$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC$œ’m…Îmo“LÒDüÜ;˜%gÏ?wêÁÅ·øîùovH0õÉa‡5£Ú*î Ø’ÃÌlÍ››S iyä”rÕO7ª“ž�%L]Ý×%±ºÇhk¶«·÷>v1­HB£®±ßÞÚd\�(e oIx¢>3´6BS%ÌØá“( œÛf$Ãhýé ¿¶åeÔŽôÚèHœ�‚`ݶ f{�Fo©Yò¿Ôó@00uMb’z-ëìXI$&ÂgfÖú¶7Ó´Þu|'K.ÌoP PÝÀùFË.Ðýoûò9B<~.’ïÅË[’´˜Ë<Ù­„$¯•¢·ä{1¹A�•.òbKxºL �¯�Ý·'¯u8n5 ’ºe,]ñH©–’ÆV¨ŒWwÃ$ùCƒel¹“|zys«™KŠi-ðqÊݬbk,wnGÿâ;¥ ~ ÖeÉrÍ’‰ÜÔ~' 1`V⦫¹-*[ÉñLÔKÄ'2@ŸÜþÐ仪 ²n‘Íß2¸N߈ƶµG•¢ói/U¢µ'Eï@¦`H湘;J•�¼¼ÜŽÅ +Jén#»¼‚6Ú´—ĹG•ü¡NÒGð'—Z!öáí¸‰Wi�»NJ @óàšAûÜZ|ª[¨ï$q}i�Ò·µQbtTEC54 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11478 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11478 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11455 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11455 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11458 send_mail_cod have less inputs used (3) than in the step definition (5) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 11449 doesn't seem to be define in the database( WARNING : type of input 2 of step 11452 doesn't seem to be define in the database( WARNING : output 1 of step 11449 have datatype=2 whereas input 1 of step 11453 have datatype=7 WARNING : type of output 2 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11454 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 3 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11456 doesn't seem to be define in the database( WARNING : type of output 1 of step 11456 doesn't seem to be define in the database( WARNING : type of input 3 of step 11455 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11456 have datatype=10 whereas input 3 of step 11458 have datatype=6 WARNING : type of input 5 of step 11458 doesn't seem to be define in the database( WARNING : output 0 of step 11477 have datatype=11 whereas input 5 of step 11458 have datatype=None WARNING : output 0 of step 11456 have datatype=10 whereas input 0 of step 11477 have datatype=18 WARNING : type of input 2 of step 11478 doesn't seem to be define in the database( WARNING : output 1 of step 11454 have datatype=7 whereas input 2 of step 11478 have datatype=None WARNING : type of output 3 of step 11478 doesn't seem to be define in the database( WARNING : type of input 2 of step 11456 doesn't seem to be define in the database( WARNING : output 0 of step 11453 have datatype=1 whereas input 0 of step 11454 have datatype=2 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, crop_condition, thcl, merge_mask_thcl_custom, rle_unique_nms_with_priority, crop_condition, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , WARNING: data may be incomplete, need to offset and complete ! BFBFBFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 10 ; length of list_pids : 10 ; length of list_args : 10 time to download the photos : 2.032212495803833 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 11 step1:mask_detect Fri Mar 7 12:18:30 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3957 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-07 12:18:34.215700: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-07 12:18:34.247136: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-07 12:18:34.249789: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f0fd8000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-07 12:18:34.249847: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-07 12:18:34.255269: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-07 12:18:34.515312: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x24428fc0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-07 12:18:34.515373: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-07 12:18:34.516333: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-03-07 12:18:34.516808: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 12:18:34.519913: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 12:18:34.534590: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-07 12:18:34.535262: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-07 12:18:34.542508: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-07 12:18:34.543941: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-07 12:18:34.551655: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 12:18:34.553060: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-07 12:18:34.553163: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 12:18:34.553916: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-07 12:18:34.553937: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-07 12:18:34.553949: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-07 12:18:34.555219: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3505 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-03-07 12:18:34.878490: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-03-07 12:18:34.878623: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 12:18:34.878652: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 12:18:34.878679: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-07 12:18:34.878706: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-07 