ELF>P @@@8@@@@@@@@@@ aa ((a(a@@DDPtd  A A\\Qtd/lib64/ld-linux-x86-64.so.2GNUGNU*XQ5+)le  )gUa<.  jX]z8Qc3Jaalibm.so.6__gmon_start___Jv_RegisterClassestanhsqrtpowexplibc.so.6fflushstrcpyexitfopenperror__isoc99_sscanf__isnanputsputcharclockstdinstrtodstrtolfeoffgetsstdout__isoc99_fscanffclosemalloc__ctype_b_locfwritefprintf_IO_getc__libc_start_mainfreeGLIBC_2.3GLIBC_2.7GLIBC_2.2.5@@ii ii  ui *ui *aa aaaaaaaa a (a 0a 8a @aHaPaXa`ahapaxaaaaaaaaaaHH5Z!%\!@%Z!h%R!h%J!h%B!h%:!h%2!h%*!h%"!hp%!h`%!h P% !h @%!h 0%!h %!h %!h%!h%!h%!h%!h%!h%!h%!h%!h%!hp%!h`%!hP%!h@%!h01I^HHPTIAHЛAH @HHA!HtHÐUHSH=h!uKaHb!HaHHH9s$fDHH=!aH/!H9r!H[fff.H=!UHtHt aÐHAzH=!HfHȜAќAA1 ȝA?לA5A+0A!ApA AAОA ApAAA0AXAAA AhAAAw Am@AcAYAOAEPA;A1A'A(AxA AȤAA0AhAAA(AhAAA A`AA}ȧAsAihA_AUAKAA`A7A-A#0AxAȪAAXAAA@AAAA AhAAAAH=!%Am@AcAYخAOAEHA;A1A'7A8AA аA A`AAAHDAWI?Ih㈵>HcAVAUI?ATUHSHHtrans_prHHL$LD$Isvm_modeL$LL$ IMbP?HT$0LIV瞯-Hl$8LIfDV#Wv$LA1`1!1f.$AfDLhH|$@J4FfDIEL9kH4H€>-tHl$8IH|$0H$L;l$H$} HtHI|$`D$@Ht$@9hT$A:uWI$I|$xtI>I|$pdIt$8HDI;t$@It$`HfWfA.D$AD$ f.}fWfA.D$]fWfA.D$PBfWfA.$I$dHĸ[]A\A]A^A_@LhH|$J4IEL9fA1?2f.Lh 1JHHHdID$`>̄9u1V:u%I$E0AID$xK9t)9tGȱA11C6fDV:\uI$AiF:JuI$ID$0A19It$@hA1(넿زA1sA;aеA) ApABA 8AA$AxA 0AoAA޿A1ffff.AVAAUIATUSH H$Ld$ tLAaA a@a`aDHHl$L$$wH$H$H$L$`aE1*=s!H$HT$ 1HDŽ$HHGHHHt+H޿@aLL,1HH$~+1DH$H@ATL$UHSHHGLLHHCLHCHC PLHC0HHC(~LH H3H{H[0w@1fHHHHHH9u[]A\HH H H ڃuHVH9HPH9I1IMMtHf1fWfoxfDHff)f f)HI9wL9L{HHHHHH9JHWH9[HSH9Kff.AWIILAVAUATUHSHHHH$HH$XL$PH$`L\$L$H$H$H$hH$L$L$@H$H$If(L\$Y LX\$ L\$LLT$0HIH$\$ LT$0L\$}HƒHH9HGH!H9HtWII)LHIMt-fI<1HHHH9fwLM9tIHH9I HDŽ$H~[I{I`A0E1fDHH\fA.DvII IHH9|L$L\$ L\$1H$H1H\$ L\$~!H$I<tHHHH9uH$HHDHDHDHfW1E1HHeLf(Mf(IHDŽ$HDŽ$E1HDŽ$HfK<kJTH$H*HB A\KIYf(\f(f(f(fTfUAfVC<YYXf.IHf(H$f(H$\H$LYXH$H$IMHD$8L$pLT$0T$PL\$Lt$\\$ d$`l$@^IL\$LT$0HD$8f(l$@d$`\$ T$PL$pHH$J|H$HIL9}MHH*H*$H$H*$f(H$H$H$^ sYI*^\\YH*$X^YFH$H[]A\A]A^A_(H$H$L$pCHD$8T$PLT$0J4\$ L\$d$`l$@H$$LT$0Y$HD$8$L\$C<L$pXT$P\$ d$`l$@YXXf._H$lf.HDŽ$HDŽ$HDŽ$jE11HDŽ$HDŽ$HDŽ$&b1f.AWAVAUATU1SH1HHIHL$L$L$L$HL$x;H~0LV`MM+HM9I|tHIHyH;$%HB H9BH=ם!