├── .gitignore ├── README.md ├── TransNorm-poster.pdf ├── TransNorm-slide.pdf ├── data ├── image-clef │ ├── b_list.txt │ ├── c_list.txt │ ├── i_list.txt │ └── p_list.txt ├── office-home │ ├── Art.txt │ ├── Clipart.txt │ ├── Product.txt │ └── Real_World.txt ├── office │ ├── amazon_list.txt │ ├── dslr_list.txt │ └── webcam_list.txt └── visda-2017 │ ├── test_list.txt │ ├── train_list.txt │ └── validation_list.txt └── src ├── __init__.py ├── data_list.py ├── loss.py ├── lr_schedule.py ├── network.py ├── pre_process.py ├── resnet_tn.py ├── train_image.py └── trans_norm.py /.gitignore: -------------------------------------------------------------------------------- 1 | .idea/ 2 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # TransNorm 2 | Code release for ["Transferable Normalization: Towards Improving Transferability of Deep Neural Networks"](https://papers.nips.cc/paper/8470-transferable-normalization-towards-improving-transferability-of-deep-neural-networks) (NeurIPS 2019) 3 | 4 | ## Prerequisites 5 | - PyTorch >= 0.4.0 (with suitable CUDA and CuDNN version) 6 | - torchvision >= 0.2.1 7 | - Python3 8 | - Numpy 9 | - argparse 10 | - PIL 11 | 12 | ## Training 13 | ``` 14 | Office-31 15 | 16 | pythonn train_image.py --gpu_id id --net ResNet50 --dset office --test_interval 500 --s_dset_path ../data/office/amazon_list.txt --t_dset_path ../data/office/webcam_list.txt 17 | ``` 18 | ``` 19 | Office-Home 20 | 21 | pythonn train_image.py --gpu_id id --net ResNet50 --dset office-home --test_interval 2000 --s_dset_path ../data/office-home/Art.txt --t_dset_path ../data/office-home/Clipart.txt 22 | ``` 23 | ``` 24 | VisDA 2017 25 | 26 | pythonn train_image.py --gpu_id id --net ResNet50 --dset visda --test_interval 5000 --s_dset_path ../data/visda-2017/train_list.txt --t_dset_path ../data/visda-2017/validation_list.txt 27 | ``` 28 | ``` 29 | Image-clef 30 | 31 | pythonn train_image.py --gpu_id id --net ResNet50 --dset image-clef --test_interval 500 --s_dset_path ../data/image-clef/b_list.txt --t_dset_path ../data/image-clef/i_list.txt 32 | ``` 33 | 34 | ## Acknowledgement 35 | This code is implemented based on the published code of CDAN and BatchNorm, and it is our pleasure to acknowledge their contributions. 36 | CDAN (Conditional Adversarial Domain Adaptation) 37 | BatchNorm (Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift) 38 | 39 | ## Citation 40 | If you use this code for your research, please consider citing: 41 | ``` 42 | @inproceedings{Wang19TransNorm, 43 | title = {Transferable Normalization: Towards Improving Transferability of Deep Neural Networks}, 44 | author = {Wang, Ximei and Jin, Ying and Long, Mingsheng and Wang, Jianmin and Jordan, Michael I}, 45 | booktitle = {Advances in Neural Information Processing Systems 32}, 46 | year = {2019} 47 | } 48 | ``` 49 | 50 | ## Contact 51 | If you have any problem about our code, feel free to contact 52 | - wxm17@mails.tsinghua.edu.cn 53 | - longmingsheng@gmail.com 54 | 55 | or describe your problem in Issues. 56 | -------------------------------------------------------------------------------- /TransNorm-poster.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuml/TransNorm/713c2e28a0d8e73cac7aaf9b30b47e7654ac1939/TransNorm-poster.pdf -------------------------------------------------------------------------------- /TransNorm-slide.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuml/TransNorm/713c2e28a0d8e73cac7aaf9b30b47e7654ac1939/TransNorm-slide.pdf -------------------------------------------------------------------------------- /data/image-clef/b_list.txt: -------------------------------------------------------------------------------- 1 | /data/image-clef/b/252_0446.jpg 6 2 | /data/image-clef/b/252_0337.jpg 6 3 | /data/image-clef/b/252_0493.jpg 6 4 | /data/image-clef/b/252_0242.jpg 6 5 | /data/image-clef/b/252_0057.jpg 6 6 | /data/image-clef/b/252_0273.jpg 6 7 | /data/image-clef/b/252_0505.jpg 6 8 | /data/image-clef/b/252_0345.jpg 6 9 | /data/image-clef/b/252_0463.jpg 6 10 | /data/image-clef/b/252_0408.jpg 6 11 | /data/image-clef/b/252_0173.jpg 6 12 | /data/image-clef/b/252_0300.jpg 6 13 | /data/image-clef/b/252_0142.jpg 6 14 | /data/image-clef/b/252_0030.jpg 6 15 | /data/image-clef/b/252_0036.jpg 6 16 | /data/image-clef/b/252_0487.jpg 6 17 | /data/image-clef/b/252_0033.jpg 6 18 | /data/image-clef/b/252_0481.jpg 6 19 | /data/image-clef/b/252_0297.jpg 6 20 | /data/image-clef/b/252_0397.jpg 6 21 | /data/image-clef/b/252_0280.jpg 6 22 | /data/image-clef/b/252_0424.jpg 6 23 | /data/image-clef/b/252_0278.jpg 6 24 | /data/image-clef/b/252_0445.jpg 6 25 | /data/image-clef/b/252_0267.jpg 6 26 | /data/image-clef/b/252_0331.jpg 6 27 | /data/image-clef/b/252_0092.jpg 6 28 | /data/image-clef/b/252_0494.jpg 6 29 | /data/image-clef/b/252_0211.jpg 6 30 | /data/image-clef/b/252_0014.jpg 6 31 | /data/image-clef/b/252_0438.jpg 6 32 | /data/image-clef/b/252_0072.jpg 6 33 | /data/image-clef/b/252_0327.jpg 6 34 | /data/image-clef/b/252_0025.jpg 6 35 | /data/image-clef/b/252_0196.jpg 6 36 | /data/image-clef/b/252_0285.jpg 6 37 | /data/image-clef/b/252_0400.jpg 6 38 | /data/image-clef/b/252_0467.jpg 6 39 | /data/image-clef/b/252_0232.jpg 6 40 | /data/image-clef/b/252_0279.jpg 6 41 | /data/image-clef/b/252_0189.jpg 6 42 | /data/image-clef/b/252_0187.jpg 6 43 | /data/image-clef/b/252_0229.jpg 6 44 | /data/image-clef/b/252_0066.jpg 6 45 | /data/image-clef/b/252_0499.jpg 6 46 | /data/image-clef/b/252_0016.jpg 6 47 | /data/image-clef/b/252_0175.jpg 6 48 | /data/image-clef/b/252_0512.jpg 6 49 | /data/image-clef/b/252_0296.jpg 6 50 | /data/image-clef/b/252_0144.jpg 6 51 | /data/image-clef/b/99B047454CD9B6D811D0288BE087715E.jpg 9 52 | /data/image-clef/b/4368FC8E03F2A288ADF2DCDBD712E750.jpg 9 53 | /data/image-clef/b/954071A67971CBA89764EDB20428D8F3.jpg 9 54 | /data/image-clef/b/8EB65F199E94D875FFD6768F35710276.jpg 9 55 | /data/image-clef/b/A04FC61BCC99C49B353D39F7D471D554.jpg 9 56 | /data/image-clef/b/A4088A337FAB3ECA4D7520729FC56AEF.jpg 9 57 | /data/image-clef/b/A692A3E48919A104D3A706C94844A4C2.jpg 9 58 | /data/image-clef/b/7FAC9E56C4F8DBF4C968445000B7DFD2.jpg 9 59 | /data/image-clef/b/BCA5859E1E87F738CDE4E9FCC43616AD.jpg 9 60 | /data/image-clef/b/16128B2C344486D5B22CCB544A498D26.jpg 9 61 | /data/image-clef/b/68D2FB34573152F7E5E8569257C177B4.jpg 9 62 | /data/image-clef/b/934CDA1D8798ACC1F31B0C0994F1A254.jpg 9 63 | /data/image-clef/b/07B9E5E73C8EF79063FA07B3F52F2735.jpg 9 64 | /data/image-clef/b/6879DEF4F6D2339688FDD82DA2C85754.jpg 9 65 | /data/image-clef/b/10092B6598A5EAB2C52212C76B66636F.jpg 9 66 | /data/image-clef/b/30E1B08A10F380EF9AF1F2C54BC37F99.jpg 9 67 | /data/image-clef/b/5C3E621FBCACCF9DD0783EC9C48086AB.jpg 9 68 | /data/image-clef/b/996A4E7860E0E124D0E28B4624EF7A3E.jpg 9 69 | /data/image-clef/b/7A614107DF056752DCEB1884EB48F52E.jpg 9 70 | /data/image-clef/b/167F8C023E0564EA731D5AD4443DCC78.jpg 9 71 | /data/image-clef/b/5D7D2E837FC15A257C810B6F99E8E2C3.jpg 9 72 | /data/image-clef/b/EAADBBFFC051985B11BF51FEA90738DD.jpg 9 73 | /data/image-clef/b/FF6854B0B1F13AF2FD62A3744D95F890.jpg 9 74 | /data/image-clef/b/01624A6E5002E7A3DF9AC102D1EE025E.jpg 9 75 | /data/image-clef/b/CFA34381EA85F93404A0CB2BC291D659.jpg 9 76 | /data/image-clef/b/E068BF4E458356B9A18A106DE11DEB62.jpg 9 77 | /data/image-clef/b/EF1993AEEB6D084ED31B0F29B4D01119.jpg 9 78 | /data/image-clef/b/040AADC700F811DA31F02DB6C3B01403.jpg 9 79 | /data/image-clef/b/9120B69B673D10FFF15DE9306FB63E26.jpg 9 80 | /data/image-clef/b/5B7D32115CEF942A9E5C67D9CE59E5BA.jpg 9 81 | /data/image-clef/b/4CDACA16FEB95BFA24FCC83D7AADEB51.jpg 9 82 | /data/image-clef/b/111002CDE28DE7FC6EC8105C0F6F1913.jpg 9 83 | /data/image-clef/b/7812BB4418847E19B6863BE7D93FC516.jpg 9 84 | /data/image-clef/b/2547D105CAEB73242F8342EE9AA0EB10.jpg 9 85 | /data/image-clef/b/1519B34721FF9BF0E289C4B92FA6DDE8.jpg 9 86 | /data/image-clef/b/C8579112A830E3894B23DD259CA6F651.jpg 9 87 | /data/image-clef/b/371105E72FC205275879A002EC3CBA91.jpg 9 88 | /data/image-clef/b/446C104E4DE6AD474C82AFFC25D97CC7.jpg 9 89 | /data/image-clef/b/4335FEB13FB8E95B80825CBC367B74A6.jpg 9 90 | /data/image-clef/b/4C543ADD81590F54708E9EE604718661.jpg 9 91 | /data/image-clef/b/A63E71DFFB82DDA6134F95547978D5A6.jpg 9 92 | /data/image-clef/b/0BD2328961DD8A5777BC756044CC41CE.jpg 9 93 | /data/image-clef/b/CE7003F44D239819AC24BB18D57EAF36.jpg 9 94 | /data/image-clef/b/C946D7BC36A1D1A6BA5B362C4B317B0B.jpg 9 95 | /data/image-clef/b/E3BE7EAE643951A8949B71552B12DD3C.jpg 9 96 | /data/image-clef/b/765653A4C9F07D2258700ED49854152E.jpg 9 97 | /data/image-clef/b/F2F3C096D8D349605A76EBE3B189507C.jpg 9 98 | /data/image-clef/b/2939ED3DAB0021BFACF058D4EB72739E.jpg 9 99 | /data/image-clef/b/78B37D75172C8C1F40C9B8209D9E57D2.jpg 9 100 | /data/image-clef/b/2BF59300B51BFF87A9F920E7D1EF2363.jpg 9 101 | /data/image-clef/b/E44C9A35C92B27D3F812608DE6CA910F.jpg 7 102 | /data/image-clef/b/9B64A10D9D3F0D8DDF0A4FD6B620F793.jpg 7 103 | /data/image-clef/b/016E08E303ACBDF596B0C071830D9D0E.jpg 7 104 | /data/image-clef/b/019B54A87F8663382B80E9EB5F11ECE6.jpg 7 105 | /data/image-clef/b/14706E0F6C0A886F93BDC4564D9FCF1C.jpg 7 106 | /data/image-clef/b/2993174C7CD5AFF712DDDCB1DD1F5F05.jpg 7 107 | /data/image-clef/b/1D284A29CD3A93D678C3F43A7C1240D0.jpg 7 108 | /data/image-clef/b/2EBBBE60D95063CBC9500076F91B1414.jpg 7 109 | /data/image-clef/b/A099C89E07064CB065A200ED5A56AA3D.jpg 7 110 | /data/image-clef/b/3574F45BD92A71A04A51302BBA3076C6.jpg 7 111 | /data/image-clef/b/6FD717560C67FCD1A8D69F246CDC1DBF.jpg 7 112 | /data/image-clef/b/5DA4CB45E851C166D7405927602BC592.jpg 7 113 | /data/image-clef/b/51147F65309C1B9329152EA4DFD1E7EF.jpg 7 114 | /data/image-clef/b/4EAD0040169FB171151B987CF678C89C.jpg 7 115 | /data/image-clef/b/BDDCDA3C43D1FBE339830675EE790BC4.jpg 7 116 | /data/image-clef/b/D93244D2E8D5FE0B0203C7E3CF032D8C.jpg 7 117 | /data/image-clef/b/665B2EA7D97C3ECD5961CD787B3E4B10.jpg 7 118 | /data/image-clef/b/44AF4192DB14121B9607E40F45852D3F.jpg 7 119 | /data/image-clef/b/40C049DCD2D6E864164A0FEF468DD27E.jpg 7 120 | /data/image-clef/b/1E8B1161C3248FBF8C8B4E2C193DBEA5.jpg 7 121 | /data/image-clef/b/046AE64BF285C34A173C93896F9201B7.jpg 7 122 | /data/image-clef/b/BF8881854887B688AE2552853B06634D.jpg 7 123 | /data/image-clef/b/D347B5C3B30BE0BB5DF85C17CEC9026A.jpg 7 124 | /data/image-clef/b/2E3EF19FEB17FB00C6EE6A6FFE9DA084.jpg 7 125 | /data/image-clef/b/C5DAC51DD6730DD1D8B65CA3F4260F17.jpg 7 126 | /data/image-clef/b/5CAC03956E4F77658D31A427918AB441.jpg 7 127 | /data/image-clef/b/0C64DF97C1F7D93798EE7AC39C1C5DB6.jpg 7 128 | /data/image-clef/b/FD03B59B87DA6912FAEE634B6745AAB0.jpg 7 129 | /data/image-clef/b/FDD66506D81871A8536C27563483C4A9.jpg 7 130 | /data/image-clef/b/D208B7A14FB2CC965D2D27D72AB0F7B6.jpg 7 131 | /data/image-clef/b/8E5E8683D65BB32C27556F1A92484C06.jpg 7 132 | /data/image-clef/b/2E182D5D0084A990BB181D029FECB134.jpg 7 133 | /data/image-clef/b/5D68FA5DA23492AD102E4C51D751E0C5.jpg 7 134 | /data/image-clef/b/757B031495A588F1288D1484103ABEF7.jpg 7 135 | /data/image-clef/b/A2953E5DBEA8844396FA196A136A443A.jpg 7 136 | /data/image-clef/b/187585E2FA471A9A3110E2E49DC23D89.jpg 7 137 | /data/image-clef/b/06176B915EDED374DD9538A26C9355AF.jpg 7 138 | /data/image-clef/b/C46892BD2F5F640D094D003966E47198.jpg 7 139 | /data/image-clef/b/890AB1D52F11EA1F7565D6EB22E03160.jpg 7 140 | /data/image-clef/b/4E5A38B53C9ECDB70994B82D0EE24324.jpg 7 141 | /data/image-clef/b/5CBCD72CAF98C2F10EE428C5A41095F3.jpg 7 142 | /data/image-clef/b/5E1D3F56E8620456A323EB3DFA28FA98.jpg 7 143 | /data/image-clef/b/79A4DB5AD3C4319B030C41041C1CC772.jpg 7 144 | /data/image-clef/b/399A73127E633BE4CF615585D1100EDB.jpg 7 145 | /data/image-clef/b/93A4AE80A27C7C57F09B81C82144A5AB.jpg 7 146 | /data/image-clef/b/C9C938D6C83343D26920F4F19F194390.jpg 7 147 | /data/image-clef/b/E59FF601F1D61841567C57D146D3630B.jpg 7 148 | /data/image-clef/b/EBEC99772324C0FCE5D5313F7109D6BA.jpg 7 149 | /data/image-clef/b/D80939E4CFDB90FBBD5095F6162FA29B.jpg 7 150 | /data/image-clef/b/0F1910541E4594BF6AE30CB4104FFB00.jpg 7 151 | /data/image-clef/b/303A184971074E3B4E2A8F049A5E4FE9.jpg 8 152 | /data/image-clef/b/897D3867A3683B2C299F1128AC4DA9EC.jpg 8 153 | /data/image-clef/b/9032A8B30A6BF5C274E3EBBF49BDA72D.jpg 8 154 | /data/image-clef/b/174BBA9C9AEEC116C8CD8263692FFB12.jpg 8 155 | /data/image-clef/b/EF10E0D4A505AF42D51C62301C811B1D.jpg 8 156 | /data/image-clef/b/DFF071F32258BE98D31E0293E0B42F52.jpg 8 157 | /data/image-clef/b/DF36EC86BBDBF157ECC9F71DA41F492F.jpg 8 158 | /data/image-clef/b/F7722CEC2C7F49DCF0300E9089FBE550.jpg 8 159 | /data/image-clef/b/9CB03D84405DA70A405FCD8555645736.jpg 8 160 | /data/image-clef/b/E4475F5F4123E77D2E64F11187269E0B.jpg 8 161 | /data/image-clef/b/00EFC6FC24740AD02D1322AB2847424B.jpg 8 162 | /data/image-clef/b/FADB6C2AB826CBFB2464734E9B28E0C6.jpg 8 163 | /data/image-clef/b/E865F0CCB33DC97EB24BC9FA9CC66F3C.jpg 8 164 | /data/image-clef/b/37FFF33C040CD9B023F2B0C739346584.jpg 8 165 | /data/image-clef/b/B0BE1146B7B543C5CC8BF636EBE73ABD.jpg 8 166 | /data/image-clef/b/CF2C04C18ACA69DEE41E4AEB3AC40F66.jpg 8 167 | /data/image-clef/b/2B70CCF18FF865B58AA4979943E73A4A.jpg 8 168 | /data/image-clef/b/AEEBA1619227AD5E712D167CB3A76560.jpg 8 169 | /data/image-clef/b/C69B2009A9C540609C3DFB527D433D37.jpg 8 170 | /data/image-clef/b/0227FDEC0640B5B4B8A2622807186F9D.jpg 8 171 | /data/image-clef/b/03F7E9713302C8B0E06130D062325B91.jpg 8 172 | /data/image-clef/b/D2EBBD22BEC2B5191E7C9EDC408F41F7.jpg 8 173 | /data/image-clef/b/596D7BF182188DED40B7CD7884BACF52.jpg 8 174 | /data/image-clef/b/9B5359845473A61E01EB975FBD724B22.jpg 8 175 | /data/image-clef/b/BF9E2B9D99F713CE4C09938D85182D45.jpg 8 176 | /data/image-clef/b/6E3075911EDF41B0F5E7B77353575DE1.jpg 8 177 | /data/image-clef/b/A236F01F2E14CE72392A541B83ED6300.jpg 8 178 | /data/image-clef/b/0C6F1DD934D222BD7F61080CB8D54476.jpg 8 179 | /data/image-clef/b/C73821398958DC39961B67106D563AD1.jpg 8 180 | /data/image-clef/b/8B5500DAF0401C20CAF76BCA013CA965.jpg 8 181 | /data/image-clef/b/AF5697859340324FEFB037BA79E791DE.jpg 8 182 | /data/image-clef/b/942C4ECC3AA6CAB343D2B3D6D6587536.jpg 8 183 | /data/image-clef/b/C326C13E0E4848D3F9A0398706951D18.jpg 8 184 | /data/image-clef/b/910DBD0C045BFE8611CF317C0C60DC43.jpg 8 185 | /data/image-clef/b/0843F6ECD367B7817B4700ED4B1095FF.jpg 8 186 | /data/image-clef/b/CB3495A971A1AC9B6326C24A205A1FB9.jpg 8 187 | /data/image-clef/b/3633025B7252C562E88C3AAAEF390367.jpg 8 188 | /data/image-clef/b/B5B0D85CCCFBEA76A3CB33C2396B183E.jpg 8 189 | /data/image-clef/b/0755FF97B7389BCB05CA783DED6CE38F.jpg 8 190 | /data/image-clef/b/6202D0BBD5CCF3A45F72983790E5FDCD.jpg 8 191 | /data/image-clef/b/8D5E4FADA5D6496B225965569C3A6A6E.jpg 8 192 | /data/image-clef/b/936A95DD2C9500B38DCBF4664E4B999C.jpg 8 193 | /data/image-clef/b/3F1C070BABD316E8E2CAC4CF5E5A3162.jpg 8 194 | /data/image-clef/b/BCDD2121DDFB641DCF219A42FCD226EF.jpg 8 195 | /data/image-clef/b/062A86011D7D4462D7A1D910DE5406CC.jpg 8 196 | /data/image-clef/b/28909B95CF0342F0A6146E69779B4C79.jpg 8 197 | /data/image-clef/b/0833521B6398D33469B12C52131E1FF9.jpg 8 198 | /data/image-clef/b/0F19F4F4B449AA3DC30EC5C5080931FE.jpg 8 199 | /data/image-clef/b/A10F8941898D7FDAF1250AD86517D160.jpg 8 200 | /data/image-clef/b/D564E45383C6AE04BA53E5867DA81BCE.jpg 8 201 | /data/image-clef/b/1DA9F95F105A84908AA2E6138036EADB.jpg 2 202 | /data/image-clef/b/C3C49A4123224889DAEACDB04036AFF9.jpg 2 203 | /data/image-clef/b/3198FE1A6CE6ACD0E9F05765CDD888AC.jpg 2 204 | /data/image-clef/b/95BD5D17B8EE9A5B0B7140AF3D3EE155.jpg 2 205 | /data/image-clef/b/CC33B67CEAB260C70B484FD728D77A11.jpg 2 206 | /data/image-clef/b/95F124A5CFD54F6C6156257869B902B3.jpg 2 207 | /data/image-clef/b/461CBE2E4490B1126D75BF5774BF7E2B.jpg 2 208 | /data/image-clef/b/26DEE9250A7B866F49301B50BCE4A8D9.jpg 2 209 | /data/image-clef/b/5F7090EE7DB242C7808CFAE3C158E2CA.jpg 2 210 | /data/image-clef/b/2C914AD42D56193E456E8C5C4F606AA8.jpg 2 211 | /data/image-clef/b/0D4C4128FB03C80B4A70762B9F730BE0.jpg 2 212 | /data/image-clef/b/943EAF8EE6F3DAD93C350D7334E5D43E.jpg 2 213 | /data/image-clef/b/8E71498075A52224B9DB53DC5AB9E03C.jpg 2 214 | /data/image-clef/b/C3F566E1F64CDC2E5E39D8DB53A9A92F.jpg 2 215 | /data/image-clef/b/5513CAD5A526CAA15FF2D7858088EC7A.jpg 2 216 | /data/image-clef/b/8DE0CA1C66B13C3422D2510F5741A7CF.jpg 2 217 | /data/image-clef/b/2D2AF15FD593F6831AC50A9F9D2EC9EF.jpg 2 218 | /data/image-clef/b/AC866E2E87C79A4C6DDBBF2957B60641.jpg 2 219 | /data/image-clef/b/F8454BD5C7267E9348BE34B46DAF9C3E.jpg 2 220 | /data/image-clef/b/A806021E59957A157359258F1B0FCCFD.jpg 2 221 | /data/image-clef/b/570734E61A79E0DD7DAA759AA16E84CB.jpg 2 222 | /data/image-clef/b/37E972099EBA6B295EA443DA17288B27.jpg 2 223 | /data/image-clef/b/76F78EAC76E1E476ABECBE4E6A55A321.jpg 2 224 | /data/image-clef/b/5453A1F47A601A8D0BF3F4741BDF3DFA.jpg 2 225 | /data/image-clef/b/161E937F0769F6018D4A2DE89A94ED72.jpg 2 226 | /data/image-clef/b/C256C06CD8FE55EA7D06DEAA60A8F325.jpg 2 227 | /data/image-clef/b/535C060A2B6BF625B3F63FEDAB9FC4ED.jpg 2 228 | /data/image-clef/b/EA0256F7A672A1253A5720B0F480B1D7.jpg 2 229 | /data/image-clef/b/88816EF105060A2840E8D0B9818BE02D.jpg 2 230 | /data/image-clef/b/2F812EE05204B95D035679AE36260953.jpg 2 231 | /data/image-clef/b/5D2DD16038474585420053AF925FDC61.jpg 2 232 | /data/image-clef/b/95A176181338C3F6609D508147F05CC0.jpg 2 233 | /data/image-clef/b/A05BB25301885E2CBBFB48B684EFF4C3.jpg 2 234 | /data/image-clef/b/0E3763A7051609ED45055CE2AA187B56.jpg 2 235 | /data/image-clef/b/AFEA94305B7BAE3D6FDC3AEEAF4A5B8D.jpg 2 236 | /data/image-clef/b/0367235F822FB39337329ADB8431D7A7.jpg 2 237 | /data/image-clef/b/C3896EDD27F601950AEB5CF67F4E7CD4.jpg 2 238 | /data/image-clef/b/8D57C4BB57E86CC5E547A82D88433255.jpg 2 239 | /data/image-clef/b/E92D3FAEC1DB5564E9B8B37674482A4D.jpg 2 240 | /data/image-clef/b/F9AB469CCB792CBFB072C6AAF4819943.jpg 2 241 | /data/image-clef/b/16FC961DBAE75E0EE096F6FAF7832DA3.jpg 2 242 | /data/image-clef/b/4A583BE465941467859B35D5E3D99BEC.jpg 2 243 | /data/image-clef/b/0130814315084D9CD4F6093CE25041FB.jpg 2 244 | /data/image-clef/b/8873695BFD8E3D2393439161466588B0.jpg 2 245 | /data/image-clef/b/5E5FED6EDA0768E31CD136A73210D9AA.jpg 2 246 | /data/image-clef/b/06343E0AE2FF16BAC012CA8298EB7C37.jpg 2 247 | /data/image-clef/b/02971601D6B855172D5D81615234BFFF.jpg 2 248 | /data/image-clef/b/9BCD41863FCC0699EA960611ECB3D9B1.jpg 2 249 | /data/image-clef/b/1B88B667A17F9BE3041276D4F1982296.jpg 2 250 | /data/image-clef/b/FBDA9B9254483E1060FD2CE0E819DEAA.jpg 2 251 | /data/image-clef/b/ADC96D0263E181615FE9D491CA4BD721.jpg 10 252 | /data/image-clef/b/596FFF97CCADE4C6D56A7F86B7ADC4AA.jpg 10 253 | /data/image-clef/b/AF59B7AF2928BDAC7DA78EA4DE7E789F.jpg 10 254 | /data/image-clef/b/B2387134FDBA1728EE31D8DBA5F929A6.jpg 10 255 | /data/image-clef/b/0A36A7B9A724B01A5E98E90210E224E0.jpg 10 256 | /data/image-clef/b/D4226310F8543F66BE53820C40697F2D.jpg 10 257 | /data/image-clef/b/A19462EE3C53688CEA99DEEE65B2CE34.jpg 10 258 | /data/image-clef/b/6144F29AFFEC5C70D42F4E85A7C145E8.jpg 10 259 | /data/image-clef/b/BEDF5F6174AE0035B91BC442AB4C5442.jpg 10 260 | /data/image-clef/b/BE202CAF702644FBB2958ACF4E35A8BE.jpg 10 261 | /data/image-clef/b/04FACB943377EDE55F37678DBF85B6FD.jpg 10 262 | /data/image-clef/b/086464B2C7F1CA924457B741F7B010C4.jpg 10 263 | /data/image-clef/b/D21F9071E3A393C47E4CA26783B81F15.jpg 10 264 | /data/image-clef/b/4407233DC2E2EE980AC3A42B729EADA4.jpg 10 265 | /data/image-clef/b/568BD2B97C5A8F14F683FABAE41FBF66.jpg 10 266 | /data/image-clef/b/009D596B8E08DFCF4884A9E266CBE6F3.jpg 10 267 | /data/image-clef/b/11BBBF5DB04DE5F6C398EE8EA358357F.jpg 10 268 | /data/image-clef/b/DFB46188BA5754B86A5DC9A0C40D4888.jpg 10 269 | /data/image-clef/b/683DC3083CB96BD64836EA29F9BB344A.jpg 10 270 | /data/image-clef/b/7F5595160FCDE0286A91D43F1B84D851.jpg 10 271 | /data/image-clef/b/1DC986B87E0FB98BC070E5700289DABF.jpg 10 272 | /data/image-clef/b/2068B6BCF55638C892A00A96E781A1ED.jpg 10 273 | /data/image-clef/b/53EE4E1C64548B33EF93C44EC14411A7.jpg 10 274 | /data/image-clef/b/E5DD48CF34AD63DAEDD82BF0802771AD.jpg 10 275 | /data/image-clef/b/B6C7DD34EC67078C780ED311B2F69F2A.jpg 10 276 | /data/image-clef/b/1F1FEB24B5B015089952F97940996505.jpg 10 277 | /data/image-clef/b/9443B8E8F682CB83C6775904E6347E7F.jpg 10 278 | /data/image-clef/b/4BD66FAAC250C47F90216B31D38FDAFD.jpg 10 279 | /data/image-clef/b/A1C06B307C726981112446BBC2440A88.jpg 10 280 | /data/image-clef/b/5E9EE691E2073B77B302D9B88633FD24.jpg 10 281 | /data/image-clef/b/C15001D8FA6E8134415BF4C6F9CCD686.jpg 10 282 | /data/image-clef/b/C7764F2DE2E1C19855C41F9D34EE9F97.jpg 10 283 | /data/image-clef/b/E651FFD6C847D1DAD806AA7AAC10D5EE.jpg 10 284 | /data/image-clef/b/28F885B7E338D2EC76E4223D65E5600C.jpg 10 285 | /data/image-clef/b/B39D78380CFFCE66F619F886CDF35B00.jpg 10 286 | /data/image-clef/b/64709DAC7F8F19B5A159D6688D9C1C4C.jpg 10 287 | /data/image-clef/b/9D9061A2750C82A87F05429E0FDDB982.jpg 10 288 | /data/image-clef/b/3DEF7317699E60DEAE12069826FCBAC5.jpg 10 289 | /data/image-clef/b/598AEB6C824EA77ED116588E4A66718D.jpg 10 290 | /data/image-clef/b/C7E185C1A43618E9D4555106C4CDAEA2.jpg 10 291 | /data/image-clef/b/DE32BB1C556018C204BCF88792FF26D3.jpg 10 292 | /data/image-clef/b/36105C43E7BF401AF4C83AD609BC88F4.jpg 10 293 | /data/image-clef/b/3C003BB2F384B6E7CB247B15C029C18B.jpg 10 294 | /data/image-clef/b/2376DEF9BC3D8361D1C2D945FAB837A0.jpg 10 295 | /data/image-clef/b/085902158622DB7E8F473263FF3DF9E7.jpg 10 296 | /data/image-clef/b/68B1481A01ABDDA278E17FF02C124FCC.jpg 10 297 | /data/image-clef/b/3ADDD2423A59963FE4A61F5904DE8557.jpg 10 298 | /data/image-clef/b/786218FB02044550259D737210398787.jpg 10 299 | /data/image-clef/b/E2F3BA7D4BD5FBF8E58CF3E5DB4338E6.jpg 10 300 | /data/image-clef/b/1DAE745F1341E3005CA5E575AA688EEC.jpg 10 301 | /data/image-clef/b/9453C5315949BFF5E0EE9C9A0592A740.jpg 1 302 | /data/image-clef/b/6B14D3B3308C0ABED6C0EECD1A8204D6.jpg 1 303 | /data/image-clef/b/20D3C7E0E7D94B1B499CEA7EB0301491.jpg 1 304 | /data/image-clef/b/D1C9313072151C95F0AA44C0E4BA9736.jpg 1 305 | /data/image-clef/b/22B33A4BB6D5A58B0539C9AB825D8A8E.jpg 1 306 | /data/image-clef/b/5DE6ADD369366694C47B4C3E8899FF18.jpg 1 307 | /data/image-clef/b/A60F1AC1F67D99F8A98DD9024AA3F152.jpg 1 308 | /data/image-clef/b/F1AB4EF686776E64E172B26D2CEF767D.jpg 1 309 | /data/image-clef/b/AFA4A5B756A09DCC41D1504A0909088E.jpg 1 310 | /data/image-clef/b/98BB12769E4C068CFAAB64E918D4F225.jpg 1 311 | /data/image-clef/b/907AFED2066568F94F93E6B0D56D6FD0.jpg 1 312 | /data/image-clef/b/C747E2B2C1EC047F1C8046F1E1AE91BC.jpg 1 313 | /data/image-clef/b/F424A7D73A0BAC6C6AA1B9B8F950B5ED.jpg 1 314 | /data/image-clef/b/D04DAD8F9D392EA5630A47AF1B2D1779.jpg 1 315 | /data/image-clef/b/7FAB94B2111213A776CAA0FCA99AF1F6.jpg 1 316 | /data/image-clef/b/4A58CC87C8DD2AAE688E155CE8755452.jpg 1 317 | /data/image-clef/b/566659F4593FD6F9AB411F740EEFD905.jpg 1 318 | /data/image-clef/b/76AAF2650B393E7A3B08F2988211054C.jpg 1 319 | /data/image-clef/b/45FA1628256DF18227854492FB02AAA2.jpg 1 320 | /data/image-clef/b/CA96AE286CDC5A937D9493E004FBD9AB.jpg 1 321 | /data/image-clef/b/0D33206B4C64086D4E957E172C9D4FE6.jpg 1 322 | /data/image-clef/b/57429E195F95DD9541E3E657C77146B4.jpg 1 323 | /data/image-clef/b/13A3E38BA7D48C0CB1D8C33E3CF3F894.jpg 1 324 | /data/image-clef/b/036CCB4FC76BAEF206B5449F5656466A.jpg 1 325 | /data/image-clef/b/35C01806318A3DF97A3CBC919A2B61E1.jpg 1 326 | /data/image-clef/b/9BC12726749D602634F7949CE6001EE9.jpg 1 327 | /data/image-clef/b/431C61C7FBD08E5E8F8164355467C746.jpg 1 328 | /data/image-clef/b/EB6C6B1B61CC73355284A942C79A5FB3.jpg 1 329 | /data/image-clef/b/D168AEFBDEF1E7B96297AAB4F213A991.jpg 1 330 | /data/image-clef/b/6CDF9D50D0F1168FED0788A2A955D754.jpg 1 331 | /data/image-clef/b/0EE0504FFB3B686D2E9B4CBFBC4E726D.jpg 1 332 | /data/image-clef/b/365FD760A1CB66D7A7DC7D8630B4BF76.jpg 1 333 | /data/image-clef/b/A566F2968A534836141295685294BAC5.jpg 1 334 | /data/image-clef/b/3317C84412D8247C7ACFA6ECCA1F4732.jpg 1 335 | /data/image-clef/b/A58B2BEF5B2EFFBAC16DD6BAA0B9D133.jpg 1 336 | /data/image-clef/b/5A4CE68844E38D3F53CC2D921585CF21.jpg 1 337 | /data/image-clef/b/5280C73955AA328043F283D7E4AED17E.jpg 1 338 | /data/image-clef/b/11C71EA217F8AB294345CC7D070CA6A9.jpg 1 339 | /data/image-clef/b/03641633A7AE916AC692F4F86E9F6358.jpg 1 340 | /data/image-clef/b/D2C0AADC00688164B9D2084425BA6429.jpg 1 341 | /data/image-clef/b/5E674690B23F473EBCD64C430307E85F.jpg 1 342 | /data/image-clef/b/A3CDC8101E8164F7E5C3D8608F97760A.jpg 1 343 | /data/image-clef/b/18906D40FE8F1F0D6E9E90397A77E681.jpg 1 344 | /data/image-clef/b/A5951C7CE55D44D1D7983675C8E66076.jpg 1 345 | /data/image-clef/b/9A7E2D2853F2CBBF65FDA0AD0EA186BF.jpg 1 346 | /data/image-clef/b/8BFED687E998CC76FB15ABC222B549E0.jpg 1 347 | /data/image-clef/b/9B62E39749832D4D081558F1DBEA1A54.jpg 1 348 | /data/image-clef/b/06A0E6EB6E2A6CEDE167D56124F42D3B.jpg 1 349 | /data/image-clef/b/E2FBA63A04C5C623EC946420D69FC712.jpg 1 350 | /data/image-clef/b/18575192544A1997E2771E096B3B59AF.jpg 1 351 | /data/image-clef/b/4BBC9E1799C77EBE97CDB3A9C2A6A0F6.jpg 11 352 | /data/image-clef/b/29E875A1614ACAB4FEA4FC35D4F53874.jpg 11 353 | /data/image-clef/b/EDA3CCF6C1650A0033E65F7F85C3E320.jpg 11 354 | /data/image-clef/b/AEEC33BD87BCF638A90024C57ECFF976.jpg 11 355 | /data/image-clef/b/B874B113808639835BB69389B473C25F.jpg 11 356 | /data/image-clef/b/BD67EAB839C733091BF4D5EFA00BAF53.jpg 11 357 | /data/image-clef/b/347A65B54C8634ECA5DB93646B9BD593.jpg 11 358 | /data/image-clef/b/C845EA4BF5699C6FC9861C3239ED3521.jpg 11 359 | /data/image-clef/b/5EF40468FF1F809ABAA073FAF202DECE.jpg 11 360 | /data/image-clef/b/830B37B1BF68AC6EBE88172583EC051C.jpg 11 361 | /data/image-clef/b/02D06D9DB1DF35626E74CFFFFDC1D924.jpg 11 362 | /data/image-clef/b/6E8738180B3E92989069E424A0F2E821.jpg 11 363 | /data/image-clef/b/60EFE50F000FE800C88C49C6B7BA78AE.jpg 11 364 | /data/image-clef/b/BE59980E6EA01751AC9D2528F6B4E3CE.jpg 11 365 | /data/image-clef/b/4AE44E88B0D3EB56168844D35E9512E1.jpg 11 366 | /data/image-clef/b/43D91B6329EB66B10A48DEB2D2ECE5DB.jpg 11 367 | /data/image-clef/b/F7D7EDC248D40404B3779BD8B1F528C2.jpg 11 368 | /data/image-clef/b/EA091E5439B0432B2784BDF35CEE4355.jpg 11 369 | /data/image-clef/b/1DFFAAA472A5EB0DF80D6B9E39D75D11.jpg 11 370 | /data/image-clef/b/D59FFC521FEC8E220A741312ACFE07F9.jpg 11 371 | /data/image-clef/b/3636B1978F58F9610EABCEB1932558D1.jpg 11 372 | /data/image-clef/b/B3670F67E80DACFDE64B3D90435389F6.jpg 11 373 | /data/image-clef/b/47963CB2B8B734EA2106C8D5AD079B30.jpg 11 374 | /data/image-clef/b/4A105B56BF1CDF4C63361E8A28709004.jpg 11 375 | /data/image-clef/b/24931A873672F774CC3D9C042DED63C7.jpg 11 376 | /data/image-clef/b/C868CCB253B127B4734D8501AD9F47C6.jpg 11 377 | /data/image-clef/b/78B752D6A3A8FA6BD555049BEEDC329F.jpg 11 378 | /data/image-clef/b/D5714A245ABC39F3D2F32DFACD5062CA.jpg 11 379 | /data/image-clef/b/B08049B07C47E849CAE17BA138A377F9.jpg 11 380 | /data/image-clef/b/EA475C1E5432E4DEA3E76C2EFAF99E37.jpg 11 381 | /data/image-clef/b/184A89BA4F190FA4AF48A29A0542A415.jpg 11 382 | /data/image-clef/b/53FC876F8EE34EAFAF11D73FBFA9EC1A.jpg 11 383 | /data/image-clef/b/39B8649F0687BB45ABFAD9A8081EA7C0.jpg 11 384 | /data/image-clef/b/A052ECA2821412200310D413D537082C.jpg 11 385 | /data/image-clef/b/3A020B73ED69802A175A6C83153A552B.jpg 11 386 | /data/image-clef/b/A17B141138A1459E0A8160B7658DA72F.jpg 11 387 | /data/image-clef/b/2EF970002819A676E1F31BCAA0DFB798.jpg 11 388 | /data/image-clef/b/54597E7B450CF9F28EF72B6AF595E8F3.jpg 11 389 | /data/image-clef/b/7003CC063E5B011E284CC4654119738A.jpg 11 390 | /data/image-clef/b/A9D710641FBA1E9CCEADD93DD5EAF80C.jpg 11 391 | /data/image-clef/b/2791E6092748248C63C70FBC5FB9F8DE.jpg 11 392 | /data/image-clef/b/69A926F25C78E8DB02CCA5BB6483A63F.jpg 11 393 | /data/image-clef/b/CCB24C9F1F9475243D20F69406B36ADC.jpg 11 394 | /data/image-clef/b/2D55EA21C405EF4E9B1B38D84EEFE1F6.jpg 11 395 | /data/image-clef/b/77517FC7561F32D5120FD1CFA4BA5A51.jpg 11 396 | /data/image-clef/b/A24468CDF86147584D240FF17517F4C4.jpg 11 397 | /data/image-clef/b/E62C4F3C9887B98E398F2F54CE4379C1.jpg 11 398 | /data/image-clef/b/16AAE9074F5C00F9615C2C6A705E8513.jpg 11 399 | /data/image-clef/b/AF195E97A0B7A1CB3C144D723FA5A16F.jpg 11 400 | /data/image-clef/b/409B9D974570529C2F089BF27850AA99.jpg 11 401 | /data/image-clef/b/74930C08A2D258C3AC15FEE7FB1F624B.jpg 5 402 | /data/image-clef/b/24547E5BE40D231A049CFC56DE2ABF5F.jpg 5 403 | /data/image-clef/b/683FB74ADD52CFABEA685F6DC74EE7C9.jpg 5 404 | /data/image-clef/b/06DCB8E35A75236B1468ACF669D9FEC9.jpg 5 405 | /data/image-clef/b/C897A37C845E34312B5D71CC821D0B68.jpg 5 406 | /data/image-clef/b/21A81279C43ABAA217DB5FC4FFC752BF.jpg 5 407 | /data/image-clef/b/7548A8A889828B4C5C3268891AB60CAF.jpg 5 408 | /data/image-clef/b/2676F53BB1434E7F9707FA6E2624FD4B.jpg 5 409 | /data/image-clef/b/A0000F9AD52E520510F524676E6660D6.jpg 5 410 | /data/image-clef/b/A12E1F7F294F3C2BDFD63AC2271FE73F.jpg 5 411 | /data/image-clef/b/48A1252DBF7C94311ADC01F7DBF2AFAC.jpg 5 412 | /data/image-clef/b/DC6E7F8458FDB4DCB18FD008166DB0D2.jpg 5 413 | /data/image-clef/b/2037016AA33095757AE76833449D6C7B.jpg 5 414 | /data/image-clef/b/B69C8086ED89805885ECD2413B8BD67C.jpg 5 415 | /data/image-clef/b/559056179A304125379DC520E3B46CB4.jpg 5 416 | /data/image-clef/b/822E14FB3EC8BCB4280E90D10A5D1D96.jpg 5 417 | /data/image-clef/b/AFE2A7F8CDAD296A3BCF06CF2448645E.jpg 5 418 | /data/image-clef/b/D34E5483FF07167BAA9FD039B57A0429.jpg 5 419 | /data/image-clef/b/040050435E808D9336DB106741F5AC4E.jpg 5 420 | /data/image-clef/b/1D0BEC676E3B784D975D5A13E557FCF7.jpg 5 421 | /data/image-clef/b/206A8B6699A93818F0E87BC14FDDD781.jpg 5 422 | /data/image-clef/b/1E25189101FB8A7CB582396126180F79.jpg 5 423 | /data/image-clef/b/22D94AB94209F9657A9BE5083C53B611.jpg 5 424 | /data/image-clef/b/8D975391F91BC8CB3360467DC09EFE75.jpg 5 425 | /data/image-clef/b/ED50CB1365FA1640C6C8171F8B6BEF6E.jpg 5 426 | /data/image-clef/b/FFA7E4965BE7A26BA9F12AA353691B84.jpg 5 427 | /data/image-clef/b/A81A589E0D5C484D0F81B7B05C123322.jpg 5 428 | /data/image-clef/b/5DB33AB5D8F811249D2DE8808708D4E7.jpg 5 429 | /data/image-clef/b/FC54B028496416FC58F910E6EFBDA84B.jpg 5 430 | /data/image-clef/b/13CDE870001E9405EAF4323C599E2FB6.jpg 5 431 | /data/image-clef/b/D0C517CD4FA4986E432E23642FCC8ABC.jpg 5 432 | /data/image-clef/b/9C2F957F2FE350314AC15A399770C415.jpg 5 433 | /data/image-clef/b/DB3E24C36C4FA21940A15DA5B7351695.jpg 5 434 | /data/image-clef/b/3ACD3D6FB09F5CECCB4D1D10A3567D15.jpg 5 435 | /data/image-clef/b/58988BE83794045DF9F87E1D9111B164.jpg 5 436 | /data/image-clef/b/A38061C092DDADDBC12026B2FD8BBD9C.jpg 5 437 | /data/image-clef/b/2F654121C020F97F9F5B7D2E4EEE4809.jpg 5 438 | /data/image-clef/b/69D957D426E8BBB87F2BB27C3DAE0F5D.jpg 5 439 | /data/image-clef/b/0815025A981C055CBF1528B2DA2C6FA3.jpg 5 440 | /data/image-clef/b/154A793A0B1DDF8A49D5257395197051.jpg 5 441 | /data/image-clef/b/BF604F291613A1A5AFCB5756C26D5A42.jpg 5 442 | /data/image-clef/b/7553530C20E3EF5F72748CAF3FBDD319.jpg 5 443 | /data/image-clef/b/A4F5C2A63B0E9FD648890802B0D3794A.jpg 5 444 | /data/image-clef/b/9E1794FDA934CB0932EF635C86CE5529.jpg 5 445 | /data/image-clef/b/41DF079F00FC1CDF7A34F5148B98BB64.jpg 5 446 | /data/image-clef/b/9CFFC763C8A64604881052DA33C7462C.jpg 5 447 | /data/image-clef/b/56D45AD69679E30A5CB5CAAD444E58AA.jpg 5 448 | /data/image-clef/b/7D35D7E2A4727E36EC185ACE4E3BAD88.jpg 5 449 | /data/image-clef/b/0674D9FAE1C8F77FD76E2710EFE51E4D.jpg 5 450 | /data/image-clef/b/0AB55F775D31F53C97AD0FF64CD92569.jpg 5 451 | /data/image-clef/b/2F199132AE8C1BB012B9874803423633.jpg 3 452 | /data/image-clef/b/06E7546A599DCE0994635A0F17C13546.jpg 3 453 | /data/image-clef/b/4782FB6A9D47E59DF335EEB19F3BBC81.jpg 3 454 | /data/image-clef/b/228B6EBA3138877AB8A024E63E11E480.jpg 3 455 | /data/image-clef/b/A4D35F1F675A516BA5E104415DCD7239.jpg 3 456 | /data/image-clef/b/9D86C31949F3335A6492F2236F6BBAA9.jpg 3 457 | /data/image-clef/b/FD02BE5DED1CA899B4442876F6FD5831.jpg 3 458 | /data/image-clef/b/0CD8F80A3C9803F22FDCFEDA5D3074A9.jpg 3 459 | /data/image-clef/b/E13547193B8C726914E729CDA16ACE01.jpg 3 460 | /data/image-clef/b/D953D8AD757D5D212EDD957D319514FC.jpg 3 461 | /data/image-clef/b/64A8A592A04C5BFA8D4B7162781D3CA3.jpg 3 462 | /data/image-clef/b/97528AD153732B5068745E6E2D44B8B7.jpg 3 463 | /data/image-clef/b/30DB9418D3FB20C0FC1B3B737034721A.jpg 3 464 | /data/image-clef/b/CB0A27D55803905C32261563CA27710B.jpg 3 465 | /data/image-clef/b/4FB9D549000737F4950B57BAE0A6C020.jpg 3 466 | /data/image-clef/b/0C1717639BC4DB6AB6432D16D5BE4A36.jpg 3 467 | /data/image-clef/b/7EEAD5FCA7472F45D3657A49B44FA630.jpg 3 468 | /data/image-clef/b/4EB35DD3E37CB2DEE0148DD62D846F2F.jpg 3 469 | /data/image-clef/b/0CFECC943A10E78B1F334E9890B3422F.jpg 3 470 | /data/image-clef/b/42617D7195453D01B4B111A25FEFC29C.jpg 3 471 | /data/image-clef/b/DA60919B42F494EDBCFFCD815E967072.jpg 3 472 | /data/image-clef/b/6CD65842EC674D9F12FCA544E61DDA28.jpg 3 473 | /data/image-clef/b/08031F2F2B4C021D60F48026732E00C1.jpg 3 474 | /data/image-clef/b/BFDEBE9806FC27CFD3690DBA41FDBE9C.jpg 3 475 | /data/image-clef/b/A012B46899B919BFE0D757D68C881071.jpg 3 476 | /data/image-clef/b/24572C6C1C529ECB960452FCE75563F6.jpg 3 477 | /data/image-clef/b/B930D323361F24D9EF58E8445C315233.jpg 3 478 | /data/image-clef/b/97E78A339A2756D4236FFB5F3E3C9B63.jpg 3 479 | /data/image-clef/b/984F6499EAE3914660AEA0E9DF7D56E1.jpg 3 480 | /data/image-clef/b/AFAF6AC01AD231E2B18AFCF43415544A.jpg 3 481 | /data/image-clef/b/CFAD48F3E12C0C8D438EC95C010BC068.jpg 3 482 | /data/image-clef/b/F6F06F76058694E41507028B090C0A8B.jpg 3 483 | /data/image-clef/b/88D0FE64FC6D6A50E6A96FAA7BAAC556.jpg 3 484 | /data/image-clef/b/5BC690DF7D75B389223E7DEF473D2CC6.jpg 3 485 | /data/image-clef/b/C094FDB6DCAECFF2F5D58D85DB320747.jpg 3 486 | /data/image-clef/b/750102ED0679A6D627322CD80030B2D9.jpg 3 487 | /data/image-clef/b/523DCBEFC4F30B105D7E301F97FFA5F3.jpg 3 488 | /data/image-clef/b/412B17B2E79287572F2637B919BB4DDF.jpg 3 489 | /data/image-clef/b/B216913893C6B401DE2C197B1D15EAA2.jpg 3 490 | /data/image-clef/b/57EC5444895376BC7CA3E9CD5CF897E7.jpg 3 491 | /data/image-clef/b/D374801C0DF141A571BE581F0809F577.jpg 3 492 | /data/image-clef/b/4D622E71A186AA212734EDDEF38B6609.jpg 3 493 | /data/image-clef/b/6FB55C18F30020039C7538E370FE0C98.jpg 3 494 | /data/image-clef/b/71FD3B82BAE375019956E511975F0805.jpg 3 495 | /data/image-clef/b/02326FC55FAD21E3EB032C2ADF4E9B9A.jpg 3 496 | /data/image-clef/b/F2FB4DFD2FDCD6959500F70B09D11A0D.jpg 3 497 | /data/image-clef/b/244DAC3142BEDCBC42D23B4D55B197A0.jpg 3 498 | /data/image-clef/b/0760F5D5CAF936B9B1015CBF0D51FC2F.jpg 3 499 | /data/image-clef/b/A81431784F0A65CBB5C70EFDA72621FA.jpg 3 500 | /data/image-clef/b/0D9C5CD65F9A0CC60311CF67F6B9BA90.jpg 3 501 | /data/image-clef/b/EFB685AA6FBC4FAD89001CFB4B0FD6C7.jpg 4 502 | /data/image-clef/b/FD105C1FB90A02D2255BE57D53325243.jpg 4 503 | /data/image-clef/b/533D29D9F1F6C2E19F5B5F972C44D99A.jpg 4 504 | /data/image-clef/b/77C978E318BCD9662EB96B4A5F19F35F.jpg 4 505 | /data/image-clef/b/CD1B98237D442FDE38B61D99020E7917.jpg 4 506 | /data/image-clef/b/2CD7FF443E26A0D31021009F46734EB2.jpg 4 507 | /data/image-clef/b/312445DB721563C7752B34D51DA10454.jpg 4 508 | /data/image-clef/b/E0D30B7B88E6B718A253C82D44C3F54A.jpg 4 509 | /data/image-clef/b/2C016F70D7C1E0342F39513BC0B6BC43.jpg 4 510 | /data/image-clef/b/D5849BCFAF8E1BA0EBA6E2787B8323B1.jpg 4 511 | /data/image-clef/b/3846B97DC94DA51BFCFCA3E95A287CC0.jpg 4 512 | /data/image-clef/b/AE872A16D1602FD9B09D75CB8C58F277.jpg 4 513 | /data/image-clef/b/430ECD392E4424EDA2F74F400F91881E.jpg 4 514 | /data/image-clef/b/F0C293D43F9A12BD84F9B9C61D317EFB.jpg 4 515 | /data/image-clef/b/E363DFA32CD85C5649C4F832566365F5.jpg 4 516 | /data/image-clef/b/5ACAA63B3F6B1F5CC64B5533A38CFC22.jpg 4 517 | /data/image-clef/b/5FC21CB04B95C90E1476A3CE27A3EA9E.jpg 4 518 | /data/image-clef/b/65B5ED01282AC4707E6613F75FE6AAD4.jpg 4 519 | /data/image-clef/b/33A09E862D6FFD5ED7D153C023A9F030.jpg 4 520 | /data/image-clef/b/B197C4415626DF2BBB8CCC656B891CFE.jpg 4 521 | /data/image-clef/b/9852BE61326A774F0B174D4F4A7A5D03.jpg 4 522 | /data/image-clef/b/5EF88A8D0EA57BB9D08A30B303834C29.jpg 4 523 | /data/image-clef/b/88A72A70A267147B21292A19402F3778.jpg 4 524 | /data/image-clef/b/BFEA935ED5E0B1544C791AF6C068440D.jpg 4 525 | /data/image-clef/b/519E025BE461AF37D3420D645E243394.jpg 4 526 | /data/image-clef/b/444EFD0A5C55381E8A8F79BCF443B7E4.jpg 4 527 | /data/image-clef/b/639C13BF14259D98FC6D735CE24C420E.jpg 4 528 | /data/image-clef/b/C6EF53B2FCB9EC242AC3FE334D2130F5.jpg 4 529 | /data/image-clef/b/B63C63EF218EEF64529B532078BC89B4.jpg 4 530 | /data/image-clef/b/B63E13EFAB4A3D798C08D55FF091EAB5.jpg 4 531 | /data/image-clef/b/BC81191105B77516130EAF663AE4D8BC.jpg 4 532 | /data/image-clef/b/F757946EC23E096CD6FB913DB56882B9.jpg 4 533 | /data/image-clef/b/BDE75A335C9B90AC5F2EA1625CE96475.jpg 4 534 | /data/image-clef/b/58283D505FF4FF899D119DCA4EFFFE58.jpg 4 535 | /data/image-clef/b/5F402D72C71B0517C0EF4D98E1C12905.jpg 4 536 | /data/image-clef/b/FCBABF0F60B8816680F4731B63B7246A.jpg 4 537 | /data/image-clef/b/39ACDCCE22EEC3B54879E72969A50FC9.jpg 4 538 | /data/image-clef/b/8CBE9DE02660DF5AB5DB2C58F44E520F.jpg 4 539 | /data/image-clef/b/4250D9B8CF2C72C833C4AE52858AE5AF.jpg 4 540 | /data/image-clef/b/F5D0B77FD3F671FEDB4611DA99605419.jpg 4 541 | /data/image-clef/b/6E6DD6C0B6C8F6D907B3816D57E6967B.jpg 4 542 | /data/image-clef/b/2EB3068FDBFCF4EF9F0BF93B6854EE53.jpg 4 543 | /data/image-clef/b/0E55BCE89CFCFC250051C1E18E4CE483.jpg 4 544 | /data/image-clef/b/B23FCF5AFA32C175D0D46D68724D7A0A.jpg 4 545 | /data/image-clef/b/7DC857179CF8863E60CB16A2F99EE572.jpg 4 546 | /data/image-clef/b/43C8E3F1DB3E2308349366426E2C2B5B.jpg 4 547 | /data/image-clef/b/C9A2153FEDD0552FEDA60EA661CE5D2D.jpg 4 548 | /data/image-clef/b/33F04496C0C38E835AE314ED95BE955B.jpg 4 549 | /data/image-clef/b/70C738ED5F27D6D5A17686090A3A4CD4.jpg 4 550 | /data/image-clef/b/B11AA83F5D9E776A69FFE740EDB0F6D4.jpg 4 551 | /data/image-clef/b/E3FF9BF44ABD7A590386FD6DC04441FE.jpg 0 552 | /data/image-clef/b/1F3E4785017945B9A068DF759CC94DF2.jpg 0 553 | /data/image-clef/b/CA83C6D5DED56226F8A64C45C2167407.jpg 0 554 | /data/image-clef/b/CB72DC4FCF9ABCFEF06936C5684581E8.jpg 0 555 | /data/image-clef/b/E9430381F2493159A32F5F236B4FDF8A.jpg 0 556 | /data/image-clef/b/620031A94BE8545E599268C596ACA55D.jpg 0 557 | /data/image-clef/b/18A92EDCCC167E5057B779E3CF142F89.jpg 0 558 | /data/image-clef/b/2E862EC1688653B70B53A2C1E6A87A11.jpg 0 559 | /data/image-clef/b/1BF53EEAD6CEF9203DF40C5A1A67744B.jpg 0 560 | /data/image-clef/b/BD5902152B26285D91A08A86168FF8D1.jpg 0 561 | /data/image-clef/b/6436B37ADAAAB84B9099841E0EA633F5.jpg 0 562 | /data/image-clef/b/02B33FC50DBA873198FAED4689BBFBFF.jpg 0 563 | /data/image-clef/b/78DD91697DE5840D45AF40C888EFB69D.jpg 0 564 | /data/image-clef/b/7E9F04E7B8523AAB6AE77776C1103883.jpg 0 565 | /data/image-clef/b/B0113FE6B343D901B163493258BBF919.jpg 0 566 | /data/image-clef/b/17C58ED7CD8A3CDBB79AD8DD64AB9D0A.jpg 0 567 | /data/image-clef/b/4C34DA2860E01687A2172F220D39368B.jpg 0 568 | /data/image-clef/b/C419985418C4740BB85228D8B3F157C4.jpg 0 569 | /data/image-clef/b/6E3D27967CF815A6DD3BA7260A81ACC8.jpg 0 570 | /data/image-clef/b/27F8578B1C3157CD25387AE3580E604E.jpg 0 571 | /data/image-clef/b/AA2F131C6EADCAC7B05A1FAB059DBBFF.jpg 0 572 | /data/image-clef/b/6E74BE7740A6A0EF30BFEFCC1A7FE2DC.jpg 0 573 | /data/image-clef/b/92C723F600E72B846A35236CBB4F7A4B.jpg 0 574 | /data/image-clef/b/C56E1372BFB223FAE049EBC4917D059C.jpg 0 575 | /data/image-clef/b/A6F9044F6A1275795531794DE44D7D88.jpg 0 576 | /data/image-clef/b/211C525E9ADF1E92923FBF9FDDAD317E.jpg 0 577 | /data/image-clef/b/3D07CCD1290EBDFDFC26F2469B8F94A6.jpg 0 578 | /data/image-clef/b/0F6DD993FA6C0086C3B2D476F3128EEC.jpg 0 579 | /data/image-clef/b/70214AD47A30556F16A65C256AADD066.jpg 0 580 | /data/image-clef/b/11AAB1206CBA2BB2F966A53D9D1EE087.jpg 0 581 | /data/image-clef/b/F9016E99A54A7EE51FBBE6E13FF5AE0F.jpg 0 582 | /data/image-clef/b/D4821FE0B02A69FCE94ADEA98828C687.jpg 0 583 | /data/image-clef/b/0CBDC7E01B8280AC537A9FA32D897D62.jpg 0 584 | /data/image-clef/b/8928965F493DB82C700227DD207C4B6C.jpg 0 585 | /data/image-clef/b/10EC208950F689A3377AC2F9566BE86C.jpg 0 586 | /data/image-clef/b/5764B3EB17C3D76AF1826F7EA8B226AF.jpg 0 587 | /data/image-clef/b/09EC5D53CE789A34F3E05DB048B55849.jpg 0 588 | /data/image-clef/b/007859D83594D527355CA287E096218B.jpg 0 589 | /data/image-clef/b/9CEBB04C1B69A165740138ABE077645E.jpg 0 590 | /data/image-clef/b/060FBA0F642012BCC2F4E427E7444248.jpg 0 591 | /data/image-clef/b/FDDE05B3132C71CE3E07C4182199B9CB.jpg 0 592 | /data/image-clef/b/652823C3559FF2C5C15A25ECA120A626.jpg 0 593 | /data/image-clef/b/3504460129C1001C390F787870CB1DD4.jpg 0 594 | /data/image-clef/b/8D1A5ADB91499E383ED331ED912B09EC.jpg 0 595 | /data/image-clef/b/27205A7335FA260E8446F9371AD9A3C4.jpg 0 596 | /data/image-clef/b/9228DF8B79C57CDEB6A23D94A34232E3.jpg 0 597 | /data/image-clef/b/5C915F5961F37AD219CA5DCDFF2B78BA.jpg 0 598 | /data/image-clef/b/95498E27EC444C2BBC56FC86CF245165.jpg 0 599 | /data/image-clef/b/33D891118F9D9D6090B033394B7D2B7E.jpg 0 600 | /data/image-clef/b/B08A893A4CFF2B0F3B39CF1CBF2385D2.jpg 0 601 | -------------------------------------------------------------------------------- /data/image-clef/c_list.txt: -------------------------------------------------------------------------------- 1 | /data/image-clef/c/113_0114.jpg 2 2 | /data/image-clef/c/113_0025.jpg 2 3 | /data/image-clef/c/113_0003.jpg 2 4 | /data/image-clef/c/113_0034.jpg 2 5 | /data/image-clef/c/113_0058.jpg 2 6 | /data/image-clef/c/113_0042.jpg 2 7 | /data/image-clef/c/113_0057.jpg 2 8 | /data/image-clef/c/113_0083.jpg 2 9 | /data/image-clef/c/113_0055.jpg 2 10 | /data/image-clef/c/113_0109.jpg 2 11 | /data/image-clef/c/113_0090.jpg 2 12 | /data/image-clef/c/113_0060.jpg 2 13 | /data/image-clef/c/113_0074.jpg 2 14 | /data/image-clef/c/113_0012.jpg 2 15 | /data/image-clef/c/113_0030.jpg 2 16 | /data/image-clef/c/113_0099.jpg 2 17 | /data/image-clef/c/113_0115.jpg 2 18 | /data/image-clef/c/113_0054.jpg 2 19 | /data/image-clef/c/113_0062.jpg 2 20 | /data/image-clef/c/113_0035.jpg 2 21 | /data/image-clef/c/113_0103.jpg 2 22 | /data/image-clef/c/113_0036.jpg 2 23 | /data/image-clef/c/113_0029.jpg 2 24 | /data/image-clef/c/113_0037.jpg 2 25 | /data/image-clef/c/113_0010.jpg 2 26 | /data/image-clef/c/113_0020.jpg 2 27 | /data/image-clef/c/113_0048.jpg 2 28 | /data/image-clef/c/113_0051.jpg 2 29 | /data/image-clef/c/113_0061.jpg 2 30 | /data/image-clef/c/113_0068.jpg 2 31 | /data/image-clef/c/113_0108.jpg 2 32 | /data/image-clef/c/113_0014.jpg 2 33 | /data/image-clef/c/113_0031.jpg 2 34 | /data/image-clef/c/113_0095.jpg 2 35 | /data/image-clef/c/113_0066.jpg 2 36 | /data/image-clef/c/113_0002.jpg 2 37 | /data/image-clef/c/113_0013.jpg 2 38 | /data/image-clef/c/113_0001.jpg 2 39 | /data/image-clef/c/113_0022.jpg 2 40 | /data/image-clef/c/113_0016.jpg 2 41 | /data/image-clef/c/113_0116.jpg 2 42 | /data/image-clef/c/113_0011.jpg 2 43 | /data/image-clef/c/113_0046.jpg 2 44 | /data/image-clef/c/113_0071.jpg 2 45 | /data/image-clef/c/113_0092.jpg 2 46 | /data/image-clef/c/113_0072.jpg 2 47 | /data/image-clef/c/113_0050.jpg 2 48 | /data/image-clef/c/113_0070.jpg 2 49 | /data/image-clef/c/113_0089.jpg 2 50 | /data/image-clef/c/113_0064.jpg 2 51 | /data/image-clef/c/224_0053.jpg 1 52 | /data/image-clef/c/146_0021.jpg 1 53 | /data/image-clef/c/146_0061.jpg 1 54 | /data/image-clef/c/146_0057.jpg 1 55 | /data/image-clef/c/224_0015.jpg 1 56 | /data/image-clef/c/146_0072.jpg 1 57 | /data/image-clef/c/224_0096.jpg 1 58 | /data/image-clef/c/146_0063.jpg 1 59 | /data/image-clef/c/224_0063.jpg 1 60 | /data/image-clef/c/224_0035.jpg 1 61 | /data/image-clef/c/146_0041.jpg 1 62 | /data/image-clef/c/224_0110.jpg 1 63 | /data/image-clef/c/224_0082.jpg 1 64 | /data/image-clef/c/224_0023.jpg 1 65 | /data/image-clef/c/146_0011.jpg 1 66 | /data/image-clef/c/146_0071.jpg 1 67 | /data/image-clef/c/224_0044.jpg 1 68 | /data/image-clef/c/224_0066.jpg 1 69 | /data/image-clef/c/224_0051.jpg 1 70 | /data/image-clef/c/146_0074.jpg 1 71 | /data/image-clef/c/224_0040.jpg 1 72 | /data/image-clef/c/224_0098.jpg 1 73 | /data/image-clef/c/224_0007.jpg 1 74 | /data/image-clef/c/224_0008.jpg 1 75 | /data/image-clef/c/146_0062.jpg 1 76 | /data/image-clef/c/224_0107.jpg 1 77 | /data/image-clef/c/224_0027.jpg 1 78 | /data/image-clef/c/224_0021.jpg 1 79 | /data/image-clef/c/224_0087.jpg 1 80 | /data/image-clef/c/224_0046.jpg 1 81 | /data/image-clef/c/224_0004.jpg 1 82 | /data/image-clef/c/224_0097.jpg 1 83 | /data/image-clef/c/146_0073.jpg 1 84 | /data/image-clef/c/146_0006.jpg 1 85 | /data/image-clef/c/224_0070.jpg 1 86 | /data/image-clef/c/224_0092.jpg 1 87 | /data/image-clef/c/146_0054.jpg 1 88 | /data/image-clef/c/224_0072.jpg 1 89 | /data/image-clef/c/224_0039.jpg 1 90 | /data/image-clef/c/224_0068.jpg 1 91 | /data/image-clef/c/146_0080.jpg 1 92 | /data/image-clef/c/224_0016.jpg 1 93 | /data/image-clef/c/146_0045.jpg 1 94 | /data/image-clef/c/224_0078.jpg 1 95 | /data/image-clef/c/224_0059.jpg 1 96 | /data/image-clef/c/224_0025.jpg 1 97 | /data/image-clef/c/146_0017.jpg 1 98 | /data/image-clef/c/224_0067.jpg 1 99 | /data/image-clef/c/224_0022.jpg 1 100 | /data/image-clef/c/224_0003.jpg 1 101 | /data/image-clef/c/105_0250.jpg 8 102 | /data/image-clef/c/105_0022.jpg 8 103 | /data/image-clef/c/105_0010.jpg 8 104 | /data/image-clef/c/105_0229.jpg 8 105 | /data/image-clef/c/105_0248.jpg 8 106 | /data/image-clef/c/105_0132.jpg 8 107 | /data/image-clef/c/105_0055.jpg 8 108 | /data/image-clef/c/105_0069.jpg 8 109 | /data/image-clef/c/105_0067.jpg 8 110 | /data/image-clef/c/105_0268.jpg 8 111 | /data/image-clef/c/105_0192.jpg 8 112 | /data/image-clef/c/105_0068.jpg 8 113 | /data/image-clef/c/105_0140.jpg 8 114 | /data/image-clef/c/105_0218.jpg 8 115 | /data/image-clef/c/105_0044.jpg 8 116 | /data/image-clef/c/105_0100.jpg 8 117 | /data/image-clef/c/105_0222.jpg 8 118 | /data/image-clef/c/105_0003.jpg 8 119 | /data/image-clef/c/105_0175.jpg 8 120 | /data/image-clef/c/105_0242.jpg 8 121 | /data/image-clef/c/105_0247.jpg 8 122 | /data/image-clef/c/105_0023.jpg 8 123 | /data/image-clef/c/105_0061.jpg 8 124 | /data/image-clef/c/105_0223.jpg 8 125 | /data/image-clef/c/105_0065.jpg 8 126 | /data/image-clef/c/105_0238.jpg 8 127 | /data/image-clef/c/105_0062.jpg 8 128 | /data/image-clef/c/105_0105.jpg 8 129 | /data/image-clef/c/105_0191.jpg 8 130 | /data/image-clef/c/105_0073.jpg 8 131 | /data/image-clef/c/105_0173.jpg 8 132 | /data/image-clef/c/105_0212.jpg 8 133 | /data/image-clef/c/105_0082.jpg 8 134 | /data/image-clef/c/105_0030.jpg 8 135 | /data/image-clef/c/105_0092.jpg 8 136 | /data/image-clef/c/105_0138.jpg 8 137 | /data/image-clef/c/105_0113.jpg 8 138 | /data/image-clef/c/105_0117.jpg 8 139 | /data/image-clef/c/105_0129.jpg 8 140 | /data/image-clef/c/105_0252.jpg 8 141 | /data/image-clef/c/105_0141.jpg 8 142 | /data/image-clef/c/105_0094.jpg 8 143 | /data/image-clef/c/105_0115.jpg 8 144 | /data/image-clef/c/105_0116.jpg 8 145 | /data/image-clef/c/105_0179.jpg 8 146 | /data/image-clef/c/105_0060.jpg 8 147 | /data/image-clef/c/105_0139.jpg 8 148 | /data/image-clef/c/105_0133.jpg 8 149 | /data/image-clef/c/105_0221.jpg 8 150 | /data/image-clef/c/105_0204.jpg 8 151 | /data/image-clef/c/159_0068.jpg 11 152 | /data/image-clef/c/159_0017.jpg 11 153 | /data/image-clef/c/159_0046.jpg 11 154 | /data/image-clef/c/159_0158.jpg 11 155 | /data/image-clef/c/159_0074.jpg 11 156 | /data/image-clef/c/159_0199.jpg 11 157 | /data/image-clef/c/159_0137.jpg 11 158 | /data/image-clef/c/159_0060.jpg 11 159 | /data/image-clef/c/159_0048.jpg 11 160 | /data/image-clef/c/159_0200.jpg 11 161 | /data/image-clef/c/159_0098.jpg 11 162 | /data/image-clef/c/159_0180.jpg 11 163 | /data/image-clef/c/159_0160.jpg 11 164 | /data/image-clef/c/159_0178.jpg 11 165 | /data/image-clef/c/159_0134.jpg 11 166 | /data/image-clef/c/159_0022.jpg 11 167 | /data/image-clef/c/159_0186.jpg 11 168 | /data/image-clef/c/159_0129.jpg 11 169 | /data/image-clef/c/159_0170.jpg 11 170 | /data/image-clef/c/159_0179.jpg 11 171 | /data/image-clef/c/159_0196.jpg 11 172 | /data/image-clef/c/159_0126.jpg 11 173 | /data/image-clef/c/159_0182.jpg 11 174 | /data/image-clef/c/159_0108.jpg 11 175 | /data/image-clef/c/159_0055.jpg 11 176 | /data/image-clef/c/159_0197.jpg 11 177 | /data/image-clef/c/159_0149.jpg 11 178 | /data/image-clef/c/159_0176.jpg 11 179 | /data/image-clef/c/159_0094.jpg 11 180 | /data/image-clef/c/159_0096.jpg 11 181 | /data/image-clef/c/159_0141.jpg 11 182 | /data/image-clef/c/159_0120.jpg 11 183 | /data/image-clef/c/159_0030.jpg 11 184 | /data/image-clef/c/159_0114.jpg 11 185 | /data/image-clef/c/159_0009.jpg 11 186 | /data/image-clef/c/159_0163.jpg 11 187 | /data/image-clef/c/159_0039.jpg 11 188 | /data/image-clef/c/159_0045.jpg 11 189 | /data/image-clef/c/159_0021.jpg 11 190 | /data/image-clef/c/159_0131.jpg 11 191 | /data/image-clef/c/159_0041.jpg 11 192 | /data/image-clef/c/159_0066.jpg 11 193 | /data/image-clef/c/159_0153.jpg 11 194 | /data/image-clef/c/159_0181.jpg 11 195 | /data/image-clef/c/159_0024.jpg 11 196 | /data/image-clef/c/159_0143.jpg 11 197 | /data/image-clef/c/159_0043.jpg 11 198 | /data/image-clef/c/159_0166.jpg 11 199 | /data/image-clef/c/159_0040.jpg 11 200 | /data/image-clef/c/159_0083.jpg 11 201 | /data/image-clef/c/046_0076.jpg 9 202 | /data/image-clef/c/046_0087.jpg 9 203 | /data/image-clef/c/046_0100.jpg 9 204 | /data/image-clef/c/046_0072.jpg 9 205 | /data/image-clef/c/046_0069.jpg 9 206 | /data/image-clef/c/046_0025.jpg 9 207 | /data/image-clef/c/046_0124.jpg 9 208 | /data/image-clef/c/046_0105.jpg 9 209 | /data/image-clef/c/046_0128.jpg 9 210 | /data/image-clef/c/046_0005.jpg 9 211 | /data/image-clef/c/046_0001.jpg 9 212 | /data/image-clef/c/046_0021.jpg 9 213 | /data/image-clef/c/046_0023.jpg 9 214 | /data/image-clef/c/046_0093.jpg 9 215 | /data/image-clef/c/046_0058.jpg 9 216 | /data/image-clef/c/046_0106.jpg 9 217 | /data/image-clef/c/046_0050.jpg 9 218 | /data/image-clef/c/046_0060.jpg 9 219 | /data/image-clef/c/046_0026.jpg 9 220 | /data/image-clef/c/046_0014.jpg 9 221 | /data/image-clef/c/046_0054.jpg 9 222 | /data/image-clef/c/046_0077.jpg 9 223 | /data/image-clef/c/046_0048.jpg 9 224 | /data/image-clef/c/046_0066.jpg 9 225 | /data/image-clef/c/046_0110.jpg 9 226 | /data/image-clef/c/046_0020.jpg 9 227 | /data/image-clef/c/046_0024.jpg 9 228 | /data/image-clef/c/046_0008.jpg 9 229 | /data/image-clef/c/046_0038.jpg 9 230 | /data/image-clef/c/046_0096.jpg 9 231 | /data/image-clef/c/046_0121.jpg 9 232 | /data/image-clef/c/046_0102.jpg 9 233 | /data/image-clef/c/046_0051.jpg 9 234 | /data/image-clef/c/046_0006.jpg 9 235 | /data/image-clef/c/046_0062.jpg 9 236 | /data/image-clef/c/046_0052.jpg 9 237 | /data/image-clef/c/046_0073.jpg 9 238 | /data/image-clef/c/046_0012.jpg 9 239 | /data/image-clef/c/046_0118.jpg 9 240 | /data/image-clef/c/046_0114.jpg 9 241 | /data/image-clef/c/046_0092.jpg 9 242 | /data/image-clef/c/046_0067.jpg 9 243 | /data/image-clef/c/046_0079.jpg 9 244 | /data/image-clef/c/046_0113.jpg 9 245 | /data/image-clef/c/046_0085.jpg 9 246 | /data/image-clef/c/046_0101.jpg 9 247 | /data/image-clef/c/046_0040.jpg 9 248 | /data/image-clef/c/046_0104.jpg 9 249 | /data/image-clef/c/046_0013.jpg 9 250 | /data/image-clef/c/046_0017.jpg 9 251 | /data/image-clef/c/246_0100.jpg 4 252 | /data/image-clef/c/246_0048.jpg 4 253 | /data/image-clef/c/246_0070.jpg 4 254 | /data/image-clef/c/246_0011.jpg 4 255 | /data/image-clef/c/246_0038.jpg 4 256 | /data/image-clef/c/246_0029.jpg 4 257 | /data/image-clef/c/246_0086.jpg 4 258 | /data/image-clef/c/246_0044.jpg 4 259 | /data/image-clef/c/246_0037.jpg 4 260 | /data/image-clef/c/246_0056.jpg 4 261 | /data/image-clef/c/246_0083.jpg 4 262 | /data/image-clef/c/246_0042.jpg 4 263 | /data/image-clef/c/246_0055.jpg 4 264 | /data/image-clef/c/246_0039.jpg 4 265 | /data/image-clef/c/246_0018.jpg 4 266 | /data/image-clef/c/246_0064.jpg 4 267 | /data/image-clef/c/246_0053.jpg 4 268 | /data/image-clef/c/246_0052.jpg 4 269 | /data/image-clef/c/246_0033.jpg 4 270 | /data/image-clef/c/246_0058.jpg 4 271 | /data/image-clef/c/246_0041.jpg 4 272 | /data/image-clef/c/246_0067.jpg 4 273 | /data/image-clef/c/246_0008.jpg 4 274 | /data/image-clef/c/246_0093.jpg 4 275 | /data/image-clef/c/246_0045.jpg 4 276 | /data/image-clef/c/246_0002.jpg 4 277 | /data/image-clef/c/246_0101.jpg 4 278 | /data/image-clef/c/246_0043.jpg 4 279 | /data/image-clef/c/246_0020.jpg 4 280 | /data/image-clef/c/246_0031.jpg 4 281 | /data/image-clef/c/246_0096.jpg 4 282 | /data/image-clef/c/246_0049.jpg 4 283 | /data/image-clef/c/246_0074.jpg 4 284 | /data/image-clef/c/246_0005.jpg 4 285 | /data/image-clef/c/246_0071.jpg 4 286 | /data/image-clef/c/246_0057.jpg 4 287 | /data/image-clef/c/246_0085.jpg 4 288 | /data/image-clef/c/246_0082.jpg 