ray_Lucas Ray_Lucas_0001 1265 | Ray_Morrough Ray_Morrough_0001 1266 | Ray_Nagin Ray_Nagin_0002 1267 | Ray_Young Ray_Young_0001 1268 | Razali_Ismail Razali_Ismail_0001 1269 | Rebekah_Chantay_Revels Rebekah_Chantay_Revels_0002 1270 | Rebekah_Chantay_Revels Rebekah_Chantay_Revels_0003 1271 | Rebekah_Chantay_Revels Rebekah_Chantay_Revels_0004 1272 | Recep_Tayyip_Erdogan Recep_Tayyip_Erdogan_0002 1273 | Recep_Tayyip_Erdogan Recep_Tayyip_Erdogan_0004 1274 | Recep_Tayyip_Erdogan Recep_Tayyip_Erdogan_0008 1275 | Recep_Tayyip_Erdogan Recep_Tayyip_Erdogan_0014 1276 | Recep_Tayyip_Erdogan Recep_Tayyip_Erdogan_0029 1277 | Reggie_Miller Reggie_Miller_0002 1278 | Rene_Antonio_Leon_Rodriguez Rene_Antonio_Leon_Rodriguez_0001 1279 | Rhina_Villatoro Rhina_Villatoro_0001 1280 | Ricardo_Sanchez Ricardo_Sanchez_0003 1281 | Ricardo_Sanchez Ricardo_Sanchez_0004 1282 | Riccardo_Muti Riccardo_Muti_0001 1283 | Richard_Fine Richard_Fine_0001 1284 | Richard_Jefferson Richard_Jefferson_0001 1285 | Richard_Myers Richard_Myers_0003 1286 | Richard_Myers Richard_Myers_0004 1287 | Richard_Myers Richard_Myers_0014 1288 | Richard_Sterner Richard_Sterner_0001 1289 | Rick_Barnes Rick_Barnes_0001 1290 | Rick_Barnes Rick_Barnes_0002 1291 | Rick_Barnes Rick_Barnes_0003 1292 | Rick_Lu Rick_Lu_0001 1293 | Rick_Santorum Rick_Santorum_0002 1294 | Rick_Santorum Rick_Santorum_0003 1295 | Rick_Stansbury Rick_Stansbury_0001 1296 | Rien_Long Rien_Long_0001 1297 | Rita_Wilson Rita_Wilson_0003 1298 | Rob_Lowe Rob_Lowe_0001 1299 | Rob_Lowe Rob_Lowe_0002 1300 | Rob_Lowe Rob_Lowe_0003 1301 | Rob_Lowe Rob_Lowe_0004 1302 | Rob_Marshall Rob_Marshall_0004 1303 | Rob_Marshall Rob_Marshall_0005 1304 | Rob_Marshall Rob_Marshall_0006 1305 | Robert_Blackwill Robert_Blackwill_0001 1306 | Robert_Blackwill Robert_Blackwill_0002 1307 | Robert_Bullock Robert_Bullock_0002 1308 | Robert_De_Niro Robert_De_Niro_0001 1309 | Robert_De_Niro Robert_De_Niro_0002 1310 | Robert_De_Niro Robert_De_Niro_0006 1311 | Robert_Ehrlich Robert_Ehrlich_0001 1312 | Robert_Ehrlich Robert_Ehrlich_0002 1313 | Robert_Kocharian Robert_Kocharian_0003 1314 | Robert_Kocharian Robert_Kocharian_0004 1315 | Robert_Mugabe Robert_Mugabe_0001 1316 | Robert_Mugabe Robert_Mugabe_0002 1317 | Robert_Wiener Robert_Wiener_0001 1318 | Roberto_Laratro Roberto_Laratro_0001 1319 | Robin_McLaurin_Williams Robin_McLaurin_Williams_0002 1320 | Robinson_Stevenin Robinson_Stevenin_0002 1321 | Rodney_Rempt Rodney_Rempt_0001 1322 | Roger_Federer Roger_Federer_0003 1323 | Roger_Federer Roger_Federer_0004 1324 | Roger_Grimes Roger_Grimes_0001 1325 | Roger_Moore Roger_Moore_0003 1326 | Roger_Staubach Roger_Staubach_0001 1327 | Rogerio_Romero Rogerio_Romero_0002 1328 | Roh_Moo-hyun Roh_Moo-hyun_0001 1329 | Roh_Moo-hyun Roh_Moo-hyun_0007 1330 | Roman_Polanski Roman_Polanski_0002 1331 | Roman_Polanski Roman_Polanski_0005 1332 | Ron_Dittemore Ron_Dittemore_0005 1333 | Ron_Gonzales Ron_Gonzales_0001 1334 | Ron_Zook Ron_Zook_0001 1335 | Ronald_Ito Ronald_Ito_0001 1336 | Ronald_Perelman Ronald_Perelman_0001 1337 | Ronald_Young_Jr Ronald_Young_Jr_0001 1338 | Rose_Marie Rose_Marie_0001 1339 | Roseanne_Barr Roseanne_Barr_0001 1340 | Roseanne_Barr Roseanne_Barr_0002 1341 | Roseanne_Barr Roseanne_Barr_0003 1342 | Roy_Chaderton Roy_Chaderton_0001 1343 | Ruben_Studdard Ruben_Studdard_0001 1344 | Ruben_Studdard Ruben_Studdard_0002 1345 | Rubens_Barrichello Rubens_Barrichello_0001 1346 | Rubens_Barrichello Rubens_Barrichello_0002 1347 | Rubens_Barrichello Rubens_Barrichello_0005 1348 | Rubens_Barrichello Rubens_Barrichello_0009 1349 | Rudolph_Giuliani Rudolph_Giuliani_0017 1350 | Rudy_Tomjanovich Rudy_Tomjanovich_0001 1351 | Russell_Simmons Russell_Simmons_0003 1352 | Russell_Simmons Russell_Simmons_0004 1353 | Ruth_Harlow Ruth_Harlow_0001 1354 | Ruth_Harlow Ruth_Harlow_0002 1355 | Ryan_Leaf Ryan_Leaf_0001 1356 | Saburo_Kawabuchi Saburo_Kawabuchi_0002 1357 | Sachiko_Yamada Sachiko_Yamada_0001 1358 | Sachiko_Yamada Sachiko_Yamada_0002 1359 | Sachiko_Yamada Sachiko_Yamada_0003 1360 | Sachiko_Yamada Sachiko_Yamada_0004 1361 | Saeb_Erekat Saeb_Erekat_0001 1362 | Saeb_Erekat Saeb_Erekat_0002 1363 | Sam_Bith Sam_Bith_0001 1364 | Sam_Torrance Sam_Torrance_0002 1365 | Sam_Torrance Sam_Torrance_0003 1366 | Samantha_Daniels Samantha_Daniels_0001 1367 | Samantha_Ledster Samantha_Ledster_0001 1368 | Samira_Makhmalbaf Samira_Makhmalbaf_0001 1369 | Samira_Makhmalbaf Samira_Makhmalbaf_0002 1370 | Sandra_Bullock Sandra_Bullock_0003 1371 | Sandra_Bullock Sandra_Bullock_0004 1372 | Sandy_Smith Sandy_Smith_0001 1373 | Sanjay_Chawla Sanjay_Chawla_0001 1374 | Sanjay_Gupta Sanjay_Gupta_0001 1375 | Sasha_Alexander Sasha_Alexander_0001 1376 | Scott_Hamilton Scott_Hamilton_0001 1377 | Scott_Sullivan Scott_Sullivan_0001 1378 | Scott_Wolf Scott_Wolf_0001 1379 | Scott_Wolf Scott_Wolf_0002 1380 | Sebastien_Grosjean Sebastien_Grosjean_0001 1381 | Sebastien_Grosjean Sebastien_Grosjean_0002 1382 | Sebastien_Grosjean Sebastien_Grosjean_0003 1383 | Sebastien_Grosjean Sebastien_Grosjean_0004 1384 | Sepp_Blatter Sepp_Blatter_0001 1385 | Sepp_Blatter Sepp_Blatter_0002 1386 | Sepp_Blatter Sepp_Blatter_0003 1387 | Sepp_Blatter Sepp_Blatter_0004 1388 | Serena_Williams Serena_Williams_0052 1389 | Sergio_Garcia Sergio_Garcia_0001 1390 | Sergio_Garcia Sergio_Garcia_0002 1391 | Sergio_Vieira_De_Mello Sergio_Vieira_De_Mello_0005 1392 | Sergio_Vieira_De_Mello Sergio_Vieira_De_Mello_0006 1393 | Shafal_Mosed Shafal_Mosed_0001 1394 | Shamai_Leibowitz Shamai_Leibowitz_0001 1395 | Shane_Warne Shane_Warne_0002 1396 | Sharon_Davis Sharon_Davis_0001 1397 | Sharon_Frey Sharon_Frey_0002 1398 | Sharon_Osbourne Sharon_Osbourne_0001 1399 | Sharon_Stone Sharon_Stone_0005 1400 | Shaun_Rusling Shaun_Rusling_0001 1401 | Shawn_Bradley Shawn_Bradley_0001 1402 | Sheila_Copps Sheila_Copps_0003 1403 | Sheila_Fraser Sheila_Fraser_0001 1404 | Sheldon_Silver Sheldon_Silver_0001 1405 | Sheryl_Crow Sheryl_Crow_0004 1406 | Sheryl_Crow Sheryl_Crow_0008 1407 | Shi_Guangsheng Shi_Guangsheng_0001 1408 | Silvan_Shalom Silvan_Shalom_0006 1409 | Silvie_Cabero Silvie_Cabero_0001 1410 | Simona_Hradil Simona_Hradil_0001 1411 | Sok_An Sok_An_0001 1412 | Soon_Yi Soon_Yi_0001 1413 | Sophie Sophie_0001 1414 | Stacy_Dragila Stacy_Dragila_0001 1415 | Stacy_Dragila Stacy_Dragila_0002 1416 | Stanley_McChrystal Stanley_McChrystal_0001 1417 | Stanley_McChrystal Stanley_McChrystal_0002 1418 | Stanley_Nelson Stanley_Nelson_0001 1419 | Stefaan_Declerk Stefaan_Declerk_0001 1420 | Stella_Keitel Stella_Keitel_0001 1421 | Stella_Tennant Stella_Tennant_0001 1422 | Steny_Hoyer Steny_Hoyer_0001 1423 | Stephane_Rousseau Stephane_Rousseau_0001 1424 | Stephanie_Moore Stephanie_Moore_0001 1425 | Stephen_Ambrose Stephen_Ambrose_0002 1426 | Stephen_Frears Stephen_Frears_0001 1427 | Stephen_Joseph Stephen_Joseph_0001 1428 | Stephen_Webster Stephen_Webster_0001 1429 | Steve_Avery Steve_Avery_0001 1430 | Steve_Ballmer Steve_Ballmer_0001 1431 | Steve_Ballmer Steve_Ballmer_0002 1432 | Steve_Fehr Steve_Fehr_0001 1433 | Steve_Mariucci Steve_Mariucci_0001 1434 | Steve_Mariucci Steve_Mariucci_0002 1435 | Steve_Nash Steve_Nash_0002 1436 | Steve_Waugh Steve_Waugh_0001 1437 | Steve_Waugh Steve_Waugh_0002 1438 | Steven_Briggs Steven_Briggs_0001 1439 | Steven_Feldman Steven_Feldman_0001 1440 | Steven_Seagal Steven_Seagal_0001 1441 | Steven_Seagal Steven_Seagal_0002 1442 | Steven_Spielberg Steven_Spielberg_0001 1443 | Steven_Spielberg Steven_Spielberg_0007 1444 | Sue_Wicks Sue_Wicks_0001 1445 | Susan_Sarandon Susan_Sarandon_0002 1446 | Susan_Sarandon Susan_Sarandon_0003 1447 | Susan_Sarandon Susan_Sarandon_0004 1448 | Susan_Sarandon Susan_Sarandon_0006 1449 | Susilo_Bambang_Yudhoyono Susilo_Bambang_Yudhoyono_0001 1450 | Susilo_Bambang_Yudhoyono Susilo_Bambang_Yudhoyono_0002 1451 | Suzie_McConnell_Serio Suzie_McConnell_Serio_0001 1452 | Sven_Ottke Sven_Ottke_0001 1453 | Svend_Robinson Svend_Robinson_0001 1454 | Taha_Yassin_Ramadan Taha_Yassin_Ramadan_0009 1455 | Takahiro_Mori Takahiro_Mori_0001 1456 | Takaloo Takaloo_0001 1457 | Takashi_Sorimachi Takashi_Sorimachi_0001 1458 | Takashi_Sorimachi Takashi_Sorimachi_0002 1459 | Talisa_Bratt Talisa_Bratt_0001 1460 | Tammy_Helm Tammy_Helm_0001 1461 | Taoufik_Mathlouthi Taoufik_Mathlouthi_0001 1462 | Tatjana_Gsell Tatjana_Gsell_0001 1463 | Taufik_Kiemas Taufik_Kiemas_0001 1464 | Ted_Turner Ted_Turner_0001 1465 | Terence_Newman Terence_Newman_0001 1466 | Teresa_Heinz_Kerry Teresa_Heinz_Kerry_0001 1467 | Teresa_Worbis Teresa_Worbis_0001 1468 | Terry_Hoeppner Terry_Hoeppner_0001 1469 | Tex_Ritter Tex_Ritter_0001 1470 | Thad_Matta Thad_Matta_0001 1471 | Thierry_Falise Thierry_Falise_0001 1472 | Thierry_Falise Thierry_Falise_0003 1473 | Thomas_Bjorn Thomas_Bjorn_0001 1474 | Thomas_Malchow Thomas_Malchow_0001 1475 | Thomas_Malchow Thomas_Malchow_0002 1476 | Thomas_Weston Thomas_Weston_0001 1477 | Thomas_Wilkens Thomas_Wilkens_0001 1478 | Tiger_Woods Tiger_Woods_0001 1479 | Tiger_Woods Tiger_Woods_0003 1480 | Tiger_Woods Tiger_Woods_0007 1481 | Tiger_Woods Tiger_Woods_0017 1482 | Tiger_Woods Tiger_Woods_0019 1483 | Tiger_Woods Tiger_Woods_0020 1484 | Tim_Chapman Tim_Chapman_0001 1485 | Tim_Conway Tim_Conway_0001 1486 | Tim_Conway Tim_Conway_0002 1487 | Tim_Duncan Tim_Duncan_0003 1488 | Tim_Duncan Tim_Duncan_0004 1489 | Tim_Henman Tim_Henman_0002 1490 | Tim_Henman Tim_Henman_0010 1491 | Tim_Henman Tim_Henman_0015 1492 | Tim_Henman Tim_Henman_0016 1493 | Tim_Henman Tim_Henman_0018 1494 | Tim_Henman Tim_Henman_0019 1495 | Tim_Robbins Tim_Robbins_0002 1496 | Timothy_Rigas Timothy_Rigas_0001 1497 | Tina_Andrews Tina_Andrews_0001 1498 | Todd_Reid Todd_Reid_0001 1499 | Tom_Brady Tom_Brady_0001 1500 | Tom_Craddick Tom_Craddick_0001 1501 | Tom_Craddick Tom_Craddick_0002 1502 | Tom_Craddick Tom_Craddick_0003 1503 | Tom_Curley Tom_Curley_0001 1504 | Tom_Daschle Tom_Daschle_0018 1505 | Tom_Daschle Tom_Daschle_0021 1506 | Tom_DeLay Tom_DeLay_0001 1507 | Tom_Hanks Tom_Hanks_0001 1508 | Tom_Hanks Tom_Hanks_0002 1509 | Tom_Hanks Tom_Hanks_0003 1510 | Tom_Hanks Tom_Hanks_0006 1511 | Tom_Hanks Tom_Hanks_0010 1512 | Tom_Miller Tom_Miller_0001 1513 | Tom_Reilly Tom_Reilly_0002 1514 | Tom_Reilly Tom_Reilly_0003 1515 | Tom_Ridge Tom_Ridge_0002 1516 | Tom_Ridge Tom_Ridge_0003 1517 | Tom_Ridge Tom_Ridge_0015 1518 | Tom_Ridge Tom_Ridge_0018 1519 | Tom_Ridge Tom_Ridge_0022 1520 | Tom_Schnackenberg Tom_Schnackenberg_0001 1521 | Tom_Vilsack Tom_Vilsack_0001 1522 | Tommy_Robredo Tommy_Robredo_0001 1523 | Tommy_Robredo Tommy_Robredo_0003 1524 | Tony_Fernandes Tony_Fernandes_0001 1525 | Tori_Amos Tori_Amos_0001 1526 | Torri_Edwards Torri_Edwards_0001 1527 | Torri_Edwards Torri_Edwards_0002 1528 | Trista_Rehn Trista_Rehn_0001 1529 | Tubby_Smith Tubby_Smith_0002 1530 | Tubby_Smith Tubby_Smith_0003 1531 | Ty_Votaw Ty_Votaw_0001 1532 | Tyra_Banks Tyra_Banks_0002 1533 | Tyron_Garner Tyron_Garner_0002 1534 | Ulrich_Kueperkoch Ulrich_Kueperkoch_0001 1535 | Uma_Thurman Uma_Thurman_0001 1536 | Uma_Thurman Uma_Thurman_0002 1537 | Urmila_Matondkar Urmila_Matondkar_0001 1538 | Uzi_Even Uzi_Even_0001 1539 | Val_Ackerman Val_Ackerman_0001 1540 | Valdas_Adamkus Valdas_Adamkus_0001 1541 | Valdas_Adamkus Valdas_Adamkus_0002 1542 | Vanessa_Williams Vanessa_Williams_0001 1543 | Venus_Williams Venus_Williams_0001 1544 | Venus_Williams Venus_Williams_0004 1545 | Venus_Williams Venus_Williams_0006 1546 | Venus_Williams Venus_Williams_0008 1547 | Venus_Williams Venus_Williams_0009 1548 | Victor_Kraatz Victor_Kraatz_0001 1549 | Victoria_Clarke Victoria_Clarke_0002 1550 | Victoria_Clarke Victoria_Clarke_0003 1551 | Vin_Diesel Vin_Diesel_0001 1552 | Vin_Diesel Vin_Diesel_0002 1553 | Vladimir_Putin Vladimir_Putin_0001 1554 | Vladimir_Putin Vladimir_Putin_0022 1555 | Vladimiro_Montesinos Vladimiro_Montesinos_0003 1556 | Vytas_Danelius Vytas_Danelius_0001 1557 | Wan_Yanhai Wan_Yanhai_0001 1558 | Wang_Nan Wang_Nan_0001 1559 | Warren_Granados Warren_Granados_0001 1560 | Wendy_Kennedy Wendy_Kennedy_0001 1561 | Wes_Craven Wes_Craven_0001 1562 | Will_Ferrell Will_Ferrell_0001 1563 | Will_Young Will_Young_0001 1564 | William_Cocksedge William_Cocksedge_0001 1565 | William_Ford_Jr William_Ford_Jr_0001 1566 | William_Ford_Jr William_Ford_Jr_0003 1567 | William_Ford_Jr William_Ford_Jr_0004 1568 | William_Hochul William_Hochul_0002 1569 | Wilson_Alvarez Wilson_Alvarez_0001 1570 | Win_Aung Win_Aung_0003 1571 | Win_Aung Win_Aung_0004 1572 | Wu_Peng Wu_Peng_0001 1573 | Wu_Yi Wu_Yi_0001 1574 | Wu_Yi Wu_Yi_0002 1575 | Wu_Yi Wu_Yi_0003 1576 | Xanana_Gusmao Xanana_Gusmao_0002 1577 | Xanana_Gusmao Xanana_Gusmao_0003 1578 | Yann_Martel Yann_Martel_0001 1579 | Yoko_Ono Yoko_Ono_0001 1580 | Yoko_Ono Yoko_Ono_0004 1581 | Yossi_Beilin Yossi_Beilin_0001 1582 | Yossi_Beilin Yossi_Beilin_0002 1583 | Yu_Shyi-kun Yu_Shyi-kun_0003 1584 | Yu_Shyi-kun Yu_Shyi-kun_0004 1585 | Yuri_Fedotov Yuri_Fedotov_0001 1586 | Yuri_Fedotov Yuri_Fedotov_0002 1587 | Yuri_Malenchenko Yuri_Malenchenko_0001 1588 | Yuri_Malenchenko Yuri_Malenchenko_0002 1589 | Yuvraj_Singh Yuvraj_Singh_0001 1590 | Zafarullah_Khan_Jamali Zafarullah_Khan_Jamali_0001 1591 | Zahir_Shah Zahir_Shah_0001 1592 | Zaini_Abdullah Zaini_Abdullah_0001 1593 | Zalmay_Khalilzad Zalmay_Khalilzad_0001 1594 | Zara_Akhmadova Zara_Akhmadova_0001 1595 | Zarai_Toledo Zarai_Toledo_0002 