12:18:34.878730: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-07 12:18:34.878756: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-07 12:18:34.878781: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 12:18:34.879980: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-07 12:18:34.881511: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-03-07 12:18:34.881573: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 12:18:34.881610: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 12:18:34.881641: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-07 12:18:34.881669: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-07 12:18:34.881699: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-07 12:18:34.881726: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-07 12:18:34.881754: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 12:18:34.882885: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-07 12:18:34.882950: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-07 12:18:34.882961: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-07 12:18:34.882969: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-07 12:18:34.883920: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3505 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2896 thcls : [{'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5309 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5309, 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 16384, 25088, 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 5, 10, 19, 20, 46), datetime.datetime(2021, 5, 10, 19, 20, 46)) {'thcl': {'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'carton_brun', 'carton_gris', 'cartonnette', 'kraft', 'autre_refus', 'metal', 'plastique', 'teint_dans_la_masse', 'environnement'], 'list_hashtags_csv': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'svm_hashtag_type_desc': 5309, 'photo_desc_type': 5309, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'carton_brun', 'carton_gris', 'cartonnette', 'kraft', 'autre_refus', 'metal', 'plastique', 'teint_dans_la_masse', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_convoyeur_qualipapia_nantes_poly_100521_1 NUM_CLASSES 10 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_convoyeur_qualipapia_nantes_poly_100521_1 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-03-07 12:18:47.815807: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 12:18:47.971452: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 12:18:49.849380: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:49.850022: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.63G (2826318592 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.628882: W tensorflow/core/common_runtime/bfc_allocator.cc:311] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently, you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature. 2025-03-07 12:18:50.686554: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.686633: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.67GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:18:50.687981: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.688020: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.67GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:18:50.695780: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:18:50.695843: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:18:50.703353: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.703411: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:18:50.704384: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.704413: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:18:50.759025: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.759082: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:18:50.759970: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.759994: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:18:50.760897: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.760923: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.26GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:18:50.761814: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.761834: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.26GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:18:50.770298: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.771043: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.787024: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.787713: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.788347: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.788986: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.793530: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.794324: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.795131: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.795904: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.797241: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.797275: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-03-07 