4 289 | /data/image-clef/c/246_0034.jpg 4 290 | /data/image-clef/c/246_0062.jpg 4 291 | /data/image-clef/c/246_0010.jpg 4 292 | /data/image-clef/c/246_0061.jpg 4 293 | /data/image-clef/c/246_0017.jpg 4 294 | /data/image-clef/c/246_0028.jpg 4 295 | /data/image-clef/c/246_0035.jpg 4 296 | /data/image-clef/c/246_0084.jpg 4 297 | /data/image-clef/c/246_0030.jpg 4 298 | /data/image-clef/c/246_0098.jpg 4 299 | /data/image-clef/c/246_0088.jpg 4 300 | /data/image-clef/c/246_0032.jpg 4 301 | /data/image-clef/c/145_0167.jpg 10 302 | /data/image-clef/c/145_0511.jpg 10 303 | /data/image-clef/c/145_0555.jpg 10 304 | /data/image-clef/c/145_0758.jpg 10 305 | /data/image-clef/c/145_0692.jpg 10 306 | /data/image-clef/c/145_0074.jpg 10 307 | /data/image-clef/c/145_0155.jpg 10 308 | /data/image-clef/c/145_0267.jpg 10 309 | /data/image-clef/c/145_0314.jpg 10 310 | /data/image-clef/c/145_0127.jpg 10 311 | /data/image-clef/c/145_0069.jpg 10 312 | /data/image-clef/c/145_0635.jpg 10 313 | /data/image-clef/c/145_0234.jpg 10 314 | /data/image-clef/c/145_0338.jpg 10 315 | /data/image-clef/c/145_0462.jpg 10 316 | /data/image-clef/c/145_0422.jpg 10 317 | /data/image-clef/c/145_0233.jpg 10 318 | /data/image-clef/c/145_0697.jpg 10 319 | /data/image-clef/c/145_0084.jpg 10 320 | /data/image-clef/c/145_0266.jpg 10 321 | /data/image-clef/c/145_0413.jpg 10 322 | /data/image-clef/c/145_0552.jpg 10 323 | /data/image-clef/c/145_0450.jpg 10 324 | /data/image-clef/c/145_0284.jpg 10 325 | /data/image-clef/c/145_0442.jpg 10 326 | /data/image-clef/c/145_0636.jpg 10 327 | /data/image-clef/c/145_0185.jpg 10 328 | /data/image-clef/c/145_0451.jpg 10 329 | /data/image-clef/c/145_0476.jpg 10 330 | /data/image-clef/c/145_0087.jpg 10 331 | /data/image-clef/c/145_0776.jpg 10 332 | /data/image-clef/c/145_0734.jpg 10 333 | /data/image-clef/c/145_0719.jpg 10 334 | /data/image-clef/c/145_0223.jpg 10 335 | /data/image-clef/c/145_0533.jpg 10 336 | /data/image-clef/c/145_0513.jpg 10 337 | /data/image-clef/c/145_0780.jpg 10 338 | /data/image-clef/c/145_0560.jpg 10 339 | /data/image-clef/c/145_0458.jpg 10 340 | /data/image-clef/c/145_0494.jpg 10 341 | /data/image-clef/c/145_0798.jpg 10 342 | /data/image-clef/c/145_0559.jpg 10 343 | /data/image-clef/c/145_0277.jpg 10 344 | /data/image-clef/c/145_0742.jpg 10 345 | /data/image-clef/c/145_0322.jpg 10 346 | /data/image-clef/c/145_0191.jpg 10 347 | /data/image-clef/c/145_0165.jpg 10 348 | /data/image-clef/c/145_0715.jpg 10 349 | /data/image-clef/c/145_0433.jpg 10 350 | /data/image-clef/c/145_0032.jpg 10 351 | /data/image-clef/c/178_0050.jpg 5 352 | /data/image-clef/c/178_0091.jpg 5 353 | /data/image-clef/c/178_0062.jpg 5 354 | /data/image-clef/c/178_0068.jpg 5 355 | /data/image-clef/c/178_0045.jpg 5 356 | /data/image-clef/c/178_0031.jpg 5 357 | /data/image-clef/c/178_0079.jpg 5 358 | /data/image-clef/c/178_0046.jpg 5 359 | /data/image-clef/c/178_0037.jpg 5 360 | /data/image-clef/c/178_0013.jpg 5 361 | /data/image-clef/c/178_0074.jpg 5 362 | /data/image-clef/c/178_0051.jpg 5 363 | /data/image-clef/c/178_0034.jpg 5 364 | /data/image-clef/c/178_0040.jpg 5 365 | /data/image-clef/c/178_0010.jpg 5 366 | /data/image-clef/c/178_0041.jpg 5 367 | /data/image-clef/c/178_0017.jpg 5 368 | /data/image-clef/c/178_0016.jpg 5 369 | /data/image-clef/c/178_0005.jpg 5 370 | /data/image-clef/c/178_0025.jpg 5 371 | /data/image-clef/c/178_0097.jpg 5 372 | /data/image-clef/c/178_0078.jpg 5 373 | /data/image-clef/c/178_0058.jpg 5 374 | /data/image-clef/c/178_0067.jpg 5 375 | /data/image-clef/c/178_0027.jpg 5 376 | /data/image-clef/c/178_0012.jpg 5 377 | /data/image-clef/c/178_0044.jpg 5 378 | /data/image-clef/c/178_0060.jpg 5 379 | /data/image-clef/c/178_0043.jpg 5 380 | /data/image-clef/c/178_0087.jpg 5 381 | /data/image-clef/c/178_0085.jpg 5 382 | /data/image-clef/c/178_0004.jpg 5 383 | /data/image-clef/c/178_0047.jpg 5 384 | /data/image-clef/c/178_0029.jpg 5 385 | /data/image-clef/c/178_0080.jpg 5 386 | /data/image-clef/c/178_0039.jpg 5 387 | /data/image-clef/c/178_0065.jpg 5 388 | /data/image-clef/c/178_0083.jpg 5 389 | /data/image-clef/c/178_0002.jpg 5 390 | /data/image-clef/c/178_0061.jpg 5 391 | /data/image-clef/c/178_0095.jpg 5 392 | /data/image-clef/c/178_0054.jpg 5 393 | /data/image-clef/c/178_0022.jpg 5 394 | /data/image-clef/c/178_0053.jpg 5 395 | /data/image-clef/c/178_0030.jpg 5 396 | /data/image-clef/c/178_0071.jpg 5 397 | /data/image-clef/c/178_0090.jpg 5 398 | /data/image-clef/c/178_0092.jpg 5 399 | /data/image-clef/c/178_0077.jpg 5 400 | /data/image-clef/c/178_0064.jpg 5 401 | /data/image-clef/c/251_0041.jpg 0 402 | /data/image-clef/c/251_0095.jpg 0 403 | /data/image-clef/c/251_0069.jpg 0 404 | /data/image-clef/c/251_0561.jpg 0 405 | /data/image-clef/c/251_0326.jpg 0 406 | /data/image-clef/c/251_0478.jpg 0 407 | /data/image-clef/c/251_0121.jpg 0 408 | /data/image-clef/c/251_0390.jpg 0 409 | /data/image-clef/c/251_0419.jpg 0 410 | /data/image-clef/c/251_0519.jpg 0 411 | /data/image-clef/c/251_0090.jpg 0 412 | /data/image-clef/c/251_0238.jpg 0 413 | /data/image-clef/c/251_0366.jpg 0 414 | /data/image-clef/c/251_0231.jpg 0 415 | /data/image-clef/c/251_0714.jpg 0 416 | /data/image-clef/c/251_0545.jpg 0 417 | /data/image-clef/c/251_0587.jpg 0 418 | /data/image-clef/c/251_0115.jpg 0 419 | /data/image-clef/c/251_0769.jpg 0 420 | /data/image-clef/c/251_0061.jpg 0 421 | /data/image-clef/c/251_0381.jpg 0 422 | /data/image-clef/c/251_0126.jpg 0 423 | /data/image-clef/c/251_0248.jpg 0 424 | /data/image-clef/c/251_0800.jpg 0 425 | /data/image-clef/c/251_0023.jpg 0 426 | /data/image-clef/c/251_0371.jpg 0 427 | /data/image-clef/c/251_0646.jpg 0 428 | /data/image-clef/c/251_0679.jpg 0 429 | /data/image-clef/c/251_0618.jpg 0 430 | /data/image-clef/c/251_0779.jpg 0 431 | /data/image-clef/c/251_0741.jpg 0 432 | /data/image-clef/c/251_0481.jpg 0 433 | /data/image-clef/c/251_0425.jpg 0 434 | /data/image-clef/c/251_0642.jpg 0 435 | /data/image-clef/c/251_0377.jpg 0 436 | /data/image-clef/c/251_0447.jpg 0 437 | /data/image-clef/c/251_0361.jpg 0 438 | /data/image-clef/c/251_0743.jpg 0 439 | /data/image-clef/c/251_0215.jpg 0 440 | /data/image-clef/c/251_0746.jpg 0 441 | /data/image-clef/c/251_0682.jpg 0 442 | /data/image-clef/c/251_0614.jpg 0 443 | /data/image-clef/c/251_0599.jpg 0 444 | /data/image-clef/c/251_0048.jpg 0 445 | /data/image-clef/c/251_0389.jpg 0 446 | /data/image-clef/c/251_0766.jpg 0 447 | /data/image-clef/c/251_0189.jpg 0 448 | /data/image-clef/c/251_0404.jpg 0 449 | /data/image-clef/c/251_0183.jpg 0 450 | /data/image-clef/c/251_0570.jpg 0 451 | /data/image-clef/c/056_0021.jpg 7 452 | /data/image-clef/c/056_0043.jpg 7 453 | /data/image-clef/c/056_0100.jpg 7 454 | /data/image-clef/c/056_0055.jpg 7 455 | /data/image-clef/c/056_0078.jpg 7 456 | /data/image-clef/c/056_0031.jpg 7 457 | /data/image-clef/c/056_0095.jpg 7 458 | /data/image-clef/c/056_0101.jpg 7 459 | /data/image-clef/c/056_0076.jpg 7 460 | /data/image-clef/c/056_0037.jpg 7 461 | /data/image-clef/c/056_0009.jpg 7 462 | /data/image-clef/c/056_0013.jpg 7 463 | /data/image-clef/c/056_0048.jpg 7 464 | /data/image-clef/c/056_0057.jpg 7 465 | /data/image-clef/c/056_0046.jpg 7 466 | /data/image-clef/c/056_0072.jpg 7 467 | /data/image-clef/c/056_0014.jpg 7 468 | /data/image-clef/c/056_0050.jpg 7 469 | /data/image-clef/c/056_0023.jpg 7 470 | /data/image-clef/c/056_0039.jpg 7 471 | /data/image-clef/c/056_0024.jpg 7 472 | /data/image-clef/c/056_0069.jpg 7 473 | /data/image-clef/c/056_0038.jpg 7 474 | /data/image-clef/c/056_0093.jpg 7 475 | /data/image-clef/c/056_0058.jpg 7 476 | /data/image-clef/c/056_0063.jpg 7 477 | /data/image-clef/c/056_0082.jpg 7 478 | /data/image-clef/c/056_0077.jpg 7 479 | /data/image-clef/c/056_0099.jpg 7 480 | /data/image-clef/c/056_0052.jpg 7 481 | /data/image-clef/c/056_0070.jpg 7 482 | /data/image-clef/c/056_0054.jpg 7 483 | /data/image-clef/c/056_0064.jpg 7 484 | /data/image-clef/c/056_0081.jpg 7 485 | /data/image-clef/c/056_0056.jpg 7 486 | /data/image-clef/c/056_0028.jpg 7 487 | /data/image-clef/c/056_0004.jpg 7 488 | /data/image-clef/c/056_0090.jpg 7 489 | /data/image-clef/c/056_0006.jpg 7 490 | /data/image-clef/c/056_0033.jpg 7 491 | /data/image-clef/c/056_0025.jpg 7 492 | /data/image-clef/c/056_0029.jpg 7 493 | /data/image-clef/c/056_0080.jpg 7 494 | /data/image-clef/c/056_0079.jpg 7 495 | /data/image-clef/c/056_0065.jpg 7 496 | /data/image-clef/c/056_0088.jpg 7 497 | /data/image-clef/c/056_0061.jpg 7 498 | /data/image-clef/c/056_0001.jpg 7 499 | /data/image-clef/c/056_0016.jpg 7 500 | /data/image-clef/c/056_0091.jpg 7 501 | /data/image-clef/c/252_0059.jpg 6 502 | /data/image-clef/c/252_0092.jpg 6 503 | /data/image-clef/c/252_0085.jpg 6 504 | /data/image-clef/c/252_0068.jpg 6 505 | /data/image-clef/c/252_0098.jpg 6 506 | /data/image-clef/c/252_0087.jpg 6 507 | /data/image-clef/c/252_0034.jpg 6 508 | /data/image-clef/c/252_0003.jpg 6 509 | /data/image-clef/c/252_0077.jpg 6 510 | /data/image-clef/c/252_0062.jpg 6 511 | /data/image-clef/c/252_0045.jpg 6 512 | /data/image-clef/c/252_0043.jpg 6 513 | /data/image-clef/c/252_0073.jpg 6 514 | /data/image-clef/c/252_0002.jpg 6 515 | /data/image-clef/c/252_0005.jpg 6 516 | /data/image-clef/c/252_0114.jpg 6 517 | /data/image-clef/c/252_0042.jpg 6 518 | /data/image-clef/c/252_0113.jpg 6 519 | /data/image-clef/c/252_0089.jpg 6 520 | /data/image-clef/c/252_0037.jpg 6 521 | /data/image-clef/c/252_0052.jpg 6 522 | /data/image-clef/c/252_0028.jpg 6 523 | /data/image-clef/c/252_0083.jpg 6 524 | /data/image-clef/c/252_0056.jpg 6 525 | /data/image-clef/c/252_0109.jpg 6 526 | /data/image-clef/c/252_0078.jpg 6 527 | /data/image-clef/c/252_0039.jpg 6 528 | /data/image-clef/c/252_0093.jpg 6 529 | /data/image-clef/c/252_0026.jpg 6 530 | /data/image-clef/c/252_0076.jpg 6 531 | /data/image-clef/c/252_0071.jpg 6 532 | /data/image-clef/c/252_0044.jpg 6 533 | /data/image-clef/c/252_0040.jpg 6 534 | /data/image-clef/c/252_0091.jpg 6 535 | /data/image-clef/c/252_0027.jpg 6 536 | /data/image-clef/c/252_0115.jpg 6 537 | /data/image-clef/c/252_0074.jpg 6 538 | /data/image-clef/c/252_0025.jpg 6 539 | /data/image-clef/c/252_0104.jpg 6 540 | /data/image-clef/c/252_0033.jpg 6 541 | /data/image-clef/c/252_0105.jpg 6 542 | /data/image-clef/c/252_0116.jpg 6 543 | /data/image-clef/c/252_0007.jpg 6 544 | /data/image-clef/c/252_0111.jpg 6 545 | /data/image-clef/c/252_0064.jpg 6 546 | /data/image-clef/c/252_0006.jpg 6 547 | /data/image-clef/c/252_0070.jpg 6 548 | /data/image-clef/c/252_0082.jpg 6 549 | /data/image-clef/c/252_0080.jpg 6 550 | /data/image-clef/c/252_0029.jpg 6 551 | /data/image-clef/c/197_0019.jpg 3 552 | /data/image-clef/c/197_0087.jpg 3 553 | /data/image-clef/c/197_0059.jpg 3 554 | /data/image-clef/c/197_0038.jpg 3 555 | /data/image-clef/c/197_0064.jpg 3 556 | /data/image-clef/c/197_0043.jpg 3 557 | /data/image-clef/c/197_0012.jpg 3 558 | /data/image-clef/c/197_0037.jpg 3 559 | /data/image-clef/c/197_0010.jpg 3 560 | /data/image-clef/c/197_0013.jpg 3 561 | /data/image-clef/c/197_0074.jpg 3 562 | /data/image-clef/c/197_0079.jpg 3 563 | /data/image-clef/c/197_0014.jpg 3 564 | /data/image-clef/c/197_0091.jpg 3 565 | /data/image-clef/c/197_0068.jpg 3 566 | /data/image-clef/c/197_0060.jpg 3 567 | /data/image-clef/c/197_0077.jpg 3 568 | /data/image-clef/c/197_0011.jpg 3 569 | /data/image-clef/c/197_0051.jpg 3 570 | /data/image-clef/c/197_0052.jpg 3 571 | /data/image-clef/c/197_0057.jpg 3 572 | /data/image-clef/c/197_0007.jpg 3 573 | /data/image-clef/c/197_0085.jpg 3 574 | /data/image-clef/c/197_0058.jpg 3 575 | /data/image-clef/c/197_0016.jpg 3 576 | /data/image-clef/c/197_0001.jpg 3 577 | /data/image-clef/c/197_0082.jpg 3 578 | /data/image-clef/c/197_0028.jpg 3 579 | /data/image-clef/c/197_0030.jpg 3 580 | /data/image-clef/c/197_0034.jpg 3 581 | /data/image-clef/c/197_0055.jpg 3 582 | /data/image-clef/c/197_0073.jpg 3 583 | /data/image-clef/c/197_0031.jpg 3 584 | /data/image-clef/c/197_0065.jpg 3 585 | /data/image-clef/c/197_0070.jpg 3 586 | /data/image-clef/c/197_0099.jpg 3 587 | /data/image-clef/c/197_0081.jpg 3 588 | /data/image-clef/c/197_0035.jpg 3 589 | /data/image-clef/c/197_0090.jpg 3 590 | /data/image-clef/c/197_0025.jpg 3 591 | /data/image-clef/c/197_0047.jpg 3 592 | /data/image-clef/c/197_0040.jpg 3 593 | /data/image-clef/c/197_0084.jpg 3 594 | /data/image-clef/c/197_0054.jpg 3 595 | /data/image-clef/c/197_0046.jpg 3 596 | /data/image-clef/c/197_0004.jpg 3 597 | /data/image-clef/c/197_0053.jpg 3 598 | /data/image-clef/c/197_0061.jpg 3 599 | /data/image-clef/c/197_0020.jpg 3 600 | /data/image-clef/c/197_0049.jpg 3 601 | -------------------------------------------------------------------------------- /data/image-clef/i_list.txt: -------------------------------------------------------------------------------- 1 | /data/image-clef/i/n02691156_7563.JPEG 0 2 | /data/image-clef/i/n02691156_30456.JPEG 0 3 | /data/image-clef/i/n02691156_4273.JPEG 0 4 | /data/image-clef/i/n02691156_21342.JPEG 0 5 | /data/image-clef/i/n02691156_11944.JPEG 0 6 | /data/image-clef/i/n02691156_8007.JPEG 0 7 | /data/image-clef/i/n02691156_2510.JPEG 0 8 | /data/image-clef/i/n02691156_1682.JPEG 0 9 | /data/image-clef/i/n02691156_30294.JPEG 0 10 | /data/image-clef/i/n02691156_6973.JPEG 0 11 | /data/image-clef/i/n02691156_2351.JPEG 0 12 | /data/image-clef/i/n02691156_12350.JPEG 0 13 | /data/image-clef/i/n02691156_6382.JPEG 0 14 | /data/image-clef/i/n02691156_10045.JPEG 0 15 | /data/image-clef/i/n02691156_1663.JPEG 0 16 | /data/image-clef/i/n02691156_12546.JPEG 0 17 | /data/image-clef/i/n02691156_240.JPEG 0 18 | /data/image-clef/i/n02691156_49198.JPEG 0 19 | /data/image-clef/i/n02691156_7515.JPEG 0 20 | /data/image-clef/i/n02691156_2701.JPEG 0 21 | /data/image-clef/i/n02691156_10027.JPEG 0 22 | /data/image-clef/i/n02691156_29561.JPEG 0 23 | /data/image-clef/i/n02691156_11169.JPEG 0 24 | /data/image-clef/i/n02691156_10494.JPEG 0 25 | /data/image-clef/i/n02691156_54301.JPEG 0 26 | /data/image-clef/i/n02691156_1806.JPEG 0 27 | /data/image-clef/i/n02691156_38031.JPEG 0 28 | /data/image-clef/i/n02691156_38968.JPEG 0 29 | /data/image-clef/i/n02691156_3107.JPEG 0 30 | /data/image-clef/i/n02691156_11788.JPEG 0 31 | /data/image-clef/i/n02691156_3581.JPEG 0 32 | /data/image-clef/i/n02691156_7304.JPEG 0 33 | /data/image-clef/i/n02691156_12581.JPEG 0 34 | /data/image-clef/i/n02691156_11550.JPEG 0 35 | /data/image-clef/i/n02691156_31395.JPEG 0 36 | /data/image-clef/i/n02691156_52254.JPEG 0 37 | /data/image-clef/i/n02691156_7196.JPEG 0 38 | /data/image-clef/i/n02691156_6587.JPEG 0 39 | /data/image-clef/i/n02691156_1015.JPEG 0 40 | /data/image-clef/i/n02691156_38570.JPEG 0 41 | /data/image-clef/i/n02691156_6673.JPEG 0 42 | /data/image-clef/i/n02691156_9079.JPEG 0 43 | /data/image-clef/i/n02691156_5975.JPEG 0 44 | /data/image-clef/i/n02691156_6122.JPEG 0 45 | /data/image-clef/i/n02691156_7027.JPEG 0 46 | /data/image-clef/i/n02691156_11729.JPEG 0 47 | /data/image-clef/i/n02691156_2289.JPEG 0 48 | /data/image-clef/i/n02691156_89.JPEG 0 49 | /data/image-clef/i/n02691156_4662.JPEG 0 50 | /data/image-clef/i/n02691156_14912.JPEG 0 51 | /data/image-clef/i/n02084071_12460.JPEG 7 52 | /data/image-clef/i/n02084071_766.JPEG 7 53 | /data/image-clef/i/n02084071_25409.JPEG 7 54 | /data/image-clef/i/n02084071_1389.JPEG 7 55 | /data/image-clef/i/n02084071_1445.JPEG 7 56 | /data/image-clef/i/n02084071_15074.JPEG 7 57 | /data/image-clef/i/n02084071_18746.JPEG 7 58 | /data/image-clef/i/n02084071_7940.JPEG 7 59 | /data/image-clef/i/n02084071_23498.JPEG 7 60 | /data/image-clef/i/n02084071_23239.JPEG 7 61 | /data/image-clef/i/n02084071_661.JPEG 7 62 | /data/image-clef/i/n02084071_525.JPEG 7 63 | /data/image-clef/i/n02084071_11564.JPEG 7 64 | /data/image-clef/i/n02084071_32835.JPEG 7 65 | /data/image-clef/i/n02084071_32500.JPEG 7 66 | /data/image-clef/i/n02084071_9138.JPEG 7 67 | /data/image-clef/i/n02084071_4657.JPEG 7 68 | /data/image-clef/i/n02084071_27936.JPEG 7 69 | /data/image-clef/i/n02084071_760.JPEG 7 70 | /data/image-clef/i/n02084071_32569.JPEG 7 71 | /data/image-clef/i/n02084071_17496.JPEG 7 72 | /data/image-clef/i/n02084071_2103.JPEG 7 73 | /data/image-clef/i/n02084071_11287.JPEG 7 74 | /data/image-clef/i/n02084071_31709.JPEG 7 75 | /data/image-clef/i/n02084071_5662.JPEG 7 76 | /data/image-clef/i/n02084071_5128.JPEG 7 77 | /data/image-clef/i/n02084071_182.JPEG 7 78 | /data/image-clef/i/n02084071_24007.JPEG 7 79 | /data/image-clef/i/n02084071_22620.JPEG 7 80 | /data/image-clef/i/n02084071_29560.JPEG 7 81 | /data/image-clef/i/n02084071_27730.JPEG 7 82 | /data/image-clef/i/n02084071_34874.JPEG 7 83 | /data/image-clef/i/n02084071_25631.JPEG 7 84 | /data/image-clef/i/n02084071_17180.JPEG 7 85 | /data/image-clef/i/n02084071_2732.JPEG 7 86 | /data/image-clef/i/n02084071_7098.JPEG 7 87 | /data/image-clef/i/n02084071_16131.JPEG 7 88 | /data/image-clef/i/n02084071_1848.JPEG 7 89 | /data/image-clef/i/n02084071_19134.JPEG 7 90 | /data/image-clef/i/n02084071_545.JPEG 7 91 | /data/image-clef/i/n02084071_243.JPEG 7 92 | /data/image-clef/i/n02084071_22252.JPEG 7 93 | /data/image-clef/i/n02084071_8803.JPEG 7 94 | /data/image-clef/i/n02084071_22378.JPEG 7 95 | /data/image-clef/i/n02084071_31703.JPEG 7 96 | /data/image-clef/i/n02084071_108.JPEG 7 97 | /data/image-clef/i/n02084071_26796.JPEG 7 98 | /data/image-clef/i/n02084071_27298.JPEG 7 99 | /data/image-clef/i/n02084071_29282.JPEG 7 100 | /data/image-clef/i/n02084071_28769.JPEG 7 101 | /data/image-clef/i/n02858304_9777.JPEG 3 102 | /data/image-clef/i/n02858304_837.JPEG 3 103 | /data/image-clef/i/n02858304_9962.JPEG 3 104 | /data/image-clef/i/n02858304_576.JPEG 3 105 | /data/image-clef/i/n02858304_236.JPEG 3 106 | /data/image-clef/i/n02858304_1610.JPEG 3 107 | /data/image-clef/i/n02858304_1921.JPEG 3 108 | /data/image-clef/i/n02858304_3759.JPEG 3 109 | /data/image-clef/i/n02858304_3730.JPEG 3 110 | /data/image-clef/i/n02858304_20876.JPEG 3 111 | /data/image-clef/i/n02858304_7454.JPEG 3 112 | /data/image-clef/i/n02858304_9208.JPEG 3 113 | /data/image-clef/i/n02858304_169.JPEG 3 114 | /data/image-clef/i/n02858304_312.JPEG 3 115 | /data/image-clef/i/n02858304_3137.JPEG 3 116 | /data/image-clef/i/n02858304_676.JPEG 3 117 | /data/image-clef/i/n02858304_3574.JPEG 3 118 | /data/image-clef/i/n02858304_1249.JPEG 3 119 | /data/image-clef/i/n02858304_1883.JPEG 3 120 | /data/image-clef/i/n02858304_9938.JPEG 3 121 | /data/image-clef/i/n02858304_3268.JPEG 3 122 | /data/image-clef/i/n02858304_3030.JPEG 3 123 | /data/image-clef/i/n02858304_917.JPEG 3 124 | /data/image-clef/i/n02858304_3175.JPEG 3 125 | /data/image-clef/i/n02858304_2400.JPEG 3 126 | /data/image-clef/i/n02858304_416.JPEG 3 127 | /data/image-clef/i/n02858304_746.JPEG 3 128 | /data/image-clef/i/n02858304_4082.JPEG 3 129 | /data/image-clef/i/n02858304_454.JPEG 3 130 | /data/image-clef/i/n02858304_3112.JPEG 3 131 | /data/image-clef/i/n02858304_9362.JPEG 3 132 | /data/image-clef/i/n02858304_8049.JPEG 3 133 | /data/image-clef/i/n02858304_9973.JPEG 3 134 | /data/image-clef/i/n02858304_19915.JPEG 3 135 | /data/image-clef/i/n02858304_2818.JPEG 3 136 | /data/image-clef/i/n02858304_4052.JPEG 3 137 | /data/image-clef/i/n02858304_2348.JPEG 3 138 | /data/image-clef/i/n02858304_379.JPEG 3 139 | /data/image-clef/i/n02858304_8479.JPEG 3 140 | /data/image-clef/i/n02858304_10332.JPEG 3 141 | /data/image-clef/i/n02858304_1612.JPEG 3 142 | /data/image-clef/i/n02858304_10526.JPEG 3 143 | /data/image-clef/i/n02858304_8155.JPEG 3 144 | /data/image-clef/i/n02858304_4545.JPEG 3 145 | /data/image-clef/i/n02858304_2126.JPEG 3 146 | /data/image-clef/i/n02858304_391.JPEG 3 147 | /data/image-clef/i/n02858304_2049.JPEG 3 148 | /data/image-clef/i/n02858304_7231.JPEG 3 149 | /data/image-clef/i/n02858304_2175.JPEG 3 150 | /data/image-clef/i/n02858304_9844.JPEG 3 151 | /data/image-clef/i/n02924116_64004.JPEG 5 152 | /data/image-clef/i/n02924116_84238.JPEG 5 153 | /data/image-clef/i/n02924116_53329.JPEG 5 154 | /data/image-clef/i/n02924116_9012.JPEG 5 155 | /data/image-clef/i/n02924116_73751.JPEG 5 156 | /data/image-clef/i/n02924116_56702.JPEG 5 157 | /data/image-clef/i/n02924116_85589.JPEG 5 158 | /data/image-clef/i/n02924116_34753.JPEG 5 159 | /data/image-clef/i/n02924116_20498.JPEG 5 160 | /data/image-clef/i/n02924116_57267.JPEG 5 161 | /data/image-clef/i/n02924116_38704.JPEG 5 162 | /data/image-clef/i/n02924116_93395.JPEG 5 163 | /data/image-clef/i/n02924116_14503.JPEG 5 164 | /data/image-clef/i/n02924116_51663.JPEG 5 165 | /data/image-clef/i/n02924116_33800.JPEG 5 166 | /data/image-clef/i/n02924116_73378.JPEG 5 167 | /data/image-clef/i/n02924116_39743.JPEG 5 168 | /data/image-clef/i/n02924116_10156.JPEG 5 169 | /data/image-clef/i/n02924116_78093.JPEG 5 170 | /data/image-clef/i/n02924116_18209.JPEG 5 171 | /data/image-clef/i/n02924116_73434.JPEG 5 172 | /data/image-clef/i/n02924116_3470.JPEG 5 173 | /data/image-clef/i/n02924116_61109.JPEG 5 174 | /data/image-clef/i/n02924116_61339.JPEG 5 175 | /data/image-clef/i/n02924116_35958.JPEG 5 176 | /data/image-clef/i/n02924116_84781.JPEG 5 177 | /data/image-clef/i/n02924116_33755.JPEG 5 178 | /data/image-clef/i/n02924116_43906.JPEG 5 179 | /data/image-clef/i/n02924116_67006.JPEG 5 180 | /data/image-clef/i/n02924116_73904.JPEG 5 181 | /data/image-clef/i/n02924116_44980.JPEG 5 182 | /data/image-clef/i/n02924116_78812.JPEG 5 183 | /data/image-clef/i/n02924116_37730.JPEG 5 184 | /data/image-clef/i/n02924116_82999.JPEG 5 185 | /data/image-clef/i/n02924116_37402.JPEG 5 186 | /data/image-clef/i/n02924116_73389.JPEG 5 187 | /data/image-clef/i/n02924116_3941.JPEG 5 188 | /data/image-clef/i/n02924116_77225.JPEG 5 189 | /data/image-clef/i/n02924116_8054.JPEG 5 190 | /data/image-clef/i/n02924116_50926.JPEG 5 191 | /data/image-clef/i/n02924116_68762.JPEG 5 192 | /data/image-clef/i/n02924116_95090.JPEG 5 193 | /data/image-clef/i/n02924116_82453.JPEG 5 194 | /data/image-clef/i/n02924116_37624.JPEG 5 195 | /data/image-clef/i/n02924116_65903.JPEG 5 196 | /data/image-clef/i/n02924116_33400.JPEG 5 197 | /data/image-clef/i/n02924116_647.JPEG 5 198 | /data/image-clef/i/n02924116_86629.JPEG 5 199 | /data/image-clef/i/n02924116_3352.JPEG 5 200 | /data/image-clef/i/n02924116_30382.JPEG 5 201 | /data/image-clef/i/n03782190_12209.JPEG 9 202 | /data/image-clef/i/n03782190_2426.JPEG 9 203 | /data/image-clef/i/n03782190_5658.JPEG 9 204 | /data/image-clef/i/n03782190_2152.JPEG 9 205 | /data/image-clef/i/n03782190_11158.JPEG 9 206 | /data/image-clef/i/n03782190_13975.JPEG 9 207 | /data/image-clef/i/n03782190_225.JPEG 9 208 | /data/image-clef/i/n03782190_15774.JPEG 9 209 | /data/image-clef/i/n03782190_14408.JPEG 9 210 | /data/image-clef/i/n03782190_12880.JPEG 9 211 | /data/image-clef/i/n03782190_5464.JPEG 9 212 | /data/image-clef/i/n03782190_7494.JPEG 9 213 | /data/image-clef/i/n03782190_4205.JPEG 9 214 | /data/image-clef/i/n03782190_12034.JPEG 9 215 | /data/image-clef/i/n03782190_4945.JPEG 9 216 | /data/image-clef/i/n03782190_4268.JPEG 9 217 | /data/image-clef/i/n03782190_10175.JPEG 9 218 | /data/image-clef/i/n03782190_14532.JPEG 9 219 | /data/image-clef/i/n03782190_2218.JPEG 9 220 | /data/image-clef/i/n03782190_9627.JPEG 9 221 | /data/image-clef/i/n03782190_8233.JPEG 9 222 | /data/image-clef/i/n03782190_9951.JPEG 9 223 | /data/image-clef/i/n03782190_6762.JPEG 9 224 | /data/image-clef/i/n03782190_14178.JPEG 9 225 | /data/image-clef/i/n03782190_4015.JPEG 9 226 | /data/image-clef/i/n03782190_1982.JPEG 9 227 | /data/image-clef/i/n03782190_1626.JPEG 9 228 | /data/image-clef/i/n03782190_1214.JPEG 9 229 | /data/image-clef/i/n03782190_15928.JPEG 9 230 | /data/image-clef/i/n03782190_2513.JPEG 9 231 | /data/image-clef/i/n03782190_5220.JPEG 9 232 | /data/image-clef/i/n03782190_220.JPEG 9 233 | /data/image-clef/i/n03782190_19506.JPEG 9 234 | /data/image-clef/i/n03782190_1776.JPEG 9 235 | /data/image-clef/i/n03782190_11918.JPEG 9 236 | /data/image-clef/i/n03782190_20760.JPEG 9 237 | /data/image-clef/i/n03782190_11999.JPEG 9 238 | /data/image-clef/i/n03782190_7533.JPEG 9 239 | /data/image-clef/i/n03782190_15896.JPEG 9 240 | /data/image-clef/i/n03782190_2523.JPEG 9 241 | /data/image-clef/i/n03782190_7111.JPEG 9 242 | /data/image-clef/i/n03782190_14888.JPEG 9 243 | /data/image-clef/i/n03782190_6319.JPEG 9 244 | /data/image-clef/i/n03782190_2154.JPEG 9 245 | /data/image-clef/i/n03782190_17955.JPEG 9 246 | /data/image-clef/i/n03782190_4211.JPEG 9 247 | /data/image-clef/i/n03782190_3964.JPEG 9 248 | /data/image-clef/i/n03782190_11648.JPEG 9 249 | /data/image-clef/i/n03782190_7286.JPEG 9 250 | /data/image-clef/i/n03782190_17779.JPEG 9 251 | /data/image-clef/i/n07942152_33397.JPEG 11 252 | /data/image-clef/i/n07942152_27123.JPEG 11 253 | /data/image-clef/i/n07942152_19556.JPEG 11 254 | /data/image-clef/i/n07942152_56.JPEG 11 255 | /data/image-clef/i/n07942152_12547.JPEG 11 256 | /data/image-clef/i/n07942152_76119.JPEG 11 257 | /data/image-clef/i/n07942152_22807.JPEG 11 258 | /data/image-clef/i/n07942152_32300.JPEG 11 259 | /data/image-clef/i/n07942152_33090.JPEG 11 260 | /data/image-clef/i/n07942152_13151.JPEG 11 261 | /data/image-clef/i/n07942152_56835.JPEG 11 262 | /data/image-clef/i/n07942152_36134.JPEG 11 263 | /data/image-clef/i/n07942152_16845.JPEG 11 264 | /data/image-clef/i/n07942152_9563.JPEG 11 265 | /data/image-clef/i/n07942152_16633.JPEG 11 266 | /data/image-clef/i/n07942152_8261.JPEG 11 267 | /data/image-clef/i/n07942152_27105.JPEG 11 268 | /data/image-clef/i/n07942152_4183.JPEG 11 269 | /data/image-clef/i/n07942152_34434.JPEG 11 270 | /data/image-clef/i/n07942152_18551.JPEG 11 271 | /data/image-clef/i/n07942152_413.JPEG 11 272 | /data/image-clef/i/n07942152_510.JPEG 11 273 | /data/image-clef/i/n07942152_27529.JPEG 11 274 | /data/image-clef/i/n07942152_31584.JPEG 11 275 | /data/image-clef/i/n07942152_38507.JPEG 11 276 | /data/image-clef/i/n07942152_37969.JPEG 11 277 | /data/image-clef/i/n07942152_30118.JPEG 11 278 | /data/image-clef/i/n07942152_3594.JPEG 11 279 | /data/image-clef/i/n07942152_5568.JPEG 11 280 | /data/image-clef/i/n07942152_35239.JPEG 11 281 | /data/image-clef/i/n07942152_5588.JPEG 11 282 | /data/image-clef/i/n07942152_42078.JPEG 11 283 | /data/image-clef/i/n07942152_34679.JPEG 11 284 | /data/image-clef/i/n07942152_8418.JPEG 11 285 | /data/image-clef/i/n07942152_24975.JPEG 11 286 | /data/image-clef/i/n07942152_28165.JPEG 11 287 | /data/image-clef/i/n07942152_8542.JPEG 