1596 | Zhang_Wenkang Zhang_Wenkang_0001 1597 | Zhang_Wenkang Zhang_Wenkang_0002 1598 | Zhong_Nanshan Zhong_Nanshan_0001 1599 | Zinedine_Zidane Zinedine_Zidane_0002 1600 | Zinedine_Zidane Zinedine_Zidane_0004 1601 | -------------------------------------------------------------------------------- /datasplits/lfw-funneled/val.txt: -------------------------------------------------------------------------------- 1 | Aaron_Peirsol Aaron_Peirsol_0001 2 | Aaron_Peirsol Aaron_Peirsol_0002 3 | Aaron_Peirsol Aaron_Peirsol_0003 4 | Aaron_Peirsol Aaron_Peirsol_0004 5 | Aaron_Sorkin Aaron_Sorkin_0001 6 | Aaron_Sorkin Aaron_Sorkin_0002 7 | Abner_Martinez Abner_Martinez_0001 8 | Adam_Scott Adam_Scott_0001 9 | Adam_Scott Adam_Scott_0002 10 | Adolfo_Aguilar_Zinser Adolfo_Aguilar_Zinser_0001 11 | Adolfo_Aguilar_Zinser Adolfo_Aguilar_Zinser_0003 12 | Adolfo_Rodriguez_Saa Adolfo_Rodriguez_Saa_0001 13 | Ahmed_Ahmed Ahmed_Ahmed_0001 14 | Ahmed_Lopez Ahmed_Lopez_0001 15 | Ahmet_Demir Ahmet_Demir_0001 16 | Aishwarya_Rai Aishwarya_Rai_0001 17 | Akbar_Hashemi_Rafsanjani Akbar_Hashemi_Rafsanjani_0001 18 | Akbar_Hashemi_Rafsanjani Akbar_Hashemi_Rafsanjani_0003 19 | Akhmed_Zakayev Akhmed_Zakayev_0001 20 | Akhmed_Zakayev Akhmed_Zakayev_0002 21 | Akhmed_Zakayev Akhmed_Zakayev_0003 22 | Akmal_Taher Akmal_Taher_0001 23 | Alain_Ducasse Alain_Ducasse_0001 24 | Alan_Ball Alan_Ball_0001 25 | Alan_Ball Alan_Ball_0002 26 | Alejandro_Lembo Alejandro_Lembo_0001 27 | Alex_King Alex_King_0001 28 | Alexander_Payne Alexander_Payne_0001 29 | Alexandra_Stevenson Alexandra_Stevenson_0001 30 | Alexandra_Stevenson Alexandra_Stevenson_0002 31 | Alexandra_Stevenson Alexandra_Stevenson_0003 32 | Alexandra_Vodjanikova Alexandra_Vodjanikova_0001 33 | Alexandra_Vodjanikova Alexandra_Vodjanikova_0002 34 | Alfonso_Cuaron Alfonso_Cuaron_0001 35 | Alfredo_di_Stefano Alfredo_di_Stefano_0001 36 | Ali_Abbas Ali_Abbas_0001 37 | Ali_Abbas Ali_Abbas_0002 38 | Ali_Hammoud Ali_Hammoud_0001 39 | Ali_Khamenei Ali_Khamenei_0001 40 | Ali_Khamenei Ali_Khamenei_0002 41 | Alison_Lohman Alison_Lohman_0001 42 | Alison_Lohman Alison_Lohman_0002 43 | Amanda_Beard Amanda_Beard_0001 44 | Amanda_Beard Amanda_Beard_0002 45 | Amanda_Plumer Amanda_Plumer_0001 46 | Amber_Tamblyn Amber_Tamblyn_0001 47 | Amber_Tamblyn Amber_Tamblyn_0002 48 | Amy_Cotton Amy_Cotton_0001 49 | Andre_Agassi Andre_Agassi_0009 50 | Andre_Agassi Andre_Agassi_0018 51 | Andrea_Bocelli Andrea_Bocelli_0001 52 | Andrea_Yates Andrea_Yates_0001 53 | Andrei_Nikolishin Andrei_Nikolishin_0001 54 | Andrew_Cuomo Andrew_Cuomo_0001 55 | Andrew_Cuomo Andrew_Cuomo_0002 56 | Andrew_Fastow Andrew_Fastow_0001 57 | Andrew_Gilligan Andrew_Gilligan_0001 58 | Andrew_Jarecki Andrew_Jarecki_0001 59 | Andy_Roddick Andy_Roddick_0001 60 | Andy_Roddick Andy_Roddick_0003 61 | Andy_Roddick Andy_Roddick_0009 62 | Andy_Roddick Andy_Roddick_0012 63 | Andy_Roddick Andy_Roddick_0014 64 | Andy_Roddick Andy_Roddick_0015 65 | Angela_Merkel Angela_Merkel_0001 66 | Angelina_Jolie Angelina_Jolie_0003 67 | Angelina_Jolie Angelina_Jolie_0004 68 | Angelina_Jolie Angelina_Jolie_0008 69 | Angelina_Jolie Angelina_Jolie_0009 70 | Angelina_Jolie Angelina_Jolie_0015 71 | Angelina_Jolie Angelina_Jolie_0016 72 | Angelina_Jolie Angelina_Jolie_0017 73 | Ann_Morgan Ann_Morgan_0001 74 | Anthony_Pisciotti Anthony_Pisciotti_0001 75 | Anthony_Rackauckas Anthony_Rackauckas_0001 76 | Antonio_Banderas Antonio_Banderas_0002 77 | Antonio_Banderas Antonio_Banderas_0003 78 | Antonio_Banderas Antonio_Banderas_0004 79 | Antony_Leung Antony_Leung_0002 80 | Antony_Leung Antony_Leung_0003 81 | Anwar_Ibrahim Anwar_Ibrahim_0001 82 | Anwar_Ibrahim Anwar_Ibrahim_0002 83 | Aram_Adler Aram_Adler_0001 84 | Arantxa_Sanchez-Vicario Arantxa_Sanchez-Vicario_0001 85 | Arantxa_Sanchez-Vicario Arantxa_Sanchez-Vicario_0002 86 | Ari_Fleischer Ari_Fleischer_0001 87 | Ari_Fleischer Ari_Fleischer_0002 88 | Ari_Fleischer Ari_Fleischer_0004 89 | Ari_Fleischer Ari_Fleischer_0006 90 | Ari_Fleischer Ari_Fleischer_0008 91 | Ari_Fleischer Ari_Fleischer_0013 92 | Arianna_Huffington Arianna_Huffington_0001 93 | Arianna_Huffington Arianna_Huffington_0002 94 | Arianna_Huffington Arianna_Huffington_0003 95 | Arnie_Boehm Arnie_Boehm_0001 96 | Arnold_Palmer Arnold_Palmer_0001 97 | Arnold_Palmer Arnold_Palmer_0002 98 | Arnold_Palmer Arnold_Palmer_0003 99 | Aron_Ralston Aron_Ralston_0001 100 | Aron_Ralston Aron_Ralston_0002 101 | Artieas_Shanks Artieas_Shanks_0001 102 | Arturo_Gatti Arturo_Gatti_0001 103 | Arturo_Gatti Arturo_Gatti_0002 104 | Arturo_Gatti Arturo_Gatti_0003 105 | Arye_Mekel Arye_Mekel_0001 106 | Arye_Mekel Arye_Mekel_0002 107 | Ashanti Ashanti_0004 108 | Ashraf_Ghani Ashraf_Ghani_0001 109 | Atal_Bihari_Vajpayee Atal_Bihari_Vajpayee_0010 110 | Atal_Bihari_Vajpayee Atal_Bihari_Vajpayee_0017 111 | Atal_Bihari_Vajpayee Atal_Bihari_Vajpayee_0020 112 | Atal_Bihari_Vajpayee Atal_Bihari_Vajpayee_0024 113 | Azmi_Bishara Azmi_Bishara_0001 114 | Barbara_Walters Barbara_Walters_0001 115 | Barbara_Walters Barbara_Walters_0002 116 | Barbara_Walters Barbara_Walters_0003 117 | Barbara_Walters Barbara_Walters_0004 118 | Barrett_Jackman Barrett_Jackman_0001 119 | Barrett_Jackman Barrett_Jackman_0002 120 | Barry_Hinson Barry_Hinson_0001 121 | Barry_Zito Barry_Zito_0001 122 | Barry_Zito Barry_Zito_0002 123 | Bart_Hendricks Bart_Hendricks_0001 124 | Basdeo_Panday Basdeo_Panday_0001 125 | Bashar_Assad Bashar_Assad_0001 126 | Bashar_Assad Bashar_Assad_0003 127 | Bashar_Assad Bashar_Assad_0004 128 | Ben_Glisan Ben_Glisan_0001 129 | Ben_Glisan Ben_Glisan_0002 130 | Ben_Howland Ben_Howland_0001 131 | Ben_Howland Ben_Howland_0002 132 | Benazir_Bhutto Benazir_Bhutto_0001 133 | Benazir_Bhutto Benazir_Bhutto_0002 134 | Benazir_Bhutto Benazir_Bhutto_0005 135 | Benedita_da_Silva Benedita_da_Silva_0001 136 | Benjamin_Martinez Benjamin_Martinez_0001 137 | Bernard_Landry Bernard_Landry_0001 138 | Bernard_Landry Bernard_Landry_0002 139 | Bernard_Landry Bernard_Landry_0004 140 | Bettina_Rheims Bettina_Rheims_0001 141 | Bill_Callahan Bill_Callahan_0001 142 | Bill_Callahan Bill_Callahan_0002 143 | Bill_Callahan Bill_Callahan_0003 144 | Bill_Clinton Bill_Clinton_0004 145 | Bill_Clinton Bill_Clinton_0020 146 | Bill_Duffey Bill_Duffey_0001 147 | Bill_Gates Bill_Gates_0003 148 | Bill_Gates Bill_Gates_0004 149 | Bill_Gates Bill_Gates_0011 150 | Bill_Gates Bill_Gates_0015 151 | Bill_Graham Bill_Graham_0001 152 | Bill_Graham Bill_Graham_0007 153 | Bill_Graham Bill_Graham_0008 154 | Bill_Graham Bill_Graham_0009 155 | Bill_Kong Bill_Kong_0001 156 | Bill_Lerach Bill_Lerach_0001 157 | Bill_Nelson Bill_Nelson_0001 158 | Bill_Nelson Bill_Nelson_0002 159 | Bill_Pryor Bill_Pryor_0001 160 | Bill_Stein Bill_Stein_0001 161 | Billy_Bob_Thornton Billy_Bob_Thornton_0001 162 | Billy_Crystal Billy_Crystal_0003 163 | Billy_Crystal Billy_Crystal_0005 164 | Billy_Crystal Billy_Crystal_0006 165 | Billy_Joel Billy_Joel_0001 166 | Bison_Dele Bison_Dele_0001 167 | Blythe_Hartley Blythe_Hartley_0002 168 | Bob_Curtis Bob_Curtis_0001 169 | Bob_Ferguson Bob_Ferguson_0001 170 | Bob_Graham Bob_Graham_0001 171 | Bob_Graham Bob_Graham_0002 172 | Bob_Graham Bob_Graham_0003 173 | Bob_Graham Bob_Graham_0004 174 | Bob_Graham Bob_Graham_0005 175 | Bob_Graham Bob_Graham_0006 176 | Bob_Krueger Bob_Krueger_0001 177 | Bob_Stoops Bob_Stoops_0002 178 | Bob_Stoops Bob_Stoops_0004 179 | Bob_Stoops Bob_Stoops_0005 180 | Bob_Stoops Bob_Stoops_0007 181 | Bob_Wright Bob_Wright_0001 182 | Bobby_Robson Bobby_Robson_0001 183 | Bobby_Robson Bobby_Robson_0002 184 | Boris_Berezovsky Boris_Berezovsky_0001 185 | Boris_Berezovsky Boris_Berezovsky_0002 186 | Brandon_Inge Brandon_Inge_0001 187 | Branko_Crvenkovski Branko_Crvenkovski_0001 188 | Branko_Crvenkovski Branko_Crvenkovski_0003 189 | Brendan_Hansen Brendan_Hansen_0001 190 | Brendan_Hansen Brendan_Hansen_0002 191 | Brent_Coles Brent_Coles_0001 192 | Brett_Hull Brett_Hull_0001 193 | Brian_Mulroney Brian_Mulroney_0002 194 | Brook_Robinson Brook_Robinson_0001 195 | Bruce_Arena Bruce_Arena_0001 196 | Bruno_Junquiera Bruno_Junquiera_0001 197 | Bryant_Young Bryant_Young_0001 198 | Buck_Rodgers Buck_Rodgers_0001 199 | Bud_Selig Bud_Selig_0001 200 | Bud_Selig Bud_Selig_0002 201 | Bud_Selig Bud_Selig_0004 202 | Budd_Schulberg Budd_Schulberg_0001 203 | Bulent_Ecevit Bulent_Ecevit_0001 204 | Bulent_Ecevit Bulent_Ecevit_0002 205 | Bulent_Ecevit Bulent_Ecevit_0003 206 | Bulent_Ecevit Bulent_Ecevit_0004 207 | Bulent_Ecevit Bulent_Ecevit_0005 208 | Bulent_Ecevit Bulent_Ecevit_0006 209 | Candie_Kung Candie_Kung_0001 210 | Candie_Kung Candie_Kung_0002 211 | Candie_Kung Candie_Kung_0003 212 | Carla_Myers Carla_Myers_0001 213 | Carla_Myers Carla_Myers_0002 214 | Carla_Sullivan Carla_Sullivan_0001 215 | Carlos_Savedra Carlos_Savedra_0001 216 | Carmen_Electra Carmen_Electra_0001 217 | Carmen_Electra Carmen_Electra_0006 218 | Carol_Moseley_Braun Carol_Moseley_Braun_0001 219 | Carol_Moseley_Braun Carol_Moseley_Braun_0002 220 | Carolina_Barco Carolina_Barco_0001 221 | Carolina_Moraes Carolina_Moraes_0002 222 | Catherine_Zeta-Jones Catherine_Zeta-Jones_0001 223 | Catherine_Zeta-Jones Catherine_Zeta-Jones_0004 224 | Catherine_Zeta-Jones Catherine_Zeta-Jones_0006 225 | Catherine_Zeta-Jones Catherine_Zeta-Jones_0008 226 | Catherine_Zeta-Jones Catherine_Zeta-Jones_0009 227 | Catherine_Zeta-Jones Catherine_Zeta-Jones_0010 228 | Cecilia_Bolocco Cecilia_Bolocco_0001 229 | Cecilia_Bolocco Cecilia_Bolocco_0002 230 | Cecilia_Bolocco Cecilia_Bolocco_0003 231 | Charlotte_Casiraghi Charlotte_Casiraghi_0001 232 | Chelsea_Clinton Chelsea_Clinton_0001 233 | Chen_Liang_Yu Chen_Liang_Yu_0001 234 | Chen_Liang_Yu Chen_Liang_Yu_0002 235 | Cherie_Blair Cherie_Blair_0001 236 | Cherie_Blair Cherie_Blair_0002 237 | Cherie_Blair Cherie_Blair_0003 238 | Cherie_Blair Cherie_Blair_0004 239 | Chris_Columbus Chris_Columbus_0001 240 | Chris_Cooper Chris_Cooper_0001 241 | Chris_Cooper Chris_Cooper_0002 242 | Chris_Moore Chris_Moore_0001 243 | Chris_Rock Chris_Rock_0001 244 | Chris_Rock Chris_Rock_0002 245 | Christian_Bale Christian_Bale_0001 246 | Christian_Fittipaldi Christian_Fittipaldi_0001 247 | Christian_Fittipaldi Christian_Fittipaldi_0002 248 | Christina_Aguilera Christina_Aguilera_0004 249 | Christine_Arron Christine_Arron_0001 250 | Christine_Gregoire Christine_Gregoire_0002 251 | Christine_Gregoire Christine_Gregoire_0003 252 | Christoph_Daum Christoph_Daum_0001 253 | Christopher_Amolsch Christopher_Amolsch_0001 254 | Christopher_Matero Christopher_Matero_0001 255 | Chuck_Amato Chuck_Amato_0001 256 | Chuck_Amato Chuck_Amato_0002 257 | Chuck_Finley Chuck_Finley_0001 258 | Chung_Mong-hun Chung_Mong-hun_0001 259 | Chung_Mong-hun Chung_Mong-hun_0002 260 | Claude_Jorda Claude_Jorda_0001 261 | Claudia_Pechstein Claudia_Pechstein_0001 262 | Claudia_Pechstein Claudia_Pechstein_0002 263 | Clemente_de_la_Vega Clemente_de_la_Vega_0001 264 | Clint_Eastwood Clint_Eastwood_0001 265 | Clint_Eastwood Clint_Eastwood_0003 266 | Clint_Eastwood Clint_Eastwood_0005 267 | Clint_Eastwood Clint_Eastwood_0006 268 | Clive_Woodward Clive_Woodward_0001 269 | Colin_Cowie Colin_Cowie_0001 270 | Colin_Farrell Colin_Farrell_0001 271 | Colin_Farrell Colin_Farrell_0003 272 | Colin_Farrell Colin_Farrell_0006 273 | Colin_Farrell Colin_Farrell_0007 274 | Colin_Jackson Colin_Jackson_0001 275 | Colin_Jackson Colin_Jackson_0002 276 | Colin_Montgomerie Colin_Montgomerie_0002 277 | Colin_Montgomerie Colin_Montgomerie_0004 278 | Colin_Montgomerie Colin_Montgomerie_0005 279 | Colin_Powell Colin_Powell_0038 280 | Colin_Powell Colin_Powell_0074 281 | Colin_Powell Colin_Powell_0120 282 | Colin_Powell Colin_Powell_0166 283 | Colin_Powell Colin_Powell_0205 284 | Colin_Powell Colin_Powell_0212 285 | Colleen_Atwood Colleen_Atwood_0001 286 | Costas_Simitis Costas_Simitis_0001 287 | Costas_Simitis Costas_Simitis_0002 288 | Costas_Simitis Costas_Simitis_0003 289 | Costas_Simitis Costas_Simitis_0004 290 | Courtney_Cox Courtney_Cox_0001 291 | Craig_Doblin Craig_Doblin_0001 292 | Craig_Wilson Craig_Wilson_0001 293 | Cristina_Saralegui Cristina_Saralegui_0001 294 | Cristina_Saralegui Cristina_Saralegui_0002 295 | Cruz_Bustamante Cruz_Bustamante_0001 296 | Cruz_Bustamante Cruz_Bustamante_0004 297 | Curtis_Rodriguez Curtis_Rodriguez_0001 298 | Daja_Bedanova Daja_Bedanova_0001 299 | Dalai_Lama Dalai_Lama_0001 300 | Dalai_Lama Dalai_Lama_0002 301 | Dale_Earnhardt Dale_Earnhardt_0001 302 | Dan_Guerrero Dan_Guerrero_0001 303 | Danny_Ainge Danny_Ainge_0001 304 | Darla_Moore Darla_Moore_0001 305 | Darrell_Issa Darrell_Issa_0001 306 | Darrell_Issa Darrell_Issa_0002 307 | Darren_Clarke Darren_Clarke_0001 308 | Darren_Clarke Darren_Clarke_0002 309 | Daryl_Hannah Daryl_Hannah_0001 310 | Daryl_Hannah Daryl_Hannah_0002 311 | David_Bowie David_Bowie_0001 312 | David_Duke David_Duke_0001 313 | David_Heymann David_Heymann_0001 314 | David_Heymann David_Heymann_0002 315 | David_Myers David_Myers_0001 316 | David_Myers David_Myers_0002 317 | David_Przybyszewski David_Przybyszewski_0001 318 | David_Siegel David_Siegel_0001 319 | Dean_Barker Dean_Barker_0001 320 | Deb_Santos Deb_Santos_0001 321 | Demetrius_Ferraciu Demetrius_Ferraciu_0002 322 | Demi_Moore Demi_Moore_0001 323 | Demi_Moore Demi_Moore_0002 324 | Demi_Moore Demi_Moore_0003 325 | Demi_Moore Demi_Moore_0004 