12:18:50.807809: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.808481: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.818267: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.818977: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.819609: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.820215: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.820831: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:18:50.821444: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_convoyeur_qualipapia_nantes_poly_100521_1 /data/models_weight/learn_convoyeur_qualipapia_nantes_poly_100521_1/mask_model.h5 size_local : 256031040 size in s3 : 256031040 create time local : 2021-08-09 05:45:48 create time in s3 : 2021-08-06 18:59:51 mask_model.h5 already exist and didn't need to update list_images length : 10 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 145.10000 image_metas shape: (1, 18) min: 0.00000 max: 3840.00000 nb d'objets trouves : 6 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 139.35000 image_metas shape: (1, 18) min: 0.00000 max: 3840.00000 nb d'objets trouves : 11 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 141.85000 image_metas shape: (1, 18) min: 0.00000 max: 3840.00000 nb d'objets trouves : 4 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 140.85000 image_metas shape: (1, 18) min: 0.00000 max: 3840.00000 nb d'objets trouves : 7 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 3.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 140.60000 image_metas shape: (1, 18) min: 0.00000 max: 3840.00000 nb d'objets trouves : 7 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.35000 image_metas shape: (1, 18) min: 0.00000 max: 3840.00000 nb d'objets trouves : 8 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 251.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 137.35000 image_metas shape: (1, 18) min: 0.00000 max: 3840.00000 nb d'objets trouves : 12 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 138.35000 image_metas shape: (1, 18) min: 0.00000 max: 3840.00000 nb d'objets trouves : 14 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 142.60000 image_metas shape: (1, 18) min: 0.00000 max: 3840.00000 nb d'objets trouves : 7 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 141.35000 image_metas shape: (1, 18) min: 0.00000 max: 3840.00000 nb d'objets trouves : 4 Detection mask done ! Trying to reset tf kernel 2594878 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 2543 tf kernel not reseted sub process len(results) : 10 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 10 len(list_Values) 0 process is alive finish correctly or not : True after detect begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 3957 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl2896 Catched exception ! Connect or reconnect ! thcls : [{'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5309 ['background', 'carton_brun', 'carton_gris', 'cartonnette', 'kraft', 'autre_refus', 'metal', 'plastique', 'teint_dans_la_masse', 'environnement'] time for calcul the mask position with numpy : 0.0048503875732421875 nb_pixel_total : 162890 time to create 1 rle with new method : 0.015076398849487305 length of segment : 1110 time for calcul the mask position with numpy : 0.0013692378997802734 nb_pixel_total : 94477 time to create 1 rle with old method : 0.10937070846557617 length of segment : 497 time for calcul the mask position with numpy : 0.0018138885498046875 nb_pixel_total : 73892 time to create 1 rle with old method : 0.08947992324829102 length of segment : 540 time for calcul the mask position with numpy : 0.0019075870513916016 nb_pixel_total : 118861 time to create 1 rle with old method : 0.13668274879455566 length of segment : 392 time for calcul the mask position with numpy : 0.00047707557678222656 nb_pixel_total : 23733 time to create 1 rle with old method : 0.027352571487426758 length of segment : 274 time for calcul the mask position with numpy : 0.0006239414215087891 nb_pixel_total : 31298 time to create 1 rle with old method : 0.03804326057434082 length of segment : 251 time for calcul the mask position with numpy : 0.0008289813995361328 nb_pixel_total : 41922 time to create 1 rle with old method : 0.04704427719116211 length of segment : 441 time for calcul the mask position with numpy : 0.0005612373352050781 nb_pixel_total : 15888 time to create 1 rle with old method : 0.024649620056152344 length of segment : 213 time for calcul the mask position with numpy : 0.0006549358367919922 nb_pixel_total : 30967 time to create 1 rle with old method : 0.03742718696594238 length of segment : 403 time for calcul the mask position with numpy : 0.0002243518829345703 nb_pixel_total : 9391 time to create 1 rle with old method : 0.011185169219970703 length of segment : 182 time for calcul the mask position with numpy : 0.0009644031524658203 nb_pixel_total : 44046 time to create 1 rle with old method : 0.051400184631347656 length