11 288 | /data/image-clef/i/n07942152_5592.JPEG 11 289 | /data/image-clef/i/n07942152_4777.JPEG 11 290 | /data/image-clef/i/n07942152_33797.JPEG 11 291 | /data/image-clef/i/n07942152_14349.JPEG 11 292 | /data/image-clef/i/n07942152_36072.JPEG 11 293 | /data/image-clef/i/n07942152_40587.JPEG 11 294 | /data/image-clef/i/n07942152_37972.JPEG 11 295 | /data/image-clef/i/n07942152_33751.JPEG 11 296 | /data/image-clef/i/n07942152_14138.JPEG 11 297 | /data/image-clef/i/n07942152_27703.JPEG 11 298 | /data/image-clef/i/n07942152_27649.JPEG 11 299 | /data/image-clef/i/n07942152_38584.JPEG 11 300 | /data/image-clef/i/n07942152_37885.JPEG 11 301 | /data/image-clef/i/n01503061_1868.JPEG 2 302 | /data/image-clef/i/n01503061_11612.JPEG 2 303 | /data/image-clef/i/n01503061_5453.JPEG 2 304 | /data/image-clef/i/n01503061_8646.JPEG 2 305 | /data/image-clef/i/n01503061_4167.JPEG 2 306 | /data/image-clef/i/n01503061_17521.JPEG 2 307 | /data/image-clef/i/n01503061_1387.JPEG 2 308 | /data/image-clef/i/n01503061_12696.JPEG 2 309 | /data/image-clef/i/n01503061_2819.JPEG 2 310 | /data/image-clef/i/n01503061_2744.JPEG 2 311 | /data/image-clef/i/n01503061_2378.JPEG 2 312 | /data/image-clef/i/n01503061_6413.JPEG 2 313 | /data/image-clef/i/n01503061_688.JPEG 2 314 | /data/image-clef/i/n01503061_3094.JPEG 2 315 | /data/image-clef/i/n01503061_2076.JPEG 2 316 | /data/image-clef/i/n01503061_1457.JPEG 2 317 | /data/image-clef/i/n01503061_2839.JPEG 2 318 | /data/image-clef/i/n01503061_13213.JPEG 2 319 | /data/image-clef/i/n01503061_13929.JPEG 2 320 | /data/image-clef/i/n01503061_14761.JPEG 2 321 | /data/image-clef/i/n01503061_1202.JPEG 2 322 | /data/image-clef/i/n01503061_1780.JPEG 2 323 | /data/image-clef/i/n01503061_9799.JPEG 2 324 | /data/image-clef/i/n01503061_5215.JPEG 2 325 | /data/image-clef/i/n01503061_1227.JPEG 2 326 | /data/image-clef/i/n01503061_6456.JPEG 2 327 | /data/image-clef/i/n01503061_3028.JPEG 2 328 | /data/image-clef/i/n01503061_6454.JPEG 2 329 | /data/image-clef/i/n01503061_552.JPEG 2 330 | /data/image-clef/i/n01503061_9622.JPEG 2 331 | /data/image-clef/i/n01503061_1825.JPEG 2 332 | /data/image-clef/i/n01503061_12735.JPEG 2 333 | /data/image-clef/i/n01503061_14886.JPEG 2 334 | /data/image-clef/i/n01503061_10665.JPEG 2 335 | /data/image-clef/i/n01503061_12662.JPEG 2 336 | /data/image-clef/i/n01503061_14700.JPEG 2 337 | /data/image-clef/i/n01503061_4379.JPEG 2 338 | /data/image-clef/i/n01503061_13119.JPEG 2 339 | /data/image-clef/i/n01503061_3862.JPEG 2 340 | /data/image-clef/i/n01503061_5054.JPEG 2 341 | /data/image-clef/i/n01503061_2167.JPEG 2 342 | /data/image-clef/i/n01503061_11048.JPEG 2 343 | /data/image-clef/i/n01503061_4150.JPEG 2 344 | /data/image-clef/i/n01503061_13495.JPEG 2 345 | /data/image-clef/i/n01503061_1306.JPEG 2 346 | /data/image-clef/i/n01503061_7783.JPEG 2 347 | /data/image-clef/i/n01503061_13307.JPEG 2 348 | /data/image-clef/i/n01503061_9390.JPEG 2 349 | /data/image-clef/i/n01503061_9081.JPEG 2 350 | /data/image-clef/i/n01503061_2386.JPEG 2 351 | /data/image-clef/i/n02374451_12030.JPEG 8 352 | /data/image-clef/i/n02374451_151.JPEG 8 353 | /data/image-clef/i/n02374451_15002.JPEG 8 354 | /data/image-clef/i/n02374451_9975.JPEG 8 355 | /data/image-clef/i/n02374451_2978.JPEG 8 356 | /data/image-clef/i/n02374451_4722.JPEG 8 357 | /data/image-clef/i/n02374451_8251.JPEG 8 358 | /data/image-clef/i/n02374451_13125.JPEG 8 359 | /data/image-clef/i/n02374451_6254.JPEG 8 360 | /data/image-clef/i/n02374451_4795.JPEG 8 361 | /data/image-clef/i/n02374451_1284.JPEG 8 362 | /data/image-clef/i/n02374451_16310.JPEG 8 363 | /data/image-clef/i/n02374451_6017.JPEG 8 364 | /data/image-clef/i/n02374451_13929.JPEG 8 365 | /data/image-clef/i/n02374451_5598.JPEG 8 366 | /data/image-clef/i/n02374451_5013.JPEG 8 367 | /data/image-clef/i/n02374451_16603.JPEG 8 368 | /data/image-clef/i/n02374451_15685.JPEG 8 369 | /data/image-clef/i/n02374451_14586.JPEG 8 370 | /data/image-clef/i/n02374451_17474.JPEG 8 371 | /data/image-clef/i/n02374451_816.JPEG 8 372 | /data/image-clef/i/n02374451_15098.JPEG 8 373 | /data/image-clef/i/n02374451_9897.JPEG 8 374 | /data/image-clef/i/n02374451_14233.JPEG 8 375 | /data/image-clef/i/n02374451_15663.JPEG 8 376 | /data/image-clef/i/n02374451_13953.JPEG 8 377 | /data/image-clef/i/n02374451_11173.JPEG 8 378 | /data/image-clef/i/n02374451_12024.JPEG 8 379 | /data/image-clef/i/n02374451_12086.JPEG 8 380 | /data/image-clef/i/n02374451_19198.JPEG 8 381 | /data/image-clef/i/n02374451_20103.JPEG 8 382 | /data/image-clef/i/n02374451_8301.JPEG 8 383 | /data/image-clef/i/n02374451_16785.JPEG 8 384 | /data/image-clef/i/n02374451_15633.JPEG 8 385 | /data/image-clef/i/n02374451_14329.JPEG 8 386 | /data/image-clef/i/n02374451_597.JPEG 8 387 | /data/image-clef/i/n02374451_820.JPEG 8 388 | /data/image-clef/i/n02374451_2944.JPEG 8 389 | /data/image-clef/i/n02374451_9264.JPEG 8 390 | /data/image-clef/i/n02374451_11057.JPEG 8 391 | /data/image-clef/i/n02374451_13159.JPEG 8 392 | /data/image-clef/i/n02374451_4240.JPEG 8 393 | /data/image-clef/i/n02374451_11483.JPEG 8 394 | /data/image-clef/i/n02374451_4479.JPEG 8 395 | /data/image-clef/i/n02374451_2846.JPEG 8 396 | /data/image-clef/i/n02374451_18419.JPEG 8 397 | /data/image-clef/i/n02374451_12376.JPEG 8 398 | /data/image-clef/i/n02374451_18141.JPEG 8 399 | /data/image-clef/i/n02374451_16449.JPEG 8 400 | /data/image-clef/i/n02374451_1062.JPEG 8 401 | /data/image-clef/i/n02834778_5790.JPEG 1 402 | /data/image-clef/i/n02834778_8639.JPEG 1 403 | /data/image-clef/i/n02834778_10647.JPEG 1 404 | /data/image-clef/i/n02834778_6733.JPEG 1 405 | /data/image-clef/i/n02834778_5206.JPEG 1 406 | /data/image-clef/i/n02834778_10288.JPEG 1 407 | /data/image-clef/i/n02834778_763.JPEG 1 408 | /data/image-clef/i/n02834778_1533.JPEG 1 409 | /data/image-clef/i/n02834778_3090.JPEG 1 410 | /data/image-clef/i/n02834778_8949.JPEG 1 411 | /data/image-clef/i/n02834778_5311.JPEG 1 412 | /data/image-clef/i/n02834778_6571.JPEG 1 413 | /data/image-clef/i/n02834778_12206.JPEG 1 414 | /data/image-clef/i/n02834778_2196.JPEG 1 415 | /data/image-clef/i/n02834778_4013.JPEG 1 416 | /data/image-clef/i/n02834778_5247.JPEG 1 417 | /data/image-clef/i/n02834778_8507.JPEG 1 418 | /data/image-clef/i/n02834778_9153.JPEG 1 419 | /data/image-clef/i/n02834778_43697.JPEG 1 420 | /data/image-clef/i/n02834778_5420.JPEG 1 421 | /data/image-clef/i/n02834778_11280.JPEG 1 422 | /data/image-clef/i/n02834778_716.JPEG 1 423 | /data/image-clef/i/n02834778_31006.JPEG 1 424 | /data/image-clef/i/n02834778_8044.JPEG 1 425 | /data/image-clef/i/n02834778_7161.JPEG 1 426 | /data/image-clef/i/n02834778_9223.JPEG 1 427 | /data/image-clef/i/n02834778_11400.JPEG 1 428 | /data/image-clef/i/n02834778_5314.JPEG 1 429 | /data/image-clef/i/n02834778_10781.JPEG 1 430 | /data/image-clef/i/n02834778_187.JPEG 1 431 | /data/image-clef/i/n02834778_3345.JPEG 1 432 | /data/image-clef/i/n02834778_10227.JPEG 1 433 | /data/image-clef/i/n02834778_817.JPEG 1 434 | /data/image-clef/i/n02834778_700.JPEG 1 435 | /data/image-clef/i/n02834778_46418.JPEG 1 436 | /data/image-clef/i/n02834778_6597.JPEG 1 437 | /data/image-clef/i/n02834778_4695.JPEG 1 438 | /data/image-clef/i/n02834778_3311.JPEG 1 439 | /data/image-clef/i/n02834778_8918.JPEG 1 440 | /data/image-clef/i/n02834778_3735.JPEG 1 441 | /data/image-clef/i/n02834778_3119.JPEG 1 442 | /data/image-clef/i/n02834778_32473.JPEG 1 443 | /data/image-clef/i/n02834778_2737.JPEG 1 444 | /data/image-clef/i/n02834778_673.JPEG 1 445 | /data/image-clef/i/n02834778_6375.JPEG 1 446 | /data/image-clef/i/n02834778_9232.JPEG 1 447 | /data/image-clef/i/n02834778_12188.JPEG 1 448 | /data/image-clef/i/n02834778_4302.JPEG 1 449 | /data/image-clef/i/n02834778_12386.JPEG 1 450 | /data/image-clef/i/n02834778_12754.JPEG 1 451 | /data/image-clef/i/n02876657_13023.JPEG 4 452 | /data/image-clef/i/n02876657_5177.JPEG 4 453 | /data/image-clef/i/n02876657_7612.JPEG 4 454 | /data/image-clef/i/n02876657_7965.JPEG 4 455 | /data/image-clef/i/n02876657_3827.JPEG 4 456 | /data/image-clef/i/n02876657_12118.JPEG 4 457 | /data/image-clef/i/n02876657_7993.JPEG 4 458 | /data/image-clef/i/n02876657_7201.JPEG 4 459 | /data/image-clef/i/n02876657_4709.JPEG 4 460 | /data/image-clef/i/n02876657_15101.JPEG 4 461 | /data/image-clef/i/n02876657_9504.JPEG 4 462 | /data/image-clef/i/n02876657_3720.JPEG 4 463 | /data/image-clef/i/n02876657_2631.JPEG 4 464 | /data/image-clef/i/n02876657_8629.JPEG 4 465 | /data/image-clef/i/n02876657_2245.JPEG 4 466 | /data/image-clef/i/n02876657_7018.JPEG 4 467 | /data/image-clef/i/n02876657_2856.JPEG 4 468 | /data/image-clef/i/n02876657_13959.JPEG 4 469 | /data/image-clef/i/n02876657_6293.JPEG 4 470 | /data/image-clef/i/n02876657_10725.JPEG 4 471 | /data/image-clef/i/n02876657_7886.JPEG 4 472 | /data/image-clef/i/n02876657_5324.JPEG 4 473 | /data/image-clef/i/n02876657_11443.JPEG 4 474 | /data/image-clef/i/n02876657_5481.JPEG 4 475 | /data/image-clef/i/n02876657_12301.JPEG 4 476 | /data/image-clef/i/n02876657_7718.JPEG 4 477 | /data/image-clef/i/n02876657_7244.JPEG 4 478 | /data/image-clef/i/n02876657_7535.JPEG 4 479 | /data/image-clef/i/n02876657_11695.JPEG 4 480 | /data/image-clef/i/n02876657_2625.JPEG 4 481 | /data/image-clef/i/n02876657_198.JPEG 4 482 | /data/image-clef/i/n02876657_668.JPEG 4 483 | /data/image-clef/i/n02876657_4138.JPEG 4 484 | /data/image-clef/i/n02876657_5822.JPEG 4 485 | /data/image-clef/i/n02876657_10178.JPEG 4 486 | /data/image-clef/i/n02876657_5094.JPEG 4 487 | /data/image-clef/i/n02876657_14142.JPEG 4 488 | /data/image-clef/i/n02876657_10103.JPEG 4 489 | /data/image-clef/i/n02876657_7576.JPEG 4 490 | /data/image-clef/i/n02876657_5276.JPEG 4 491 | /data/image-clef/i/n02876657_6246.JPEG 4 492 | /data/image-clef/i/n02876657_8209.JPEG 4 493 | /data/image-clef/i/n02876657_5612.JPEG 4 494 | /data/image-clef/i/n02876657_2191.JPEG 4 495 | /data/image-clef/i/n02876657_16228.JPEG 4 496 | /data/image-clef/i/n02876657_4991.JPEG 4 497 | /data/image-clef/i/n02876657_12397.JPEG 4 498 | /data/image-clef/i/n02876657_12206.JPEG 4 499 | /data/image-clef/i/n02876657_11898.JPEG 4 500 | /data/image-clef/i/n02876657_6550.JPEG 4 501 | /data/image-clef/i/n02958343_4976.JPEG 6 502 | /data/image-clef/i/n02958343_80662.JPEG 6 503 | /data/image-clef/i/n02958343_9147.JPEG 6 504 | /data/image-clef/i/n02958343_4414.JPEG 6 505 | /data/image-clef/i/n02958343_12811.JPEG 6 506 | /data/image-clef/i/n02958343_80339.JPEG 6 507 | /data/image-clef/i/n02958343_8796.JPEG 6 508 | /data/image-clef/i/n02958343_8490.JPEG 6 509 | /data/image-clef/i/n02958343_3541.JPEG 6 510 | /data/image-clef/i/n02958343_14006.JPEG 6 511 | /data/image-clef/i/n02958343_9672.JPEG 6 512 | /data/image-clef/i/n02958343_8811.JPEG 6 513 | /data/image-clef/i/n02958343_75694.JPEG 6 514 | /data/image-clef/i/n02958343_44103.JPEG 6 515 | /data/image-clef/i/n02958343_11718.JPEG 6 516 | /data/image-clef/i/n02958343_67754.JPEG 6 517 | /data/image-clef/i/n02958343_11586.JPEG 6 518 | /data/image-clef/i/n02958343_14713.JPEG 6 519 | /data/image-clef/i/n02958343_4478.JPEG 6 520 | /data/image-clef/i/n02958343_6654.JPEG 6 521 | /data/image-clef/i/n02958343_939.JPEG 6 522 | /data/image-clef/i/n02958343_4881.JPEG 6 523 | /data/image-clef/i/n02958343_13459.JPEG 6 524 | /data/image-clef/i/n02958343_10892.JPEG 6 525 | /data/image-clef/i/n02958343_5281.JPEG 6 526 | /data/image-clef/i/n02958343_3098.JPEG 6 527 | /data/image-clef/i/n02958343_13760.JPEG 6 528 | /data/image-clef/i/n02958343_10580.JPEG 6 529 | /data/image-clef/i/n02958343_9561.JPEG 6 530 | /data/image-clef/i/n02958343_52439.JPEG 6 531 | /data/image-clef/i/n02958343_8307.JPEG 6 532 | /data/image-clef/i/n02958343_50886.JPEG 6 533 | /data/image-clef/i/n02958343_9154.JPEG 6 534 | /data/image-clef/i/n02958343_13352.JPEG 6 535 | /data/image-clef/i/n02958343_4524.JPEG 6 536 | /data/image-clef/i/n02958343_5126.JPEG 6 537 | /data/image-clef/i/n02958343_9290.JPEG 6 538 | /data/image-clef/i/n02958343_4643.JPEG 6 539 | /data/image-clef/i/n02958343_9081.JPEG 6 540 | /data/image-clef/i/n02958343_8712.JPEG 6 541 | /data/image-clef/i/n02958343_61122.JPEG 6 542 | /data/image-clef/i/n02958343_12116.JPEG 6 543 | /data/image-clef/i/n02958343_55286.JPEG 6 544 | /data/image-clef/i/n02958343_65338.JPEG 6 545 | /data/image-clef/i/n02958343_14347.JPEG 6 546 | /data/image-clef/i/n02958343_8994.JPEG 6 547 | /data/image-clef/i/n02958343_77917.JPEG 6 548 | /data/image-clef/i/n02958343_11703.JPEG 6 549 | /data/image-clef/i/n02958343_2032.JPEG 6 550 | /data/image-clef/i/n02958343_11693.JPEG 6 551 | /data/image-clef/i/n03790512_722.JPEG 10 552 | /data/image-clef/i/n03790512_9326.JPEG 10 553 | /data/image-clef/i/n03790512_13080.JPEG 10 554 | /data/image-clef/i/n03790512_7537.JPEG 10 555 | /data/image-clef/i/n03790512_2370.JPEG 10 556 | /data/image-clef/i/n03790512_37212.JPEG 10 557 | /data/image-clef/i/n03790512_11812.JPEG 10 558 | /data/image-clef/i/n03790512_13431.JPEG 10 559 | /data/image-clef/i/n03790512_10965.JPEG 10 560 | /data/image-clef/i/n03790512_10260.JPEG 10 561 | /data/image-clef/i/n03790512_2068.JPEG 10 562 | /data/image-clef/i/n03790512_9022.JPEG 10 563 | /data/image-clef/i/n03790512_11545.JPEG 10 564 | /data/image-clef/i/n03790512_17139.JPEG 10 565 | /data/image-clef/i/n03790512_40609.JPEG 10 566 | /data/image-clef/i/n03790512_8982.JPEG 10 567 | /data/image-clef/i/n03790512_12426.JPEG 10 568 | /data/image-clef/i/n03790512_10023.JPEG 10 569 | /data/image-clef/i/n03790512_9187.JPEG 10 570 | /data/image-clef/i/n03790512_8654.JPEG 10 571 | /data/image-clef/i/n03790512_7308.JPEG 10 572 | /data/image-clef/i/n03790512_11298.JPEG 10 573 | /data/image-clef/i/n03790512_14972.JPEG 10 574 | /data/image-clef/i/n03790512_12946.JPEG 10 575 | /data/image-clef/i/n03790512_12093.JPEG 10 576 | /data/image-clef/i/n03790512_25915.JPEG 10 577 | /data/image-clef/i/n03790512_14967.JPEG 10 578 | /data/image-clef/i/n03790512_5081.JPEG 10 579 | /data/image-clef/i/n03790512_9328.JPEG 10 580 | /data/image-clef/i/n03790512_4460.JPEG 10 581 | /data/image-clef/i/n03790512_8100.JPEG 10 582 | /data/image-clef/i/n03790512_38917.JPEG 10 583 | /data/image-clef/i/n03790512_6136.JPEG 10 584 | /data/image-clef/i/n03790512_5722.JPEG 10 585 | /data/image-clef/i/n03790512_11613.JPEG 10 586 | /data/image-clef/i/n03790512_14709.JPEG 10 587 | /data/image-clef/i/n03790512_6062.JPEG 10 588 | /data/image-clef/i/n03790512_9794.JPEG 10 589 | /data/image-clef/i/n03790512_6410.JPEG 10 590 | /data/image-clef/i/n03790512_7851.JPEG 10 591 | /data/image-clef/i/n03790512_10451.JPEG 10 592 | /data/image-clef/i/n03790512_8955.JPEG 10 593 | /data/image-clef/i/n03790512_310.JPEG 10 594 | /data/image-clef/i/n03790512_7743.JPEG 10 595 | /data/image-clef/i/n03790512_6050.JPEG 10 596 | /data/image-clef/i/n03790512_10888.JPEG 10 597 | /data/image-clef/i/n03790512_5892.JPEG 10 598 | /data/image-clef/i/n03790512_248.JPEG 10 599 | /data/image-clef/i/n03790512_1579.JPEG 10 600 | /data/image-clef/i/n03790512_13338.JPEG 10 601 | -------------------------------------------------------------------------------- /data/image-clef/p_list.txt: -------------------------------------------------------------------------------- 1 | /data/image-clef/p/2008_006463.jpg 0 2 | /data/image-clef/p/2011_000163.jpg 0 3 | /data/image-clef/p/2009_003635.jpg 0 4 | /data/image-clef/p/2009_002888.jpg 0 5 | /data/image-clef/p/2010_002695.jpg 0 6 | /data/image-clef/p/2008_003423.jpg 0 7 | /data/image-clef/p/2008_007970.jpg 0 8 | /data/image-clef/p/2008_005834.jpg 0 9 | /data/image-clef/p/2009_002199.jpg 0 10 | /data/image-clef/p/2009_000387.jpg 0 11 | /data/image-clef/p/2008_003703.jpg 0 12 | /data/image-clef/p/2009_000801.jpg 0 13 | /data/image-clef/p/2010_003559.jpg 0 14 | /data/image-clef/p/2009_000545.jpg 0 15 | /data/image-clef/p/2010_004312.jpg 0 16 | /data/image-clef/p/2008_006951.jpg 0 17 | /data/image-clef/p/2009_002432.jpg 0 18 | /data/image-clef/p/2010_003737.jpg 0 19 | /data/image-clef/p/2010_003933.jpg 0 20 | /data/image-clef/p/2011_001044.jpg 0 21 | /data/image-clef/p/2010_005224.jpg 0 22 | /data/image-clef/p/2011_002993.jpg 0 23 | /data/image-clef/p/2009_003199.jpg 0 24 | /data/image-clef/p/2009_002752.jpg 0 25 | /data/image-clef/p/2008_003575.jpg 0 26 | /data/image-clef/p/2010_000437.jpg 0 27 | /data/image-clef/p/2010_001139.jpg 0 28 | /data/image-clef/p/2009_004414.jpg 0 29 | /data/image-clef/p/2008_005905.jpg 0 30 | /data/image-clef/p/2009_002914.jpg 0 31 | /data/image-clef/p/2009_002714.jpg 0 32 | /data/image-clef/p/2009_000734.jpg 0 33 | /data/image-clef/p/2010_004063.jpg 0 34 | /data/image-clef/p/2009_005215.jpg 0 35 | /data/image-clef/p/2011_002675.jpg 0 36 | /data/image-clef/p/2008_007758.jpg 0 37 | /data/image-clef/p/2009_001199.jpg 0 38 | /data/image-clef/p/2011_001489.jpg 0 39 | /data/image-clef/p/2008_003033.jpg 0 40 | /data/image-clef/p/2010_000418.jpg 0 41 | /data/image-clef/p/2010_001413.jpg 0 42 | /data/image-clef/p/2011_001858.jpg 0 43 | /data/image-clef/p/2009_002999.jpg 0 44 | /data/image-clef/p/2010_000270.jpg 0 45 | /data/image-clef/p/2009_004653.jpg 0 46 | /data/image-clef/p/2008_000291.jpg 0 47 | /data/image-clef/p/2010_004917.jpg 0 48 | /data/image-clef/p/2009_000661.jpg 0 49 | /data/image-clef/p/2008_007442.jpg 0 50 | /data/image-clef/p/2011_002751.jpg 0 51 | /data/image-clef/p/2009_001585.jpg 11 52 | /data/image-clef/p/2008_002947.jpg 11 53 | /data/image-clef/p/2008_008231.jpg 11 54 | /data/image-clef/p/2011_001030.jpg 11 55 | /data/image-clef/p/2009_001011.jpg 11 56 | /data/image-clef/p/2008_000689.jpg 11 57 | /data/image-clef/p/2009_004205.jpg 11 58 | /data/image-clef/p/2008_000568.jpg 11 59 | /data/image-clef/p/2008_004814.jpg 11 60 | /data/image-clef/p/2009_004794.jpg 11 61 | /data/image-clef/p/2008_001408.jpg 11 62 | /data/image-clef/p/2011_000559.jpg 11 63 | /data/image-clef/p/2009_001690.jpg 11 64 | /data/image-clef/p/2009_004285.jpg 11 65 | /data/image-clef/p/2008_008745.jpg 11 66 | /data/image-clef/p/2008_001223.jpg 11 67 | /data/image-clef/p/2008_002499.jpg 11 68 | /data/image-clef/p/2011_002519.jpg 11 69 | /data/image-clef/p/2008_002809.jpg 11 70 | /data/image-clef/p/2010_000324.jpg 11 71 | /data/image-clef/p/2010_004222.jpg 11 72 | /data/image-clef/p/2011_002987.jpg 11 73 | /data/image-clef/p/2008_008659.jpg 11 74 | /data/image-clef/p/2008_005168.jpg 11 75 | /data/image-clef/p/2009_003071.jpg 11 76 | /data/image-clef/p/2010_004666.jpg 11 77 | /data/image-clef/p/2009_001952.jpg 11 78 | /data/image-clef/p/2010_004708.jpg 11 79 | /data/image-clef/p/2008_002758.jpg 11 80 | /data/image-clef/p/2008_006145.jpg 11 81 | /data/image-clef/p/2011_002097.jpg 11 82 | /data/image-clef/p/2009_001581.jpg 11 83 | /data/image-clef/p/2008_008162.jpg 11 84 | /data/image-clef/p/2009_002285.jpg 11 85 | /data/image-clef/p/2008_002675.jpg 11 86 | /data/image-clef/p/2008_002908.jpg 11 87 | /data/image-clef/p/2008_000552.jpg 11 88 | /data/image-clef/p/2008_000203.jpg 11 89 | /data/image-clef/p/2009_000529.jpg 11 90 | /data/image-clef/p/2008_002700.jpg 11 91 | /data/image-clef/p/2008_006554.jpg 11 92 | /data/image-clef/p/2008_006991.jpg 11 93 | /data/image-clef/p/2009_004032.jpg 11 94 | /data/image-clef/p/2008_000965.jpg 11 95 | /data/image-clef/p/2010_004160.jpg 11 96 | /data/image-clef/p/2011_003020.jpg 11 97 | /data/image-clef/p/2008_008705.jpg 11 98 | /data/image-clef/p/2008_002067.jpg 11 99 | /data/image-clef/p/2010_002346.jpg 11 100 | /data/image-clef/p/2008_005825.jpg 11 101 | /data/image-clef/p/2009_004197.jpg 5 102 | /data/image-clef/p/2009_000199.jpg 5 103 | /data/image-clef/p/2008_005196.jpg 5 104 | /data/image-clef/p/2010_002203.jpg 5 105 | /data/image-clef/p/2009_002436.jpg 5 106 | /data/image-clef/p/2010_005959.jpg 5 107 | /data/image-clef/p/2010_003293.jpg 5 108 | /data/image-clef/p/2008_008343.jpg 5 109 | /data/image-clef/p/2010_000603.jpg 5 110 | /data/image-clef/p/2009_000335.jpg 5 111 | /data/image-clef/p/2008_004794.jpg 5 112 | /data/image-clef/p/2010_001403.jpg 5 113 | /data/image-clef/p/2011_000267.jpg 5 114 | /data/image-clef/p/2009_001967.jpg 5 115 | /data/image-clef/p/2009_002066.jpg 5 116 | /data/image-clef/p/2009_001822.jpg 5 117 | /data/image-clef/p/2010_004637.jpg 5 118 | /data/image-clef/p/2011_001105.jpg 5 119 | /data/image-clef/p/2009_002566.jpg 5 120 | /data/image-clef/p/2008_003673.jpg 5 121 | /data/image-clef/p/2011_002330.jpg 5 122 | /data/image-clef/p/2009_002105.jpg 5 123 | /data/image-clef/p/2011_000007.jpg 5 124 | /data/image-clef/p/2010_001646.jpg 5 125 | /data/image-clef/p/2011_000138.jpg 5 126 | /data/image-clef/p/2010_000947.jpg 5 127 | /data/image-clef/p/2011_003114.jpg 5 128 | /data/image-clef/p/2010_002263.jpg 5 129 | /data/image-clef/p/2009_002398.jpg 5 130 | /data/image-clef/p/2008_006483.jpg 5 131 | /data/image-clef/p/2010_003173.jpg 5 132 | /data/image-clef/p/2010_005118.jpg 5 133 | /data/image-clef/p/2009_001847.jpg 5 134 | /data/image-clef/p/2009_001098.jpg 5 135 | /data/image-clef/p/2011_001536.jpg 5 136 | /data/image-clef/p/2010_005063.jpg 5 137 | /data/image-clef/p/2011_001341.jpg 5 138 | /data/image-clef/p/2010_005080.jpg 5 139 | /data/image-clef/p/2009_000140.jpg 5 140 | /data/image-clef/p/2009_004040.jpg 5 141 | /data/image-clef/p/2011_001110.jpg 5 142 | /data/image-clef/p/2010_001771.jpg 5 143 | /data/image-clef/p/2010_002102.jpg 5 144 | /data/image-clef/p/2008_008080.jpg 5 145 | /data/image-clef/p/2009_005279.jpg 5 146 | /data/image-clef/p/2009_001675.jpg 5 147 | /data/image-clef/p/2009_001590.jpg 5 148 | /data/image-clef/p/2010_003534.jpg 5 149 | /data/image-clef/p/2010_004997.jpg 5 150 | /data/image-clef/p/2009_002052.jpg 5 151 | /data/image-clef/p/2010_004766.jpg 10 152 | /data/image-clef/p/2008_004345.jpg 10 153 | /data/image-clef/p/2011_000927.jpg 10 154 | /data/image-clef/p/2009_004845.jpg 10 155 | /data/image-clef/p/2010_003947.jpg 10 156 | /data/image-clef/p/2008_005637.jpg 10 157 | /data/image-clef/p/2009_002894.jpg 10 158 | /data/image-clef/p/2010_000495.jpg 10 159 | /data/image-clef/p/2010_002408.jpg 10 160 | /data/image-clef/p/2008_005427.jpg 10 161 | /data/image-clef/p/2011_000496.jpg 10 162 | /data/image-clef/p/2008_000545.jpg 10 163 | /data/image-clef/p/2009_001135.jpg 10 164 | /data/image-clef/p/2010_005252.jpg 10 165 | /data/image-clef/p/2010_005199.jpg 10 166 | /data/image-clef/p/2009_001805.jpg 10 167 | /data/image-clef/p/2009_004502.jpg 10 168 | /data/image-clef/p/2008_004615.jpg 10 169 | /data/image-clef/p/2011_000512.jpg 10 170 | /data/image-clef/p/2011_001040.jpg 10 171 | /data/image-clef/p/2008_003249.jpg 10 172 | /data/image-clef/p/2008_003618.jpg 10 173 | /data/image-clef/p/2008_004371.jpg 10 174 | /data/image-clef/p/2008_002191.jpg 10 175 | /data/image-clef/p/2011_000034.jpg 10 176 | /data/image-clef/p/2008_003429.jpg 10 177 | /data/image-clef/p/2010_005997.jpg 10 178 | /data/image-clef/p/2008_005893.jpg 10 179 | /data/image-clef/p/2009_001646.jpg 10 180 | /data/image-clef/p/2010_000695.jpg 10 181 | /data/image-clef/p/2008_001150.jpg 10 182 | /data/image-clef/p/2009_003560.jpg 10 183 | /data/image-clef/p/2011_002598.jpg 10 184 | /data/image-clef/p/2010_004143.jpg 10 185 | /data/image-clef/p/2010_001828.jpg 10 186 | /data/image-clef/p/2009_003020.jpg 10 187 | /data/image-clef/p/2009_003090.jpg 10 188 | /data/image-clef/p/2009_004117.jpg 10 189 | /data/image-clef/p/2008_008218.jpg 10 190 | /data/image-clef/p/2009_003747.jpg 10 191 | /data/image-clef/p/2009_004738.jpg 10 192 | /data/image-clef/p/2008_008097.jpg 10 193 | /data/image-clef/p/2008_007558.jpg 10 194 | /data/image-clef/p/2008_002115.jpg 10 195 | /data/image-clef/p/2008_007075.jpg 10 196 | /data/image-clef/p/2008_004084.jpg 10 197 | /data/image-clef/p/2008_001119.jpg 10 198 | /data/image-clef/p/2008_001631.jpg 10 199 | /data/image-clef/p/2009_003639.jpg 10 200 | /data/image-clef/p/2008_008227.jpg 10 201 | /data/image-clef/p/2009_002453.jpg 3 202 | /data/image-clef/p/2011_002871.jpg 3 203 | /data/image-clef/p/2011_000086.jpg 3 204 | /data/image-clef/p/2011_001221.jpg 3 205 | /data/image-clef/p/2008_007750.jpg 3 206 | /data/image-clef/p/2008_004969.jpg 3 207 | /data/image-clef/p/2008_005923.jpg 3 208 | /data/image-clef/p/2008_007643.jpg 3 209 | /data/image-clef/p/2011_003025.jpg 3 210 | /data/image-clef/p/2009_001289.jpg 3 211 | /data/image-clef/p/2011_001591.jpg 3 212 | /data/image-clef/p/2010_001916.jpg 3 213 | /data/image-clef/p/2008_003858.jpg 3 214 | /data/image-clef/p/2010_005198.jpg 3 215 | /data/image-clef/p/2008_007841.jpg 3 216 | /data/image-clef/p/2009_002662.jpg 3 217 | /data/image-clef/p/2011_000435.jpg 3 218 | /data/image-clef/p/2009_002308.jpg 3 219 | /data/image-clef/p/2008_004291.jpg 3 220 | /data/image-clef/p/2009_003652.jpg 3 221 | /data/image-clef/p/2011_000286.jpg 3 222 | /data/image-clef/p/2011_001901.jpg 3 223 | /data/image-clef/p/2008_004053.jpg 3 224 | /data/image-clef/p/2009_003936.jpg 3 225 | /data/image-clef/p/2009_002449.jpg 3 226 | /data/image-clef/p/2010_002150.jpg 3 227 | /data/image-clef/p/2009_001406.jpg 3 228 | /data/image-clef/p/2011_001001.jpg 3 229 | /data/image-clef/p/2010_005705.jpg 3 230 | /data/image-clef/p/2008_004124.jpg 3 231 | /data/image-clef/p/2009_004224.jpg 3 232 | /data/image-clef/p/2010_002104.jpg 3 233 | /data/image-clef/p/2009_000686.jpg 3 234 | /data/image-clef/p/2010_003640.jpg 3 235 | /data/image-clef/p/2008_007305.jpg 3 236 | /data/image-clef/p/2008_002773.jpg 3 237 | /data/image-clef/p/2010_005192.jpg 3 238 | /data/image-clef/p/2009_002543.jpg 3 239 | /data/image-clef/p/2008_005517.jpg 3 240 | /data/image-clef/p/2009_005015.jpg 3 241 | /data/image-clef/p/2011_002854.jpg 3 242 | /data/image-clef/p/2009_003019.jpg 3 243 | /data/image-clef/p/2011_001991.jpg 3 244 | /data/image-clef/p/2008_001858.jpg 3 245 | /data/image-clef/p/2011_001310.jpg 3 246 | /data/image-clef/p/2009_003136.jpg 3 247 | /data/image-clef/p/2010_004714.jpg 3 248 | /data/image-clef/p/2010_003815.jpg 3 249 | /data/image-clef/p/2008_003362.jpg 3 250 | /data/image-clef/p/2008_003480.jpg 3 251 | /data/image-clef/p/2009_002975.jpg 8 252 | /data/image-clef/p/2008_003782.jpg 8 253 | /data/image-clef/p/2008_008279.jpg 8 254 | /data/image-clef/p/2009_003128.jpg 8 255 | /data/image-clef/p/2008_000765.jpg 8 256 | /data/image-clef/p/2008_006317.jpg 8 257 | /data/image-clef/p/2011_001956.jpg 8 258 | /data/image-clef/p/2009_004134.jpg 8 259 | /data/image-clef/p/2009_004942.jpg 8 260 | /data/image-clef/p/2009_001837.jpg 