326 | Deniz_Baykal Deniz_Baykal_0001 327 | Dennis_Erickson Dennis_Erickson_0001 328 | Dennis_Erickson Dennis_Erickson_0002 329 | Derek_Bond Derek_Bond_0001 330 | Derek_Lowe Derek_Lowe_0001 331 | Derek_Lowe Derek_Lowe_0002 332 | Derrick_Rodgers Derrick_Rodgers_0001 333 | Des_Brown Des_Brown_0001 334 | Dexter_Jackson Dexter_Jackson_0001 335 | Dexter_Jackson Dexter_Jackson_0002 336 | Diana_Krall Diana_Krall_0001 337 | Diana_Krall Diana_Krall_0002 338 | Diana_Krall Diana_Krall_0003 339 | Diana_Krall Diana_Krall_0004 340 | Diana_Krall Diana_Krall_0006 341 | Diana_Munz Diana_Munz_0002 342 | Diana_Munz Diana_Munz_0003 343 | Dianne_Feinstein Dianne_Feinstein_0001 344 | Dianne_Feinstein Dianne_Feinstein_0002 345 | Dianne_Feinstein Dianne_Feinstein_0003 346 | Dick_Bennett Dick_Bennett_0001 347 | Didier_Defago Didier_Defago_0001 348 | Diego_Armando_Maradona Diego_Armando_Maradona_0001 349 | Dinah_Turner Dinah_Turner_0001 350 | Djabir_Said-Guerni Djabir_Said-Guerni_0001 351 | Dolma_Tsering Dolma_Tsering_0001 352 | Dolma_Tsering Dolma_Tsering_0002 353 | Don_Nickles Don_Nickles_0001 354 | Don_Nickles Don_Nickles_0002 355 | Don_Siegelman Don_Siegelman_0002 356 | Don_Siegelman Don_Siegelman_0003 357 | Donald_Fehr Donald_Fehr_0003 358 | Donald_Fehr Donald_Fehr_0004 359 | Donnie_Brennan Donnie_Brennan_0001 360 | Dora_Bakoyianni Dora_Bakoyianni_0001 361 | Dorothy_Lamour Dorothy_Lamour_0001 362 | Doug_Christie Doug_Christie_0001 363 | Doug_Duncan Doug_Duncan_0001 364 | Doug_Duncan Doug_Duncan_0002 365 | Doug_Wilson Doug_Wilson_0001 366 | Dustin_Brown Dustin_Brown_0001 367 | Dwain_Kyles Dwain_Kyles_0001 368 | Dyab_Abou_Jahjah Dyab_Abou_Jahjah_0001 369 | Ed_Book Ed_Book_0001 370 | Eddie_Compass Eddie_Compass_0001 371 | Eddie_Jordan Eddie_Jordan_0001 372 | Eddie_Murray Eddie_Murray_0001 373 | Edgar_Savisaar Edgar_Savisaar_0001 374 | Edie_Falco Edie_Falco_0001 375 | Edie_Falco Edie_Falco_0002 376 | Edina_Batar Edina_Batar_0001 377 | Edmund_Hillary Edmund_Hillary_0002 378 | Edmund_Hillary Edmund_Hillary_0003 379 | Eduardo_Duhalde Eduardo_Duhalde_0005 380 | Eduardo_Duhalde Eduardo_Duhalde_0011 381 | Eduardo_Romero Eduardo_Romero_0001 382 | Edward_Lohn Edward_Lohn_0001 383 | Edwina_Currie Edwina_Currie_0002 384 | Edwina_Currie Edwina_Currie_0003 385 | Eileen_Coparropa Eileen_Coparropa_0001 386 | Eileen_Coparropa Eileen_Coparropa_0002 387 | Eileen_Coparropa Eileen_Coparropa_0003 388 | Elena_Bovina Elena_Bovina_0001 389 | Elena_Bovina Elena_Bovina_0002 390 | Eli_Stutsman Eli_Stutsman_0001 391 | Elijah_Wood Elijah_Wood_0002 392 | Elijah_Wood Elijah_Wood_0003 393 | Elijan_Ingram Elijan_Ingram_0001 394 | Elizabeth_Dole Elizabeth_Dole_0001 395 | Elizabeth_Dole Elizabeth_Dole_0003 396 | Elizabeth_Hurley Elizabeth_Hurley_0001 397 | Elizabeth_Hurley Elizabeth_Hurley_0002 398 | Elizabeth_Hurley Elizabeth_Hurley_0003 399 | Elizabeth_Hurley Elizabeth_Hurley_0004 400 | Elizabeth_Hurley Elizabeth_Hurley_0005 401 | Ellen_DeGeneres Ellen_DeGeneres_0001 402 | Ellen_DeGeneres Ellen_DeGeneres_0002 403 | Elton_John Elton_John_0001 404 | Elton_John Elton_John_0003 405 | Elton_John Elton_John_0005 406 | Elton_John Elton_John_0007 407 | Elvis_Presley Elvis_Presley_0001 408 | Elvis_Presley Elvis_Presley_0002 409 | Emma_Thompson Emma_Thompson_0001 410 | Emma_Thompson Emma_Thompson_0002 411 | Emma_Thompson Emma_Thompson_0003 412 | Emmit_Smith Emmit_Smith_0001 413 | Emmit_Smith Emmit_Smith_0002 414 | Enola_Rice Enola_Rice_0001 415 | Enrique_Iglesias Enrique_Iglesias_0001 416 | Eric_Clapton Eric_Clapton_0001 417 | Eric_Clapton Eric_Clapton_0002 418 | Erika_Harold Erika_Harold_0002 419 | Erika_Harold Erika_Harold_0004 420 | Erika_Harold Erika_Harold_0005 421 | Eriko_Tamura Eriko_Tamura_0001 422 | Ernest_Hollings Ernest_Hollings_0001 423 | Ernesto_Zedillo Ernesto_Zedillo_0001 424 | Ernesto_Zedillo Ernesto_Zedillo_0002 425 | Ernie_Els Ernie_Els_0001 426 | Ernie_Els Ernie_Els_0003 427 | Ernie_Harwell Ernie_Harwell_0001 428 | Ernie_Stewart Ernie_Stewart_0001 429 | Ethan_Hawke Ethan_Hawke_0001 430 | Ethan_Hawke Ethan_Hawke_0002 431 | Ethan_Hawke Ethan_Hawke_0003 432 | Ethan_Hawke Ethan_Hawke_0004 433 | Eve_Pelletier Eve_Pelletier_0001 434 | Eve_Pelletier Eve_Pelletier_0002 435 | Fabrice_Santoro Fabrice_Santoro_0003 436 | Faisal_Iqbal Faisal_Iqbal_0001 437 | Faisal_Saleh_Hayat Faisal_Saleh_Hayat_0001 438 | Feliciano_Lopez Feliciano_Lopez_0001 439 | Felix_Mantilla Felix_Mantilla_0001 440 | Felix_Mantilla Felix_Mantilla_0002 441 | Fernando_Velardez Fernando_Velardez_0001 442 | Fidel_Castro Fidel_Castro_0004 443 | Fidel_Castro Fidel_Castro_0014 444 | Frances_Fisher Frances_Fisher_0001 445 | Frances_Fisher Frances_Fisher_0002 446 | Francisco_Santos Francisco_Santos_0001 447 | Francisco_Urenda Francisco_Urenda_0001 448 | Franck_Cerutti Franck_Cerutti_0001 449 | Frank_Griswold Frank_Griswold_0001 450 | Frank_Griswold Frank_Griswold_0002 451 | Franko_Simatovic Franko_Simatovic_0001 452 | Fred_Thompson Fred_Thompson_0002 453 | Fred_Thompson Fred_Thompson_0003 454 | Frederique_van_der_Wal Frederique_van_der_Wal_0001 455 | Fujio_Cho Fujio_Cho_0001 456 | Fujio_Cho Fujio_Cho_0004 457 | Fujio_Cho Fujio_Cho_0005 458 | Gabi_Zimmer Gabi_Zimmer_0001 459 | Gabriel_Hughes Gabriel_Hughes_0001 460 | Gael_Garcia_Bermal Gael_Garcia_Bermal_0001 461 | Gary_Carter Gary_Carter_0001 462 | Gary_Carter Gary_Carter_0002 463 | Gary_Carter Gary_Carter_0003 464 | Gary_Gitnick Gary_Gitnick_0001 465 | Gary_Locke Gary_Locke_0001 466 | Gary_Locke Gary_Locke_0002 467 | Gary_Marshall Gary_Marshall_0001 468 | Geoffrey_Rush Geoffrey_Rush_0001 469 | George_Allen George_Allen_0001 470 | George_P_Bush George_P_Bush_0001 471 | George_P_Bush George_P_Bush_0002 472 | George_Ryan George_Ryan_0002 473 | George_Ryan George_Ryan_0004 474 | Georgina_Bardach Georgina_Bardach_0001 475 | Gerard_Depardieu Gerard_Depardieu_0001 476 | Gerardo_Gambala Gerardo_Gambala_0001 477 | Gerardo_Gambala Gerardo_Gambala_0002 478 | Gerhard_Schmid Gerhard_Schmid_0001 479 | Glenn_Plummer Glenn_Plummer_0001 480 | Gloria_Macapagal_Arroyo Gloria_Macapagal_Arroyo_0029 481 | Gloria_Macapagal_Arroyo Gloria_Macapagal_Arroyo_0034 482 | Gloria_Macapagal_Arroyo Gloria_Macapagal_Arroyo_0040 483 | Grady_Irvin_Jr Grady_Irvin_Jr_0001 484 | Grady_Irvin_Jr Grady_Irvin_Jr_0002 485 | Grant_Hackett Grant_Hackett_0002 486 | Grant_Hackett Grant_Hackett_0003 487 | Greg_Rusedski Greg_Rusedski_0001 488 | Greg_Rusedski Greg_Rusedski_0002 489 | Greg_Rusedski Greg_Rusedski_0003 490 | Greg_Rusedski Greg_Rusedski_0004 491 | Guillaume_Soro Guillaume_Soro_0001 492 | Guillaume_Soro Guillaume_Soro_0002 493 | Guillermo_Canas Guillermo_Canas_0001 494 | Guillermo_Canas Guillermo_Canas_0002 495 | Guillermo_Canas Guillermo_Canas_0004 496 | Guillermo_Ortiz Guillermo_Ortiz_0001 497 | Guillermo_Ortiz Guillermo_Ortiz_0002 498 | Gunter_Pleuger Gunter_Pleuger_0002 499 | Gunter_Pleuger Gunter_Pleuger_0005 500 | Gustavo_Kuerten Gustavo_Kuerten_0001 501 | Gustavo_Kuerten Gustavo_Kuerten_0002 502 | Gustavo_Kuerten Gustavo_Kuerten_0003 503 | Gustavo_Terrazas Gustavo_Terrazas_0001 504 | Guy_Hemmings Guy_Hemmings_0002 505 | Guy_Ritchie Guy_Ritchie_0001 506 | Hank_Stram Hank_Stram_0001 507 | Hans-Christian_Schmid Hans-Christian_Schmid_0001 508 | Harbhajan_Singh Harbhajan_Singh_0001 509 | Harbhajan_Singh Harbhajan_Singh_0002 510 | Hasan_Wirayuda Hasan_Wirayuda_0001 511 | Hatsui_Hasuike Hatsui_Hasuike_0001 512 | Heath_Ledger Heath_Ledger_0001 513 | Heath_Ledger Heath_Ledger_0002 514 | Heather_Locklear Heather_Locklear_0001 515 | Hector_Babenco Hector_Babenco_0002 516 | Hector_Grullon Hector_Grullon_0001 517 | Hee-Won_Han Hee-Won_Han_0001 518 | Hee-Won_Han Hee-Won_Han_0003 519 | Heidi_Klum Heidi_Klum_0003 520 | Heinrich_Wolfgang Heinrich_Wolfgang_0001 521 | Helen_Alvare Helen_Alvare_0001 522 | Helen_Clark Helen_Clark_0002 523 | Helen_Clark Helen_Clark_0003 524 | Helen_Clark Helen_Clark_0004 525 | Henk_Bekedam Henk_Bekedam_0001 526 | Herb_Sendek Herb_Sendek_0003 527 | Herman_Edwards Herman_Edwards_0001 528 | Hernan_Diaz Hernan_Diaz_0001 529 | Hideki_Matsui Hideki_Matsui_0001 530 | Hideki_Matsui Hideki_Matsui_0002 531 | Hikmat_al-Azzawi Hikmat_al-Azzawi_0001 532 | Hisham_Halawi Hisham_Halawi_0001 533 | Hosni_Mubarak Hosni_Mubarak_0008 534 | Hosni_Mubarak Hosni_Mubarak_0009 535 | Howard_Stringer Howard_Stringer_0001 536 | Hu_Jintao Hu_Jintao_0001 537 | Hu_Jintao Hu_Jintao_0002 538 | Hu_Jintao Hu_Jintao_0003 539 | Hu_Jintao Hu_Jintao_0012 540 | Hugh_Grant Hugh_Grant_0001 541 | Hugh_Grant Hugh_Grant_0007 542 | Hugh_Grant Hugh_Grant_0009 543 | Hun_Sen Hun_Sen_0001 544 | Hun_Sen Hun_Sen_0002 545 | Hun_Sen Hun_Sen_0004 546 | Hushiar_Zebari Hushiar_Zebari_0001 547 | Hussein_Malik Hussein_Malik_0001 548 | Ian_McKellen Ian_McKellen_0001 549 | Ian_McKellen Ian_McKellen_0002 550 | Ian_McKellen Ian_McKellen_0003 551 | Ibrahim_Hilal Ibrahim_Hilal_0001 552 | Inocencio_Arias Inocencio_Arias_0001 553 | Inocencio_Arias Inocencio_Arias_0002 554 | Irwan_Fadzi_Idris Irwan_Fadzi_Idris_0001 555 | JT_Snow JT_Snow_0001 556 | Jack_Valenti Jack_Valenti_0001 557 | Jackie_Chan Jackie_Chan_0001 558 | Jackie_Chan Jackie_Chan_0007 559 | Jackie_Chan Jackie_Chan_0010 560 | Jackie_Chan Jackie_Chan_0012 561 | Jacob_Frenkel Jacob_Frenkel_0001 562 | Jacques_Kallis Jacques_Kallis_0001 563 | Jada_Pinkett_Smith Jada_Pinkett_Smith_0001 564 | Jada_Pinkett_Smith Jada_Pinkett_Smith_0002 565 | Jaime_Orti Jaime_Orti_0001 566 | James_Caan James_Caan_0001 567 | James_Caan James_Caan_0002 568 | James_Collinson James_Collinson_0001 569 | James_Cunningham James_Cunningham_0001 570 | James_Cunningham James_Cunningham_0002 571 | James_Cunningham James_Cunningham_0003 572 | James_Gandolfini James_Gandolfini_0001 573 | James_Gandolfini James_Gandolfini_0003 574 | James_Hakett James_Hakett_0001 575 | James_Robertson_Jr James_Robertson_Jr_0001 576 | James_Schultz James_Schultz_0001 577 | James_Schultz James_Schultz_0002 578 | James_Spalding James_Spalding_0001 579 | James_Traficant James_Traficant_0001 580 | James_Traficant James_Traficant_0002 581 | James_Traficant James_Traficant_0003 582 | James_W_Kennedy James_W_Kennedy_0001 583 | James_Wolfensohn James_Wolfensohn_0001 584 | James_Wolfensohn James_Wolfensohn_0003 585 | Jane_Fonda Jane_Fonda_0001 586 | Jane_Fonda Jane_Fonda_0002 587 | Jane_Pauley Jane_Pauley_0001 588 | Jane_Pauley Jane_Pauley_0002 589 | Janet_Napolitano Janet_Napolitano_0001 590 | Janet_Napolitano Janet_Napolitano_0002 591 | Janet_Napolitano Janet_Napolitano_0003 592 | Janet_Napolitano Janet_Napolitano_0004 593 | Janette_Husarova Janette_Husarova_0001 594 | Jaromir_Jagr Jaromir_Jagr_0001 595 | Jason_Gardner Jason_Gardner_0001 596 | Jason_Jennings Jason_Jennings_0001 597 | Jason_Jennings Jason_Jennings_0002 598 | Jason_Sorens Jason_Sorens_0001 599 | Jason_Statham Jason_Statham_0001 600 | Javier_Solana Javier_Solana_0002 601 | Javier_Solana Javier_Solana_0006 602 | Javier_Solana Javier_Solana_0007 603 | Javier_Solana Javier_Solana_0009 604 | Jay_Leno Jay_Leno_0002 605 | Jay_Leno Jay_Leno_0003 606 | Jayson_Williams Jayson_Williams_0001 607 | Jayson_Williams Jayson_Williams_0002 608 | Jayson_Williams Jayson_Williams_0003 609 | Jean-Luc_Bideau Jean-Luc_Bideau_0001 610 | Jean-Rene_Fourtou Jean-Rene_Fourtou_0001 611 | Jean-Sebastien_Giguere Jean-Sebastien_Giguere_0001 612 | Jean-Sebastien_Giguere Jean-Sebastien_Giguere_0002 613 | Jean_Brumley Jean_Brumley_0001 614 | Jean_Brumley Jean_Brumley_0002 615 | Jeff_Feldman Jeff_Feldman_0001 616 | Jeffery_Strelzin Jeffery_Strelzin_0001 617 | Jeffrey_Donaldson Jeffrey_Donaldson_0001 618 | Jeffrey_Immelt Jeffrey_Immelt_0001 619 | Jeffrey_Immelt Jeffrey_Immelt_0002 620 | Jeffrey_Jones Jeffrey_Jones_0001 621 | Jeffrey_Jones Jeffrey_Jones_0002 622 | Jennifer_Garner Jennifer_Garner_0001 623 | Jennifer_Garner Jennifer_Garner_0002 624 | Jennifer_Garner Jennifer_Garner_0004 625 | Jennifer_Garner Jennifer_Garner_0005 626 | Jennifer_Garner Jennifer_Garner_0006 627 | Jennifer_Garner Jennifer_Garner_0010 628 | Jennifer_Garner Jennifer_Garner_0011 629 | Jennifer_Lopez Jennifer_Lopez_0004 630 | Jennifer_Lopez Jennifer_Lopez_0005 631 | Jennifer_Lopez Jennifer_Lopez_0007 632 | Jennifer_Lopez Jennifer_Lopez_0009 633 | Jennifer_Lopez Jennifer_Lopez_0010 634 | Jennifer_Lopez Jennifer_Lopez_0015 635 | Jennifer_Lopez Jennifer_Lopez_0021 636 | Jennifer_Reilly Jennifer_Reilly_0001 637 | Jeremy_Fogel Jeremy_Fogel_0001 638 | Jeremy_Gompertz Jeremy_Gompertz_0001 639 | Jerry_Colangelo Jerry_Colangelo_0001 640 | Jerry_Lewis Jerry_Lewis_0001 641 | Jerry_Tarkanian Jerry_Tarkanian_0001 642 | Jesper_Parnevik Jesper_Parnevik_0001 643 | Jesse_James_Leija Jesse_James_Leija_0001 644 | Jesus_Cardenal Jesus_Cardenal_0001 645 | Jim_Bunning Jim_Bunning_0001 646 | Jim_Edmonds Jim_Edmonds_0001 647 | Jim_Edmonds Jim_Edmonds_0002 648 | Jim_Fassel Jim_Fassel_0001 649 | Jim_Hardin Jim_Hardin_0001 650 | Jim_Nochols Jim_Nochols_0001 651 | Jim_OBrien Jim_OBrien_0001 652 | Jim_OBrien Jim_OBrien_0002 653 | Jim_OBrien Jim_OBrien_0003 654 | Jim_Ryan Jim_Ryan_0001 655 | Jim_Taylor Jim_Taylor_0001 656 | Jim_Tressel Jim_Tressel_0001 657 | Jim_Tressel Jim_Tressel_0002 658 | Jim_Tressel Jim_Tressel_0003 659 | Jim_Wall Jim_Wall_0001 660 | Jiri_Novak Jiri_Novak_0001 661 | Jiri_Novak Jiri_Novak_0004 662 | Jiri_Novak Jiri_Novak_0007 663 | Jiri_Novak