of segment : 293 time for calcul the mask position with numpy : 0.019489049911499023 nb_pixel_total : 720682 time to create 1 rle with new method : 0.3041234016418457 length of segment : 1970 time for calcul the mask position with numpy : 0.0012073516845703125 nb_pixel_total : 49130 time to create 1 rle with old method : 0.07616925239562988 length of segment : 426 time for calcul the mask position with numpy : 0.0014178752899169922 nb_pixel_total : 76099 time to create 1 rle with old method : 0.09371399879455566 length of segment : 358 time for calcul the mask position with numpy : 0.0012006759643554688 nb_pixel_total : 66351 time to create 1 rle with old method : 0.077728271484375 length of segment : 348 time for calcul the mask position with numpy : 0.0037374496459960938 nb_pixel_total : 184904 time to create 1 rle with new method : 0.009354114532470703 length of segment : 550 time for calcul the mask position with numpy : 0.0016775131225585938 nb_pixel_total : 109908 time to create 1 rle with old method : 0.1255817413330078 length of segment : 556 time for calcul the mask position with numpy : 0.00045299530029296875 nb_pixel_total : 25878 time to create 1 rle with old method : 0.030988454818725586 length of segment : 223 time for calcul the mask position with numpy : 0.00460052490234375 nb_pixel_total : 175625 time to create 1 rle with new method : 0.010677337646484375 length of segment : 739 time for calcul the mask position with numpy : 0.0016515254974365234 nb_pixel_total : 29998 time to create 1 rle with old method : 0.03572416305541992 length of segment : 431 time for calcul the mask position with numpy : 0.005620718002319336 nb_pixel_total : 279009 time to create 1 rle with new method : 0.010116100311279297 length of segment : 690 time for calcul the mask position with numpy : 0.000606536865234375 nb_pixel_total : 20818 time to create 1 rle with old method : 0.02459716796875 length of segment : 200 time for calcul the mask position with numpy : 0.0002415180206298828 nb_pixel_total : 3843 time to create 1 rle with old method : 0.0045969486236572266 length of segment : 93 time for calcul the mask position with numpy : 0.009203433990478516 nb_pixel_total : 376572 time to create 1 rle with new method : 0.016840696334838867 length of segment : 1621 time for calcul the mask position with numpy : 0.0018603801727294922 nb_pixel_total : 78907 time to create 1 rle with old method : 0.11235332489013672 length of segment : 374 time for calcul the mask position with numpy : 0.0003960132598876953 nb_pixel_total : 10294 time to create 1 rle with old method : 0.012984037399291992 length of segment : 110 time for calcul the mask position with numpy : 0.0012392997741699219 nb_pixel_total : 49515 time to create 1 rle with old method : 0.05781221389770508 length of segment : 320 time for calcul the mask position with numpy : 0.005260467529296875 nb_pixel_total : 234583 time to create 1 rle with new method : 0.009824275970458984 length of segment : 538 time for calcul the mask position with numpy : 0.0005807876586914062 nb_pixel_total : 14991 time to create 1 rle with old method : 0.01883220672607422 length of segment : 137 time for calcul the mask position with numpy : 0.0004665851593017578 nb_pixel_total : 11296 time to create 1 rle with old method : 0.014093637466430664 length of segment : 168 time for calcul the mask position with numpy : 0.011655330657958984 nb_pixel_total : 520184 time to create 1 rle with new method : 0.018163442611694336 length of segment : 616 time for calcul the mask position with numpy : 0.001110076904296875 nb_pixel_total : 32012 time to create 1 rle with old method : 0.03801536560058594 length of segment : 219 time for calcul the mask position with numpy : 0.0006437301635742188 nb_pixel_total : 17024 time to create 1 rle with old method : 0.02082228660583496 length of segment : 178 time for calcul the mask position with numpy : 0.00421595573425293 nb_pixel_total : 222303 time to create 1 rle with new method : 0.008931875228881836 length of segment : 690 time for calcul the mask position with numpy : 0.0026483535766601562 nb_pixel_total : 99220 time to create 1 rle with old method : 0.11636781692504883 length of segment : 1220 time for calcul the mask position with numpy : 0.005292654037475586 nb_pixel_total : 255702 time to create 1 rle with new method : 0.009160995483398438 length of segment : 671 time for calcul the mask position with numpy : 0.003154754638671875 nb_pixel_total : 144896 time to create 1 rle with old method : 0.16171860694885254 length of segment : 752 time for calcul the mask position with numpy : 0.0032737255096435547 nb_pixel_total : 164733 time to create 1 rle with new method : 0.005008697509765625 length of segment : 534 time for calcul the mask position with numpy : 0.0009961128234863281 nb_pixel_total : 29413 time to create 1 rle with old method : 0.03370070457458496 length of segment : 221 time for calcul the mask position with numpy : 0.0035190582275390625 nb_pixel_total : 218401 time to