8 261 | /data/image-clef/p/2009_000409.jpg 8 262 | /data/image-clef/p/2008_004624.jpg 8 263 | /data/image-clef/p/2009_000412.jpg 8 264 | /data/image-clef/p/2008_007625.jpg 8 265 | /data/image-clef/p/2011_002583.jpg 8 266 | /data/image-clef/p/2008_007004.jpg 8 267 | /data/image-clef/p/2009_002697.jpg 8 268 | /data/image-clef/p/2008_001934.jpg 8 269 | /data/image-clef/p/2010_000749.jpg 8 270 | /data/image-clef/p/2008_006219.jpg 8 271 | /data/image-clef/p/2010_001759.jpg 8 272 | /data/image-clef/p/2008_003272.jpg 8 273 | /data/image-clef/p/2008_003800.jpg 8 274 | /data/image-clef/p/2010_002168.jpg 8 275 | /data/image-clef/p/2010_003714.jpg 8 276 | /data/image-clef/p/2008_000076.jpg 8 277 | /data/image-clef/p/2010_004228.jpg 8 278 | /data/image-clef/p/2008_007576.jpg 8 279 | /data/image-clef/p/2008_001218.jpg 8 280 | /data/image-clef/p/2009_004790.jpg 8 281 | /data/image-clef/p/2009_001323.jpg 8 282 | /data/image-clef/p/2008_006758.jpg 8 283 | /data/image-clef/p/2008_007588.jpg 8 284 | /data/image-clef/p/2008_002589.jpg 8 285 | /data/image-clef/p/2011_002341.jpg 8 286 | /data/image-clef/p/2011_000771.jpg 8 287 | /data/image-clef/p/2010_001675.jpg 8 288 | /data/image-clef/p/2008_004705.jpg 8 289 | /data/image-clef/p/2008_001542.jpg 8 290 | /data/image-clef/p/2008_004195.jpg 8 291 | /data/image-clef/p/2008_003802.jpg 8 292 | /data/image-clef/p/2008_005525.jpg 8 293 | /data/image-clef/p/2009_001433.jpg 8 294 | /data/image-clef/p/2009_000001.jpg 8 295 | /data/image-clef/p/2009_002882.jpg 8 296 | /data/image-clef/p/2008_007531.jpg 8 297 | /data/image-clef/p/2008_004764.jpg 8 298 | /data/image-clef/p/2008_003055.jpg 8 299 | /data/image-clef/p/2011_000022.jpg 8 300 | /data/image-clef/p/2011_000210.jpg 8 301 | /data/image-clef/p/2009_003551.jpg 9 302 | /data/image-clef/p/2011_001726.jpg 9 303 | /data/image-clef/p/2010_002513.jpg 9 304 | /data/image-clef/p/2008_000244.jpg 9 305 | /data/image-clef/p/2009_002758.jpg 9 306 | /data/image-clef/p/2009_001553.jpg 9 307 | /data/image-clef/p/2008_004665.jpg 9 308 | /data/image-clef/p/2010_005744.jpg 9 309 | /data/image-clef/p/2008_003264.jpg 9 310 | /data/image-clef/p/2008_007038.jpg 9 311 | /data/image-clef/p/2008_006624.jpg 9 312 | /data/image-clef/p/2009_005030.jpg 9 313 | /data/image-clef/p/2008_002464.jpg 9 314 | /data/image-clef/p/2010_005410.jpg 9 315 | /data/image-clef/p/2010_002247.jpg 9 316 | /data/image-clef/p/2011_000253.jpg 9 317 | /data/image-clef/p/2010_004009.jpg 9 318 | /data/image-clef/p/2010_005345.jpg 9 319 | /data/image-clef/p/2008_007361.jpg 9 320 | /data/image-clef/p/2010_002843.jpg 9 321 | /data/image-clef/p/2010_005305.jpg 9 322 | /data/image-clef/p/2010_003236.jpg 9 323 | /data/image-clef/p/2008_003885.jpg 9 324 | /data/image-clef/p/2008_000305.jpg 9 325 | /data/image-clef/p/2008_005817.jpg 9 326 | /data/image-clef/p/2011_001910.jpg 9 327 | /data/image-clef/p/2008_005066.jpg 9 328 | /data/image-clef/p/2008_007536.jpg 9 329 | /data/image-clef/p/2008_003667.jpg 9 330 | /data/image-clef/p/2011_002418.jpg 9 331 | /data/image-clef/p/2008_005954.jpg 9 332 | /data/image-clef/p/2009_005288.jpg 9 333 | /data/image-clef/p/2009_001608.jpg 9 334 | /data/image-clef/p/2010_000435.jpg 9 335 | /data/image-clef/p/2008_005064.jpg 9 336 | /data/image-clef/p/2008_004807.jpg 9 337 | /data/image-clef/p/2008_006591.jpg 9 338 | /data/image-clef/p/2011_001705.jpg 9 339 | /data/image-clef/p/2009_003140.jpg 9 340 | /data/image-clef/p/2010_002152.jpg 9 341 | /data/image-clef/p/2010_003035.jpg 9 342 | /data/image-clef/p/2008_007446.jpg 9 343 | /data/image-clef/p/2009_001106.jpg 9 344 | /data/image-clef/p/2008_000070.jpg 9 345 | /data/image-clef/p/2008_003435.jpg 9 346 | /data/image-clef/p/2008_006233.jpg 9 347 | /data/image-clef/p/2008_001481.jpg 9 348 | /data/image-clef/p/2009_003078.jpg 9 349 | /data/image-clef/p/2008_002066.jpg 9 350 | /data/image-clef/p/2009_000981.jpg 9 351 | /data/image-clef/p/2008_005325.jpg 6 352 | /data/image-clef/p/2008_006310.jpg 6 353 | /data/image-clef/p/2010_002807.jpg 6 354 | /data/image-clef/p/2011_001901.jpg 6 355 | /data/image-clef/p/2008_005865.jpg 6 356 | /data/image-clef/p/2008_003647.jpg 6 357 | /data/image-clef/p/2009_003031.jpg 6 358 | /data/image-clef/p/2009_004290.jpg 6 359 | /data/image-clef/p/2009_004271.jpg 6 360 | /data/image-clef/p/2010_003139.jpg 6 361 | /data/image-clef/p/2009_000631.jpg 6 362 | /data/image-clef/p/2008_004411.jpg 6 363 | /data/image-clef/p/2009_000390.jpg 6 364 | /data/image-clef/p/2008_001717.jpg 6 365 | /data/image-clef/p/2009_000720.jpg 6 366 | /data/image-clef/p/2008_002746.jpg 6 367 | /data/image-clef/p/2008_007171.jpg 6 368 | /data/image-clef/p/2008_006833.jpg 6 369 | /data/image-clef/p/2008_007739.jpg 6 370 | /data/image-clef/p/2008_007090.jpg 6 371 | /data/image-clef/p/2008_002199.jpg 6 372 | /data/image-clef/p/2008_001681.jpg 6 373 | /data/image-clef/p/2008_007877.jpg 6 374 | /data/image-clef/p/2011_002598.jpg 6 375 | /data/image-clef/p/2008_001007.jpg 6 376 | /data/image-clef/p/2008_006989.jpg 6 377 | /data/image-clef/p/2010_004349.jpg 6 378 | /data/image-clef/p/2011_003114.jpg 6 379 | /data/image-clef/p/2009_004518.jpg 6 380 | /data/image-clef/p/2011_002585.jpg 6 381 | /data/image-clef/p/2009_000886.jpg 6 382 | /data/image-clef/p/2008_006483.jpg 6 383 | /data/image-clef/p/2010_001403.jpg 6 384 | /data/image-clef/p/2010_003562.jpg 6 385 | /data/image-clef/p/2008_006872.jpg 6 386 | /data/image-clef/p/2008_004711.jpg 6 387 | /data/image-clef/p/2009_002380.jpg 6 388 | /data/image-clef/p/2010_003129.jpg 6 389 | /data/image-clef/p/2011_001271.jpg 6 390 | /data/image-clef/p/2010_003450.jpg 6 391 | /data/image-clef/p/2008_000176.jpg 6 392 | /data/image-clef/p/2009_000737.jpg 6 393 | /data/image-clef/p/2010_000947.jpg 6 394 | /data/image-clef/p/2010_005733.jpg 6 395 | /data/image-clef/p/2008_001432.jpg 6 396 | /data/image-clef/p/2010_004690.jpg 6 397 | /data/image-clef/p/2010_005804.jpg 6 398 | /data/image-clef/p/2008_007364.jpg 6 399 | /data/image-clef/p/2008_000719.jpg 6 400 | /data/image-clef/p/2008_004923.jpg 6 401 | /data/image-clef/p/2010_005671.jpg 7 402 | /data/image-clef/p/2010_000655.jpg 7 403 | /data/image-clef/p/2009_004688.jpg 7 404 | /data/image-clef/p/2010_002398.jpg 7 405 | /data/image-clef/p/2009_001687.jpg 7 406 | /data/image-clef/p/2011_000317.jpg 7 407 | /data/image-clef/p/2008_007286.jpg 7 408 | /data/image-clef/p/2010_002674.jpg 7 409 | /data/image-clef/p/2010_005109.jpg 7 410 | /data/image-clef/p/2010_001838.jpg 7 411 | /data/image-clef/p/2008_003801.jpg 7 412 | /data/image-clef/p/2010_001626.jpg 7 413 | /data/image-clef/p/2010_001432.jpg 7 414 | /data/image-clef/p/2010_004345.jpg 7 415 | /data/image-clef/p/2009_004772.jpg 7 416 | /data/image-clef/p/2010_001768.jpg 7 417 | /data/image-clef/p/2010_001422.jpg 7 418 | /data/image-clef/p/2010_004227.jpg 7 419 | /data/image-clef/p/2010_001421.jpg 7 420 | /data/image-clef/p/2008_001420.jpg 7 421 | /data/image-clef/p/2011_000981.jpg 7 422 | /data/image-clef/p/2008_005379.jpg 7 423 | /data/image-clef/p/2009_002605.jpg 7 424 | /data/image-clef/p/2008_007583.jpg 7 425 | /data/image-clef/p/2008_007358.jpg 7 426 | /data/image-clef/p/2009_002865.jpg 7 427 | /data/image-clef/p/2008_006724.jpg 7 428 | /data/image-clef/p/2010_000263.jpg 7 429 | /data/image-clef/p/2008_005333.jpg 7 430 | /data/image-clef/p/2011_002239.jpg 7 431 | /data/image-clef/p/2008_006032.jpg 7 432 | /data/image-clef/p/2010_003351.jpg 7 433 | /data/image-clef/p/2010_003056.jpg 7 434 | /data/image-clef/p/2008_000419.jpg 7 435 | /data/image-clef/p/2010_001756.jpg 7 436 | /data/image-clef/p/2008_006716.jpg 7 437 | /data/image-clef/p/2008_000162.jpg 7 438 | /data/image-clef/p/2010_003554.jpg 7 439 | /data/image-clef/p/2009_000874.jpg 7 440 | /data/image-clef/p/2010_002644.jpg 7 441 | /data/image-clef/p/2011_002900.jpg 7 442 | /data/image-clef/p/2010_004417.jpg 7 443 | /data/image-clef/p/2010_002129.jpg 7 444 | /data/image-clef/p/2010_003879.jpg 7 445 | /data/image-clef/p/2008_000931.jpg 7 446 | /data/image-clef/p/2008_007208.jpg 7 447 | /data/image-clef/p/2008_006220.jpg 7 448 | /data/image-clef/p/2009_001538.jpg 7 449 | /data/image-clef/p/2008_001550.jpg 7 450 | /data/image-clef/p/2009_003735.jpg 7 451 | /data/image-clef/p/2008_008724.jpg 1 452 | /data/image-clef/p/2010_003828.jpg 1 453 | /data/image-clef/p/2009_000820.jpg 1 454 | /data/image-clef/p/2009_001642.jpg 1 455 | /data/image-clef/p/2009_000445.jpg 1 456 | /data/image-clef/p/2008_004758.jpg 1 457 | /data/image-clef/p/2010_001119.jpg 1 458 | /data/image-clef/p/2011_000453.jpg 1 459 | /data/image-clef/p/2010_003701.jpg 1 460 | /data/image-clef/p/2010_005000.jpg 1 461 | /data/image-clef/p/2011_000087.jpg 1 462 | /data/image-clef/p/2010_005374.jpg 1 463 | /data/image-clef/p/2011_001937.jpg 1 464 | /data/image-clef/p/2009_005154.jpg 1 465 | /data/image-clef/p/2009_003175.jpg 1 466 | /data/image-clef/p/2010_001753.jpg 1 467 | /data/image-clef/p/2008_002714.jpg 1 468 | /data/image-clef/p/2010_002927.jpg 1 469 | /data/image-clef/p/2010_002497.jpg 1 470 | /data/image-clef/p/2010_006070.jpg 1 471 | /data/image-clef/p/2008_008758.jpg 1 472 | /data/image-clef/p/2011_002913.jpg 1 473 | /data/image-clef/p/2010_005226.jpg 1 474 | /data/image-clef/p/2009_001384.jpg 1 475 | /data/image-clef/p/2008_008337.jpg 1 476 | /data/image-clef/p/2009_003075.jpg 1 477 | /data/image-clef/p/2011_000505.jpg 1 478 | /data/image-clef/p/2010_005782.jpg 1 479 | /data/image-clef/p/2008_000133.jpg 1 480 | /data/image-clef/p/2009_004876.jpg 1 481 | /data/image-clef/p/2008_002883.jpg 1 482 | /data/image-clef/p/2010_005556.jpg 1 483 | /data/image-clef/p/2010_003912.jpg 1 484 | /data/image-clef/p/2008_005175.jpg 1 485 | /data/image-clef/p/2009_003860.jpg 1 486 | /data/image-clef/p/2008_007510.jpg 1 487 | /data/image-clef/p/2008_008629.jpg 1 488 | /data/image-clef/p/2009_000015.jpg 1 489 | /data/image-clef/p/2008_000803.jpg 1 490 | /data/image-clef/p/2008_002679.jpg 1 491 | /data/image-clef/p/2010_000893.jpg 1 492 | /data/image-clef/p/2011_002406.jpg 1 493 | /data/image-clef/p/2009_004797.jpg 1 494 | /data/image-clef/p/2008_005412.jpg 1 495 | /data/image-clef/p/2008_004995.jpg 1 496 | /data/image-clef/p/2011_000485.jpg 1 497 | /data/image-clef/p/2008_002787.jpg 1 498 | /data/image-clef/p/2010_005848.jpg 1 499 | /data/image-clef/p/2009_004848.jpg 1 500 | /data/image-clef/p/2009_002983.jpg 1 501 | /data/image-clef/p/2010_002457.jpg 4 502 | /data/image-clef/p/2010_004198.jpg 4 503 | /data/image-clef/p/2008_003467.jpg 4 504 | /data/image-clef/p/2011_003038.jpg 4 505 | /data/image-clef/p/2010_005512.jpg 4 506 | /data/image-clef/p/2008_008072.jpg 4 507 | /data/image-clef/p/2008_007219.jpg 4 508 | /data/image-clef/p/2011_001538.jpg 4 509 | /data/image-clef/p/2009_002980.jpg 4 510 | /data/image-clef/p/2008_003591.jpg 4 511 | /data/image-clef/p/2008_005991.jpg 4 512 | /data/image-clef/p/2008_004979.jpg 4 513 | /data/image-clef/p/2010_002858.jpg 4 514 | /data/image-clef/p/2008_006145.jpg 4 515 | /data/image-clef/p/2011_002186.jpg 4 516 | /data/image-clef/p/2008_000801.jpg 4 517 | /data/image-clef/p/2008_000290.jpg 4 518 | /data/image-clef/p/2009_005302.jpg 4 519 | /data/image-clef/p/2008_001593.jpg 4 520 | /data/image-clef/p/2010_003912.jpg 4 521 | /data/image-clef/p/2008_007146.jpg 4 522 | /data/image-clef/p/2009_003588.jpg 4 523 | /data/image-clef/p/2008_000703.jpg 4 524 | /data/image-clef/p/2010_000089.jpg 4 525 | /data/image-clef/p/2008_000691.jpg 4 526 | /data/image-clef/p/2008_003635.jpg 4 527 | /data/image-clef/p/2008_000522.jpg 4 528 | /data/image-clef/p/2010_005663.jpg 4 529 | /data/image-clef/p/2008_000953.jpg 4 530 | /data/image-clef/p/2009_004247.jpg 4 531 | /data/image-clef/p/2009_000464.jpg 4 532 | /data/image-clef/p/2009_002649.jpg 4 533 | /data/image-clef/p/2008_005758.jpg 4 534 | /data/image-clef/p/2008_000851.jpg 4 535 | /data/image-clef/p/2009_002594.jpg 4 536 | /data/image-clef/p/2011_002590.jpg 4 537 | /data/image-clef/p/2009_003214.jpg 4 538 | /data/image-clef/p/2010_005540.jpg 4 539 | /data/image-clef/p/2009_000494.jpg 4 540 | /data/image-clef/p/2009_001908.jpg 4 541 | /data/image-clef/p/2009_001106.jpg 4 542 | /data/image-clef/p/2009_003154.jpg 4 543 | /data/image-clef/p/2008_004016.jpg 4 544 | /data/image-clef/p/2011_000747.jpg 4 545 | /data/image-clef/p/2010_002455.jpg 4 546 | /data/image-clef/p/2009_005278.jpg 4 547 | /data/image-clef/p/2008_001638.jpg 4 548 | /data/image-clef/p/2008_008266.jpg 4 549 | /data/image-clef/p/2011_002814.jpg 4 550 | /data/image-clef/p/2008_005140.jpg 4 551 | /data/image-clef/p/2008_007870.jpg 2 552 | /data/image-clef/p/2008_004671.jpg 2 553 | /data/image-clef/p/2008_006802.jpg 2 554 | /data/image-clef/p/2010_000621.jpg 2 555 | /data/image-clef/p/2008_008523.jpg 2 556 | /data/image-clef/p/2009_005040.jpg 2 557 | /data/image-clef/p/2008_006164.jpg 2 558 | /data/image-clef/p/2008_007120.jpg 2 559 | /data/image-clef/p/2008_001673.jpg 2 560 | /data/image-clef/p/2008_007486.jpg 2 561 | /data/image-clef/p/2009_000930.jpg 2 562 | /data/image-clef/p/2009_003285.jpg 2 563 | /data/image-clef/p/2008_004551.jpg 2 564 | /data/image-clef/p/2008_002784.jpg 2 565 | /data/image-clef/p/2008_003426.jpg 2 566 | /data/image-clef/p/2010_000918.jpg 2 567 | /data/image-clef/p/2008_008309.jpg 2 568 | /data/image-clef/p/2008_007003.jpg 2 569 | /data/image-clef/p/2009_003531.jpg 2 570 | /data/image-clef/p/2008_007465.jpg 2 571 | /data/image-clef/p/2008_003484.jpg 2 572 | /data/image-clef/p/2008_004689.jpg 2 573 | /data/image-clef/p/2008_000103.jpg 2 574 | /data/image-clef/p/2011_001967.jpg 2 575 | /data/image-clef/p/2008_002255.jpg 2 576 | /data/image-clef/p/2009_000317.jpg 2 577 | /data/image-clef/p/2008_008197.jpg 2 578 | /data/image-clef/p/2009_001128.jpg 2 579 | /data/image-clef/p/2009_000664.jpg 2 580 | /data/image-clef/p/2010_002023.jpg 2 581 | /data/image-clef/p/2008_006090.jpg 2 582 | /data/image-clef/p/2011_002463.jpg 2 583 | /data/image-clef/p/2009_002286.jpg 2 584 | /data/image-clef/p/2009_001660.jpg 2 585 | /data/image-clef/p/2010_004187.jpg 2 586 | /data/image-clef/p/2011_001134.jpg 2 587 | /data/image-clef/p/2008_002970.jpg 2 588 | /data/image-clef/p/2008_007656.jpg 2 589 | /data/image-clef/p/2009_000790.jpg 2 590 | /data/image-clef/p/2008_007854.jpg 2 591 | /data/image-clef/p/2009_002629.jpg 2 592 | /data/image-clef/p/2010_001992.jpg 2 593 | /data/image-clef/p/2008_005757.jpg 2 594 | /data/image-clef/p/2010_005428.jpg 2 595 | /data/image-clef/p/2009_001397.jpg 2 596 | /data/image-clef/p/2008_001415.jpg 2 597 | /data/image-clef/p/2009_002877.jpg 2 598 | /data/image-clef/p/2010_005993.jpg 2 599 | /data/image-clef/p/2010_003771.jpg 2 600 | /data/image-clef/p/2008_004147.jpg 2 601 | -------------------------------------------------------------------------------- /data/office/dslr_list.txt: -------------------------------------------------------------------------------- 1 | /data/office/domain_adaptation_images/dslr/images/calculator/frame_0001.jpg 5 2 | /data/office/domain_adaptation_images/dslr/images/calculator/frame_0002.jpg 5 3 | /data/office/domain_adaptation_images/dslr/images/calculator/frame_0003.jpg 5 4 | /data/office/domain_adaptation_images/dslr/images/calculator/frame_0004.jpg 5 5 | /data/office/domain_adaptation_images/dslr/images/calculator/frame_0005.jpg 5 6 | /data/office/domain_adaptation_images/dslr/images/calculator/frame_0006.jpg 5 7 | /data/office/domain_adaptation_images/dslr/images/calculator/frame_0007.jpg 5 8 | /data/office/domain_adaptation_images/dslr/images/calculator/frame_0008.jpg 5 9 | /data/office/domain_adaptation_images/dslr/images/calculator/frame_0009.jpg 5 10 | /data/office/domain_adaptation_images/dslr/images/calculator/frame_0010.jpg 5 11 | /data/office/domain_adaptation_images/dslr/images/calculator/frame_0011.jpg 5 12 | /data/office/domain_adaptation_images/dslr/images/calculator/frame_0012.jpg 5 13 | /data/office/domain_adaptation_images/dslr/images/ring_binder/frame_0001.jpg 24 14 | /data/office/domain_adaptation_images/dslr/images/ring_binder/frame_0002.jpg 24 15 | /data/office/domain_adaptation_images/dslr/images/ring_binder/frame_0003.jpg 24 16 | /data/office/domain_adaptation_images/dslr/images/ring_binder/frame_0004.jpg 24 17 | /data/office/domain_adaptation_images/dslr/images/ring_binder/frame_0005.jpg 24 18 | /data/office/domain_adaptation_images/dslr/images/ring_binder/frame_0006.jpg 24 19 | /data/office/domain_adaptation_images/dslr/images/ring_binder/frame_0007.jpg 24 20 | /data/office/domain_adaptation_images/dslr/images/ring_binder/frame_0008.jpg 24 21 | /data/office/domain_adaptation_images/dslr/images/ring_binder/frame_0009.jpg 24 22 | /data/office/domain_adaptation_images/dslr/images/ring_binder/frame_0010.jpg 24 23 | /data/office/domain_adaptation_images/dslr/images/printer/frame_0001.jpg 21 24 | /data/office/domain_adaptation_images/dslr/images/printer/frame_0002.jpg 21 25 | /data/office/domain_adaptation_images/dslr/images/printer/frame_0003.jpg 21 26 | /data/office/domain_adaptation_images/dslr/images/printer/frame_0004.jpg 21 27 | /data/office/domain_adaptation_images/dslr/images/printer/frame_0005.jpg 21 28 | /data/office/domain_adaptation_images/dslr/images/printer/frame_0006.jpg 21 29 | /data/office/domain_adaptation_images/dslr/images/printer/frame_0007.jpg 21 30 | /data/office/domain_adaptation_images/dslr/images/printer/frame_0008.jpg 21 31 | /data/office/domain_adaptation_images/dslr/images/printer/frame_0009.jpg 21 32 | /data/office/domain_adaptation_images/dslr/images/printer/frame_0010.jpg 21 33 | /data/office/domain_adaptation_images/dslr/images/printer/frame_0011.jpg 21 34 | /data/office/domain_adaptation_images/dslr/images/printer/frame_0012.jpg 21 35 | /data/office/domain_adaptation_images/dslr/images/printer/frame_0013.jpg 21 36 | /data/office/domain_adaptation_images/dslr/images/printer/frame_0014.jpg 21 37 | /data/office/domain_adaptation_images/dslr/images/printer/frame_0015.jpg 21 38 | /data/office/domain_adaptation_images/dslr/images/keyboard/frame_0001.jpg 11 39 | /data/office/domain_adaptation_images/dslr/images/keyboard/frame_0002.jpg 11 40 | /data/office/domain_adaptation_images/dslr/images/keyboard/frame_0003.jpg 11 41 | /data/office/domain_adaptation_images/dslr/images/keyboard/frame_0004.jpg 11 42 | /data/office/domain_adaptation_images/dslr/images/keyboard/frame_0005.jpg 11 43 | /data/office/domain_adaptation_images/dslr/images/keyboard/frame_0006.jpg 11 44 | /data/office/domain_adaptation_images/dslr/images/keyboard/frame_0007.jpg 11 45 | /data/office/domain_adaptation_images/dslr/images/keyboard/frame_0008.jpg 11 46 | /data/office/domain_adaptation_images/dslr/images/keyboard/frame_0009.jpg 11 47 | /data/office/domain_adaptation_images/dslr/images/keyboard/frame_0010.jpg 11 48 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0001.jpg 26 49 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0002.jpg 26 50 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0003.jpg 26 51 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0004.jpg 26 52 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0005.jpg 26 53 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0006.jpg 26 54 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0007.jpg 26 55 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0008.jpg 26 56 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0009.jpg 26 57 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0010.jpg 26 58 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0011.jpg 26 59 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0012.jpg 26 60 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0013.jpg 26 61 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0014.jpg 26 62 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0015.jpg 26 63 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0016.jpg 26 64 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0017.jpg 26 65 | /data/office/domain_adaptation_images/dslr/images/scissors/frame_0018.jpg 26 66 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0001.jpg 12 67 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0002.jpg 12 68 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0003.jpg 12 69 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0004.jpg 12 70 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0005.jpg 12 71 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0006.jpg 12 72 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0007.jpg 12 73 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0008.jpg 12 74 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0009.jpg 12 75 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0010.jpg 12 76 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0011.jpg 12 77 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0012.jpg 12 78 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0013.jpg 12 79 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0014.jpg 12 80 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0015.jpg 12 81 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0016.jpg 12 82 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0017.jpg 12 83 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0018.jpg 12 84 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0019.jpg 12 85 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0020.jpg 12 86 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0021.jpg 12 87 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0022.jpg 12 88 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0023.jpg 12 89 | /data/office/domain_adaptation_images/dslr/images/laptop_computer/frame_0024.jpg 12 90 | /data/office/domain_adaptation_images/dslr/images/mouse/frame_0001.jpg 16 91 | /data/office/domain_adaptation_images/dslr/images/mouse/frame_0002.jpg 16 92 | /data/office/domain_adaptation_images/dslr/images/mouse/frame_0003.jpg 16 93 | /data/office/domain_adaptation_images/dslr/images/mouse/frame_0004.jpg 16 94 | /data/office/domain_adaptation_images/dslr/images/mouse/frame_0005.jpg 16 95 | /data/office/domain_adaptation_images/dslr/images/mouse/frame_0006.jpg 16 96 | /data/office/domain_adaptation_images/dslr/images/mouse/frame_0007.jpg 16 97 | /data/office/domain_adaptation_images/dslr/images/mouse/frame_0008.jpg 16 98 | /data/office/domain_adaptation_images/dslr/images/mouse/frame_0009.jpg 16 99 | /data/office/domain_adaptation_images/dslr/images/mouse/frame_0010.jpg 16 100 | /data/office/domain_adaptation_images/dslr/images/mouse/frame_0011.jpg 16 101 | /data/office/domain_adaptation_images/dslr/images/mouse/frame_0012.jpg 16 102 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0001.jpg 15 103 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0002.jpg 15 104 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0003.jpg 15 105 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0004.jpg 15 106 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0005.jpg 15 107 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0006.jpg 15 108 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0007.jpg 15 109 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0008.jpg 15 110 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0009.jpg 15 111 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0010.jpg 15 112 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0011.jpg 15 113 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0012.jpg 15 114 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0013.jpg 15 115 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0014.jpg 15 116 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0015.jpg 15 117 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0016.jpg 15 118 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0017.jpg 15 119 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0018.jpg 15 120 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0019.jpg 15 121 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0020.jpg 15 122 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0021.jpg 15 123 | /data/office/domain_adaptation_images/dslr/images/monitor/frame_0022.jpg 15 124 | /data/office/domain_adaptation_images/dslr/images/mug/frame_0001.jpg 17 125 | /data/office/domain_adaptation_images/dslr/images/mug/frame_0002.jpg 17 126 | /data/office/domain_adaptation_images/dslr/images/mug/frame_0003.jpg 17 127 | /data/office/domain_adaptation_images/dslr/images/mug/frame_0004.jpg 17 128 | /data/office/domain_adaptation_images/dslr/images/mug/frame_0005.jpg 17 129 | /data/office/domain_adaptation_images/dslr/images/mug/frame_0006.jpg 17 130 | /data/office/domain_adaptation_images/dslr/images/mug/frame_0007.jpg 17 131 | /data/office/domain_adaptation_images/dslr/images/mug/frame_0008.jpg 17 132 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0001.jpg 29 133 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0002.jpg 29 134 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0003.jpg 29 135 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0004.jpg 29 136 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0005.jpg 29 137 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0006.jpg 29 138 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0007.jpg 29 139 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0008.jpg 29 140 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0009.jpg 29 141 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0010.jpg 29 142 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0011.jpg 29 143 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0012.jpg 29 144 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0013.jpg 29 145 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0014.jpg 29 146 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0015.jpg 29 147 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0016.jpg 29 148 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0017.jpg 29 149 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0018.jpg 29 150 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0019.jpg 29 151 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0020.jpg 29 152 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0021.jpg 29 153 | /data/office/domain_adaptation_images/dslr/images/tape_dispenser/frame_0022.jpg 29 154 | /data/office/domain_adaptation_images/dslr/images/pen/frame_0001.jpg 19 155 | /data/office/domain_adaptation_images/dslr/images/pen/frame_0002.jpg 19 156 | /data/office/domain_adaptation_images/dslr/images/pen/frame_0003.jpg 19 157 | /data/office/domain_adaptation_images/dslr/images/pen/frame_0004.jpg 19 158 | /data/office/domain_adaptation_images/dslr/images/pen/frame_0005.jpg 19 159 | /data/office/domain_adaptation_images/dslr/images/pen/frame_0006.jpg 19 160 | /data/office/domain_adaptation_images/dslr/images/pen/frame_0007.jpg 19 161 | /data/office/domain_adaptation_images/dslr/images/pen/frame_0008.jpg 19 162 | /data/office/domain_adaptation_images/dslr/images/pen/frame_0009.jpg 19 163 | /data/office/domain_adaptation_images/dslr/images/pen/frame_0010.jpg 19 164 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0001.jpg 1 165 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0002.jpg 1 166 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0003.jpg 1 167 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0004.jpg 1 168 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0005.jpg 1 169 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0006.jpg 1 170 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0007.jpg 1 171 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0008.jpg 1 172 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0009.jpg 1 173 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0010.jpg 1 174 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0011.jpg 1 175 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0012.jpg 1 176 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0013.jpg 1 177 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0014.jpg 1 178 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0015.jpg 1 179 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0016.jpg 1 180 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0017.jpg 1 181 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0018.jpg 1 182 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0019.jpg 1 183 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0020.jpg 1 184 | /data/office/domain_adaptation_images/dslr/images/bike/frame_0021.jpg 1 185 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0001.jpg 23 186 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0002.jpg 23 187 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0003.jpg 23 188 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0004.jpg 23 189 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0005.jpg 23 190 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0006.jpg 23 191 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0007.jpg 23 192 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0008.jpg 23 193 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0009.jpg 23 194 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0010.jpg 23 195 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0011.jpg 23 196 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0012.jpg 23 197 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0013.jpg 23 198 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0014.jpg 23 199 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0015.jpg 23 200 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0016.jpg 23 201 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0017.jpg 23 202 | /data/office/domain_adaptation_images/dslr/images/punchers/frame_0018.jpg 23 203 | /data/office/domain_adaptation_images/dslr/images/back_pack/frame_0001.jpg 0 204 | /data/office/domain_adaptation_images/dslr/images/back_pack/frame_0002.jpg 0 205 | /data/office/domain_adaptation_images/dslr/images/back_pack/frame_0003.jpg 0 206 | /data/office/domain_adaptation_images/dslr/images/back_pack/frame_0004.jpg 0 207 | /data/office/domain_adaptation_images/dslr/images/back_pack/frame_0005.jpg 0 208 | /data/office/domain_adaptation_images/dslr/images/back_pack/frame_0006.jpg 0 209 | /data/office/domain_adaptation_images/dslr/images/back_pack/frame_0007.jpg 0 210 | /data/office/domain_adaptation_images/dslr/images/back_pack/frame_0008.jpg 0 211 | /data/office/domain_adaptation_images/dslr/images/back_pack/frame_0009.jpg 0 212 | /data/office/domain_adaptation_images/dslr/images/back_pack/frame_0010.jpg 0 213 | /data/office/domain_adaptation_images/dslr/images/back_pack/frame_0011.jpg 0 214 | /data/office/domain_adaptation_images/dslr/images/back_pack/frame_0012.jpg 0 215 | /data/office/domain_adaptation_images/dslr/images/desktop_computer/frame_0001.jpg 8 216 | /data/office/domain_adaptation_images/dslr/images/desktop_computer/frame_0002.jpg 8 217 | /data/office/domain_adaptation_images/dslr/images/desktop_computer/frame_0003.jpg 8 218 | /data/office/domain_adaptation_images/dslr/images/desktop_computer/frame_0004.jpg 8 219 | /data/office/domain_adaptation_images/dslr/images/desktop_computer/frame_0005.jpg 8 220 | /data/office/domain_adaptation_images/dslr/images/desktop_computer/frame_0006.jpg 8 221 | /data/office/domain_adaptation_images/dslr/images/desktop_computer/frame_0007.jpg 8 222 | /data/office/domain_adaptation_images/dslr/images/desktop_computer/frame_0008.jpg 8 223 | /data/office/domain_adaptation_images/dslr/images/desktop_computer/frame_0009.jpg 8 224 | /data/office/domain_adaptation_images/dslr/images/desktop_computer/frame_0010.jpg 8 225 | /data/office/domain_adaptation_images/dslr/images/desktop_computer/frame_0011.jpg 8 226 | /data/office/domain_adaptation_images/dslr/images/desktop_computer/frame_0012.jpg 8 227 | /data/office/domain_adaptation_images/dslr/images/desktop_computer/frame_0013.jpg 8 228 | /data/office/domain_adaptation_images/dslr/images/desktop_computer/frame_0014.jpg 8 229 | /data/office/domain_adaptation_images/dslr/images/desktop_computer/frame_0015.jpg 8 230 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0001.jpg 27 231 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0002.jpg 27 232 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0003.jpg 27 233 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0004.jpg 27 234 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0005.jpg 27 235 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0006.jpg 27 236 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0007.jpg 27 237 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0008.jpg 27 238 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0009.jpg 27 239 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0010.jpg 27 240 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0011.jpg 27 241 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0012.jpg 27 242 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0013.jpg 27 243 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0014.jpg 27 244 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0015.jpg 27 245 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0016.jpg 27 246 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0017.jpg 27 247 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0018.jpg 27 248 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0019.jpg 27 249 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0020.jpg 27 250 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0021.jpg 27 251 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0022.jpg 27 252 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0023.jpg 27 253 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0024.jpg 27 254 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0025.jpg 27 255 | /data/office/domain_adaptation_images/dslr/images/speaker/frame_0026.jpg 27 256 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0001.jpg 14 257 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0002.jpg 14 258 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0003.jpg 14 259 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0004.jpg 14 260 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0005.jpg 14 261 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0006.jpg 14 262 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0007.jpg 14 263 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0008.jpg 14 264 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0009.jpg 14 265 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0010.jpg 14 266 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0011.jpg 14 267 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0012.jpg 14 268 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0013.jpg 14 269 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0014.jpg 14 270 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0015.jpg 14 271 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0016.jpg 14 272 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0017.jpg 14 273 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0018.jpg 14 274 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0019.jpg 14 275 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0020.jpg 14 276 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0021.jpg 14 277 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0022.jpg 14 278 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0023.jpg 14 279 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0024.jpg 14 280 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0025.jpg 14 281 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0026.jpg 14 282 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0027.jpg 14 283 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0028.jpg 14 284 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0029.jpg 14 285 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0030.jpg 14 286 | /data/office/domain_adaptation_images/dslr/images/mobile_phone/frame_0031.jpg 14 287 | /data/office/domain_adaptation_images/dslr/images/paper_notebook/frame_0001.jpg 18 288 | /data/office/domain_adaptation_images/dslr/images/paper_notebook/frame_0002.jpg 18 289 | /data/office/domain_adaptation_images/dslr/images/paper_notebook/frame_0003.jpg 18 290 | /data/office/domain_adaptation_images/dslr/images/paper_notebook/frame_0004.jpg 18 291 | /data/office/domain_adaptation_images/dslr/images/paper_notebook/frame_0005.jpg 18 292 | /data/office/domain_adaptation_images/dslr/images/paper_notebook/frame_0006.jpg 18 293 | /data/office/domain_adaptation_images/dslr/images/paper_notebook/frame_0007.jpg 18 294 | /data/office/domain_adaptation_images/dslr/images/paper_notebook/frame_0008.jpg 18 295 | /data/office/domain_adaptation_images/dslr/images/paper_notebook/frame_0009.jpg 18 296 | /data/office/domain_adaptation_images/dslr/images/paper_notebook/frame_0010.jpg 18 297 | /data/office/domain_adaptation_images/dslr/images/ruler/frame_0001.jpg 25 298 | /data/office/domain_adaptation_images/dslr/images/ruler/frame_0002.jpg 25 299 | /data/office/domain_adaptation_images/dslr/images/ruler/frame_0003.jpg 25 300 | /data/office/domain_adaptation_images/dslr/images/ruler/frame_0004.jpg 25 301 | /data/office/domain_adaptation_images/dslr/images/ruler/frame_0005.jpg 25 302 | /data/office/domain_adaptation_images/dslr/images/ruler/frame_0006.jpg 25 303 | /data/office/domain_adaptation_images/dslr/images/ruler/frame_0007.jpg 25 304 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0001.jpg 13 305 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0002.jpg 13 306 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0003.jpg 13 307 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0004.jpg 13 308 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0005.jpg 13 309 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0006.jpg 13 310 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0007.jpg 13 311 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0008.jpg 13 312 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0009.jpg 13 313 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0010.jpg 13 314 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0011.jpg 13 315 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0012.jpg 13 316 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0013.jpg 13 317 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0014.jpg 13 318 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0015.jpg 13 319 | /data/office/domain_adaptation_images/dslr/images/letter_tray/frame_0016.jpg 13 320 | /data/office/domain_adaptation_images/dslr/images/file_cabinet/frame_0001.jpg 9 321 | /data/office/domain_adaptation_images/dslr/images/file_cabinet/frame_0002.jpg 9 322 | /data/office/domain_adaptation_images/dslr/images/file_cabinet/frame_0003.jpg 9 323 | /data/office/domain_adaptation_images/dslr/images/file_cabinet/frame_0004.jpg 9 324 | /data/office/domain_adaptation_images/dslr/images/file_cabinet/frame_0005.jpg 9 325 | /data/office/domain_adaptation_images/dslr/images/file_cabinet/frame_0006.jpg 9 326 | /data/office/domain_adaptation_images/dslr/images/file_cabinet/frame_0007.jpg 9 327 | /data/office/domain_adaptation_images/dslr/images/file_cabinet/frame_0008.jpg 9 328 | /data/office/domain_adaptation_images/dslr/images/file_cabinet/frame_0009.jpg 9 329 | /data/office/domain_adaptation_images/dslr/images/file_cabinet/frame_0010.jpg 9 330 | /data/office/domain_adaptation_images/dslr/images/file_cabinet/frame_0011.jpg 9 331 | /data/office/domain_adaptation_images/dslr/images/file_cabinet/frame_0012.jpg 9 332 | /data/office/domain_adaptation_images/dslr/images/file_cabinet/frame_0013.jpg 9 333 | /data/office/domain_adaptation_images/dslr/images/file_cabinet/frame_0014.jpg 9 334 | /data/office/domain_adaptation_images/dslr/images/file_cabinet/frame_0015.jpg 9 335 | /data/office/domain_adaptation_images/dslr/images/phone/frame_0001.jpg 20 336 | /data/office/domain_adaptation_images/dslr/images/phone/frame_0002.jpg 20 337 | /data/office/domain_adaptation_images/dslr/images/phone/frame_0003.jpg 20 338 | /data/office/domain_adaptation_images/dslr/images/phone/frame_0004.jpg 20 339 | /data/office/domain_adaptation_images/dslr/images/phone/frame_0005.jpg 20 340 | /data/office/domain_adaptation_images/dslr/images/phone/frame_0006.jpg 20 341 | /data/office/domain_adaptation_images/dslr/images/phone/frame_0007.jpg 20 342 | /data/office/domain_adaptation_images/dslr/images/phone/frame_0008.jpg 20 343 | /data/office/domain_adaptation_images/dslr/images/phone/frame_0009.jpg 20 344 | /data/office/domain_adaptation_images/dslr/images/phone/frame_0010.jpg 20 345 | /data/office/domain_adaptation_images/dslr/images/phone/frame_0011.jpg 20 346 | /data/office/domain_adaptation_images/dslr/images/phone/frame_0012.jpg 20 347 | /data/office/domain_adaptation_images/dslr/images/phone/frame_0013.jpg 20 348 | /data/office/domain_adaptation_images/dslr/images/bookcase/frame_0001.jpg 3 349 | /data/office/domain_adaptation_images/dslr/images/bookcase/frame_0002.jpg 3 350 | /data/office/domain_adaptation_images/dslr/images/bookcase/frame_0003.jpg 3 351 | /data/office/domain_adaptation_images/dslr/images/bookcase/frame_0004.jpg 3 352 | /data/office/domain_adaptation_images/dslr/images/bookcase/frame_0005.jpg 3 353 | /data/office/domain_adaptation_images/dslr/images/bookcase/frame_0006.jpg 3 354 | /data/office/domain_adaptation_images/dslr/images/bookcase/frame_0007.jpg 3 355 | /data/office/domain_adaptation_images/dslr/images/bookcase/frame_0008.jpg 3 356 | /data/office/domain_adaptation_images/dslr/images/bookcase/frame_0009.jpg 3 357 | /data/office/domain_adaptation_images/dslr/images/bookcase/frame_0010.jpg 3 358 | /data/office/domain_adaptation_images/dslr/images/bookcase/frame_0011.jpg 3 359 | /data/office/domain_adaptation_images/dslr/images/bookcase/frame_0012.jpg 3 360 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0001.jpg 22 361 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0002.jpg 22 362 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0003.jpg 22 363 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0004.jpg 22 364 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0005.jpg 22 365 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0006.jpg 22 366 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0007.jpg 22 367 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0008.jpg 22 368 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0009.jpg 22 369 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0010.jpg 22 370 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0011.jpg 22 371 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0012.jpg 22 372 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0013.jpg 22 373 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0014.jpg 22 374 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0015.jpg 22 375 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0016.jpg 22 376 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0017.jpg 22 377 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0018.jpg 22 378 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0019.jpg 22 379 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0020.jpg 22 380 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0021.jpg 22 381 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0022.jpg 22 382 | /data/office/domain_adaptation_images/dslr/images/projector/frame_0023.jpg 22 383 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0001.jpg 28 384 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0002.jpg 28 385 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0003.jpg 28 386 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0004.jpg 28 387 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0005.jpg 28 388 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0006.jpg 28 389 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0007.jpg 28 390 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0008.jpg 28 391 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0009.jpg 28 392 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0010.jpg 28 393 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0011.jpg 28 394 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0012.jpg 28 395 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0013.jpg 28 396 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0014.jpg 28 397 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0015.jpg 28 398 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0016.jpg 28 399 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0017.jpg 28 400 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0018.jpg 28 401 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0019.jpg 28 402 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0020.jpg 28 403 | /data/office/domain_adaptation_images/dslr/images/stapler/frame_0021.jpg 28 404 | /data/office/domain_adaptation_images/dslr/images/trash_can/frame_0001.jpg 30 405 | /data/office/domain_adaptation_images/dslr/images/trash_can/frame_0002.jpg 30 406 | /data/office/domain_adaptation_images/dslr/images/trash_can/frame_0003.jpg 30 407 | /data/office/domain_adaptation_images/dslr/images/trash_can/frame_0004.jpg 30 408 | /data/office/domain_adaptation_images/dslr/images/trash_can/frame_0005.jpg 30 409 | /data/office/domain_adaptation_images/dslr/images/trash_can/frame_0006.jpg 30 410 | /data/office/domain_adaptation_images/dslr/images/trash_can/frame_0007.jpg 30 411 | /data/office/domain_adaptation_images/dslr/images/trash_can/frame_0008.jpg 30 412 | /data/office/domain_adaptation_images/dslr/images/trash_can/frame_0009.jpg 30 413 | /data/office/domain_adaptation_images/dslr/images/trash_can/frame_0010.jpg 30 414 | /data/office/domain_adaptation_images/dslr/images/trash_can/frame_0011.jpg 30 415 | /data/office/domain_adaptation_images/dslr/images/trash_can/frame_0012.jpg 30 416 | /data/office/domain_adaptation_images/dslr/images/trash_can/frame_0013.jpg 30 417 | /data/office/domain_adaptation_images/dslr/images/trash_can/frame_0014.jpg 30 418 | /data/office/domain_adaptation_images/dslr/images/trash_can/frame_0015.jpg 30 419 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0001.jpg 2 420 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0002.jpg 2 421 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0003.jpg 2 422 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0004.jpg 2 423 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0005.jpg 2 424 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0006.jpg 2 425 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0007.jpg 2 426 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0008.jpg 2 427 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0009.jpg 2 428 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0010.jpg 2 429 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0011.jpg 2 430 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0012.jpg 2 431 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0013.jpg 2 432 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0014.jpg 2 433 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0015.jpg 2 434 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0016.jpg 2 435 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0017.jpg 2 436 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0018.jpg 2 437 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0019.jpg 2 438 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0020.jpg 2 439 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0021.jpg 2 440 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0022.jpg 2 441 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0023.jpg 2 442 | /data/office/domain_adaptation_images/dslr/images/bike_helmet/frame_0024.jpg 2 443 | /data/office/domain_adaptation_images/dslr/images/headphones/frame_0001.jpg 10 444 | /data/office/domain_adaptation_images/dslr/images/headphones/frame_0002.jpg 10 445 | /data/office/domain_adaptation_images/dslr/images/headphones/frame_0003.jpg 10 446 | /data/office/domain_adaptation_images/dslr/images/headphones/frame_0004.jpg 10 447 | /data/office/domain_adaptation_images/dslr/images/headphones/frame_0005.jpg 10 448 | /data/office/domain_adaptation_images/dslr/images/headphones/frame_0006.jpg 10 449 | /data/office/domain_adaptation_images/dslr/images/headphones/frame_0007.jpg 10 450 | /data/office/domain_adaptation_images/dslr/images/headphones/frame_0008.jpg 10 451 | /data/office/domain_adaptation_images/dslr/images/headphones/frame_0009.jpg 10 452 | /data/office/domain_adaptation_images/dslr/images/headphones/frame_0010.jpg 10 453 | /data/office/domain_adaptation_images/dslr/images/headphones/frame_0011.jpg 10 454 | /data/office/domain_adaptation_images/dslr/images/headphones/frame_0012.jpg 10 455 | /data/office/domain_adaptation_images/dslr/images/headphones/frame_0013.jpg 10 456 | /data/office/domain_adaptation_images/dslr/images/desk_lamp/frame_0001.jpg 7 457 | /data/office/domain_adaptation_images/dslr/images/desk_lamp/frame_0002.jpg 7 458 | /data/office/domain_adaptation_images/dslr/images/desk_lamp/frame_0003.jpg 7 459 | /data/office/domain_adaptation_images/dslr/images/desk_lamp/frame_0004.jpg 7 460 | /data/office/domain_adaptation_images/dslr/images/desk_lamp/frame_0005.jpg 7 461 | /data/office/domain_adaptation_images/dslr/images/desk_lamp/frame_0006.jpg 7 462 | /data/office/domain_adaptation_images/dslr/images/desk_lamp/frame_0007.jpg 7 463 | /data/office/domain_adaptation_images/dslr/images/desk_lamp/frame_0008.jpg 7 464 | /data/office/domain_adaptation_images/dslr/images/desk_lamp/frame_0009.jpg 7 465 | /data/office/domain_adaptation_images/dslr/images/desk_lamp/frame_0010.jpg 7 466 | /data/office/domain_adaptation_images/dslr/images/desk_lamp/frame_0011.jpg 7 467 | /data/office/domain_adaptation_images/dslr/images/desk_lamp/frame_0012.jpg 7 468 | /data/office/domain_adaptation_images/dslr/images/desk_lamp/frame_0013.jpg 7 469 | /data/office/domain_adaptation_images/dslr/images/desk_lamp/frame_0014.jpg 7 470 | /data/office/domain_adaptation_images/dslr/images/desk_chair/frame_0001.jpg 6 471 | /data/office/domain_adaptation_images/dslr/images/desk_chair/frame_0002.jpg 6 472 | /data/office/domain_adaptation_images/dslr/images/desk_chair/frame_0003.jpg 6 473 | /data/office/domain_adaptation_images/dslr/images/desk_chair/frame_0004.jpg 6 474 | /data/office/domain_adaptation_images/dslr/images/desk_chair/frame_0005.jpg 6 475 | /data/office/domain_adaptation_images/dslr/images/desk_chair/frame_0006.jpg 6 476 | /data/office/domain_adaptation_images/dslr/images/desk_chair/frame_0007.jpg 6 477 | /data/office/domain_adaptation_images/dslr/images/desk_chair/frame_0008.jpg 6 478 | /data/office/domain_adaptation_images/dslr/images/desk_chair/frame_0009.jpg 6 479 | /data/office/domain_adaptation_images/dslr/images/desk_chair/frame_0010.jpg 6 480 | /data/office/domain_adaptation_images/dslr/images/desk_chair/frame_0011.jpg 6 481 | /data/office/domain_adaptation_images/dslr/images/desk_chair/frame_0012.jpg 6 482 | /data/office/domain_adaptation_images/dslr/images/desk_chair/frame_0013.jpg 6 483 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0001.jpg 4 484 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0002.jpg 4 485 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0003.jpg 4 486 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0004.jpg 4 487 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0005.jpg 4 488 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0006.jpg 4 489 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0007.jpg 4 490 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0008.jpg 4 491 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0009.jpg 4 492 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0010.jpg 4 493 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0011.jpg 4 494 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0012.jpg 4 495 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0013.jpg 4 496 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0014.jpg 4 497 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0015.jpg 4 498 | /data/office/domain_adaptation_images/dslr/images/bottle/frame_0016.jpg 4 499 | -------------------------------------------------------------------------------- /src/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuml/TransNorm/713c2e28a0d8e73cac7aaf9b30b47e7654ac1939/src/__init__.py -------------------------------------------------------------------------------- /src/data_list.