Jiri_Novak_0009 664 | Jiri_Novak Jiri_Novak_0010 665 | Jiri_Novak Jiri_Novak_0011 666 | Joan_Claybrook Joan_Claybrook_0001 667 | Joan_Claybrook Joan_Claybrook_0002 668 | Joanne_Woodward Joanne_Woodward_0001 669 | Joe_Carnahan Joe_Carnahan_0001 670 | Joe_Gatti Joe_Gatti_0001 671 | Joe_Gatti Joe_Gatti_0002 672 | Joe_Mendes Joe_Mendes_0001 673 | Joe_Torre Joe_Torre_0002 674 | Joe_Torre Joe_Torre_0003 675 | Joe_Torre Joe_Torre_0004 676 | Joel_Todd Joel_Todd_0001 677 | Joerg_Haider Joerg_Haider_0001 678 | Joerg_Haider Joerg_Haider_0002 679 | Joey_Mantia Joey_Mantia_0001 680 | John_Anderson John_Anderson_0001 681 | John_Connolly John_Connolly_0001 682 | John_Cusack John_Cusack_0001 683 | John_Cusack John_Cusack_0002 684 | John_Dallager John_Dallager_0001 685 | John_Edwards John_Edwards_0006 686 | John_F_Kennedy_Jr John_F_Kennedy_Jr_0001 687 | John_F_Kennedy_Jr John_F_Kennedy_Jr_0002 688 | John_Henry John_Henry_0001 689 | John_Jumper John_Jumper_0001 690 | John_Leguizamo John_Leguizamo_0001 691 | John_Lithgow John_Lithgow_0001 692 | John_Manley John_Manley_0002 693 | John_Manley John_Manley_0003 694 | John_Manley John_Manley_0004 695 | John_Manley John_Manley_0005 696 | John_Manley John_Manley_0007 697 | John_McCain John_McCain_0003 698 | John_McCain John_McCain_0004 699 | John_McCain John_McCain_0005 700 | John_McCain John_McCain_0006 701 | John_McKay John_McKay_0001 702 | John_Petty John_Petty_0001 703 | John_Philip_Elkann John_Philip_Elkann_0001 704 | John_Reid John_Reid_0001 705 | John_Reid John_Reid_0002 706 | John_Richardson John_Richardson_0001 707 | John_Rigas John_Rigas_0001 708 | John_Rigas John_Rigas_0002 709 | John_Taylor John_Taylor_0001 710 | John_Taylor John_Taylor_0002 711 | John_Thune John_Thune_0001 712 | John_Warner John_Warner_0001 713 | John_Warner John_Warner_0002 714 | John_Warner John_Warner_0003 715 | John_Warner John_Warner_0004 716 | John_White John_White_0001 717 | John_Wright John_Wright_0001 718 | Johnny_Htu Johnny_Htu_0001 719 | Jonathan_Edwards Jonathan_Edwards_0002 720 | Jonathan_Edwards Jonathan_Edwards_0004 721 | Jonathan_Karsh Jonathan_Karsh_0001 722 | Jonathan_Schroeder Jonathan_Schroeder_0001 723 | Jong_Wook_Lee Jong_Wook_Lee_0004 724 | Jorge_Batlle Jorge_Batlle_0001 725 | Jorge_Batlle Jorge_Batlle_0002 726 | Jorge_Batlle Jorge_Batlle_0003 727 | Jose_Mourinho Jose_Mourinho_0001 728 | Jose_Mourinho Jose_Mourinho_0002 729 | Jose_Rosado Jose_Rosado_0001 730 | Jose_Serra Jose_Serra_0001 731 | Jose_Serra Jose_Serra_0005 732 | Jose_Serra Jose_Serra_0009 733 | Jose_Theodore Jose_Theodore_0001 734 | Joseph_Blatter Joseph_Blatter_0002 735 | Joseph_Estrada Joseph_Estrada_0002 736 | Joseph_Nacchio Joseph_Nacchio_0001 737 | Josh_Evans Josh_Evans_0001 738 | Juan_Fernandez Juan_Fernandez_0001 739 | Juan_Ignacio_Chela Juan_Ignacio_Chela_0001 740 | Juan_Ignacio_Chela Juan_Ignacio_Chela_0003 741 | Juan_Valencia_Osorio Juan_Valencia_Osorio_0001 742 | Juan_Valencia_Osorio Juan_Valencia_Osorio_0002 743 | Juanes Juanes_0001 744 | Juanes Juanes_0002 745 | Juanes Juanes_0003 746 | Juergen_Peters Juergen_Peters_0001 747 | Juergen_Peters Juergen_Peters_0002 748 | Julio_Iglesias_Jr Julio_Iglesias_Jr_0001 749 | Julius_Barnes Julius_Barnes_0001 750 | Justin_Marshall Justin_Marshall_0001 751 | Kaspar_Villiger Kaspar_Villiger_0001 752 | Kate_Burton Kate_Burton_0001 753 | Kate_Capshaw Kate_Capshaw_0001 754 | Kate_Capshaw Kate_Capshaw_0002 755 | Kate_Winslet Kate_Winslet_0001 756 | Kate_Winslet Kate_Winslet_0002 757 | Kate_Winslet Kate_Winslet_0004 758 | Katherine_Harris Katherine_Harris_0002 759 | Kathryn_Bigelow Kathryn_Bigelow_0001 760 | Kathryn_Grayson Kathryn_Grayson_0001 761 | Kathryn_Tucker Kathryn_Tucker_0001 762 | Kathy_Bates Kathy_Bates_0001 763 | Katie_Couric Katie_Couric_0001 764 | Katrin_Cartlidge Katrin_Cartlidge_0001 765 | Katrin_Susi Katrin_Susi_0001 766 | Kaye_Young Kaye_Young_0001 767 | Keira_Knightley Keira_Knightley_0002 768 | Keith_Bishop_Jr Keith_Bishop_Jr_0001 769 | Keith_Brown Keith_Brown_0001 770 | Kellie_Coffey Kellie_Coffey_0001 771 | Kelly_Clarkson Kelly_Clarkson_0001 772 | Kelly_Clarkson Kelly_Clarkson_0003 773 | Kelvin_Sampson Kelvin_Sampson_0002 774 | Kemal_Dervis Kemal_Dervis_0001 775 | Kemal_Dervis Kemal_Dervis_0002 776 | Ken_Watanabe Ken_Watanabe_0001 777 | Ken_Watanabe Ken_Watanabe_0002 778 | Kevin_Stallings Kevin_Stallings_0001 779 | Kevin_Stallings Kevin_Stallings_0002 780 | Khalid_Qazi Khalid_Qazi_0001 781 | Kim_Clijsters Kim_Clijsters_0004 782 | Kim_Clijsters Kim_Clijsters_0006 783 | Kim_Clijsters Kim_Clijsters_0009 784 | Kim_Dae-jung Kim_Dae-jung_0004 785 | Kim_Hong-up Kim_Hong-up_0001 786 | Kimberly_Bruckner Kimberly_Bruckner_0001 787 | Kimberly_Stewart Kimberly_Stewart_0001 788 | Kirk_Doerger Kirk_Doerger_0001 789 | Kirk_Douglas Kirk_Douglas_0001 790 | Kristen_Rivera Kristen_Rivera_0001 791 | Kristin_Scott Kristin_Scott_0001 792 | Kurt_Busch Kurt_Busch_0001 793 | Kurt_Busch Kurt_Busch_0002 794 | Kurt_Schottenheimer Kurt_Schottenheimer_0001 795 | Kurt_Thomas Kurt_Thomas_0001 796 | Laila_Ali Laila_Ali_0001 797 | Laila_Ali Laila_Ali_0002 798 | Landon_Donovan Landon_Donovan_0001 799 | Lara_Logan Lara_Logan_0001 800 | Larenz_Tate Larenz_Tate_0001 801 | Larry_Wilmore Larry_Wilmore_0001 802 | Lars_Von_Trier Lars_Von_Trier_0003 803 | Laura_Bush Laura_Bush_0004 804 | Laura_Bush Laura_Bush_0011 805 | Laura_Bush Laura_Bush_0013 806 | Laura_Bush Laura_Bush_0016 807 | Laura_Bush Laura_Bush_0032 808 | Laura_Bush Laura_Bush_0040 809 | Laura_Gobai Laura_Gobai_0001 810 | Lauren_Hutton Lauren_Hutton_0002 811 | Laurie_Pirtle Laurie_Pirtle_0001 812 | Lawrence_Foley Lawrence_Foley_0001 813 | Lawrence_Vito Lawrence_Vito_0001 814 | Leah_Remini Leah_Remini_0001 815 | Leander_Paes Leander_Paes_0001 816 | Leander_Paes Leander_Paes_0002 817 | Lee_Byung-woong Lee_Byung-woong_0001 818 | Lee_Chang-dong Lee_Chang-dong_0001 819 | Lee_Jun Lee_Jun_0001 820 | Lee_Jun Lee_Jun_0002 821 | Lee_Yuan-tseh Lee_Yuan-tseh_0001 822 | Leland_Chapman Leland_Chapman_0001 823 | Lene_Espersen Lene_Espersen_0001 824 | Lennox_Lewis Lennox_Lewis_0003 825 | Lenny_Kravitz Lenny_Kravitz_0001 826 | Lesley_McCulloch Lesley_McCulloch_0001 827 | Lesley_McCulloch Lesley_McCulloch_0002 828 | Lesley_McCulloch Lesley_McCulloch_0003 829 | Leuris_Pupo Leuris_Pupo_0001 830 | Li_Ka-shing Li_Ka-shing_0001 831 | Li_Peng Li_Peng_0001 832 | Li_Peng Li_Peng_0007 833 | Li_Zhaoxing Li_Zhaoxing_0001 834 | Li_Zhaoxing Li_Zhaoxing_0002 835 | Li_Zhaoxing Li_Zhaoxing_0005 836 | Li_Zhaoxing Li_Zhaoxing_0007 837 | Li_Zhaoxing Li_Zhaoxing_0008 838 | Liliana_Cavani Liliana_Cavani_0001 839 | Lincoln_Chafee Lincoln_Chafee_0001 840 | Linda_Baboolal Linda_Baboolal_0001 841 | Lionel_Hampton Lionel_Hampton_0001 842 | Lionel_Richie Lionel_Richie_0001 843 | Lionel_Richie Lionel_Richie_0002 844 | Lloyd_Richards Lloyd_Richards_0001 845 | Lord_Hutton Lord_Hutton_0001 846 | Luciano_Bovicelli Luciano_Bovicelli_0001 847 | Lucio_Stanca Lucio_Stanca_0001 848 | Ludivine_Sagnier Ludivine_Sagnier_0001 849 | Ludivine_Sagnier Ludivine_Sagnier_0003 850 | Ludivine_Sagnier Ludivine_Sagnier_0004 851 | Luiz_Felipe_Scolari Luiz_Felipe_Scolari_0002 852 | Luke_Walton Luke_Walton_0001 853 | Luke_Walton Luke_Walton_0002 854 | Luther_Htu Luther_Htu_0001 855 | Lynne_Cheney Lynne_Cheney_0001 856 | Lynne_Cheney Lynne_Cheney_0002 857 | Lynne_Cheney Lynne_Cheney_0003 858 | Lyudmila_Putin Lyudmila_Putin_0001 859 | Madeleine_Albright Madeleine_Albright_0001 860 | Madonna Madonna_0002 861 | Madonna Madonna_0005 862 | Magdalena_Maleeva Magdalena_Maleeva_0001 863 | Magdalena_Maleeva Magdalena_Maleeva_0002 864 | Magui_Serna Magui_Serna_0001 865 | Mahathir_Mohamad Mahathir_Mohamad_0009 866 | Mahathir_Mohamad Mahathir_Mohamad_0011 867 | Mahathir_Mohamad Mahathir_Mohamad_0012 868 | Malcolm_Glazer Malcolm_Glazer_0001 869 | Marc_Gold Marc_Gold_0001 870 | Marc_Grossman Marc_Grossman_0001 871 | Marc_Grossman Marc_Grossman_0002 872 | Marc_Grossman Marc_Grossman_0003 873 | Marc_Shaiman Marc_Shaiman_0001 874 | Marcio_de_Souza Marcio_de_Souza_0001 875 | Margaret_Thatcher Margaret_Thatcher_0001 876 | Margaret_Thatcher Margaret_Thatcher_0002 877 | Maria_Luisa_Mendonca Maria_Luisa_Mendonca_0002 878 | Maria_Wetterstrand Maria_Wetterstrand_0001 879 | Mariana_Pollack Mariana_Pollack_0001 880 | Mariana_Pollack Mariana_Pollack_0002 881 | Mariangel_Ruiz_Torrealba Mariangel_Ruiz_Torrealba_0001 882 | Maribel_Dominguez Maribel_Dominguez_0001 883 | Marina_Anissina Marina_Anissina_0001 884 | Marina_Anissina Marina_Anissina_0002 885 | Mario_Austin Mario_Austin_0001 886 | Marisol_Breton Marisol_Breton_0001 887 | Mark_Salter Mark_Salter_0001 888 | Mark_Warner Mark_Warner_0001 889 | Mark_Warner Mark_Warner_0002 890 | Markus_Beyer Markus_Beyer_0001 891 | Martha_Beatriz_Roque Martha_Beatriz_Roque_0001 892 | Martha_Beatriz_Roque Martha_Beatriz_Roque_0002 893 | Martha_Smith Martha_Smith_0001 894 | Martin_Brodeur Martin_Brodeur_0002 895 | Martin_Hoellwarth Martin_Hoellwarth_0002 896 | Martin_McCauley Martin_McCauley_0001 897 | Martin_McCauley Martin_McCauley_0002 898 | Martin_Scorsese Martin_Scorsese_0001 899 | Martin_Scorsese Martin_Scorsese_0002 900 | Martin_Scorsese Martin_Scorsese_0003 901 | Martin_Scorsese Martin_Scorsese_0004 902 | Martin_Scorsese Martin_Scorsese_0005 903 | Martin_Scorsese Martin_Scorsese_0006 904 | Martina_McBride Martina_McBride_0002 905 | Martina_McBride Martina_McBride_0003 906 | Martina_McBride Martina_McBride_0004 907 | Marwan_Muasher Marwan_Muasher_0001 908 | Mary-Kate_Olsen Mary-Kate_Olsen_0001 909 | Mary_Blige Mary_Blige_0001 910 | Mary_Catherine_Correll Mary_Catherine_Correll_0001 911 | Masahiko_Nagasawa Masahiko_Nagasawa_0001 912 | Masahiko_Nagasawa Masahiko_Nagasawa_0002 913 | Massoud_Barzani Massoud_Barzani_0001 914 | Matt_Anderson Matt_Anderson_0001 915 | Matt_Roney Matt_Roney_0001 916 | Matthew_Ouimet Matthew_Ouimet_0001 917 | Maureen_Kanka Maureen_Kanka_0001 918 | Max_von_Sydow Max_von_Sydow_0001 919 | Mel_Brooks Mel_Brooks_0001 920 | Mel_Brooks Mel_Brooks_0002 921 | Melina_Kanakaredes Melina_Kanakaredes_0001 922 | Mesut_Yilmaz Mesut_Yilmaz_0001 923 | Mesut_Yilmaz Mesut_Yilmaz_0002 924 | Mian_Khursheed_Mehmood_Kasuri Mian_Khursheed_Mehmood_Kasuri_0003 925 | Michael_Bloomberg Michael_Bloomberg_0001 926 | Michael_Bloomberg Michael_Bloomberg_0016 927 | Michael_Bloomberg Michael_Bloomberg_0018 928 | Michael_Chertoff Michael_Chertoff_0001 929 | Michael_Diekmann Michael_Diekmann_0001 930 | Michael_Doleac Michael_Doleac_0001 931 | Michael_Hagee Michael_Hagee_0001 932 | Michael_Jasny Michael_Jasny_0001 933 | Michael_Kostelnik Michael_Kostelnik_0001 934 | Michael_Kostelnik Michael_Kostelnik_0002 935 | Michael_Leavitt Michael_Leavitt_0001 936 | Michael_Moore Michael_Moore_0003 937 | Michael_Patrick_King Michael_Patrick_King_0001 938 | Michael_Patrick_King Michael_Patrick_King_0002 939 | Michael_Rolinee Michael_Rolinee_0001 940 | Michelangelo_Antonioni Michelangelo_Antonioni_0001 941 | Michelle_Lecky Michelle_Lecky_0001 942 | Miguel_Juarez_Perez Miguel_Juarez_Perez_0001 943 | Mike_Babcock Mike_Babcock_0001 944 | Mike_Babcock Mike_Babcock_0002 945 | Mike_Bair Mike_Bair_0001 946 | Mike_Fisher Mike_Fisher_0001 947 | Mike_Gable Mike_Gable_0001 948 | Mike_Martz Mike_Martz_0004 949 | Mikhail_Kasyanov Mikhail_Kasyanov_0001 950 | Mikhail_Kasyanov Mikhail_Kasyanov_0002 951 | Milo_Djukanovic Milo_Djukanovic_0001 952 | Milo_Djukanovic Milo_Djukanovic_0003 953 | Milo_Maestrecampo Milo_Maestrecampo_0001 954 | Milo_Maestrecampo Milo_Maestrecampo_0002 955 | Milo_Maestrecampo Milo_Maestrecampo_0003 956 | Milt_Palacio Milt_Palacio_0001 957 | Miroljub Miroljub_0001 958 | Miroljub Miroljub_0002 959 | Misty_Dawn_Clymer Misty_Dawn_Clymer_0001 960 | Mitchell_Crooks Mitchell_Crooks_0001 961 | Miyako_Miyazaki Miyako_Miyazaki_0002 962 | Mohamed_Benaissa Mohamed_Benaissa_0001 963 | Mohamed_Benaissa Mohamed_Benaissa_0002 964 | Mohamed_Hammam Mohamed_Hammam_0001 965 | Mohammed_Al-Douri Mohammed_Al-Douri_0002 966 | Mohammed_Al-Douri Mohammed_Al-Douri_0005 967 | Mohammed_Mehdi_Saleh Mohammed_Mehdi_Saleh_0001 968 | Monique_Gagnon-Tremblay Monique_Gagnon-Tremblay_0001 969 | Monte_Kiffin Monte_Kiffin_0001 970 | Morgan_Fairchild Morgan_Fairchild_0001 971 | Muhammad_Ibrahim_Bilal Muhammad_Ibrahim_Bilal_0001 972 | Nadia_Petrova Nadia_Petrova_0001 973 | Nadia_Petrova Nadia_Petrova_0005 974 | Naji_Sabri Naji_Sabri_0004 975 | Naomi_Watts Naomi_Watts_0012 976 | Naomi_Watts Naomi_Watts_0013 977 | Naomi_Watts Naomi_Watts_0014 978 | Natalia_Vodonova Natalia_Vodonova_0001 979 | Natalie_Cole Natalie_Cole_0003 980 | Natalie_Stewart Natalie_Stewart_0001 981 | Nathalie_Baye Nathalie_Baye_0002 982 | Nathalie_Baye Nathalie_Baye_0003 983 | Nathalie_Baye Nathalie_Baye_0004 984 | Nia_Vardalos Nia_Vardalos_0004 985 | Nicolas_Cage Nicolas_Cage_0001 986 | Nicolas_Cage Nicolas_Cage_0002 987 | Nicolas_Cage Nicolas_Cage_0004 988 | Nicolas_Latorre Nicolas_Latorre_0001 989 | Noel_Forgeard Noel_Forgeard_0001 990 | Noelle_Bush Noelle_Bush_0002 991 | Noelle_Bush Noelle_Bush_0004 992 | Norah_Jones Norah_Jones_0005 993 | Norah_Jones Norah_Jones_0013 994 | Norm_Macdonald Norm_Macdonald_0001 995 | Norodom_Sihanouk Norodom_Sihanouk_0001 996 | Norodom_Sihanouk Norodom_Sihanouk_0003 997 | Oleksandr_Moroz Oleksandr_Moroz_0002 998 | Olene_Walker Olene_Walker_0001 999 | Omar_Sharif Omar_Sharif_0002 1000 | Omar_Sharif Omar_Sharif_0004 1001 | Oprah_Winfrey Oprah_Winfrey_0004 1002 | Oscar_Bolanos Oscar_Bolanos_0001 1003 | Osrat_Iosef Osrat_Iosef_0001 1004 | Pablo_Khulental Pablo_Khulental_0001 1005 | Paddy_Long Paddy_Long_0001 1006 | Paddy_Torsney Paddy_Torsney_0001 1007 | Pamela_Anderson Pamela_Anderson_0002 1008 | Pamela_Anderson Pamela_Anderson_0005 1009 | Paola_Espinoza Paola_Espinoza_0001 1010 | Paradorn_Srichaphan Paradorn_Srichaphan_0003 1011 | Paradorn_Srichaphan Paradorn_Srichaphan_0007 1012 | Paradorn_Srichaphan Paradorn_Srichaphan_0008 1013 | Paradorn_Srichaphan Paradorn_Srichaphan_0010 1014 | Pascal_Rheaume Pascal_Rheaume_0001 1015 | Pat_Cox Pat_Cox_0002 1016 | Pat_Rochester Pat_Rochester_0001 1017 | Patricia_Clarkson Patricia_Clarkson_0001 1018 | Patricia_Clarkson Patricia_Clarkson_0003 1019 | Patricia_Clarkson Patricia_Clarkson_0004 1020 | Patricia_Garone Patricia_Garone_0001 1021 | Patricia_Heaton Patricia_Heaton_0001 1022 | Patricia_Heaton Patricia_Heaton_0002 1023 | Patricia_Johnson Patricia_Johnson_0001 1024 | Patrick_Clawsen Patrick_Clawsen_0001 1025 | Patrick_Ewing Patrick_Ewing_0001 1026 | Patrick_Roy Patrick_Roy_0002 1027 | Patrick_Stewart Patrick_Stewart_0002 1028 | Paul_Farley Paul_Farley_0001 1029 | Paul_Henderson Paul_Henderson_0001 1030 | Paul_McCartney Paul_McCartney_0006 1031 | Paul_ONeill Paul_ONeill_0008 1032 | Paul_ONeill Paul_ONeill_0009 1033 | Paul_Pierce Paul_Pierce_0001 1034 | Paul_Pierce Paul_Pierce_0002 1035 | Paul_Tagliabue Paul_Tagliabue_0001 1036 | Paul_Tagliabue Paul_Tagliabue_0002 1037 | Paul_Tagliabue Paul_Tagliabue_0003 1038 | Paul_William_Hurley Paul_William_Hurley_0001 1039 | Paula_Dobriansky Paula_Dobriansky_0001 1040 | Paula_Radcliffe Paula_Radcliffe_0004 1041 | Paula_Radcliffe Paula_Radcliffe_0005 1042 | Pauline_Landers Pauline_Landers_0001 1043 | Pedro_Mahecha Pedro_Mahecha_0001 1044 | Pele Pele_0001 1045 | Penny_Lancaster Penny_Lancaster_0001 1046 | Pernilla_Bjorn Pernilla_Bjorn_0001 1047 | Pete_Beaudrault Pete_Beaudrault_0001 1048 | Pete_Gillen Pete_Gillen_0001 1049 | Pete_Sampras Pete_Sampras_0003 1050 | Pete_Sampras Pete_Sampras_0018 1051 | Peter_Albertsen Peter_Albertsen_0001 1052 | Peter_Chan Peter_Chan_0001 1053 | Peter_Hillary Peter_Hillary_0001 1054 | Peter_Hillary Peter_Hillary_0002 1055 | Peter_Medgyessy Peter_Medgyessy_0001 1056 | Peter_Struck Peter_Struck_0005 1057 | Petria_Thomas Petria_Thomas_0001 1058 | Petria_Thomas Petria_Thomas_0002 1059 | Petria_Thomas Petria_Thomas_0003 1060 | Pham_Sy_Chien Pham_Sy_Chien_0001 1061 | Phil_Mickelson Phil_Mickelson_0002 1062 | Phil_Vassar Phil_Vassar_0002 1063 | Pier_Ferdinando_Casini Pier_Ferdinando_Casini_0001 1064 | Piers_Sellers Piers_Sellers_0001 1065 | Prince_Charles Prince_Charles_0002 1066 | Prince_Charles Prince_Charles_0005 1067 | Prince_Edward Prince_Edward_0001 1068 | Prince_Edward Prince_Edward_0002 1069 | Prince_Naruhito Prince_Naruhito_0002 1070 | Prince_Naruhito Prince_Naruhito_0003 1071 | Prince_Philippe Prince_Philippe_0001 1072 | Prince_William Prince_William_0001 1073 | Pringe_Ernst_August Pringe_Ernst_August_0001 1074 | Priscilla_Owen Priscilla_Owen_0001 1075 | Queen_Beatrix Queen_Beatrix_0001 1076 | Queen_Beatrix Queen_Beatrix_0002 1077 | Queen_Beatrix Queen_Beatrix_0004 1078 | Quin_Snyder Quin_Snyder_0001 1079 | Quincy_Jones Quincy_Jones_0001 1080 | Rachel_Kempson Rachel_Kempson_0001 1081 | Rainer_Geulen Rainer_Geulen_0001 1082 | Ralph_Firman Ralph_Firman_0002 1083 | Ralph_Lauren Ralph_Lauren_0001 1084 | Ralph_Lauren Ralph_Lauren_0002 1085 | Randy_Jackson Randy_Jackson_0001 1086 | Ranil_Wickremasinghe Ranil_Wickremasinghe_0002 1087 | Ray_Halbritter Ray_Halbritter_0001 1088 | Ray_Romano Ray_Romano_0009 1089 | Raymond_Odierno Raymond_Odierno_0002 1090 | Rhett_Warrener Rhett_Warrener_0001 1091 | Ricardo_Lagos Ricardo_Lagos_0001 1092 | Ricardo_Lagos Ricardo_Lagos_0002 1093 | Ricardo_Lagos Ricardo_Lagos_0003 1094 | Ricardo_Lagos Ricardo_Lagos_0009 1095 | Ricardo_Lagos Ricardo_Lagos_0018 1096 | Ricardo_Lagos Ricardo_Lagos_0022 1097 | Ricardo_Monasterio Ricardo_Monasterio_0002 1098 | Richard_Cohen Richard_Cohen_0001 1099 | Richard_Gephardt Richard_Gephardt_0002 1100 | Richard_Gephardt Richard_Gephardt_0003 1101 | Richard_Gephardt Richard_Gephardt_0004 1102 | Richard_Gephardt Richard_Gephardt_0006 1103 | Richard_Gephardt Richard_Gephardt_0008 1104 | Richard_Haass Richard_Haass_0001 1105 | Richard_Haass Richard_Haass_0002 1106 | Richard_Krajicek Richard_Krajicek_0002 1107 | Richard_Krajicek Richard_Krajicek_0003 1108 | Richard_Naughton Richard_Naughton_0001 1109 | Richard_Palmer Richard_Palmer_0001 1110 | Richard_Perle Richard_Perle_0001 1111 | Richard_Tubb Richard_Tubb_0001 1112 | Richard_Virenque Richard_Virenque_0003 1113 | Richard_Virenque Richard_Virenque_0004 1114 | Ricky_Martin Ricky_Martin_0001 1115 | Ricky_Martin Ricky_Martin_0002 1116 | Rio_Ferdinand Rio_Ferdinand_0002 1117 | Robert_Altman Robert_Altman_0001 1118 | Robert_DeFraites Robert_DeFraites_0001 1119 | Robert_Duvall Robert_Duvall_0001 1120 | Robert_Duvall Robert_Duvall_0003 1121 | Robert_Duvall Robert_Duvall_0006 1122 | Robert_Fico Robert_Fico_0002 1123 | Robert_Lange Robert_Lange_0001 1124 | Robert_Pollack Robert_Pollack_0001 1125 | Robert_Schuller Robert_Schuller_0001 1126 | Robert_Stack Robert_Stack_0001 1127 | Robert_Stack Robert_Stack_0002 1128 | Robert_Witt Robert_Witt_0001 1129 | Robert_Witt Robert_Witt_0002 1130 | Robert_Zoellick Robert_Zoellick_0002 1131 | Robert_Zoellick Robert_Zoellick_0006 1132 | Roberto_Benigni Roberto_Benigni_0001 1133 | Roberto_Benigni Roberto_Benigni_0002 1134 | Roberto_Canessa Roberto_Canessa_0001 1135 | Roberto_Carlos Roberto_Carlos_0001 1136 | Roberto_Cercelletta Roberto_Cercelletta_0001 1137 | Rod_Bryden Rod_Bryden_0001 1138 | Roger_King Roger_King_0001 1139 | Rohinton_Mistry Rohinton_Mistry_0001 1140 | Rolf_Zimmermann Rolf_Zimmermann_0001 1141 | Ronald_Reagan Ronald_Reagan_0001 1142 | Ronald_Reagan Ronald_Reagan_0002 1143 | Rosalie_Perkov Rosalie_Perkov_0001 1144 | Roy_Halladay Roy_Halladay_0001 1145 | Rudi_Voeller Rudi_Voeller_0001 1146 | Ruth_Dreifuss Ruth_Dreifuss_0001 1147 | Ruth_Dreifuss Ruth_Dreifuss_0002 1148 | Ryan_Goodman Ryan_Goodman_0001 1149 | Ryan_Newman Ryan_Newman_0001 1150 | SJ_Twu SJ_Twu_0001 1151 | Sada_Jacobson Sada_Jacobson_0001 1152 | Sadie_Frost Sadie_Frost_0003 1153 | Saeed_Mortazavi Saeed_Mortazavi_0001 1154 | Saied_Hadi_al_Mudarissi Saied_Hadi_al_Mudarissi_0001 1155 | Sammy_Sosa Sammy_Sosa_0001 1156 | Sammy_Sosa Sammy_Sosa_0002 1157 | San_Lan San_Lan_0001 1158 | Sandra_Banning Sandra_Banning_0001 1159 | Santiago_Botero Santiago_Botero_0001 1160 | Sara_Silverman Sara_Silverman_0001 1161 | Sarah_Hughes Sarah_Hughes_0001 1162 | Sarah_Hughes Sarah_Hughes_0002 1163 | Sarah_Hughes Sarah_Hughes_0006 1164 | Sarah_Michelle_Gellar Sarah_Michelle_Gellar_0002 1165 | Sarah_Michelle_Gellar Sarah_Michelle_Gellar_0003 1166 | Sarah_Price Sarah_Price_0001 1167 | Scott_OGrady Scott_OGrady_0001 1168 | Scott_Peterson Scott_Peterson_0001 1169 | Scott_Peterson Scott_Peterson_0002 1170 | Scott_Peterson Scott_Peterson_0003 1171 | Scott_Peterson Scott_Peterson_0004 1172 | Scott_Rudin Scott_Rudin_0002 1173 | Scott_Verplank Scott_Verplank_0001 1174 | Sean_Combs Sean_Combs_0001 1175 | Sean_Hayes Sean_Hayes_0001 1176 | Selma_Phoenix Selma_Phoenix_0001 1177 | Sereyvuth_Kem Sereyvuth_Kem_0001 1178 | Sergei_Ivanov Sergei_Ivanov_0001 1179 | Shane_Loux Shane_Loux_0001 1180 | Shawn_Kemp Shawn_Kemp_0001 1181 | Sherri_Coale Sherri_Coale_0001 1182 | Shia_LaBeouf Shia_LaBeouf_0001 1183 | Shia_LaBeouf Shia_LaBeouf_0002 1184 | Shimon_Peres Shimon_Peres_0002 1185 | Shimon_Peres Shimon_Peres_0003 1186 | Shimon_Peres Shimon_Peres_0006 1187 | Shingo_Katayama Shingo_Katayama_0001 1188 | Shingo_Suetsugu Shingo_Suetsugu_0001 1189 | Shoshana_Johnson Shoshana_Johnson_0001 1190 | Sila_Calderon Sila_Calderon_0001 1191 | Silvia_Farina_Elia Silvia_Farina_Elia_0001 1192 | Silvia_Farina_Elia Silvia_Farina_Elia_0003 1193 | Slobodan_Milosevic Slobodan_Milosevic_0002 1194 | Sonia_Gandhi Sonia_Gandhi_0001 1195 | Sonia_Gandhi Sonia_Gandhi_0002 1196 | Sonia_Gandhi Sonia_Gandhi_0003 1197 | Spike_Helmick Spike_Helmick_0001 1198 | Stan_Kroenke Stan_Kroenke_0001 1199 | Stephen_Daldry Stephen_Daldry_0001 1200 | Stephen_Friedman Stephen_Friedman_0001 1201 | Stephen_Funk Stephen_Funk_0001 1202 | Steve_Karsay Steve_Karsay_0001 1203 | Steve_Largent Steve_Largent_0001 1204 | Steve_Phillips Steve_Phillips_0001 1205 | Steve_Redgrave Steve_Redgrave_0001 1206 | Steve_Spurrier Steve_Spurrier_0002 1207 | Stockard_Channing Stockard_Channing_0001 1208 | Strom_Thurmond Strom_Thurmond_0001 1209 | Susan_Walvius Susan_Walvius_0001 1210 | Suzanne_Haik_Terrell Suzanne_Haik_Terrell_0001 1211 | Suzanne_Torrance Suzanne_Torrance_0001 1212 | Sylvester_Stallone Sylvester_Stallone_0005 1213 | Sylvester_Stallone Sylvester_Stallone_0006 1214 | Tab_Turner Tab_Turner_0001 1215 | Tabare_Vazquez Tabare_Vazquez_0001 1216 | Taku_Yamasaki Taku_Yamasaki_0001 1217 | Takuma_Sato Takuma_Sato_0001 1218 | Tatiana_Paus Tatiana_Paus_0001 1219 | Tatyana_Tomashova Tatyana_Tomashova_0001 1220 | Taufik_Hidayat Taufik_Hidayat_0001 1221 | Ted_Williams Ted_Williams_0001 1222 | Terje_Roed-Larsen Terje_Roed-Larsen_0001 1223 | Terje_Roed-Larsen Terje_Roed-Larsen_0002 1224 | Terry_Gilliam Terry_Gilliam_0001 1225 | Terry_Stotts Terry_Stotts_0001 1226 | Terry_Stotts Terry_Stotts_0002 1227 | Theresa_May Theresa_May_0001 1228 | Theresa_May Theresa_May_0003 1229 | Thomas_Enqvist Thomas_Enqvist_0001 1230 | Thomas_Rupprath Thomas_Rupprath_0003 1231 | Thomas_Ulrich Thomas_Ulrich_0001 1232 | Thomas_Wyman Thomas_Wyman_0002 1233 | Tim_Curley Tim_Curley_0001 1234 | Tim_Floyd Tim_Floyd_0002 1235 | Tim_Lobinger Tim_Lobinger_0001 1236 | Tim_Welsh Tim_Welsh_0001 1237 | Tina_Pisnik Tina_Pisnik_0001 1238 | Todd_MacCulloch Todd_MacCulloch_0001 1239 | Tom_Brennan Tom_Brennan_0001 1240 | Tom_Crean Tom_Crean_0002 1241 | Tom_Crean Tom_Crean_0004 1242 | Tom_Crean Tom_Crean_0005 1243 | Tom_Harkin Tom_Harkin_0001 1244 | Tom_Harkin Tom_Harkin_0003 1245 | Tom_Harkin Tom_Harkin_0004 1246 | Tom_Harkin Tom_Harkin_0005 1247 | Tom_OBrien Tom_OBrien_0001 1248 | Tomas_Enge Tomas_Enge_0001 1249 | Tommy_Lewis Tommy_Lewis_0001 1250 | Toni_Jennings Toni_Jennings_0001 1251 | Tono_Suratman Tono_Suratman_0001 1252 | Tony_Bennett Tony_Bennett_0001 1253 | Tony_Bennett Tony_Bennett_0003 1254 | Toutai_Kefu Toutai_Kefu_0001 1255 | Tracy_McGrady Tracy_McGrady_0001 1256 | Tracy_McGrady Tracy_McGrady_0002 1257 | Trent_Lott Trent_Lott_0003 1258 | Trent_Lott Trent_Lott_0008 1259 | Trisha_Meili Trisha_Meili_0001 1260 | Tuncay_Sanli Tuncay_Sanli_0001 1261 | Tyler_Grillo Tyler_Grillo_0001 1262 | Tyrone_Medley Tyrone_Medley_0001 1263 | Vaclav_Klaus Vaclav_Klaus_0001 1264 | Vaclav_Klaus Vaclav_Klaus_0002 1265 | Valentina_Tereshkova Valentina_Tereshkova_0001 1266 | Valentino_Rossi Valentino_Rossi_0005 1267 | Valerie_Thwaites Valerie_Thwaites_0001 1268 | Vanessa_Incontrada Vanessa_Incontrada_0003 1269 | Vanessa_Incontrada Vanessa_Incontrada_0004 1270 | Vernon_Forrest Vernon_Forrest_0001 1271 | Vicki_Zhao_Wei Vicki_Zhao_Wei_0001 1272 | Vidar_Helgesen Vidar_Helgesen_0002 1273 | Vince_Carter Vince_Carter_0001 1274 | Vincent_Gallo Vincent_Gallo_0001 1275 | Vincent_Gallo Vincent_Gallo_0003 1276 | Vivica_Fox Vivica_Fox_0001 1277 | Vivica_Fox Vivica_Fox_0002 1278 | Vladimir_Voltchkov Vladimir_Voltchkov_0001 1279 | Vladimir_Voltchkov Vladimir_Voltchkov_0002 1280 | Wally_Szczerbiak Wally_Szczerbiak_0001 1281 | Walter_Mondale Walter_Mondale_0001 1282 | Walter_Mondale Walter_Mondale_0004 1283 | Walter_Mondale Walter_Mondale_0005 1284 | Wayne_Allard Wayne_Allard_0001 1285 | Wayne_Ferreira Wayne_Ferreira_0005 1286 | Wayne_Gretzky Wayne_Gretzky_0003 1287 | Wen_Jiabao Wen_Jiabao_0009 1288 | William_Bratton William_Bratton_0001 1289 | William_Bratton William_Bratton_0002 1290 | William_Bratton William_Bratton_0003 1291 | William_Bulger William_Bulger_0001 1292 | William_Bulger William_Bulger_0002 1293 | William_Bulger William_Bulger_0003 1294 | William_Bulger William_Bulger_0004 1295 | William_Ragland William_Ragland_0001 1296 | William_Shatner William_Shatner_0001 1297 | William_Swor William_Swor_0001 1298 | William_Webster William_Webster_0001 1299 | Willis_Roberts Willis_Roberts_0001 1300 | Wolfgang_Schuessel Wolfgang_Schuessel_0001 1301 | Wolfgang_Schuessel Wolfgang_Schuessel_0002 1302 | Wolfgang_Schuessel Wolfgang_Schuessel_0003 1303 | Wolfgang_Schuessel Wolfgang_Schuessel_0004 1304 | Xavier_Malisse Xavier_Malisse_0002 1305 | Xavier_Malisse Xavier_Malisse_0003 1306 | Xavier_Malisse Xavier_Malisse_0004 1307 | Yang_Hee_Kim Yang_Hee_Kim_0001 1308 | Yao_Ming Yao_Ming_0001 1309 | Yao_Ming Yao_Ming_0004 1310 | Yao_Ming Yao_Ming_0006 1311 | Yasar_Yakis Yasar_Yakis_0001 1312 | Yasar_Yakis Yasar_Yakis_0003 1313 | Yasar_Yakis Yasar_Yakis_0004 1314 | Yashwant_Sinha Yashwant_Sinha_0002 1315 | Yashwant_Sinha Yashwant_Sinha_0003 1316 | Yashwant_Sinha Yashwant_Sinha_0006 1317 | Yingfan_Wang Yingfan_Wang_0001 1318 | Yoon_Won-Sik Yoon_Won-Sik_0001 1319 | Yukio_Hatoyama Yukio_Hatoyama_0001 1320 | Zeng_Qinghong Zeng_Qinghong_0001 1321 | Zhu_Rongji Zhu_Rongji_0001 1322 | Zhu_Rongji Zhu_Rongji_0005 1323 | Zhu_Rongji Zhu_Rongji_0006 1324 | Zhu_Rongji Zhu_Rongji_0007 1325 | Zhu_Rongji Zhu_Rongji_0008 1326 | Zhu_Rongji Zhu_Rongji_0009 1327 | Zydrunas_Ilgauskas Zydrunas_Ilgauskas_0001 1328 | -------------------------------------------------------------------------------- /example_load_pretrained.