create 1 rle with new method : 0.005942106246948242 length of segment : 504 time for calcul the mask position with numpy : 0.0005276203155517578 nb_pixel_total : 32458 time to create 1 rle with old method : 0.03672909736633301 length of segment : 276 time for calcul the mask position with numpy : 0.0013031959533691406 nb_pixel_total : 63193 time to create 1 rle with old method : 0.07031106948852539 length of segment : 335 time for calcul the mask position with numpy : 0.0062444210052490234 nb_pixel_total : 228298 time to create 1 rle with new method : 0.012244462966918945 length of segment : 1040 time for calcul the mask position with numpy : 0.003708362579345703 nb_pixel_total : 150132 time to create 1 rle with new method : 0.0059893131256103516 length of segment : 391 time for calcul the mask position with numpy : 0.005093574523925781 nb_pixel_total : 185294 time to create 1 rle with new method : 0.008249521255493164 length of segment : 1170 time for calcul the mask position with numpy : 0.0002961158752441406 nb_pixel_total : 12567 time to create 1 rle with old method : 0.014961481094360352 length of segment : 160 time for calcul the mask position with numpy : 0.0020759105682373047 nb_pixel_total : 79688 time to create 1 rle with old method : 0.08957433700561523 length of segment : 457 time for calcul the mask position with numpy : 0.0004036426544189453 nb_pixel_total : 14657 time to create 1 rle with old method : 0.01758122444152832 length of segment : 116 time for calcul the mask position with numpy : 0.019695520401000977 nb_pixel_total : 612243 time to create 1 rle with new method : 0.07046365737915039 length of segment : 1767 time for calcul the mask position with numpy : 0.00746607780456543 nb_pixel_total : 293577 time to create 1 rle with new method : 0.013092756271362305 length of segment : 652 time for calcul the mask position with numpy : 0.0018982887268066406 nb_pixel_total : 96813 time to create 1 rle with old method : 0.11221194267272949 length of segment : 432 time for calcul the mask position with numpy : 0.0016620159149169922 nb_pixel_total : 95993 time to create 1 rle with old method : 0.11714601516723633 length of segment : 392 time for calcul the mask position with numpy : 0.0006432533264160156 nb_pixel_total : 19388 time to create 1 rle with old method : 0.022387027740478516 length of segment : 194 time for calcul the mask position with numpy : 0.00565338134765625 nb_pixel_total : 231607 time to create 1 rle with new method : 0.009889841079711914 length of segment : 785 time for calcul the mask position with numpy : 0.010415077209472656 nb_pixel_total : 352333 time to create 1 rle with new method : 0.13241004943847656 length of segment : 1321 time for calcul the mask position with numpy : 0.0003962516784667969 nb_pixel_total : 12069 time to create 1 rle with old method : 0.014986276626586914 length of segment : 99 time for calcul the mask position with numpy : 0.0018672943115234375 nb_pixel_total : 74515 time to create 1 rle with old method : 0.08910346031188965 length of segment : 364 time for calcul the mask position with numpy : 0.003193378448486328 nb_pixel_total : 102133 time to create 1 rle with old method : 0.12411904335021973 length of segment : 438 time for calcul the mask position with numpy : 0.0014519691467285156 nb_pixel_total : 46381 time to create 1 rle with old method : 0.052542686462402344 length of segment : 461 time for calcul the mask position with numpy : 0.0018613338470458984 nb_pixel_total : 77107 time to create 1 rle with old method : 0.08888626098632812 length of segment : 451 time for calcul the mask position with numpy : 0.0033960342407226562 nb_pixel_total : 211725 time to create 1 rle with new method : 0.008525371551513672 length of segment : 685 time for calcul the mask position with numpy : 0.006681919097900391 nb_pixel_total : 330200 time to create 1 rle with new method : 0.012368202209472656 length of segment : 1234 time for calcul the mask position with numpy : 0.0012056827545166016 nb_pixel_total : 60269 time to create 1 rle with old method : 0.07440686225891113 length of segment : 403 time for calcul the mask position with numpy : 0.0016498565673828125 nb_pixel_total : 54303 time to create 1 rle with old method : 0.06289410591125488 length of segment : 321 time for calcul the mask position with numpy : 0.004638195037841797 nb_pixel_total : 155536 time to create 1 rle with new method : 0.01028299331665039 length of segment : 706 time for calcul the mask position with numpy : 0.0008356571197509766 nb_pixel_total : 25981 time to create 1 rle with old method : 0.03034377098083496 length of segment : 225 time for calcul the mask position with numpy : 0.009644269943237305 nb_pixel_total : 291109 time to create 1 rle with new method : 0.011512517929077148 length of segment : 892 time for calcul the mask position with numpy : 0.002947092056274414 nb_pixel_total : 156400 time to create 1 rle with new method : 0.005669116973876953 length of segment : 553 time for calcul the mask position