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | from PIL import Image 3 | from torch.utils.data import Dataset 4 | 5 | def make_dataset(image_list, labels): 6 | if labels: 7 | len_ = len(image_list) 8 | images = [(image_list[i].strip(), labels[i, :]) for i in range(len_)] 9 | else: 10 | if len(image_list[0].split()) > 2: 11 | images = [(val.split()[0], np.array([int(la) for la in val.split()[1:]])) for val in image_list] 12 | else: 13 | images = [(val.split()[0], int(val.split()[1])) for val in image_list] 14 | return images 15 | 16 | 17 | def rgb_loader(path): 18 | with open(path, 'rb') as f: 19 | with Image.open(f) as img: 20 | return img.convert('RGB') 21 | 22 | def l_loader(path): 23 | with open(path, 'rb') as f: 24 | with Image.open(f) as img: 25 | return img.convert('L') 26 | 27 | class ImageList(Dataset): 28 | def __init__(self, image_list, labels=None, transform=None, target_transform=None, mode='RGB'): 29 | imgs = make_dataset(image_list, labels) 30 | self.imgs = imgs 31 | self.transform = transform 32 | self.target_transform = target_transform 33 | if mode == 'RGB': 34 | self.loader = rgb_loader 35 | elif mode == 'L': 36 | self.loader = l_loader 37 | 38 | def __getitem__(self, index): 39 | path, target = self.imgs[index] 40 | img = self.loader(path) 41 | if self.transform is not None: 42 | img = self.transform(img) 43 | if self.target_transform is not None: 44 | target = self.target_transform(target) 45 | 46 | return img, target 47 | 48 | def __len__(self): 49 | return len(self.imgs) 50 | 51 | 52 | 53 | -------------------------------------------------------------------------------- /src/loss.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | import torch 3 | import torch.nn as nn 4 | 5 | 6 | def Entropy(input_): 7 | epsilon = 1e-5 8 | entropy = -input_ * torch.log(input_ + epsilon) 9 | entropy = torch.sum(entropy, dim=1) 10 | return entropy 11 | 12 | def grl_hook(coeff): 13 | def fun1(grad): 14 | return -coeff*grad.clone() 15 | return fun1 16 | 17 | def CDAN(input_list, ad_net, entropy=None, coeff=None, random_layer=None): 18 | softmax_output = input_list[1].detach() 19 | feature = input_list[0] 20 | if random_layer is None: 21 | op_out = torch.bmm(softmax_output.unsqueeze(2), feature.unsqueeze(1)) 22 | ad_out = ad_net(op_out.view(-1, softmax_output.size(1) * feature.size(1))) 23 | else: 24 | random_out = random_layer.forward([feature, softmax_output]) 25 | ad_out = ad_net(random_out.view(-1, random_out.size(1))) 26 | batch_size = softmax_output.size(0) // 2 27 | dc_target = torch.from_numpy(np.array([[1]] * batch_size + [[0]] * batch_size)).float().cuda() 28 | if entropy is not None: 29 | entropy.register_hook(grl_hook(coeff)) 30 | entropy = 1.0+torch.exp(-entropy) 31 | source_mask = torch.ones_like(entropy) 32 | source_mask[feature.size(0)//2:] = 0 33 | source_weight = entropy*source_mask 34 | target_mask = torch.ones_like(entropy) 35 | target_mask[0:feature.size(0)//2] = 0 36 | target_weight = entropy*target_mask 37 | weight = source_weight / torch.sum(source_weight).detach().item() + \ 38 | target_weight / torch.sum(target_weight).detach().item() 39 | return torch.sum(weight.view(-1, 1) * nn.BCELoss(reduction='none')(ad_out, dc_target)) / torch.sum(weight).detach().item() 40 | else: 41 | return nn.BCELoss()(ad_out, dc_target) 42 | -------------------------------------------------------------------------------- /src/lr_schedule.py: -------------------------------------------------------------------------------- 1 | def inv_lr_scheduler(optimizer, iter_num, gamma, power, lr=0.001, weight_decay=0.0005): 2 | """Decay learning rate by a factor of 0.1 every lr_decay_epoch epochs.""" 3 | lr = lr * (1 + gamma * iter_num) ** (-power) 4 | i=0 5 | for param_group in optimizer.param_groups: 6 | param_group['lr'] = lr * param_group['lr_mult'] 7 | param_group['weight_decay'] = weight_decay * param_group['decay_mult'] 8 | i+=1 9 | 10 | return optimizer 11 | 12 | 13 | schedule_dict = {"inv":inv_lr_scheduler} 14 | -------------------------------------------------------------------------------- /src/network.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | import torch 3 | import torch.nn as nn 4 | import math 5 | import resnet_tn 6 | from trans_norm import TransNorm1d, TransNorm2d 7 | 8 | def calc_coeff(iter_num, high=1.0, low=0.0, alpha=10.0, max_iter=10000.0): 9 | return np.float(2.0 * (high - low) / (1.0 + np.exp(-alpha*iter_num / max_iter)) - (high - low) + low) 10 | 11 | def init_weights(m): 12 | classname = m.__class__.__name__ 13 | if classname.find('Conv2d') != -1 or classname.find('ConvTranspose2d') != -1: 14 | nn.init.kaiming_uniform_(m.weight) 15 | nn.init.zeros_(m.bias) 16 | elif classname.find('BatchNorm') != -1: 17 | nn.init.normal_(m.weight, 1.0, 0.02) 18 | nn.init.zeros_(m.bias) 19 | elif classname.find('Linear') != -1: 20 | nn.init.xavier_normal_(m.weight) 21 | nn.init.zeros_(m.bias) 22 | 23 | def grl_hook(coeff): 24 | def fun1(grad): 25 | return -coeff*grad.clone() 26 | return fun1 27 | 28 | class RandomLayer(nn.Module): 29 | def __init__(self, input_dim_list=[], output_dim=1024): 30 | super(RandomLayer, self).__init__() 31 | self.input_num = len(input_dim_list) 32 | self.output_dim = output_dim 33 | self.random_matrix = [torch.randn(input_dim_list[i], output_dim) for i in range(self.input_num)] 34 | 35 | def forward(self, input_list): 36 | return_list = [torch.mm(input_list[i], self.random_matrix[i]) for i in range(self.input_num)] 37 | return_tensor = return_list[0] / math.pow(float(self.output_dim), 1.0/len(return_list)) 38 | for single in return_list[1:]: 39 | return_tensor = torch.mul(return_tensor, single) 40 | return return_tensor 41 | 42 | def cuda(self): 43 | super(RandomLayer, self).cuda() 44 | self.random_matrix = [val.cuda() for val in self.random_matrix] 45 | 46 | resnet_dict = {"ResNet18": resnet_tn.resnet18, "ResNet34": resnet_tn.resnet34, "ResNet50": resnet_tn.resnet50, 47 | "ResNet101": resnet_tn.resnet101, "ResNet152": resnet_tn.resnet152} 48 | 49 | class ResNetFc(nn.Module): 50 | def __init__(self, resnet_name, use_bottleneck=True, bottleneck_dim=256, new_cls=False, class_num=1000): 51 | super(ResNetFc, self).__init__() 52 | model_resnet = resnet_dict[resnet_name](pretrained=True) 53 | self.conv1 = model_resnet.conv1 54 | self.bn1 = model_resnet.bn1 55 | self.relu = model_resnet.relu 56 | self.maxpool = model_resnet.maxpool 57 | self.layer1 = model_resnet.layer1 58 | self.layer2 = model_resnet.layer2 59 | self.layer3 = model_resnet.layer3 60 | self.layer4 = model_resnet.layer4 61 | self.avgpool = nn.AvgPool2d(7, stride=1) 62 | self.feature_layers = nn.Sequential(self.conv1, self.bn1, self.relu, self.maxpool, \ 63 | self.layer1, self.layer2, self.layer3, self.layer4,self.avgpool) 64 | 65 | self.use_bottleneck = use_bottleneck 66 | self.new_cls = new_cls 67 | if new_cls: 68 | if self.use_bottleneck: 69 | self.bottleneck = nn.Sequential() 70 | bottleneck_linear = nn.Linear(2048, bottleneck_dim) 71 | bottleneck_linear.weight.data.normal_(0, 0.005) 72 | bottleneck_linear.bias.data.fill_(0.0) 73 | self.bottleneck.add_module("linear", bottleneck_linear) 74 | self.bottleneck.add_module("tn", TransNorm1d(bottleneck_dim)) 75 | self.bottleneck.add_module("relu", nn.ReLU(True)) 76 | self.fc = nn.Linear(bottleneck_dim, class_num) 77 | self.fc.weight.data.normal_(0, 0.01) 78 | self.fc.bias.data.fill_(0.0) 79 | else: 80 | self.fc = nn.Linear(2048, class_num) 81 | self.fc.weight.data.normal_(0, 0.01) 82 | self.fc.bias.data.fill_(0.0) 83 | self.__in_features = bottleneck_dim 84 | else: 85 | self.fc = model_resnet.fc 86 | self.__in_features = model_resnet.fc.in_features 87 | 88 | def forward(self, x): 89 | x = self.feature_layers(x) 90 | x = x.view(len(x), -1) 91 | x = self.bottleneck(x) 92 | y = self.fc(x) 93 | return x, y 94 | 95 | def output_num(self): 96 | return self.__in_features 97 | 98 | def get_parameters(self): 99 | if self.new_cls: 100 | if self.use_bottleneck: 101 | parameter_list = [{"params": self.feature_layers.parameters(), "lr_mult": 1, 'decay_mult': 2}, \ 102 | {"params": self.bottleneck.parameters(), "lr_mult": 10, 'decay_mult': 2}, \ 103 | {"params": self.fc.parameters(), "lr_mult": 10, 'decay_mult': 2}] 104 | else: 105 | parameter_list = [{"params": self.feature_layers.parameters(), "lr_mult": 1, 'decay_mult': 2}, \ 106 | {"params": self.fc.parameters(), "lr_mult": 10, 'decay_mult': 2}] 107 | else: 108 | parameter_list = [{"params": self.parameters(), "lr_mult": 1, 'decay_mult': 2}] 109 | return parameter_list 110 | 111 | 112 | 113 | class AdversarialNetwork(nn.Module): 114 | def __init__(self, in_feature, hidden_size): 115 | super(AdversarialNetwork, self).__init__() 116 | self.ad_layer1 = nn.Linear(in_feature, hidden_size) 117 | self.ad_layer2 = nn.Linear(hidden_size, hidden_size) 118 | self.ad_layer3 = nn.Linear(hidden_size, 1) 119 | self.relu1 = nn.ReLU() 120 | self.relu2 = nn.ReLU() 121 | self.dropout1 = nn.Dropout(0.5) 122 | self.dropout2 = nn.Dropout(0.5) 123 | self.sigmoid = nn.Sigmoid() 124 | self.apply(init_weights) 125 | self.iter_num = 0 126 | self.alpha = 10 127 | self.low = 0.0 128 | self.high = 1.0 129 | self.max_iter = 5000.0 130 | 131 | def forward(self, x): 132 | if self.training: 133 | self.iter_num += 1 134 | coeff = calc_coeff(self.iter_num, self.high, self.low, self.alpha, self.max_iter) 135 | x = x * 1.0 136 | x.register_hook(grl_hook(coeff)) 137 | x = self.ad_layer1(x) 138 | x = self.relu1(x) 139 | x = self.dropout1(x) 140 | x = self.ad_layer2(x) 141 | x = self.relu2(x) 142 | x = self.dropout2(x) 143 | y = self.ad_layer3(x) 144 | y = self.sigmoid(y) 145 | return y 146 | 147 | def output_num(self): 148 | return 1 149 | def get_parameters(self): 150 | return [{"params":self.parameters(), "lr_mult":10, 'decay_mult':2}] 151 | -------------------------------------------------------------------------------- /src/pre_process.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | from torchvision import transforms 3 | from PIL import Image 4 | import numbers 5 | import torch 6 | 7 | class ResizeImage(): 8 | def __init__(self, size): 9 | if isinstance(size, int): 10 | self.size = (int(size), int(size)) 11 | else: 12 | self.size = size 13 | def __call__(self, img): 14 | th, tw = self.size 15 | return img.resize((th, tw)) 16 | 17 | 18 | class Normalize(object): 19 | """Normalize an tensor image with mean and standard deviation. 20 | Given mean: (R, G, B), 21 | will normalize each channel of the torch.*Tensor, i.e. 22 | channel = channel - mean 23 | Args: 24 | mean (sequence): Sequence of means for R, G, B channels respecitvely. 25 | """ 26 | 27 | def __init__(self, mean=None, meanfile=None): 28 | if mean: 29 | self.mean = mean 30 | else: 31 | arr = np.load(meanfile) 32 | self.mean = torch.from_numpy(arr.astype('float32')/255.0)[[2,1,0],:,:] 33 | 34 | def __call__(self, tensor): 35 | """ 36 | Args: 37 | tensor (Tensor): Tensor image of size (C, H, W) to be normalized. 38 | Returns: 39 | Tensor: Normalized image. 40 | """ 41 | # TODO: make efficient 42 | for t, m in zip(tensor, self.mean): 43 | t.sub_(m) 44 | return tensor 45 | 46 | 47 | 48 | class PlaceCrop(object): 49 | """Crops the given PIL.Image at the particular index. 50 | Args: 51 | size (sequence or int): Desired output size of the crop. If size is an 52 | int instead of sequence like (w, h), a square crop (size, size) is 53 | made. 54 | """ 55 | 56 | def __init__(self, size, start_x, start_y): 57 | if isinstance(size, int): 58 | self.size = (int(size), int(size)) 59 | else: 60 | self.size = size 61 | self.start_x = start_x 62 | self.start_y = start_y 63 | 64 | def __call__(self, img): 65 | """ 66 | Args: 67 | img (PIL.Image): Image to be cropped. 68 | Returns: 69 | PIL.Image: Cropped image. 70 | """ 71 | th, tw = self.size 72 | return img.crop((self.start_x, self.start_y, self.start_x + tw, self.start_y + th)) 73 | 74 | 75 | class ForceFlip(object): 76 | """Horizontally flip the given PIL.Image randomly with a probability of 0.5.""" 77 | 78 | def __call__(self, img): 79 | """ 80 | Args: 81 | img (PIL.Image): Image to be flipped. 82 | Returns: 83 | PIL.Image: Randomly flipped image. 84 | """ 85 | return img.transpose(Image.FLIP_LEFT_RIGHT) 86 | 87 | class CenterCrop(object): 88 | """Crops the given PIL.Image at the center. 89 | Args: 90 | size (sequence or int): Desired output size of the crop. If size is an 91 | int instead of sequence like (h, w), a square crop (size, size) is 92 | made. 93 | """ 94 | 95 | def __init__(self, size): 96 | if isinstance(size, numbers.Number): 97 | self.size = (int(size), int(size)) 98 | else: 99 | self.size = size 100 | 101 | def __call__(self, img): 102 | """ 103 | Args: 104 | img (PIL.Image): Image to be cropped. 105 | Returns: 106 | PIL.Image: Cropped image. 107 | """ 108 | w, h = (img.shape[1], img.shape[2]) 109 | th, tw = self.size 110 | w_off = int((w - tw) / 2.) 111 | h_off = int((h - th) / 2.) 112 | img = img[:, h_off:h_off+th, w_off:w_off+tw] 113 | return img 114 | 115 | 116 | def image_train(resize_size=256, crop_size=224): 117 | normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], 118 | std=[0.229, 0.224, 0.225]) 119 | return transforms.Compose([ 120 | ResizeImage(resize_size), 121 | transforms.RandomResizedCrop(crop_size), 122 | transforms.RandomHorizontalFlip(), 123 | transforms.ToTensor(), 124 | normalize 125 | ]) 126 | 127 | def image_test(resize_size=256, crop_size=224): 128 | normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], 129 | std=[0.229, 0.224, 0.225]) 130 | start_center = (resize_size - crop_size - 1) / 2 131 | return transforms.Compose([ 132 | ResizeImage(resize_size), 133 | PlaceCrop(crop_size, start_center, start_center), 134 | transforms.ToTensor(), 135 | normalize 136 | ]) 137 | 138 | def image_test_10crop(resize_size=256, crop_size=224): 139 | normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], 140 | std=[0.229, 0.224, 0.225]) 141 | start_first = 0 142 | start_center = (resize_size - crop_size - 1) / 2 143 | start_last = resize_size - crop_size - 1 144 | data_transforms = [ 145 | transforms.Compose([ 146 | ResizeImage(resize_size),ForceFlip(), 147 | PlaceCrop(crop_size, start_first, start_first), 148 | transforms.ToTensor(), 149 | normalize 150 | ]), 151 | transforms.Compose([ 152 | ResizeImage(resize_size),ForceFlip(), 153 | PlaceCrop(crop_size, start_last, start_last), 154 | transforms.ToTensor(), 155 | normalize 156 | ]), 157 | transforms.Compose([ 158 | ResizeImage(resize_size),ForceFlip(), 159 | PlaceCrop(crop_size, start_last, start_first), 160 | transforms.ToTensor(), 161 | normalize 162 | ]), 163 | transforms.Compose([ 164 | ResizeImage(resize_size),ForceFlip(), 165 | PlaceCrop(crop_size, start_first, start_last), 166 | transforms.ToTensor(), 167 | normalize 168 | ]), 169 | transforms.Compose([ 170 | ResizeImage(resize_size),ForceFlip(), 171 | PlaceCrop(crop_size, start_center, start_center), 172 | transforms.ToTensor(), 173 | normalize 174 | ]), 175 | transforms.Compose([ 176 | ResizeImage(resize_size), 177 | PlaceCrop(crop_size, start_first, start_first), 178 | transforms.ToTensor(), 179 | normalize 180 | ]), 181 | transforms.Compose([ 182 | ResizeImage(resize_size), 183 | PlaceCrop(crop_size, start_last, start_last), 184 | transforms.ToTensor(), 185 | normalize 186 | ]), 187 | transforms.Compose([ 188 | ResizeImage(resize_size), 189 | PlaceCrop(crop_size, start_last, start_first), 190 | transforms.ToTensor(), 191 | normalize 192 | ]), 193 | transforms.Compose([ 194 | ResizeImage(resize_size), 195 | PlaceCrop(crop_size, start_first, start_last), 196 | transforms.ToTensor(), 197 | normalize 198 | ]), 199 | transforms.Compose([ 200 | ResizeImage(resize_size), 201 | PlaceCrop(crop_size, start_center, start_center), 202 | transforms.ToTensor(), 203 | normalize 204 | ]) 205 | ] 206 | return data_transforms 207 | -------------------------------------------------------------------------------- /src/resnet_tn.py: -------------------------------------------------------------------------------- 1 | import torch.nn as nn 2 | import math 3 | import torch.utils.model_zoo as model_zoo 4 | from trans_norm import TransNorm1d, TransNorm2d 5 | 6 | __all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101', 'resnet152'] 7 | 8 | 9 | model_urls = { 10 | 'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth', 11 | 'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth', 12 | 'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth', 13 | 'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth', 14 | 'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth', 15 | } 16 | 17 | 18 | def conv3x3(in_planes, out_planes, stride=1): 19 | """3x3 convolution with padding""" 20 | return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, 21 | padding=1, bias=False) 22 | 23 | 24 | class BasicBlock(nn.Module): 25 | expansion = 1 26 | 27 | def __init__(self, inplanes, planes, stride=1, downsample=None): 28 | super(BasicBlock, self).__init__() 29 | self.conv1 = conv3x3(inplanes, planes, stride) 30 | self.bn1 = TransNorm2d(planes) ## replace 31 | self.relu = nn.ReLU(inplace=True) 32 | self.conv2 = conv3x3(planes, planes) 33 | self.bn2 = TransNorm2d(planes) ## replace 34 | self.downsample = downsample 35 | self.stride = stride 36 | 37 | def forward(self, x): 38 | residual = x 39 | 40 | out = self.conv1(x) 41 | out = self.bn1(out) 42 | out = self.relu(out) 43 | 44 | out = self.conv2(out) 45 | out = self.bn2(out) 46 | 47 | if self.downsample is not None: 48 | residual = self.downsample(x) 49 | 50 | out += residual 51 | out = self.relu(out) 52 | 53 | return out 54 | 55 | 56 | class Bottleneck(nn.Module): 57 | expansion = 4 58 | 59 | def __init__(self, inplanes, planes, stride=1, downsample=None): 60 | super(Bottleneck, self).__init__() 61 | self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False) 62 | self.bn1 = TransNorm2d(planes) ## replace 63 | self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, 64 | padding=1, bias=False) 65 | self.bn2 = TransNorm2d(planes) ## replace 66 | self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False) 67 | self.bn3 = TransNorm2d(planes * 4) ## replace 68 | self.relu = nn.ReLU(inplace=True) 69 | self.downsample = downsample 70 | self.stride = stride 71 | 72 | def forward(self, x): 73 | residual = x 74 | 75 | out = self.conv1(x) 76 | out = self.bn1(out) 77 | out = self.relu(out) 78 | 79 | out = self.conv2(out) 80 | out = self.bn2(out) 81 | out = self.relu(out) 82 | 83 | out = self.conv3(out) 84 | out = self.bn3(out) 85 | 86 | if self.downsample is not None: 87 | residual = self.downsample(x) 88 | 89 | out += residual 90 | out = self.relu(out) 91 | 92 | return out 93 | 94 | 95 | class ResNet(nn.Module): 96 | 97 | def __init__(self, block, layers, num_classes=1000): 98 | self.inplanes = 64 99 | super(ResNet, self).__init__() 100 | self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, 101 | bias=False) 102 | self.bn1 = TransNorm2d(64) 103 | self.relu = nn.ReLU(inplace=True) 104 | self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) 105 | self.layer1 = self._make_layer(block, 64, layers[0]) 106 | self.layer2 = self._make_layer(block, 128, layers[1], stride=2) 107 | self.layer3 = self._make_layer(block, 256, layers[2], stride=2) 108 | self.layer4 = self._make_layer(block, 512, layers[3], stride=2) 109 | self.avgpool = nn.AvgPool2d(7, stride=1) 110 | self.fc = nn.Linear(512 * block.expansion, num_classes) 111 | 112 | for m in self.modules(): 113 | if isinstance(m, nn.Conv2d): 114 | n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels 115 | m.weight.data.normal_(0, math.sqrt(2. / n)) 116 | elif isinstance(m, nn.BatchNorm2d): 117 | m.weight.data.fill_(1) 118 | m.bias.data.zero_() 119 | 120 | def _make_layer(self, block, planes, blocks, stride=1): 121 | downsample = None 122 | if stride != 1 or self.inplanes != planes * block.expansion: 123 | downsample = nn.Sequential( 124 | nn.Conv2d(self.inplanes, planes * block.expansion, 125 | kernel_size=1, stride=stride, bias=False), 126 | TransNorm2d(planes * block.expansion), 127 | ) 128 | 129 | layers = [] 130 | layers.append(block(self.inplanes, planes, stride, downsample)) 131 | self.inplanes = planes * block.expansion 132 | for i in range(1, blocks): 133 | layers.append(block(self.inplanes, planes)) 134 | 135 | return nn.Sequential(*layers) 136 | 137 | def forward(self, x): 138 | x = self.conv1(x) 139 | x = self.bn1(x) 140 | x = self.relu(x) 141 | x = self.maxpool(x) 142 | 143 | x = self.layer1(x) 144 | x = self.layer2(x) 145 | x = self.layer3(x) 146 | x = self.layer4(x) 147 | 148 | x = self.avgpool(x) 149 | x = x.view(x.size(0), -1) 150 | x = self.fc(x) 151 | 152 | return x 153 | 154 | 155 | def resnet18(pretrained=False, **kwargs): 156 | """Constructs a ResNet-18 model. 157 | 158 | Args: 159 | pretrained (bool): If True, returns a model pre-trained on ImageNet 160 | """ 161 | model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs) 162 | if pretrained: 163 | model.load_state_dict(model_zoo.load_url(model_urls['resnet18'])) 164 | return model 165 | 166 | 167 | def resnet34(pretrained=False, **kwargs): 168 | """Constructs a ResNet-34 model. 169 | 170 | Args: 171 | pretrained (bool): If True, returns a model pre-trained on ImageNet 172 | """ 173 | model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs) 174 | if pretrained: 175 | model.load_state_dict(model_zoo.load_url(model_urls['resnet34'])) 176 | return model 177 | 178 | 179 | def resnet50(pretrained=False, **kwargs): 180 | """Constructs a ResNet-50 model. 181 | 182 | Args: 183 | pretrained (bool): If True, returns a model pre-trained on ImageNet 184 | """ 185 | model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs) 186 | if pretrained: 187 | model.load_state_dict(model_zoo.load_url(model_urls['resnet50'])) 188 | return model 189 | 190 | 191 | def resnet101(pretrained=False, **kwargs): 192 | """Constructs a ResNet-101 model. 193 | 194 | Args: 195 | pretrained (bool): If True, returns a model pre-trained on ImageNet 196 | """ 197 | model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs) 198 | if pretrained: 199 | model.load_state_dict(model_zoo.load_url(model_urls['resnet101'])) 200 | return model 201 | 202 | 203 | def resnet152(pretrained=False, **kwargs): 204 | """Constructs a ResNet-152 model. 205 | 206 | Args: 207 | pretrained (bool): If True, returns a model pre-trained on ImageNet 208 | """ 209 | model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs) 210 | if pretrained: 211 | model.load_state_dict(model_zoo.load_url(model_urls['resnet152'])) 212 | return model 213 | -------------------------------------------------------------------------------- /src/train_image.