~@&A1HT$0Ht$8LD$(LL$ eH=֚!LL$ LD$(Ht$8HT$0HL$H9~IHLLSf.H,HH@ILH)H;N`I|-tI*HBLZL(HGHHxoH~0uH,IfLLHM[K+ L9I|tHIHyH;$DHHH[]A\A]A^A_L11M~I<tIHHL9uHD$IIDIDIDHBH8t=H=M!~A!H=b!腲L0A1H)ӰVfDHBfDJ<HT$0Ht$8LD$(LL$ HT$0MHt$8LD$(LL$ HjHzH8IvoukIH9vYMILHts1E1A /IfAL/f) (HM9wI9I,H,HI9HxI9w1I,H,HL9u1fffff.AWAVAUATUSLHH$H|$HHT$8HL$`LL$xL$H8L$H$L$-H$LLy(H$H\$Ll$E1H\$8Ll$HBC f.ztXHT$JHh Hu>@BC \K*LHLYYE(%Hm HuBCIL9$HL$`H\$E1Ll$HA0Ll$ IHHN<J<H|$ JHj Hu @HC0M(HB8LL$D$ʽYD$Hm HXD$CDuHC0IL9$B8qfWH$L*HL$`1L\$H5KlLT$8Ld$xL$HqHH$L$L$L$f.f(\fA.>vA>A0Xf.vf.w-f.rbXXf.wf.r \JXf.wHz0t HH)HI9HOH,HH I<uI* H`AA\E0Y\YJ\Af.fWf.2f.(f(\fA.>CD[H$HH$H8 H$HL$`H$HYHAHLHD$8HH9H$1HHHt2Hl$81LHfLf) HH9wH;$HtHt$8H$HHHH9HxSLD$`H,I@HH HJ|XAIL9t$3@H8[]A\A]A^A_JH~HS0H:H1@LIHH<MtHH9H{HIHC8JHCL,8HC(HsHJH4HsPHJHC?HS HJHT$JTHT$ \H|$D$E14@|$t;I9t6HHSHL$BII9H HSJH HuHt$ HTH|$(H$>H$fHsPfZBH1HC81H<@AWAVAUATUSHD$XL\$@Ht$`LD$E1HL$H8HT$HL$hLL$pH$L$HD$x@IJ<yJHT$Hl$PHEHMfWAH|$xA1E]L|$fA0L$A L4f(MXII*f.rf.w~M`C\5\f.rf.w`K<2uYMtTLl$HK|5uGI*Ld$AKLl$Hf(CY4\f(CY\5XY H@HEHH7L|$8I?L|$8IMLH҈D$D$1E1fDE1Mt(NtMfB.vN4IE1MuJHH9}CI9~>IL|$@M!L,L4I<HEHHyE@D$D$H9~lLeIHl$NI$`H AD$HIA\AXDHBHHyH=rm!~ 賒H$8H$PH$H$HH$pH$LL$pHL$0H$Ht$(HT$H$L$H$H|$ HH $LHD$Hl$aH$H7HHHH@HH@IIHAHHyHH$L$pL$xf.AH* HAD$YH AY HI\HI4fWO?\f.vI HrHHAXDyH=l!~ BH$0H$HL$pMH$xH$`HL$Ld$HT$HL$H4$H$pH$H$HD$ :H=k!H$运H=ok!H$(H$Ad$$HHxmHH$H$pH$xfDH*f(ALY\f(YY =XYY HBHHXyAuH=g! HT$pHHx"H$@ILH HBHHyH$H$H$H$H$HT$(L$xHt$@H$HL$HH$H$L$pHt$H$`$H|$8HHL$ LHD$0Ld$Lt$L<$腘HHi!HHT$`H$H$H+$H+$(HT$`HO0H$@H+$HG(HH$8H+$@HOH$0H+$8HOH$(H+$0HO HLi!H$$f.vH$$H$H$IL$hH;$HHDŽ$1HH$AD$P$$f.vAL$PH~^H$`H$H$HL$hHW@A%}H=e!~H=ah!HL$h~ `}HL$hH H$$L}L{}H$n}H$a}H$ T}H$`G}H$:}H$-}H$ }H$}H$}H$|H|$p|H$|H$|H$|H$|H$|H$|H$|H$|H$Pz|H$H$H$`ID$PHHH$H[]A\A]A^A_Ð\HHzHHHAL$H;H@I f.vf(I|=\f.w\IL$I D1HHDŽ$~ȻA+{HDf!HDŽ$1H$X?I|$xtH$1H>6H~0H$H?HtA1zH=c!