with numpy : 0.0015974044799804688 nb_pixel_total : 96056 time to create 1 rle with old method : 0.11273074150085449 length of segment : 416 time for calcul the mask position with numpy : 0.0023119449615478516 nb_pixel_total : 159915 time to create 1 rle with new method : 0.0038805007934570312 length of segment : 385 time for calcul the mask position with numpy : 0.0007638931274414062 nb_pixel_total : 25679 time to create 1 rle with old method : 0.029413461685180664 length of segment : 184 time for calcul the mask position with numpy : 0.0020852088928222656 nb_pixel_total : 119618 time to create 1 rle with old method : 0.1377859115600586 length of segment : 454 time spent for convertir_results : 10.139732837677002 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 84 chid ids of type : 3663 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 37812 save missing photos in datou_result : time spend for datou_step_exec : 78.36432313919067 time spend to save output : 2.2905819416046143 total time spend for step 1 : 80.65490508079529 step2:crop_condition Fri Mar 7 12:19:51 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure Loading chi in step crop with photo_hashtag_type : 3663 Loading chi in step crop for list_pids : 10 ! batch 1 Loaded 84 chid ids of type : 3663 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ begin to crop the class : teint_dans_la_masse param for this class : {'min_score': 0.7} filtre for class : teint_dans_la_masse hashtag_id of this class : 2107752385 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 13 About to insert : list_path_to_insert length 13 new photo from crops ! we have finished the crop for the class : teint_dans_la_masse begin to crop the class : autre_refus param for this class : {'min_score': 0.5} filtre for class : autre_refus hashtag_id of this class : 2107752406 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 6 About to insert : list_path_to_insert length 6 new photo from crops ! we have finished the crop for the class : autre_refus begin to crop the class : carton_gris param for this class : {'min_score': 0.5} filtre for class : carton_gris hashtag_id of this class : 2107753020 we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! we have finished the crop for the class : carton_gris begin to crop the class : cartonnette param for this class : {'min_score': 0.5} filtre for class : cartonnette hashtag_id of this class : 702398920 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 13 About to insert : list_path_to_insert length 13 new photo from crops ! we have finished the crop for the class : cartonnette begin to crop the class : carton_brun param for this class : {'min_score': 0.7} filtre for class : carton_brun hashtag_id of this class : 2107753024 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 4 About to insert : list_path_to_insert length 4 new photo from crops ! we have finished the crop for the class : carton_brun begin to crop the class : plastique param for this class : {'min_score': 0.5} filtre for class : plastique hashtag_id of this class : 492725882 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 4 About to insert : list_path_to_insert length 4 new photo from crops ! we have finished the crop for the class : plastique begin to crop the class : kraft param for this class : {'min_score': 0.5} filtre for class : kraft hashtag_id of this class : 493202403 we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! we have finished the crop for the class : kraft begin to crop the class : metal param for this class : {'min_score': 0.5} filtre for class : metal hashtag_id of this class : 492628673 delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1325492993, 1325492990, 1325492979, 1325492975, 1325492897, 1325492723, 1325492721, 1325492717, 1325492706, 1325492558] Looping around the photos to save general results len do output : 42 /-3592517458Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517459Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517465Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517480Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517488Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3697224977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517487Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517497Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592522957Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3697224984Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592522953Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592522956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592522959Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517441Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517454Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517457Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3697224976Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592522960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517450Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