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | import os 3 | import os.path as osp 4 | 5 | import torch 6 | import torch.nn as nn 7 | import torch.optim as optim 8 | import network 9 | import loss 10 | import pre_process as prep 11 | from torch.utils.data import DataLoader 12 | import lr_schedule 13 | from data_list import ImageList 14 | from tensorboardX import SummaryWriter 15 | 16 | def image_classification_test(loader, model, test_10crop=True): 17 | start_test = True 18 | with torch.no_grad(): 19 | if test_10crop: 20 | iter_test = [iter(loader['test'][i]) for i in range(10)] 21 | for i in range(len(loader['test'][0])): 22 | data = [iter_test[j].next() for j in range(10)] 23 | inputs = [data[j][0] for j in range(10)] 24 | labels = data[0][1] 25 | for j in range(10): 26 | inputs[j] = inputs[j].cuda() 27 | outputs = [] 28 | for j in range(10): 29 | _, predict_out = model(inputs[j]) 30 | outputs.append(nn.Softmax(dim=1)(predict_out)) 31 | outputs = sum(outputs) 32 | if start_test: 33 | all_output = outputs.float().cpu() 34 | all_label = labels.float() 35 | start_test = False 36 | else: 37 | all_output = torch.cat((all_output, outputs.float().cpu()), 0) 38 | all_label = torch.cat((all_label, labels.float()), 0) 39 | else: 40 | iter_test = iter(loader["test"]) 41 | for i in range(len(loader['test'])): 42 | data = iter_test.next() 43 | inputs = data[0] 44 | labels = data[1] 45 | inputs = inputs.cuda() 46 | _, outputs = model(inputs) 47 | if start_test: 48 | all_output = outputs.float().cpu() 49 | all_label = labels.float() 50 | start_test = False 51 | else: 52 | all_output = torch.cat((all_output, outputs.float().cpu()), 0) 53 | all_label = torch.cat((all_label, labels.float()), 0) 54 | _, predict = torch.max(all_output, 1) 55 | accuracy = torch.sum(torch.squeeze(predict).float() == all_label).item() / float(all_label.size()[0]) 56 | return accuracy 57 | 58 | 59 | def train(config): 60 | ## set pre-process 61 | tensor_writer = SummaryWriter(config["tensorboard_path"]) 62 | prep_dict = {} 63 | prep_config = config["prep"] 64 | prep_dict["source"] = prep.image_train(**config["prep"]['params']) 65 | prep_dict["target"] = prep.image_train(**config["prep"]['params']) 66 | if prep_config["test_10crop"]: 67 | prep_dict["test"] = prep.image_test_10crop(**config["prep"]['params']) 68 | else: 69 | prep_dict["test"] = prep.image_test(**config["prep"]['params']) 70 | 71 | ## prepare data 72 | dsets = {} 73 | dset_loaders = {} 74 | data_config = config["data"] 75 | train_bs = data_config["source"]["batch_size"] 76 | test_bs = data_config["test"]["batch_size"] 77 | dsets["source"] = ImageList(open(data_config["source"]["list_path"]).readlines(), \ 78 | transform=prep_dict["source"]) 79 | dset_loaders["source"] = DataLoader(dsets["source"], batch_size=train_bs, \ 80 | shuffle=True, num_workers=4, drop_last=True) 81 | dsets["target"] = ImageList(open(data_config["target"]["list_path"]).readlines(), \ 82 | transform=prep_dict["target"]) 83 | dset_loaders["target"] = DataLoader(dsets["target"], batch_size=train_bs, \ 84 | shuffle=True, num_workers=4, drop_last=True) 85 | 86 | if prep_config["test_10crop"]: 87 | for i in range(10): 88 | dsets["test"] = [ImageList(open(data_config["test"]["list_path"]).readlines(), \ 89 | transform=prep_dict["test"][i]) for i in range(10)] 90 | dset_loaders["test"] = [DataLoader(dset, batch_size=test_bs, \ 91 | shuffle=False, num_workers=4) for dset in dsets['test']] 92 | else: 93 | dsets["test"] = ImageList(open(data_config["test"]["list_path"]).readlines(), \ 94 | transform=prep_dict["test"]) 95 | dset_loaders["test"] = DataLoader(dsets["test"], batch_size=test_bs, \ 96 | shuffle=False, num_workers=4) 97 | 98 | class_num = config["network"]["params"]["class_num"] 99 | 100 | ## set base network 101 | net_config = config["network"] 102 | base_network = net_config["name"](**net_config["params"]) 103 | base_network = base_network.cuda() 104 | 105 | ## add additional network for some methods 106 | if config["loss"]["random"]: 107 | random_layer = network.RandomLayer([base_network.output_num(), class_num], config["loss"]["random_dim"]) 108 | ad_net = network.AdversarialNetwork(config["loss"]["random_dim"], 1024) 109 | else: 110 | random_layer = None 111 | ad_net = network.AdversarialNetwork(base_network.output_num() * class_num, 1024) 112 | if config["loss"]["random"]: 113 | random_layer.cuda() 114 | ad_net = ad_net.cuda() 115 | parameter_list = base_network.get_parameters() + ad_net.get_parameters() 116 | 117 | ## set optimizer 118 | optimizer_config = config["optimizer"] 119 | optimizer = optimizer_config["type"](parameter_list, \ 120 | **(optimizer_config["optim_params"])) 121 | param_lr = [] 122 | for param_group in optimizer.param_groups: 123 | param_lr.append(param_group["lr"]) 124 | schedule_param = optimizer_config["lr_param"] 125 | lr_scheduler = lr_schedule.schedule_dict[optimizer_config["lr_type"]] 126 | 127 | gpus = config['gpu'].split(',') 128 | if len(gpus) > 1: 129 | ad_net = nn.DataParallel(ad_net, device_ids=[int(i) for i in gpus]) 130 | base_network = nn.DataParallel(base_network, device_ids=[int(i) for i in gpus]) 131 | 132 | 133 | ## train 134 | len_train_source = len(dset_loaders["source"]) 135 | len_train_target = len(dset_loaders["target"]) 136 | best_acc = 0.0 137 | batch_size = config["data"]["source"]["batch_size"] 138 | 139 | for i in range(config["num_iterations"]): 140 | if i % config["test_interval"] == 0 and i > 0: 141 | base_network.train(False) 142 | temp_acc = image_classification_test(dset_loaders, \ 143 | base_network, test_10crop=prep_config["test_10crop"]) 144 | temp_model = nn.Sequential(base_network) 145 | if temp_acc > best_acc: 146 | best_acc = temp_acc 147 | best_model = temp_model 148 | torch.save(best_model, osp.join(config["output_path"], "best_model.pth.tar")) 149 | log_str = "iter: {:05d}, precision: {:.5f}".format(i, temp_acc) 150 | config["out_file"].write(log_str+"\n") 151 | config["out_file"].flush() 152 | print(log_str) 153 | 154 | loss_params = config["loss"] 155 | ## train one iter 156 | base_network.train(True) 157 | ad_net.train(True) 158 | optimizer = lr_scheduler(optimizer, i, **schedule_param) 159 | optimizer.zero_grad() 160 | if i % len_train_source == 0: 161 | iter_source = iter(dset_loaders["source"]) 162 | if i % len_train_target == 0: 163 | iter_target = iter(dset_loaders["target"]) 164 | inputs_source, labels_source = iter_source.next() 165 | inputs_target, labels_target = iter_target.next() 166 | inputs_source, inputs_target, labels_source = inputs_source.cuda(), inputs_target.cuda(), labels_source.cuda() 167 | 168 | inputs = torch.cat((inputs_source, inputs_target), dim=0) 169 | features, outputs = base_network(inputs) 170 | outputs_source, outputs_target = outputs[:batch_size], outputs[batch_size:] 171 | 172 | softmax_out = nn.Softmax(dim=1)(outputs) 173 | if config['method'] == 'CDAN+E': 174 | entropy = loss.Entropy(softmax_out) 175 | transfer_loss = loss.CDAN([features, softmax_out], ad_net, entropy, network.calc_coeff(i), random_layer) 176 | elif config['method'] == 'CDAN': 177 | transfer_loss = loss.CDAN([features, softmax_out], ad_net, None, None, random_layer) 178 | else: 179 | raise ValueError('Method cannot be recognized.') 180 | classifier_loss = nn.CrossEntropyLoss()(outputs_source, labels_source) 181 | total_loss = loss_params["trade_off"] * transfer_loss + classifier_loss 182 | total_loss.backward() 183 | optimizer.step() 184 | if i % 10 == 0: 185 | print("iter: {:05d}, classifier_loss: {:.5f}".format(i, classifier_loss)) 186 | 187 | tensor_writer.add_scalar('total_loss', total_loss, i) 188 | tensor_writer.add_scalar('classifier_loss', classifier_loss, i) 189 | tensor_writer.add_scalar('transfer_loss', transfer_loss, i) 190 | torch.save(best_model, osp.join(config["output_path"], "best_model.pth.tar")) 191 | return best_acc 192 | 193 | if __name__ == "__main__": 194 | parser = argparse.ArgumentParser(description='Conditional Domain Adversarial Network') 195 | parser.add_argument('--method', type=str, default='CDAN+E', choices=['CDAN', 'CDAN+E']) 196 | parser.add_argument('--gpu_id', type=str, nargs='?', default='2', help="device id to run") 197 | parser.add_argument('--net', type=str, default='ResNet50', choices=["ResNet18", "ResNet34", "ResNet50", "ResNet101", "ResNet152", "VGG11", "VGG13", "VGG16", "VGG19", "VGG11BN", "VGG13BN", "VGG16BN", "VGG19BN", "AlexNet"]) 198 | parser.add_argument('--dset', type=str, default='office', choices=['office', 'image-clef', 'visda', 'office-home'], help="The dataset or source dataset used") 199 | parser.add_argument('--s_dset_path', type=str, default='../data/office/amazon_list.txt', help="The source dataset path list") 200 | parser.add_argument('--t_dset_path', type=str, default='../data/office/dslr_list.txt', help="The target dataset path list") 201 | parser.add_argument('--test_interval', type=int, default=500, help="interval of two continuous test phase") 202 | parser.add_argument('--snapshot_interval', type=int, default=5000, help="interval of two continuous output model") 203 | parser.add_argument('--lr', type=float, default=0.001, help="learning rate") 204 | parser.add_argument('--random', type=bool, default=False, help="whether use random projection") 205 | args = parser.parse_args() 206 | os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu_id 207 | import os 208 | print(os.getcwd()) 209 | 210 | # train config 211 | config = {} 212 | config['method'] = args.method 213 | config["gpu"] = args.gpu_id 214 | config["num_iterations"] = 100004 215 | config["test_interval"] = args.test_interval 216 | config["snapshot_interval"] = args.snapshot_interval 217 | config["output_for_test"] = True 218 | model_name = args.method + '/' + osp.basename(args.s_dset_path)[0].upper() + '2' + osp.basename(args.t_dset_path)[0].upper() 219 | config["output_path"] = "snapshot/" + model_name 220 | config["tensorboard_path"] = "vis/" + model_name 221 | if not osp.exists(config["output_path"]): 222 | os.system('mkdir -p '+config["output_path"]) 223 | if not osp.exists(config["tensorboard_path"]): 224 | os.system('mkdir -p '+config["tensorboard_path"]) 225 | config["out_file"] = open(osp.join(config["output_path"], "log.txt"), "w") 226 | if not osp.exists(config["output_path"]): 227 | os.mkdir(config["output_path"]) 228 | 229 | config["prep"] = {"test_10crop":True, 'params':{"resize_size":256, "crop_size":224}} 230 | config["loss"] = {"trade_off":1.0} 231 | 232 | if "ResNet" in args.net: 233 | config["network"] = {"name":network.ResNetFc, \ 234 | "params":{"resnet_name":args.net, "use_bottleneck":True, "bottleneck_dim":256, "new_cls":True}} 235 | config["loss"]["random"] = args.random 236 | config["loss"]["random_dim"] = 1024 237 | 238 | config["optimizer"] = {"type":optim.SGD, "optim_params":{'lr':args.lr, "momentum":0.9, \ 239 | "weight_decay":0.0005, "nesterov":True}, "lr_type":"inv", \ 240 | "lr_param":{"lr":args.lr, "gamma":0.001, "power":0.75} } 241 | 242 | config["dataset"] = args.dset 243 | config["data"] = {"source":{"list_path":args.s_dset_path, "batch_size":36}, \ 244 | "target":{"list_path":args.t_dset_path, "batch_size":36}, \ 245 | "test":{"list_path":args.t_dset_path, "batch_size":4}} 246 | 247 | if config["dataset"] == "office": 248 | config["network"]["params"]["class_num"] = 31 249 | elif config["dataset"] == "image-clef": 250 | config["network"]["params"]["class_num"] = 12 251 | elif config["dataset"] == "visda": 252 | config["network"]["params"]["class_num"] = 12 253 | elif config["dataset"] == "office-home": 254 | config["network"]["params"]["class_num"] = 65 255 | else: 256 | raise ValueError('Dataset cannot be recognized. Please define your own dataset here.') 257 | config["out_file"].write(str(config)) 258 | config["out_file"].flush() 259 | train(config) 260 | -------------------------------------------------------------------------------- /src/trans_norm.py: -------------------------------------------------------------------------------- 1 | import torch.nn as nn 2 | import torch.nn.functional as F 3 | from torch.nn.modules.module import Module 4 | from torch.nn.parameter import Parameter 5 | import torch 6 | import itertools 7 | 8 | class _TransNorm(Module): 9 | 10 | def __init__(self, num_features, eps=1e-5, momentum=0.1, affine=True, track_running_stats=True): 11 | super(_TransNorm, self).__init__() 12 | self.num_features = num_features 13 | self.eps = eps 14 | self.momentum = momentum 15 | self.affine = affine 16 | self.track_running_stats = track_running_stats 17 | if self.affine: 18 | self.weight = Parameter(torch.Tensor(num_features)) 19 | self.bias = Parameter(torch.Tensor(num_features)) 20 | else: 21 | self.register_parameter('weight', None) 22 | self.register_parameter('bias', None) 23 | 24 | if self.track_running_stats: 25 | self.register_buffer('running_mean_source', torch.zeros(num_features)) 26 | self.register_buffer('running_mean_target', torch.zeros(num_features)) 27 | self.register_buffer('running_var_source', torch.ones(num_features)) 28 | self.register_buffer('running_var_target', torch.ones(num_features)) 29 | self.register_buffer('num_batches_tracked', torch.tensor(0, dtype=torch.long)) 30 | else: 31 | self.register_parameter('running_mean_source', None) 32 | self.register_parameter('running_mean_target', None) 33 | self.register_parameter('running_var_source', None) 34 | self.register_parameter('running_var_target', None) 35 | self.reset_parameters() 36 | 37 | def reset_parameters(self): 38 | if self.track_running_stats: 39 | self.running_mean_source.zero_() 40 | self.running_mean_target.zero_() 41 | self.running_var_source.fill_(1) 42 | self.running_var_target.fill_(1) 43 | if self.affine: 44 | self.weight.data.uniform_() 45 | self.bias.data.zero_() 46 | 47 | def _check_input_dim(self, input): 48 | return NotImplemented 49 | 50 | def _load_from_state_dict_from_pretrained_model(self, state_dict, prefix, metadata, strict, missing_keys, unexpected_keys, error_msgs): 51 | r"""Copies parameters and buffers from :attr:`state_dict` into only 52 | this module, but not its descendants. This is called on every submodule 53 | in :meth:`~torch.nn.Module.load_state_dict`. Metadata saved for this 54 | module in input :attr:`state_dict` is provided as :attr`metadata`. 55 | For state dicts without meta data, :attr`metadata` is empty. 56 | Subclasses can achieve class-specific backward compatible loading using 57 | the version number at `metadata.get("version", None)`. 58 | 59 | .. note:: 60 | :attr:`state_dict` is not the same object as the input 61 | :attr:`state_dict` to :meth:`~torch.nn.Module.load_state_dict`. So 62 | it can be modified. 63 | 64 | Arguments: 65 | state_dict (dict): a dict containing parameters and 66 | persistent buffers. 67 | prefix (str): the prefix for parameters and buffers used in this 68 | module 69 | metadata (dict): a dict containing the metadata for this moodule. 70 | See 71 | strict (bool): whether to strictly enforce that the keys in 72 | :attr:`state_dict` with :attr:`prefix` match the names of 73 | parameters and buffers in this module 74 | missing_keys (list of str): if ``strict=False``, add missing keys to 75 | this list 76 | unexpected_keys (list of str): if ``strict=False``, add unexpected 77 | keys to this list 78 | error_msgs (list of str): error messages should be added to this 79 | list, and will be reported together in 80 | :meth:`~torch.nn.Module.load_state_dict` 81 | """ 82 | local_name_params = itertools.chain(self._parameters.items(), self._buffers.items()) 83 | local_state = {k: v.data for k, v in local_name_params if v is not None} 84 | 85 | for name, param in local_state.items(): 86 | key = prefix + name 87 | if 'source' in key or 'target' in key: 88 | key = key[:-7] 89 | print(key) 90 | if key in state_dict: 91 | input_param = state_dict[key] 92 | if input_param.shape != param.shape: 93 | # local shape should match the one in checkpoint 94 | error_msgs.append('size mismatch for {}: copying a param of {} from checkpoint, ' 95 | 'where the shape is {} in current model.' 96 | .format(key, param.shape, input_param.shape)) 97 | continue 98 | if isinstance(input_param, Parameter): 99 | # backwards compatibility for serialized parameters 100 | input_param = input_param.data 101 | try: 102 | param.copy_(input_param) 103 | except Exception: 104 | error_msgs.append('While copying the parameter named "{}", ' 105 | 'whose dimensions in the model are {} and ' 106 | 'whose dimensions in the checkpoint are {}.' 107 | .format(key, param.size(), input_param.size())) 108 | elif strict: 109 | missing_keys.append(key) 110 | 111 | 112 | 113 | def forward(self, input): 114 | self._check_input_dim(input) 115 | if self.training : ## train mode 116 | 117 | ## 1. Domain Specific Mean and Variance. 118 | batch_size = input.size()[0] // 2 119 | input_source = input[:batch_size] 120 | input_target = input[batch_size:] 121 | 122 | ## 2. Domain Sharing Gamma and Beta. 123 | z_source = F.batch_norm( 124 | input_source, self.running_mean_source, self.running_var_source, self.weight, self.bias, 125 | self.training or not self.track_running_stats, self.momentum, self.eps) 126 | 127 | z_target = F.batch_norm( 128 | input_target, self.running_mean_target, self.running_var_target, self.weight, self.bias, 129 | self.training or not self.track_running_stats, self.momentum, self.eps) 130 | z = torch.cat((z_source, z_target), dim=0) 131 | 132 | if input.dim() == 4: ## TransNorm2d 133 | input_source = input_source.permute(0,2,3,1).contiguous().view(-1,self.num_features) 134 | input_target = input_target.permute(0,2,3,1).contiguous().view(-1,self.num_features) 135 | 136 | cur_mean_source = torch.mean(input_source, dim=0) 137 | cur_var_source = torch.var(input_source,dim=0) 138 | cur_mean_target = torch.mean(input_target, dim=0) 139 | cur_var_target = torch.var(input_target, dim=0) 140 | 141 | ## 3. Domain Adaptive Alpha. 142 | 143 | ### 3.1 Calculating Distance 144 | dis = torch.abs(cur_mean_source / torch.sqrt(cur_var_source + self.eps) - 145 | cur_mean_target / torch.sqrt(cur_var_target + self.eps)) 146 | 147 | ### 3.2 Generating Probability 148 | prob = 1.0 / (1.0 + dis) 149 | alpha = self.num_features * prob / sum(prob) 150 | 151 | if input.dim() == 2: 152 | alpha = alpha.view(1, self.num_features) 153 | elif input.dim() == 4: 154 | alpha = alpha.view(1, self.num_features, 1, 1) 155 | 156 | ## 3.3 Residual Connection 157 | return z * (1 + alpha.detach()) 158 | 159 | 160 | else: ##test mode 161 | z = F.batch_norm( 162 | input, self.running_mean_target, self.running_var_target, self.weight, self.bias, 163 | self.training or not self.track_running_stats, self.momentum, self.eps) 164 | 165 | dis = torch.abs(self.running_mean_source / torch.sqrt(self.running_var_source + self.eps) 166 | - self.running_mean_target / torch.sqrt(self.running_var_target + self.eps)) 167 | prob = 1.0 / (1.0 + dis) 168 | alpha = self.num_features * prob / sum(prob) 169 | 170 | if input.dim() == 2: 171 | alpha = alpha.view(1, self.num_features) 172 | elif input.dim() == 4: 173 | alpha = alpha.view(1, self.num_features, 1, 1) 174 | return z * (1 + alpha.detach()) 175 | 176 | def extra_repr(self): 177 | return '{num_features}, eps={eps}, momentum={momentum}, affine={affine}, ' \ 178 | 'track_running_stats={track_running_stats}'.format(**self.__dict__) 179 | 180 | def _load_from_state_dict(self, state_dict, prefix, metadata, strict, 181 | missing_keys, unexpected_keys, error_msgs): 182 | version = metadata.get('version', None) 183 | if (version is None or version < 2) and self.track_running_stats: 184 | # at version 2: added num_batches_tracked buffer 185 | # this should have a default value of 0 186 | num_batches_tracked_key = prefix + 'num_batches_tracked' 187 | if num_batches_tracked_key not in state_dict: 188 | state_dict[num_batches_tracked_key] = torch.tensor(0, dtype=torch.long) 189 | 190 | self._load_from_state_dict_from_pretrained_model( 191 | state_dict, prefix, metadata, strict, 192 | missing_keys, unexpected_keys, error_msgs) 193 | 194 | 195 | class TransNorm1d(_TransNorm): 196 | r"""Applies Batch Normalization over a 2D or 3D input (a mini-batch of 1D 197 | inputs with optional additional channel dimension) as described in the paper 198 | `Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift`_ . 199 | 200 | .. math:: 201 | 202 | y = \frac{x - \mathrm{E}[x]}{\sqrt{\mathrm{Var}[x] + \epsilon}} * \gamma + \beta 203 | 204 | The mean and standard-deviation are calculated per-dimension over 205 | the mini-batches and :math:`\gamma` and :math:`\beta` are learnable parameter vectors 206 | of size `C` (where `C` is the input size). 207 | 208 | By default, during training this layer keeps running estimates of its 209 | computed mean and variance, which are then used for normalization during 210 | evaluation. The running estimates are kept with a default :attr:`momentum` 211 | of 0.1. 212 | 213 | If :attr:`track_running_stats` is set to ``False``, this layer then does not 214 | keep running estimates, and batch statistics are instead used during 215 | evaluation time as well. 216 | 217 | .. note:: 218 | This :attr:`momentum` argument is different from one used in optimizer 219 | classes and the conventional notion of momentum. Mathematically, the 220 | update rule for running statistics here is 221 | :math:`\hat{x}_\text{new} = (1 - \text{momentum}) \times \hat{x} + \text{momemtum} \times x_t`, 222 | where :math:`\hat{x}` is the estimated statistic and :math:`x_t` is the 223 | new observed value. 224 | 225 | Because the Batch Normalization is done over the `C` dimension, computing statistics 226 | on `(N, L)` slices, it's common terminology to call this Temporal Batch Normalization. 227 | 228 | Args: 229 | num_features: :math:`C` from an expected input of size 230 | :math:`(N, C, L)` or :math:`L` from input of size :math:`(N, L)` 231 | eps: a value added to the denominator for numerical stability. 232 | Default: 1e-5 233 | momentum: the value used for the running_mean and running_var 234 | computation. Can be set to ``None`` for cumulative moving average 235 | (i.e. simple average). Default: 0.1 236 | affine: a boolean value that when set to ``True``, this module has 237 | learnable affine parameters. Default: ``True`` 238 | track_running_stats: a boolean value that when set to ``True``, this 239 | module tracks the running mean and variance, and when set to ``False``, 240 | this module does not track such statistics and always uses batch 241 | statistics in both training and eval modes. Default: ``True`` 242 | 243 | Shape: 244 | - Input: :math:`(N, C)` or :math:`(N, C, L)` 245 | - Output: :math:`(N, C)` or :math:`(N, C, L)` (same shape as input) 246 | 247 | Examples:: 248 | 249 | >>> # With Learnable Parameters 250 | >>> m = nn.BatchNorm1d(100) 251 | >>> # Without Learnable Parameters 252 | >>> m = nn.BatchNorm1d(100, affine=False) 253 | >>> input = torch.randn(20, 100) 254 | >>> output = m(input) 255 | 256 | .. _`Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift`: 257 | https://arxiv.org/abs/1502.03167 258 | """ 259 | 260 | def _check_input_dim(self, input): 261 | if input.dim() != 2 and input.dim() != 3: 262 | raise ValueError('expected 2D or 3D input (got {}D input)' 263 | .format(input.dim())) 264 | 265 | 266 | class TransNorm2d(_TransNorm): 267 | r"""Applies Batch Normalization over a 4D input (a mini-batch of 2D inputs 268 | with additional channel dimension) as described in the paper 269 | `Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift`_ . 270 | 271 | .. math:: 272 | 273 | y = \frac{x - \mathrm{E}[x]}{ \sqrt{\mathrm{Var}[x] + \epsilon}} * \gamma + \beta 274 | 275 | The mean and standard-deviation are calculated per-dimension over 276 | the mini-batches and :math:`\gamma` and :math:`\beta` are learnable parameter vectors 277 | of size `C` (where `C` is the input size). 278 | 279 | By default, during training this layer keeps running estimates of its 280 | computed mean and variance, which are then used for normalization during 281 | evaluation. The running estimates are kept with a default :attr:`momentum` 282 | of 0.1. 283 | 284 | If :attr:`track_running_stats` is set to ``False``, this layer then does not 285 | keep running estimates, and batch statistics are instead used during 286 | evaluation time as well. 287 | 288 | .. note:: 289 | This :attr:`momentum` argument is different from one used in optimizer 290 | classes and the conventional notion of momentum. Mathematically, the 291 | update rule for running statistics here is 292 | :math:`\hat{x}_\text{new} = (1 - \text{momentum}) \times \hat{x} + \text{momemtum} \times x_t`, 293 | where :math:`\hat{x}` is the estimated statistic and :math:`x_t` is the 294 | new observed value. 295 | 296 | Because the Batch Normalization is done over the `C` dimension, computing statistics 297 | on `(N, H, W)` slices, it's common terminology to call this Spatial Batch Normalization. 298 | 299 | Args: 300 | num_features: :math:`C` from an expected input of size 301 | :math:`(N, C, H, W)` 302 | eps: a value added to the denominator for numerical stability. 303 | Default: 1e-5 304 | momentum: the value used for the running_mean and running_var 305 | computation. Can be set to ``None`` for cumulative moving average 306 | (i.e. simple average). Default: 0.1 307 | affine: a boolean value that when set to ``True``, this module has 308 | learnable affine parameters. Default: ``True`` 309 | track_running_stats: a boolean value that when set to ``True``, this 310 | module tracks the running mean and variance, and when set to ``False``, 311 | this module does not track such statistics and always uses batch 312 | statistics in both training and eval modes. Default: ``True`` 313 | 314 | Shape: 315 | - Input: :math:`(N, C, H, W)` 316 | - Output: :math:`(N, C, H, W)` (same shape as input) 317 | 318 | Examples:: 319 | 320 | >>> # With Learnable Parameters 321 | >>> m = nn.BatchNorm2d(100) 322 | >>> # Without Learnable Parameters 323 | >>> m = nn.BatchNorm2d(100, affine=False) 324 | >>> input = torch.randn(20, 100, 35, 45) 325 | >>> output = m(input) 326 | 327 | .. _`Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift`: 328 | https://arxiv.org/abs/1502.03167 329 | """ 330 | 331 | def _check_input_dim(self, input): 332 | if input.dim() != 4: 333 | raise ValueError('expected 4D input (got {}D input)' 334 | .format(input.dim())) 335 | 336 | 337 | class TransNorm3d(_TransNorm): 338 | r"""Applies Batch Normalization over a 5D input (a mini-batch of 3D inputs 339 | with additional channel dimension) as described in the paper 340 | `Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift`_ . 341 | 342 | .. math:: 343 | 344 | y = \frac{x - \mathrm{E}[x]}{ \sqrt{\mathrm{Var}[x] + \epsilon}} * \gamma + \beta 345 | 346 | The mean and standard-deviation are calculated per-dimension over 347 | the mini-batches and :math:`\gamma` and :math:`\beta` are learnable parameter vectors 348 | of size `C` (where `C` is the input size). 349 | 350 | By default, during training this layer keeps running estimates of its 351 | computed mean and variance, which are then used for normalization during 352 | evaluation. The running estimates are kept with a default :attr:`momentum` 353 | of 0.1. 354 | 355 | If :attr:`track_running_stats` is set to ``False``, this layer then does not 356 | keep running estimates, and batch statistics are instead used during 357 | evaluation time as well. 358 | 359 | .. note:: 360 | This :attr:`momentum` argument is different from one used in optimizer 361 | classes and the conventional notion of momentum. Mathematically, the 362 | update rule for running statistics here is 363 | :math:`\hat{x}_\text{new} = (1 - \text{momentum}) \times \hat{x} + \text{momemtum} \times x_t`, 364 | where :math:`\hat{x}` is the estimated statistic and :math:`x_t` is the 365 | new observed value. 366 | 367 | Because the Batch Normalization is done over the `C` dimension, computing statistics 368 | on `(N, D, H, W)` slices, it's common terminology to call this Volumetric Batch Normalization 369 | or Spatio-temporal Batch Normalization. 370 | 371 | Args: 372 | num_features: :math:`C` from an expected input of size 373 | :math:`(N, C, D, H, W)` 374 | eps: a value added to the denominator for numerical stability. 375 | Default: 1e-5 376 | momentum: the value used for the running_mean and running_var 377 | computation. Can be set to ``None`` for cumulative moving average 378 | (i.e. simple average). Default: 0.1 379 | affine: a boolean value that when set to ``True``, this module has 380 | learnable affine parameters. Default: ``True`` 381 | track_running_stats: a boolean value that when set to ``True``, this 382 | module tracks the running mean and variance, and when set to ``False``, 383 | this module does not track such statistics and always uses batch 384 | statistics in both training and eval modes. Default: ``True`` 385 | 386 | Shape: 387 | - Input: :math:`(N, C, D, H, W)` 388 | - Output: :math:`(N, C, D, H, W)` (same shape as input) 389 | 390 | Examples:: 391 | 392 | >>> # With Learnable Parameters 393 | >>> m = nn.BatchNorm3d(100) 394 | >>> # Without Learnable Parameters 395 | >>> m = nn.BatchNorm3d(100, affine=False) 396 | >>> input = torch.randn(20, 100, 35, 45, 10) 397 | >>> output = m(input) 398 | 399 | .. _`Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift`: 400 | https://arxiv.org/abs/1502.03167 401 | """ 402 | 403 | def _check_input_dim(self, input): 404 | if input.dim() != 5: 405 | raise ValueError('expected 5D input (got {}D input)' 406 | .format(input.dim())) --------------------------------------------------------------------------------