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | from PIL import Image 3 | 4 | import torch 5 | import torchvision 6 | 7 | import models 8 | import datasets 9 | 10 | parser = argparse.ArgumentParser() 11 | 12 | parser.add_argument('--batch_size', type=int, default=40, help='number of images') 13 | parser.add_argument('--device', default='cpu', help='cpu | cuda:n, device to be loaded on') 14 | parser.add_argument('--statePath', default=None, help='path to pretrained weights') 15 | parser.add_argument('--statePathM', default=None, help='path to pretrained weights for mask predictor') 16 | parser.add_argument('--statePathX', default=None, help='path to pretrained weights for region generator') 17 | parser.add_argument('--statePathZ', default=None, help='path to pretrained weights for noise reconstruction') 18 | parser.add_argument('--statePathD', default=None, help='path to pretrained weights for discriminator') 19 | parser.add_argument('--dataroot', default=None, help='path to data') 20 | 21 | load_options = parser.parse_args() 22 | 23 | device = torch.device(load_options.device) 24 | 25 | if not load_options.statePath is None: 26 | states = torch.load(load_options.statePath, map_location={'cuda:0' : load_options.device}) 27 | opt = states['options'] 28 | if "netEncM" in states: 29 | netEncM = models._netEncM(sizex=opt.sizex, nIn=opt.nx, nMasks=opt.nMasks, nRes=opt.nResM, nf=opt.nfM, temperature=opt.temperature).to(device) 30 | netEncM.load_state_dict(states["netEncM"]) 31 | netEncM.eval() 32 | if "netGenX" in states: 33 | netGenX = models._netGenX(sizex=opt.sizex, nOut=opt.nx, nc=opt.nz, nf=opt.nfX, nMasks=opt.nMasks, selfAtt=opt.useSelfAttG).to(device) 34 | netGenX.load_state_dict(states["netGenX"]) 35 | netGenX.eval() 36 | if "netRecZ" in states: 37 | netRecZ = models._netRecZ(sizex=opt.sizex, nIn=opt.nx, nc=opt.nz, nf=opt.nfZ, nMasks=opt.nMasks).to(device) 38 | netRecZ.load_state_dict(states["netRecZ"]) 39 | netRecZ.eval() 40 | if "netDX" in states: 41 | netDX = models._resDiscriminator128(nIn=opt.nx, nf=opt.nfD, selfAtt=opt.useSelfAttD).to(device) 42 | netDX.load_state_dict(states["netDX"]) 43 | netDX.eval() 44 | 45 | if not load_options.statePathM is None: 46 | states = torch.load(load_options.statePathM, map_location={'cuda:0' : load_options.device}) 47 | opt = states['options'] 48 | netEncM = models._netEncM(sizex=opt.sizex, nIn=opt.nx, nMasks=opt.nMasks, nRes=opt.nResM, nf=opt.nfM, temperature=opt.temperature).to(device) 49 | netEncM.load_state_dict(states["netEncM"]) 50 | netEncM.eval() 51 | 52 | if not load_options.statePathX is None: 53 | states = torch.load(load_options.statePathX, map_location={'cuda:0' : load_options.device}) 54 | opt = states['options'] 55 | netGenX = models._netGenX(sizex=opt.sizex, nOut=opt.nx, nc=opt.nz, nf=opt.nfX, nMasks=opt.nMasks, selfAtt=opt.useSelfAttG).to(device) 56 | netGenX.load_state_dict(states["netGenX"]) 57 | netGenX.eval() 58 | 59 | if not load_options.statePathZ is None: 60 | states = torch.load(load_options.statePathZ, map_location={'cuda:0' : load_options.device}) 61 | opt = states['options'] 62 | netRecZ = models._netRecZ(sizex=opt.sizex, nIn=opt.nx, nc=opt.nz, nf=opt.nfZ, nMasks=opt.nMasks).to(device) 63 | netRecZ.load_state_dict(states["netRecZ"]) 64 | netRecZ.eval() 65 | 66 | if not load_options.statePathD is None: 67 | states = torch.load(load_options.statePathD, map_location={'cuda:0' : load_options.device}) 68 | opt = states['options'] 69 | netDX = models._resDiscriminator128(nIn=opt.nx, nf=opt.nfD, selfAtt=opt.useSelfAttD).to(device) 70 | netDX.load_state_dict(states['netDX']) 71 | netDX.eval() 72 | 73 | if opt.dataset == "lfw": 74 | dataset = datasets.LFWDataset(dataPath=load_options.dataroot, 75 | sets='test', 76 | transform=torchvision.transforms.Compose([torchvision.transforms.Resize(opt.sizex, Image.NEAREST), 77 | torchvision.transforms.CenterCrop(opt.sizex), 78 | torchvision.transforms.ToTensor(), 79 | ]),) 80 | if opt.dataset == 'cub': 81 | dataset = datasets.CUBDataset(load_options.dataroot, 82 | "train", 83 | torchvision.transforms.Compose([torchvision.transforms.Resize(opt.sizex, Image.NEAREST), 84 | torchvision.transforms.CenterCrop(opt.sizex), 85 | torchvision.transforms.ToTensor(), 86 | ])) 87 | if opt.dataset == 'flowers': 88 | dataset = datasets.FlowersDataset(load_options.dataroot, 89 | "train", 90 | torchvision.transforms.Compose([torchvision.transforms.Resize(opt.sizex, Image.NEAREST), 91 | torchvision.transforms.CenterCrop(opt.sizex), 92 | torchvision.transforms.ToTensor(), 93 | ])) 94 | if opt.dataset == 'cmnist': 95 | dataset = datasets.CMNISTDataset(dataPath=load_options.dataroot, 96 | sets='train') 97 | 98 | loader = torch.utils.data.DataLoader(dataset, batch_size=load_options.batch_size, shuffle=True) 99 | xData, mData = next(iter(loader)) 100 | xData = xData.to(device) 101 | mData = mData.to(device) 102 | 103 | ## Use the same z for all images in batch: ## 104 | # z = torch.randn(1, opt.nMasks, opt.nz, 1, 1).repeat(batch_size, 1, 1, 1, 1).to(device) 105 | 106 | ## or use different z: ## 107 | z = torch.randn(load_options.batch_size, opt.nMasks, opt.nz, 1, 1).to(device) 108 | 109 | with torch.no_grad(): 110 | # Using the mask predictor: 111 | mPred = netEncM(xData) 112 | 113 | # Redrawing using soft predictred masks: 114 | xGen = netGenX(mPred, z) + (xData.unsqueeze(1) * (1-mPred.unsqueeze(2))) 115 | 116 | # or using binarized predictred masks: 117 | # xGen = netGenX((mPred >= .5).float(), z) + (xData.unsqueeze(1) * (mPred < .5).float().unsqueeze(2)) 118 | 119 | # or using ground truth masks: 120 | # xGen = netGenX(torch.cat((mData, 1-mData),1), z) + (xData.unsqueeze(1) * torch.cat((1-mData, mData),1).unsqueeze(2)) 121 | 122 | # Saving the images: 123 | out = torch.cat((xData*.5+.5, 124 | mData.expand_as(xData), 125 | mPred[:,0:1].expand_as(xData), 126 | (mPred[:,1:2] >= .5).float().expand_as(xData), 127 | xGen[:,0] *.5+.5, 128 | xGen[:,1]*.5+.5), 129 | 1) 130 | torchvision.utils.save_image(out.view(-1,3,128,128), 'out.png', normalize=True, range=(0,1), nrow=6) 131 | -------------------------------------------------------------------------------- /imgs/redo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mickaelChen/ReDO/d6542528ca97c5c533694c4095ba003cb7a95d4c/imgs/redo.png -------------------------------------------------------------------------------- /imgs/redo_lfwxflowers.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mickaelChen/ReDO/d6542528ca97c5c533694c4095ba003cb7a95d4c/imgs/redo_lfwxflowers.png -------------------------------------------------------------------------------- /imgs/redo_samples.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mickaelChen/ReDO/d6542528ca97c5c533694c4095ba003cb7a95d4c/imgs/redo_samples.png -------------------------------------------------------------------------------- /models.py: -------------------------------------------------------------------------------- 1 | import torch 2 | import torch.nn as nn 3 | from torch.nn.utils import spectral_norm 4 | import torch.backends.cudnn as cudnn 5 | import torch.nn.functional as F 6 | 7 | class SelfAttentionNaive(nn.Module): 8 | def __init__(self, nf, nh=False): 9 | super(SelfAttentionNaive, self).__init__() 10 | if not nh: 11 | nh = max(nf//8, 1) 12 | self.f = spectral_norm(nn.Conv2d(nf, nh, 1, bias=False)) 13 | self.g = spectral_norm(nn.Conv2d(nf, nh, 1, bias=False)) 14 | self.h = spectral_norm(nn.Conv2d(nf, nf, 1, bias=False)) 15 | self.gamma = nn.Parameter(torch.zeros(1)) 16 | self.nh = nh 17 | self.nf = nf 18 | def forward(self, x): 19 | fx = self.f(x).view(x.size(0), self.nh, x.size(2)*x.size(3)) 20 | gx = self.g(x).view(x.size(0), self.nh, x.size(2)*x.size(3)) 21 | hx = self.h(x).view(x.size(0), self.nf, x.size(2)*x.size(3)) 22 | s = fx.transpose(-1,-2).matmul(gx) 23 | b = F.softmax(s, dim=1) 24 | o = hx.matmul(b) 25 | return o.view_as(x) * self.gamma + x 26 | 27 | class SelfAttention(nn.Module): 28 | def __init__(self, nf, nh=False): 29 | super(SelfAttention, self).__init__() 30 | if not nh: 31 | nh = max(nf//8, 1) 32 | self.f = spectral_norm(nn.Conv2d(nf, nh, 1, bias=False)) 33 | self.g = spectral_norm(nn.Conv2d(nf, nh, 1, bias=False)) 34 | self.h = spectral_norm(nn.Conv2d(nf, nf//2, 1, bias=False)) 35 | self.o = spectral_norm(nn.Conv2d(nf//2, nf, 1, bias=False)) 36 | self.gamma = nn.Parameter(torch.zeros(1)) 37 | self.nh = nh 38 | self.nf = nf 39 | def forward(self, x): 40 | fx = self.f(x).view(x.size(0), self.nh, x.size(2)*x.size(3)) 41 | gx = self.g(x) 42 | gx = F.max_pool2d(gx, kernel_size=2) 43 | gx = gx.view(x.size(0), self.nh, x.size(2)*x.size(3)//4) 44 | s = gx.transpose(-1,-2).matmul(fx) 45 | s = F.softmax(s, dim=1) 46 | hx = self.h(x) 47 | hx = F.max_pool2d(hx, kernel_size=2) 48 | hx = hx.view(x.size(0), self.nf//2, x.size(2)*x.size(3)//4) 49 | ox = hx.matmul(s).view(x.size(0), self.nf//2, x.size(2), x.size(3)) 50 | ox = self.o(ox) 51 | return ox * self.gamma + x 52 | 53 | class _resDiscriminator128(nn.Module): 54 | def __init__(self, nIn=3, nf=64, selfAtt=False): 55 | super(_resDiscriminator128, self).__init__() 56 | self.blocs = [] 57 | self.sc = [] 58 | # first bloc 59 | self.bloc0 = nn.Sequential(spectral_norm(nn.Conv2d(nIn, nf, 3, 1, 1, bias=True)), 60 | nn.ReLU(), 61 | spectral_norm(nn.Conv2d(nf, nf, 3, 1, 1, bias=True)), 62 | nn.AvgPool2d(2),) 63 | self.sc0 = nn.Sequential(nn.AvgPool2d(2), 64 | spectral_norm(nn.Conv2d(nIn, nf, 1, bias=True)),) 65 | if selfAtt: 66 | self.selfAtt = SelfAttention(nf) 67 | else: 68 | self.selfAtt = nn.Sequential() 69 | # Down blocs 70 | for i in range(4): 71 | nfPrev = nf 72 | nf = nf*2 73 | self.blocs.append(nn.Sequential(nn.ReLU(), 74 | spectral_norm(nn.Conv2d(nfPrev, nf, 3, 1, 1, bias=True)), 75 | nn.ReLU(), 76 | spectral_norm(nn.Conv2d(nf, nf, 3, 1, 1, bias=True)), 77 | nn.AvgPool2d(2),)) 78 | self.sc.append(nn.Sequential(nn.AvgPool2d(2), 79 | spectral_norm(nn.Conv2d(nfPrev, nf, 1, bias=True)),)) 80 | # Last Bloc 81 | self.blocs.append(nn.Sequential(nn.ReLU(), 82 | spectral_norm(nn.Conv2d(nf, nf, 3, 1, 1, bias=True)), 83 | nn.ReLU(), 84 | spectral_norm(nn.Conv2d(nf, nf, 3, 1, 1, bias=True)))) 85 | self.sc.append(nn.Sequential()) 86 | self.dense = nn.Linear(nf, 1) 87 | self.blocs = nn.ModuleList(self.blocs) 88 | self.sc = nn.ModuleList(self.sc) 89 | def forward(self, x): 90 | x = self.selfAtt(self.bloc0(x) + self.sc0(x)) 91 | for k in range(len(self.blocs)): 92 | x = self.blocs[k](x) + self.sc[k](x) 93 | x = x.sum(3).sum(2) 94 | return self.dense(x) 95 | 96 | class _resEncoder128(nn.Module): 97 | def __init__(self, nIn=3, nf=64, nOut=8): 98 | super(_resEncoder128, self).__init__() 99 | self.blocs = [] 100 | self.sc = [] 101 | # first bloc 102 | self.blocs.append(nn.Sequential(spectral_norm(nn.Conv2d(nIn, nf, 3, 1, 1, bias=True)), 103 | nn.ReLU(), 104 | spectral_norm(nn.Conv2d(nf, nf, 3, 1, 1, bias=True)), 105 | nn.AvgPool2d(2),)) 106 | self.sc.append(nn.Sequential(nn.AvgPool2d(2), 107 | spectral_norm(nn.Conv2d(nIn, nf, 1, bias=True)),)) 108 | # Down blocs 109 | for i in range(4): 110 | nfPrev = nf 111 | nf = nf*2 112 | self.blocs.append(nn.Sequential(nn.ReLU(), 113 | spectral_norm(nn.Conv2d(nfPrev, nf, 3, 1, 1, bias=True)), 114 | nn.ReLU(), 115 | spectral_norm(nn.Conv2d(nf, nf, 3, 1, 1, bias=True)), 116 | nn.AvgPool2d(2),)) 117 | self.sc.append(nn.Sequential(nn.AvgPool2d(2), 118 | spectral_norm(nn.Conv2d(nfPrev, nf, 1, bias=True)),)) 119 | # Last Bloc 120 | self.blocs.append(nn.Sequential(nn.ReLU(), 121 | spectral_norm(nn.Conv2d(nf, nf, 3, 1, 1, bias=True)), 122 | nn.ReLU(), 123 | spectral_norm(nn.Conv2d(nf, nf, 3, 1, 1, bias=True)))) 124 | self.sc.append(nn.Sequential()) 125 | self.dense = nn.Linear(nf, nOut) 126 | self.blocs = nn.ModuleList(self.blocs) 127 | self.sc = nn.ModuleList(self.sc) 128 | def forward(self, x): 129 | for k in range(len(self.blocs)): 130 | x = self.blocs[k](x) + self.sc[k](x) 131 | x = x.sum(3).sum(2) 132 | return self.dense(x) 133 | 134 | class _resMaskedGenerator128(nn.Module): 135 | def __init__(self, nf=64, nOut=3, nc=8, selfAtt=False): 136 | super(_resMaskedGenerator128, self).