517439Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517440Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517445Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517456Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517468Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517477Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3697224978Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517492Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517502Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3697224979Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3697224982Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592522958Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3697224985Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517448Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517466Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517494Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592522955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517453Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517479Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517483Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517485Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3592517469Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . before output type Here is an output not treated by saveGeneral : Here is an output not treated by saveGeneral : Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('3459', None, None, None, None, None, None, None, '2647892') ('3459', None, '1325492993', None, None, None, None, None, '2647892') ('3459', None, None, None, None, None, None, None, '2647892') ('3459', None, '1325492990', None, None, None, None, None, '2647892') ('3459', None, None, None, None, None, None, None, '2647892') ('3459', None, '1325492979', None, None, None, None, None, '2647892') ('3459', None, None, None, None, None, None, None, '2647892') ('3459', None, '1325492975', None, None, None, None, None, '2647892') ('3459', None, None, None, None, None, None, None, '2647892') ('3459', None, '1325492897', None, None, None, None, None, '2647892') ('3459', None, None, None, None, None, None, None, '2647892') ('3459', None, '1325492723', None, None, None, None, None, '2647892') ('3459', None, None, None, None, None, None, None, '2647892') ('3459', None, '1325492721', None, None, None, None, None, '2647892') ('3459', None, None, None, None, None, None, None, '2647892') ('3459', None, '1325492717', None, None, None, None, None, '2647892') ('3459', None, None, None, None, None, None, None, '2647892') ('3459', None, '1325492706', None, None, None, None, None, '2647892') ('3459', None, None, None, None, None, None, None, '2647892') ('3459', None, '1325492558', None, None, None, None, None, '2647892') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 136 time used for this insertion : 0.0232694149017334 save_final save missing photos in datou_result : time spend for datou_step_exec : 44.85417366027832 time spend to save output : 0.02515697479248047 total time spend for step 2 : 44.8793306350708 step3:thcl Fri Mar 7 12:20:36 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step Thcl ! nombre de thcls : 2 we are using the classfication for multi_thcl [2456, 2868] time to import caffe and check if the image exist : 0.07372474670410156 time to convert the images to numpy array : 4.291534423828125e-06 time to import caffe and check if the image exist : 0.07324600219726562 time to convert the images to numpy array : 0.39953017234802246 time to import caffe and check if the image exist : 0.08123207092285156 time to convert the images to numpy array : 1.7721164226531982 time to import caffe and check if the image exist : 0.07822108268737793 time to convert the images to numpy array : 1.778083086013794 time to import caffe and check if the image exist : 0.0761721134185791 time to convert the images to numpy array : 1.7863037586212158 time to import caffe and check if the image exist : 0.08057761192321777 time to convert the images to numpy array : 2.1095519065856934 time to import caffe and check if the image exist : 0.07804012298583984 time to convert the images to numpy array : 2.1158220767974854 time to import caffe and check if the image exist : 0.08141064643859863 time to convert the images to numpy array : 2.1197597980499268 time to import caffe and check if the image exist : 0.07973194122314453 time to convert the images to numpy array : 2.188185930252075 time to import caffe and check if the image exist : 0.0787191390991211 time to convert the images to numpy array : 2.345252752304077 total time to convert the images to numpy array : 2.7481279373168945 list photo_ids error: [] list photo_ids correct : [-3592517485, -3592517469, -3697224982, -3592522958, -3697224985, -3592517448, -3592517466, -3592517494, -3592522955, -3592517453, -3592517479, -3592517483, -3592517457, -3697224976, -3592517504, -3592522960, -3592517450, -3592517458, -3592517459, -3592517465, -3592517480, -3592517488, -3697224977, -3592517487, -3592517497, -3592522957, -3697224984, -3592522953, -3592522956, -3592522959, -3592517441, -3592517454, -3592517439, -3592517440, -3592517445, -3592517456, -3592517468, -3592517477, -3697224978, -3592517492, -3592517502, -3697224979] number of photos to traite : 42 try to delete the photos incorrect in DB tagging for thcl : 2456 To do loadFromThcl(), then load ParamDescType : thcl2456 thcls : [{'id': 2456, 'mtr_user_id': 31, 'name': 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'papier,refus', 'svm_portfolios_learning': '3028087,3028251', 'photo_hashtag_type': 3049, 'photo_desc_type': 4999, 'type_classification': 'caffe', 'hashtag_id_list': '492668766,538914404'}] thcl {'id': 2456, 'mtr_user_id': 31, 'name': 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'papier,refus', 'svm_portfolios_learning': '3028087,3028251', 'photo_hashtag_type': 3049, 'photo_desc_type': 4999, 'type_classification': 'caffe', 'hashtag_id_list': '492668766,538914404'} Update svm_hashtag_type_desc : 4999 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (4999, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 16384, 25088, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'res5b', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2020, 10, 23, 14, 27, 22), datetime.datetime(2020, 10, 23, 14, 27, 22)) To loadFromThcl() : net_4999 begin to check gpu status inside check gpu memory havn't enough memory gpu , need / 2500 l 3632 free memory gpu now : 2359 wait 20 seconds l 3637 free memory gpu now : 2359 max_wait_temp : 1 max_wait : 0 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (4999, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 16384, 25088, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'res5b', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2020, 10, 23, 14, 27, 22), datetime.datetime(2020, 10, 23, 14, 27, 22)) None mean_file_type : mean_file_path : prototxt_file_path : model : learn_qualipapia_papier_refus_from_vlg_data_aug Inside get_net Inside get_net before cache_data_model model_param file didn't exist Inside get_net before CDM.load_model_par_type model_name : learn_qualipapia_papier_refus_from_vlg_data_aug model_type : caffe list file need : ['caffemodel', 'deploy_conv_normal.prototxt', 'deploy_fc.prototxt', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file exist in s3 : ['caffemodel', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file manque in s3 : ['deploy_conv_normal.prototxt', 'deploy_fc.prototxt'] WARNING: Logging before InitGoogleLogging() is written to STDERR E0307 12:21:01.211808 2594350 common.cpp:114] Cannot create Cublas handle. Cublas won't be available. E0307 12:21:01.224515 2594350 common.cpp:121] Cannot create Curand generator. Curand won't be available. local folder : /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/caffemodel size_local : 44972172 size in s3 : 44972172 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:49 caffemodel already exist and didn't need to update /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/deploy.prototxt size_local : 17311 size in s3 : 17311 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:49 deploy.prototxt already exist and didn't need to update /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/mean.npy size_local : 1572992 size in s3 : 1572992 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:51 mean.npy already exist and didn't need to update /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/synset_words.txt size_local : 57 size in s3 : 57 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:49 synset_words.txt already exist and didn't need to update Inside get_net after CDM.load_model_par_type After if not only_with_local_cache: /home/admin/workarea/install/caffe_cuda8_python3/python/:/home/admin/workarea/install/darknet/:/home/admin/workarea/git/Velours/python:/home/admin/workarea/install/caffe_frcnn_python3/py-faster-rcnn/caffe-fast-rcnn/python:/home/admin/mtr/.credentials:/home/admin/workarea/install/caffe/python:/home/admin/workarea/install/caffe_frcnn/py-faster-rcnn/tools/:/home/admin/workarea/git/fotonowerpip/:/home/admin/workarea/install/segment-anything:/home/admin//workarea/git/pyfvs/ Here before set mode gpu Doing nothing but we could set mode gpu after set mode gpu prototxt_filename : /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/deploy.prototxt caffemodel_filename : /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/caffemodel now we set caffe to gpu mode before predict begin to check gpu status inside check gpu memory havn't enough memory gpu , need / 2500 l 3632 free memory gpu now : 28 wait 20 seconds F0307 12:21:23.208837 2594350 syncedmem.cpp:78] Check failed: error == cudaSuccess (2 vs. 0) out of memory *** Check failure stack trace: *** Command terminated by signal 6 57.43user 78.80system 2:58.42elapsed 76%CPU (0avgtext+0avgdata 3639396maxresident)k 288752inputs+52224outputs (5211major+4454657minor)pagefaults 0swaps