__init__() 137 | if selfAtt: 138 | self.selfAtt = SelfAttention(nf*2) 139 | else: 140 | self.selfAtt = nn.Sequential() 141 | self.dense = nn.Linear(nc, 4*4*nf*16) 142 | self.convA = [] 143 | self.convB = [] 144 | self.normA = [] 145 | self.normB = [] 146 | self.gammaA = [] 147 | self.gammaB = [] 148 | self.betaA = [] 149 | self.betaB = [] 150 | self.sc = [] 151 | nfPrev = nf*16 152 | nfNext = nf*16 153 | for k in range(5): 154 | self.convA.append(nn.Sequential(nn.Upsample(scale_factor=2), 155 | spectral_norm(nn.Conv2d(nfPrev + 1, nfNext, 3, 1, 1, bias=False)),)) 156 | self.convB.append(spectral_norm(nn.Conv2d(nfNext, nfNext, 3, 1, 1, bias=True ))) 157 | self.normA.append(nn.InstanceNorm2d(nfPrev, affine=False)) 158 | self.normB.append(nn.InstanceNorm2d(nfNext, affine=False)) 159 | self.gammaA.append(nn.Conv2d(nc, nfPrev, 1, bias=True)) 160 | self.gammaB.append(nn.Conv2d(nc, nfNext, 1, bias=True)) 161 | self.betaA.append(nn.Conv2d(nc, nfPrev, 1, bias=True)) 162 | self.betaB.append(nn.Conv2d(nc, nfNext, 1, bias=True)) 163 | self.sc.append(nn.Sequential(nn.Upsample(scale_factor=2), 164 | spectral_norm(nn.Conv2d(nfPrev, nfNext, 1, bias=True)))) 165 | nfPrev = nfNext 166 | nfNext = nfNext // 2 167 | self.convA = nn.ModuleList(self.convA) 168 | self.convB = nn.ModuleList(self.convB) 169 | self.normA = nn.ModuleList(self.normA) 170 | self.normB = nn.ModuleList(self.normB) 171 | self.gammaA =nn.ModuleList(self.gammaA) 172 | self.gammaB =nn.ModuleList(self.gammaB) 173 | self.betaA = nn.ModuleList(self.betaA) 174 | self.betaB = nn.ModuleList(self.betaB) 175 | self.sc = nn.ModuleList(self.sc) 176 | self.normOut = nn.InstanceNorm2d(nf, affine=False) 177 | self.gammaOut = nn.Conv2d(nc, nf, 1, bias=True) 178 | self.betaOut = nn.Conv2d(nc, nf, 1, bias=True) 179 | self.convOut = spectral_norm(nn.Conv2d(nf, nOut, 3, 1, 1)) 180 | self.convOut = spectral_norm(nn.Conv2d(nf + 1, nOut, 3, 1, 1)) 181 | ############################## 182 | def forward(self, m, z, c): 183 | ######### Upsample ########### 184 | x = self.dense(z.view(z.size(0),z.size(1))).view(z.size(0), -1, 4, 4) 185 | mask_ratio = m.size(-1) // 4 186 | for k in range(5): 187 | if k == 4: 188 | x = self.selfAtt(x) 189 | h = self.convA[k](torch.cat((F.relu(self.normA[k](x) * self.gammaA[k](c) + self.betaA[k](c)), 190 | F.avg_pool2d(m, kernel_size=mask_ratio)), 1)) 191 | h = self.convB[k](F.relu(self.normB[k](h) * self.gammaB[k](c) + self.betaB[k](c))) 192 | x = h + self.sc[k](x) 193 | mask_ratio = mask_ratio // 2 194 | x = self.convOut(torch.cat((F.relu(self.normOut(x) * self.gammaOut(c) + self.betaOut(c)), 195 | m), 1)) 196 | x = torch.tanh(x) 197 | return x * m 198 | 199 | class _downConv(nn.Module): 200 | def __init__(self, nIn=3, nf=128, spectralNorm=False): 201 | super(_downConv, self).__init__() 202 | self.mods = nn.Sequential(nn.ReflectionPad2d(3), 203 | spectral_norm(nn.Conv2d(nIn, nf//4, 7, bias=False)) if spectralNorm else nn.Conv2d(nIn, nf//4, 7, bias=False), 204 | nn.InstanceNorm2d(nf//4, affine=True), 205 | nn.ReLU(), 206 | spectral_norm(nn.Conv2d(nf//4, nf//2, 3, 2, 1, bias=False)) if spectralNorm else nn.Conv2d(nf//4, nf//2, 3, 2, 1, bias=False), 207 | nn.InstanceNorm2d(nf//2, affine=True), 208 | nn.ReLU(), 209 | spectral_norm(nn.Conv2d(nf//2, nf, 3, 2, 1, bias=False)) if spectralNorm else nn.Conv2d(nf//2, nf, 3, 2, 1, bias=False), 210 | nn.InstanceNorm2d(nf, affine=True), 211 | nn.ReLU(), 212 | ) 213 | def forward(self, x): 214 | return self.mods(x) 215 | class _resBloc(nn.Module): 216 | def __init__(self, nf=128, spectralNorm=False): 217 | super(_resBloc, self).__init__() 218 | self.blocs = nn.Sequential(spectral_norm(nn.Conv2d(nf, nf, 3, 1, 1, bias=False)) if spectralNorm else nn.Conv2d(nf, nf, 3, 1, 1, bias=False), 219 | nn.InstanceNorm2d(nf, affine=True), 220 | nn.ReLU(), 221 | spectral_norm(nn.Conv2d(nf, nf, 3, 1, 1, bias=True)) if spectralNorm else nn.Conv2d(nf, nf, 3, 1, 1, bias=True), 222 | ) 223 | self.activationF = nn.Sequential(nn.InstanceNorm2d(nf, affine=True), 224 | nn.ReLU(), 225 | ) 226 | def forward(self, x): 227 | return self.activationF(self.blocs(x) + x) 228 | class _upConv(nn.Module): 229 | def __init__(self, nOut=3, nf=128, spectralNorm=False): 230 | super(_upConv, self).__init__() 231 | self.mods = nn.Sequential(nn.Upsample(scale_factor=2, mode='nearest'), 232 | spectral_norm(nn.Conv2d(nf, nf//2, 3, 1, 1, bias=False)) if spectralNorm else nn.Conv2d(nf, nf//2, 3, 1, 1, bias=False), 233 | nn.InstanceNorm2d(nf//2, affine=True), 234 | nn.ReLU(), 235 | nn.Upsample(scale_factor=2, mode='nearest'), 236 | spectral_norm(nn.Conv2d(nf//2, nf//4, 3, 1, 1, bias=False)) if spectralNorm else nn.Conv2d(nf//2, nf//4, 3, 1, 1, bias=False), 237 | nn.InstanceNorm2d(nf//4, affine=True), 238 | nn.ReLU(), 239 | nn.ReflectionPad2d(3), 240 | spectral_norm(nn.Conv2d(nf//4, nOut, 7, bias=True)) if spectralNorm else nn.Conv2d(nf//4, nOut, 7, bias=True), 241 | ) 242 | def forward(self, x): 243 | return self.mods(x) 244 | class _netEncM(nn.Module): 245 | def __init__(self, sizex=128, nIn=3, nMasks=2, nRes=5, nf=128, temperature=1): 246 | super(_netEncM, self).__init__() 247 | self.nMasks = nMasks 248 | sizex = sizex // 4 249 | self.cnn = nn.Sequential(*([_downConv(nIn, nf)] + 250 | [_resBloc(nf=nf) for i in range(nRes)])) 251 | self.psp = nn.ModuleList([nn.Sequential(nn.AvgPool2d(sizex), 252 | nn.Conv2d(nf,1,1), 253 | nn.Upsample(size=sizex, mode='bilinear')), 254 | nn.Sequential(nn.AvgPool2d(sizex//2, sizex//2), 255 | nn.Conv2d(nf,1,1), 256 | nn.Upsample(size=sizex, mode='bilinear')), 257 | nn.Sequential(nn.AvgPool2d(sizex//3, sizex//3), 258 | nn.Conv2d(nf,1,1), 259 | nn.Upsample(size=sizex, mode='bilinear')), 260 | nn.Sequential(nn.AvgPool2d(sizex//6, sizex//6), 261 | nn.Conv2d(nf,1,1), 262 | nn.Upsample(size=sizex, mode='bilinear'))]) 263 | self.out = _upConv(1 if nMasks == 2 else nMasks, nf+4) 264 | self.temperature = temperature 265 | def forward(self, x): 266 | f = self.cnn(x) 267 | m = self.out(torch.cat([f] + [pnet(f) for pnet in self.psp], 1)) 268 | if self.nMasks == 2: 269 | m = torch.sigmoid(m / self.temperature) 270 | m = torch.cat((m, (1-m)), 1) 271 | else: 272 | m = F.softmax(m / self.temperature, dim=1) 273 | return m 274 | 275 | class _netGenX(nn.Module): 276 | def __init__(self, sizex=128, nOut=3, nc=8, nf=64, nMasks=2, selfAtt=False): 277 | super(_netGenX, self).__init__() 278 | if sizex != 128: 279 | raise NotImplementedError 280 | self.net = nn.ModuleList([_resMaskedGenerator128(nf=nf, nOut=nOut, nc=nc, selfAtt=selfAtt) for k in range(nMasks)]) 281 | self.nMasks = nMasks 282 | def forward(self, masks, c): 283 | masks = masks.unsqueeze(2) 284 | y = [] 285 | for k in range(self.nMasks): 286 | y.append(self.net[k](masks[:,k], c[:,k], c[:,k]).unsqueeze(1)) 287 | return torch.cat(y,1) 288 | 289 | class _netRecZ(nn.Module): 290 | def __init__(self, sizex=128, nIn=3, nc=5, nf=64, nMasks=2): 291 | super(_netRecZ, self).__init__() 292 | if sizex == 128: 293 | self.net = _resEncoder128(nIn=nIn, nf=nf, nOut=nc*nMasks) 294 | elif sizex == 64: 295 | self.net = _resEncoder64(nIn=nIn, nf=nf, nOut=nc*nMasks) 296 | self.nc = nc 297 | self.nMasks = nMasks 298 | def forward(self, x): 299 | c = self.net(x) 300 | return c.view(c.size(0), self.nMasks, self.nc, 1 , 1) 301 | -------------------------------------------------------------------------------- /train.py: -------------------------------------------------------------------------------- 1 | ############################################################################# 2 | # Import # 3 | ############################################################################# 4 | import os 5 | import math 6 | import random 7 | import argparse 8 | 9 | import itertools 10 | 11 | import numpy as np 12 | from scipy import io 13 | from PIL import Image 14 | 15 | import torch 16 | import torch.nn as nn 17 | from torch.nn.utils import spectral_norm 18 | import torch.backends.cudnn as cudnn 19 | 20 | import torchvision 21 | import torchvision.transforms as transforms 22 | import torchvision.utils as vutils 23 | import torch.nn.functional as F 24 | 25 | import datasets 26 | import models 27 | 28 | ############################################################################# 29 | # Arguments # 30 | ############################################################################# 31 | parser = argparse.ArgumentParser() 32 | 33 | parser.add_argument('--dataset', default="flowers", help='flowers | cub | lfw') 34 | parser.add_argument('--dataroot', default='./data', help='path to dataset') 35 | parser.add_argument('--nx', type=int, default=3, help='number of canals of the input image') 36 | parser.add_argument('--sizex', type=int, default=128, help='size of the input image') 37 | parser.add_argument('--nz', type=int, default=32, help='size of the latent z vector') 38 | parser.add_argument('--nMasks', type=int, default=2, help='number of masks') 39 | parser.add_argument('--nResM', type=int, default=3, help='number of residual blocs in netM') 40 | parser.add_argument('--nf', type=int, default=64, help='base number of filters for conv nets') 41 | parser.add_argument('--nfD', type=int, default=None, help='specific nf for netD, default to nf') 42 | parser.add_argument('--nfX', type=int, default=None, help='specific nf for netX, default to nf') 43 | parser.add_argument('--nfM', type=int, default=None, help='specific nf for netM, default to nf') 44 | parser.add_argument('--nfZ', type=int, default=None, help='specific nf for netZ, default to nf') 45 | parser.add_argument('--useSelfAttD', action='store_true', help='use self attention for D') 46 | parser.add_argument('--useSelfAttG', action='store_true', help='use self attention for G') 47 | parser.add_argument('--workers', type=int, help='number of data loading workers', default=4) 48 | parser.add_argument('--batchSize', type=int, default=20, help='input batch size') 49 | parser.add_argument('--nTest', type=int, default=5, help='input batch size for visu') 50 | parser.add_argument('--nIteration', type=int, default=5e4, help='number of iterations') 51 | parser.add_argument('--initOrthoGain', type=float, default=.8, help='gain for the initialization') 52 | parser.add_argument('--lrG', type=float, default=1e-4, help='learning rate for G, default=1e-4') 53 | parser.add_argument('--lrM', type=float, default=1e-5, help='learning rate for M, default=1e-5') 54 | parser.add_argument('--lrD', type=float, default=1e-4, help='learning rate for D, default=1e-4') 55 | parser.add_argument('--lrZ', type=float, default=1e-4, help='learning rate for Z, default=1e-4') 56 | parser.add_argument('--gStepFreq', type=int, default=1, help='wait x steps for G updates') 57 | parser.add_argument('--dStepFreq', type=int, default=1, help='wait x steps for D updates') 58 | parser.add_argument('--temperature', type=float, default=1, help='softmax temperature') 59 | parser.add_argument('--wdecay', type=float, default=1e-4, help='weight decay for M, default=1e-4') 60 | parser.add_argument('--wrecZ', type=float, default=5, help='weight for z reconstruction') 61 | parser.add_argument('--outf', default='.', help='folder to output images and model checkpoints') 62 | parser.add_argument('--checkpointFreq', type=int, default=500, help='frequency of checkpoints') 63 | parser.add_argument('--iteration', type=int, default=0, help="iteration to load (to resume training)") 64 | parser.add_argument('--manualSeed', type=int, help='manual seed') 65 | parser.add_argument('--resume', action='store_true', help='resume from last save') 66 | parser.add_argument('--clean', action='store_true', help='clean previous states') 67 | parser.add_argument('--silent', action='store_true', help='silent execution') 68 | parser.add_argument('--autoRestart', type=float, default=0, help='restart training if the ratio "size of region" / "size of image" is stricly smaller than x (collapse detected)') 69 | 70 | opt = parser.parse_args() 71 | 72 | if not opt.silent: 73 | from tqdm import tqdm 74 | 75 | if opt.resume: 76 | try: 77 | opt2 = torch.load(os.path.join(opt.outf, "options.pth")) 78 | opt2.clean = opt.clean 79 | opt2.silent = opt.silent 80 | opt2.outf = opt.outf 81 | opt = opt2 82 | except: 83 | pass 84 | 85 | if 'bestValIoU' not in opt: 86 | opt.bestValIoU = 0 87 | 88 | if opt.nfD is None: 89 | opt.nfD = opt.nf 90 | if opt.nfX is None: 91 | opt.nfX = opt.nf 92 | if opt.nfM is None: 93 | opt.nfM = opt.nf 94 | if opt.nfZ is None: 95 | opt.nfZ = opt.nf 96 | 97 | try: 98 | os.makedirs(opt.outf) 99 | except OSError: 100 | pass 101 | 102 | if opt.manualSeed is None: 103 | opt.manualSeed = random.randint(1, 10000) 104 | if not opt.silent: 105 | print("Random Seed: ", opt.manualSeed) 106 | random.seed(opt.manualSeed) 107 | torch.manual_seed(opt.manualSeed) 108 | 109 | opt.device = "cuda:0" 110 | device = torch.device(opt.device) 111 | cudnn.benchmark = True 112 | 113 | 114 | if opt.dataset == 'lfw': 115 | trainset = datasets.LFWDataset(dataPath=opt.dataroot, 116 | sets='train', 117 | transform=transforms.Compose([transforms.Resize(opt.sizex, Image.NEAREST), 118 | transforms.CenterCrop(opt.sizex), 119 | transforms.ToTensor(), 120 | ]),) 121 | testset = datasets.LFWDataset(dataPath=opt.dataroot, 122 | sets='test', 123 | transform=transforms.Compose([transforms.Resize(opt.sizex, Image.NEAREST), 124 | transforms.CenterCrop(opt.sizex), 125 | transforms.ToTensor(), 126 | ]),) 127 | valset = datasets.LFWDataset(dataPath=opt.dataroot, 128 | sets='val', 129 | transform=transforms.Compose([transforms.Resize(opt.sizex, Image.NEAREST), 130 | transforms.CenterCrop(opt.sizex), 131 | transforms.ToTensor(), 132 | ]),) 133 | if opt.dataset == 'cub': 134 | trainset = datasets.CUBDataset(opt.dataroot, 135 | "train", 136 | transforms.Compose([transforms.Resize(opt.sizex, Image.NEAREST), 137 | transforms.CenterCrop(opt.sizex), 138 | transforms.ToTensor(), 139 | ])) 140 | testset = datasets.CUBDataset(opt.dataroot, 141 | "test", 142 | transforms.Compose([transforms.Resize(opt.sizex, Image.NEAREST), 143 | transforms.CenterCrop(opt.sizex), 144 | transforms.ToTensor(), 145 | ])) 146 | valset = datasets.CUBDataset(opt.dataroot, 147 | "val", 148 | transforms.Compose([transforms.Resize(opt.sizex, Image.NEAREST), 149 | transforms.CenterCrop(opt.sizex), 150 | transforms.ToTensor(), 151 | ])) 152 | if opt.dataset == 'flowers': 153 | trainset = datasets.FlowersDataset(opt.dataroot, 154 | "train", 155 | transforms.Compose([transforms.Resize(opt.sizex, Image.NEAREST), 156 | transforms.CenterCrop(opt.sizex), 157 | transforms.ToTensor(), 158 | ])) 159 | testset = datasets.FlowersDataset(opt.dataroot, 160 | "test", 161 | transforms.Compose([transforms.Resize(opt.sizex, Image.NEAREST), 162 | transforms.CenterCrop(opt.sizex), 163 | transforms.ToTensor(), 164 | ])) 165 | valset = datasets.FlowersDataset(opt.dataroot, 166 | "val", 167 | transforms.Compose([transforms.Resize(opt.sizex, Image.NEAREST), 168 | transforms.CenterCrop(opt.sizex), 169 | transforms.ToTensor(), 170 | ])) 171 | if opt.dataset == 'cmnist': 172 | trainset = datasets.CMNISTDataset(dataPath=opt.dataroot, 173 | sets='train') 174 | testset = datasets.CMNISTDataset(dataPath=opt.dataroot, 175 | sets='test') 176 | valset = datasets.CMNISTDataset(dataPath=opt.dataroot, 177 | sets='val') 178 | 179 | trainloader = torch.utils.data.DataLoader(trainset, batch_size=opt.batchSize, shuffle=True, num_workers=4, drop_last=True) 180 | 181 | def weights_init_ortho(m): 182 | if isinstance(m, nn.Conv2d) or isinstance(m, nn.ConvTranspose2d) or isinstance(m, nn.Linear): 183 | nn.init.orthogonal_(m.weight, opt.initOrthoGain) 184 | 185 | 186 | netEncM = models._netEncM(sizex=opt.sizex, nIn=opt.nx, nMasks=opt.nMasks, nRes=opt.nResM, nf=opt.nfM, temperature=opt.temperature).to(device) 187 | netGenX = models._netGenX(sizex=opt.sizex, nOut=opt.nx, nc=opt.nz, nf=opt.nfX, nMasks=opt.nMasks, selfAtt=opt.useSelfAttG).to(device) 188 | netDX = models._resDiscriminator128(nIn=opt.nx, nf=opt.nfD, selfAtt=opt.useSelfAttD).to(device) 189 | netEncM.apply(weights_init_ortho) 190 | netGenX.apply(weights_init_ortho) 191 | netDX.apply(weights_init_ortho) 192 | 193 | ############################################################################# 194 | # Optimizer # 195 | ############################################################################# 196 | optimizerEncM = torch.optim.Adam(netEncM.parameters(), lr=opt.lrM, betas=(0, 0.9), weight_decay=opt.wdecay, amsgrad=False) 197 | optimizerGenX = torch.optim.Adam(netGenX.parameters(), lr=opt.lrG, betas=(0, 0.9), amsgrad=False) 198 | optimizerDX = torch.optim.Adam(netDX.parameters(), lr=opt.lrD, betas=(0, 0.9), amsgrad=False) 199 | 200 | if opt.wrecZ > 0: 201 | netRecZ = models._netRecZ(sizex=opt.sizex, nIn=opt.nx, nc=opt.nz, nf=opt.nfZ, nMasks=opt.nMasks).to(device) 202 | netRecZ.apply(weights_init_ortho) 203 | optimizerRecZ = torch.optim.Adam(netRecZ.parameters(), lr=opt.lrZ, betas=(0, 0.9), amsgrad=False) 204 | 205 | ############################################################################# 206 | # Load # 207 | ############################################################################# 208 | if opt.iteration > 0: 209 | state = torch.load(os.path.join(opt.outf, "state_%05d.pth" % opt.iteration)) 210 | netEncM.load_state_dict(state["netEncM"]) 211 | netGenX.load_state_dict(state["netGenX"]) 212 | netDX.load_state_dict(state["netDX"]) 213 | optimizerEncM.load_state_dict(state["optimizerEncM"]) 214 | optimizerGenX.load_state_dict(state["optimizerGenX"]) 215 | optimizerDX.load_state_dict(state["optimizerDX"]) 216 | if opt.wrecZ > 0: 217 | netRecZ.load_state_dict(state["netRecZ"]) 218 | optimizerRecZ.load_state_dict(state["optimizerRecZ"]) 219 | else: 220 | try: 221 | os.remove(os.path.join(opt.outf, "train.dat")) 222 | except: 223 | pass 224 | try: 225 | os.remove(os.path.join(opt.outf, "test.dat")) 226 | except: 227 | pass 228 | try: 229 | os.remove(os.path.join(opt.outf, "val.dat")) 230 | except: 231 | pass 232 | 233 | ############################################################################# 234 | # Test # 235 | ############################################################################# 236 | def evaluate(netEncM, loader, device, nMasks=2): 237 | sumScoreAcc = 0 238 | sumScoreIoU = 0 239 | nbIter = 0 240 | if nMasks > 2: 241 | raise NotImplementedError 242 | for xLoad, mLoad in loader: 243 | xData = xLoad.to(device) 244 | mData = mLoad.to(device) 245 | mPred = netEncM(xData) 246 | sumScoreAcc += torch.max(((mPred[:,:1] >= .5).float() == mData).float().mean(-1).mean(-1), 247 | ((mPred[:,:1] < .5).float() == mData).float().mean(-1).mean(-1)).mean().item() 248 | sumScoreIoU += torch.max( 249 | ((((mPred[:,:1] >= .5).float() + mData) == 2).float().sum(-1).sum(-1) / 250 | (((mPred[:,:1] >= .5).float() + mData) >= 1).float().sum(-1).sum(-1)), 251 | ((((mPred[:,:1] < .5).float() + mData) == 2).float().sum(-1).sum(-1) / 252 | (((mPred[:,:1] < .5).float() + mData) >= 1).float().sum(-1).sum(-1))).mean().item() 253 | nbIter += 1 254 | # minRegionSize = min((mPred[:,:1] >= .5).float().mean().item(), (mPred[:,:1] < .5).float().mean().item()) 255 | minRegionSize = min(mPred[:,:1].mean().item(), mPred[:,1:].mean().item()) 256 | return sumScoreAcc / nbIter, sumScoreIoU / nbIter, minRegionSize 257 | 258 | x_test, m_test = next(iter(torch.utils.data.DataLoader(testset, batch_size=opt.nTest, shuffle=True, num_workers=4, drop_last=True))) 259 | 260 | x_test = x_test.to(device) 261 | 262 | z_test = torch.randn((opt.nTest, opt.nMasks, opt.nz, 1, 1), device=device) 263 | zn_test = torch.randn((opt.nTest, opt.nz, 1, 1), device=device) 264 | 265 | img_m_test = m_test[:,:1].float() 266 | for n in range(opt.nTest): 267 | img_m_test[n] = (img_m_test[n] / img_m_test[n].max()) * 2 - 1 268 | 269 | out_X = torch.full((opt.nMasks, opt.nTest+1, opt.nTest+5, opt.nx, opt.sizex, opt.sizex), -1).to(device) 270 | out_X[:,1:,0] = x_test 271 | out_X[:,1:,1] = img_m_test 272 | 273 | valloader = torch.utils.data.DataLoader(valset, batch_size=opt.batchSize, shuffle=True, num_workers=4, drop_last=True) 274 | 275 | ############################################################################# 276 | # Train # 277 | ############################################################################# 278 | genData = iter(trainloader) 279 | disData = iter(trainloader) 280 | if not opt.silent: 281 | pbar = tqdm(total=opt.checkpointFreq) 282 | while opt.iteration <= opt.nIteration: 283 | if not opt.silent: 284 | pbar.update(1) 285 | ########################## Get Batch ############################# 286 | try: 287 | xLoadG, mLoadG = next(genData) 288 | except StopIteration: 289 | genData = iter(trainloader) 290 | xLoadG, mLoadG = next(genData) 291 | try: 292 | xLoadD, mLoadD = next(disData) 293 | except StopIteration: 294 | disData = iter(trainloader) 295 | xLoadD, mLoadD = next(disData) 296 | xData = xLoadG.to(device) 297 | mData = mLoadG.to(device) 298 | xReal = xLoadD.to(device) 299 | zData = torch.randn((xData.size(0), opt.nMasks, opt.nz, 1, 1), device=device) 300 | ########################## Reset Nets ############################ 301 | netEncM.zero_grad() 302 | netGenX.zero_grad() 303 | netDX.zero_grad() 304 | netEncM.train() 305 | netGenX.train() 306 | netDX.train() 307 | if opt.wrecZ > 0: 308 | netRecZ.zero_grad() 309 | netRecZ.train() 310 | dStep = (opt.iteration % opt.dStepFreq == 0) 311 | gStep = (opt.iteration % opt.gStepFreq == 0) 312 | ######################### AutoEncode X ######################### 313 | ''' 314 | Instead of sampling a region at each iteration, fake images for all regions are computed at each iteration. 315 | This allow to build an entirely generated image we can feed to the information conservation network instead of partially redrawn images. 316 | ''' 317 | if gStep: 318 | mEnc = netEncM(xData) 319 | hGen = netGenX(mEnc, zData) 320 | xGen = (hGen + ((1 - mEnc.unsqueeze(2)) * xData.unsqueeze(1))).view(hGen.size(0) * hGen.size(1), hGen.size(2), hGen.size(3), hGen.size(4)) 321 | dGen = netDX(xGen) 322 | lossG = - dGen.mean() 323 | if opt.wrecZ > 0: 324 | zRec = netRecZ(hGen.sum(1)) 325 | err_recZ = ((zData - zRec) * (zData - zRec)).mean() 326 | lossG += err_recZ * opt.wrecZ 327 | lossG.backward() 328 | optimizerEncM.step() 329 | optimizerGenX.step() 330 | if opt.wrecZ > 0: 331 | optimizerRecZ.step() 332 | if dStep: 333 | netDX.zero_grad() 334 | with torch.no_grad(): 335 | mEnc = netEncM(xData) 336 | hGen = netGenX(mEnc, zData) 337 | xGen = (hGen + ((1 - mEnc.unsqueeze(2)) * xData.unsqueeze(1))).view(hGen.size(0) * hGen.size(1), hGen.size(2), hGen.size(3), hGen.size(4)) 338 | dPosX = netDX(xReal) 339 | dNegX = netDX(xGen) 340 | err_dPosX = (-1 + dPosX) 341 | err_dNegX = (-1 - dNegX) 342 | err_dPosX = ((err_dPosX < 0).float() * err_dPosX).mean() 343 | err_dNegX = ((err_dNegX < 0).float() * err_dNegX).mean() 344 | (-err_dPosX - err_dNegX).backward() 345 | optimizerDX.step() 346 | opt.iteration += 1 347 | if opt.iteration % opt.checkpointFreq == 0: 348 | if not opt.silent: 349 | pbar.close() 350 | netEncM.eval() 351 | netGenX.eval() 352 | netDX.eval() 353 | if opt.wrecZ > 0: 354 | netRecZ.eval() 355 | with torch.no_grad(): 356 | mEnc_test = netEncM(x_test) 357 | out_X[:,1:,3] = mEnc_test.transpose(0,1).unsqueeze(2)*2-1 358 | out_X[:,1:,2] = ((out_X[:,1:,3] < 0).float() * -1) + (out_X[:,1:,3] > 0).float() 359 | out_X[:,1:,4] = (netGenX(mEnc_test, z_test) + ((1 - mEnc_test.unsqueeze(2)) * x_test.unsqueeze(1))).transpose(0,1) 360 | for k in range(opt.nMasks): 361 | for i in range(opt.nTest): 362 | zx_test = z_test.clone() 363 | zx_test[:, k] = zn_test[i] 364 | out_X[k, 1:, i+5] = netGenX(mEnc_test, zx_test)[:,k] + ((1 - mEnc_test[:,k:k+1]) * x_test) 365 | scoreAccTrain, scoreIoUTrain, minRegionSizeTrain = evaluate(netEncM, trainloader, device, opt.nMasks) 366 | scoreAccVal, scoreIoUVal, minRegionSizeVal = evaluate(netEncM, valloader, device, opt.nMasks) 367 | if not opt.silent: 368 | print("train:", scoreAccTrain, scoreIoUTrain) 369 | print("val:", scoreAccVal, scoreIoUVal) 370 | try: 371 | with open(os.path.join(opt.outf, 'train.dat'), 'a') as f: 372 | f.write(str(opt.iteration) + ' ' + str(scoreAccTrain) + ' ' + str(scoreIoUTrain) + '\n') 373 | except: 374 | print("Cannot save in train.dat") 375 | try: 376 | with open(os.path.join(opt.outf, 'val.dat'), 'a') as f: 377 | f.write(str(opt.iteration) + ' ' + str(scoreAccVal) + ' ' + str(scoreIoUVal) + '\n') 378 | except: 379 | print("Cannot save in val.dat") 380 | try: 381 | vutils.save_image(out_X.view(-1,opt.nx,opt.sizex, opt.sizex), os.path.join(opt.outf, "out_%05d.png" % opt.iteration), normalize=True, range=(-1,1), nrow=opt.nTest+5) 382 | except: 383 | print("Cannot save output") 384 | netEncM.zero_grad() 385 | netGenX.zero_grad() 386 | netDX.zero_grad() 387 | if opt.wrecZ > 0: 388 | netRecZ.zero_grad() 389 | if minRegionSizeTrain < opt.autoRestart and minRegionSizeVal < opt.autoRestart: 390 | print("Training appear to have collapsed.") 391 | if opt.iteration <= 7000: 392 | print("Reinitializing training.") 393 | netEncM = models._netEncM(sizex=opt.sizex, nIn=opt.nx, nMasks=opt.nMasks, nRes=opt.nResM, nf=opt.nfM, temperature=opt.temperature).to(device) 394 | netGenX = models._netGenX(sizex=opt.sizex, nOut=opt.nx, nc=opt.nz, nf=opt.nfX, nMasks=opt.nMasks, selfAtt=opt.useSelfAttG).to(device) 395 | netDX = models._resDiscriminator128(nIn=opt.nx, nf=opt.nfD, selfAtt=opt.useSelfAttD).to(device) 396 | netEncM.apply(weights_init_ortho) 397 | netGenX.apply(weights_init_ortho) 398 | netDX.apply(weights_init_ortho) 399 | optimizerEncM = torch.optim.Adam(netEncM.parameters(), lr=opt.lrM, betas=(0, 0.9), weight_decay=opt.wdecay, amsgrad=False) 400 | optimizerGenX = torch.optim.Adam(netGenX.parameters(), lr=opt.lrG, betas=(0, 0.9), amsgrad=False) 401 | optimizerDX = torch.optim.Adam(netDX.parameters(), lr=opt.lrD, betas=(0, 0.9), amsgrad=False) 402 | if opt.wrecZ > 0: 403 | netRecZ.apply(weights_init_ortho) 404 | optimizerRecZ = torch.optim.Adam(netRecZ.parameters(), lr=opt.lrZ, betas=(0, 0.9), amsgrad=False) 405 | if not opt.silent: 406 | pbar = tqdm(total=opt.checkpointFreq) 407 | opt.iteration = 0 408 | stateDic = {} 409 | continue 410 | stateDic = { 411 | 'netEncM': netEncM.state_dict(), 412 | 'netGenX': netGenX.state_dict(), 413 | 'netDX': netDX.state_dict(), 414 | 'optimizerEncM': optimizerEncM.state_dict(), 415 | 'optimizerGenX': optimizerGenX.state_dict(), 416 | 'optimizerDX': optimizerDX.state_dict(), 417 | 'options': opt, 418 | } 419 | if opt.wrecZ > 0: 420 | stateDic['netRecZ'] = netRecZ.state_dict() 421 | stateDic['optimizerRecZ'] = optimizerRecZ.state_dict() 422 | try: 423 | torch.save(stateDic, os.path.join(opt.outf, 'state_%05d.pth' % opt.iteration)) 424 | torch.save(opt, os.path.join(opt.outf, "options.pth")) 425 | except: 426 | print("Cannot save checkpoint") 427 | if opt.bestValIoU < scoreIoUVal: 428 | opt.bestValIoU = scoreIoUVal 429 | try: 430 | torch.save(stateDic, os.path.join(opt.outf, 'best.pth')) 431 | except: 432 | print("Cannot save best") 433 | if opt.clean and opt.iteration > opt.checkpointFreq: 434 | try: 435 | os.remove(os.path.join(opt.outf, 'state_%05d.pth' % (opt.iteration - opt.checkpointFreq))) 436 | except: 437 | pass 438 | if not opt.silent: 439 | pbar = tqdm(total=opt.checkpointFreq) 440 | netEncM.train() 441 | netGenX.train() 442 | netDX.train() 443 | if opt.wrecZ > 0: 444 | netRecZ.train() 445 | --------------------------------------------------------------------------------