&|H$H$`H$PH$H$H$HL$HHt$@H$HH$HT$PH$HD$XH|$0H$ HL$H4$H$L$xL$pH$XH$HT$LHD$ Hl$8H\$(Ld$1H$H$XHDŽ$HH$H$H$fDH<tHHHH9uH$H$HHH HH4H$L$xL$p$HHH$H$H+$HH7H$HT$HH$H$H|$0H$H$XHt$8H$HT$H$`H$HL$@H|$(LHHD$ Ld$Lt$L<$LH$1H$HHfA.D$PHL$h$HT$`HL$hH+$HT$`HH$HAHOc!HH$H>u HAHT$`wH=@`!cyH$X0A1wHT$`H$Hb!HH$H$AL$Pf.8AD$P$Ƅ$f.Y>5H$$AD$P@IL$@fD.XwH=i_!xfH=(b!~_A1vH=;_!^xHt$p11HHL$H$IL$L$HH$I!fDHEI]IHl$xHx]H$IT$8It$@H,HHT$`LuHT$`HHH?HI9}HD$pHEJII]IHyLL$L$H$H$HL$HT$pHIt$8H+t$xI|$@lH~H$H91It$@I|$8H+|$xH);H$H$H$H$L$L$xHL$PHt$HHL$pH$H|$0H$ HT$(LHD$@HL$ Ht$H|$H$pH$H$Hl$8Ld$H$$HD$xHDŽ$$GI|$8H+|$xIt$@`H$H$H$H$L$L$xHT$0H$ Ht$PH|$HHt$pH$HT$HHL$(H?H$pHD$@Ht$ H|$HH$H$LHHl$8Ld$H$HD$xWfHgfffffffH$H$H?HH)HHH9$H$ddHHgfffffffH$H$H?HHH)4H$ H$H$H$XL$L$HL$ H$Ht$H<$LHLl$HD$ٿH$H$H)HH$XH$H;M@HMPH)HgfffffffH$H$HL$hH?HHH)eHL$hH9H$XH}PHHH+$H+$HL$hHL$hH$HHDfDf(Hx lriH$H$WHHM0H9H1fDH1IHH<Ht&HH9H}HRIHE8HuJL,>HE(J H]HHHMPL<NX!L$H$H$^-L$ML$L$L$W! E1HDŽ$HD$x1111H|HHL9t/H<tHLIHHHL9ufH|$xfWAY f.sHH*H*^%f.Aa1f(\^APE1E1M~HH$E1E1H1@A\f.IH<tIHL9uH=Y!H񿀼AL1T$@LL$d$ LT$0L\$8\$PLD$`mLD$`A1H$HT$xLmLT$0L\$8A\$PI*I*^f(mH=V!=oL\$8LT$0LL$d$ \$PT$@H$ MH$H$11H|A BuH<t\HALHHL9uI*YX+L,MH111Ht)ItADHfA.DvI4H1HufIHH9~cI9~^HfH_HH$FI*YXU*L,M1'I9}eMPLOHH9}ODIADLfA.DvHt ITHfA.DvIHxHu1I4HH9|H$1@IHL9HHD|11MH|uH<t HDHHL9u1HHL9tMH<H<tHLHuAAI`HAYPL9AYX9ufDH=PV!мA1jH=_S!lH=*V!~n1AjH=V!~X kHĨ[]A\A]A^A_fAAI`AYX9APH$H$H?HЃH)zH=U!~P1Ad$ LL$LT$0jH=bU!d$ LL$LT$0~ VjLT$0LL$d$ 11M1DHHL9t(H4HuHHDHHL9u1fH HL9tGH<H<tHtHuAAI`HAYPL9AYX>uH=vT!~1LֿA1d$ LL$ iH={Q!jLL$d$ fA.XHMbP?IiPH~1Mf(H$f(1A\APfD(DJH$fD(E1HDŽ$HD$x11NH{Gz?IyPf1lfA(L$`T$@LL$LT$0d$ L\$8gfL\$8LT$0LL$d$ T$@L$`AXf.Y#H=O! ~H$HM!HGfTfUfVAX!"ALL$Y;dHO!LL$AAI`AYX\HO113"3"f(f(HT$xH$1L9 L9}%H$HH<tHHH$H$ILL$IILL4$yH=N!H5K!A1@c1|AWAVAUIATULSHI9I@PH$H$H$@L$H$@L$hH$uH$@I@1MpPH$N4I@I?L]XHhN!~A1RH=Z;!}THEpH H H H>!H#ARH$H$H$,SH$pSH$hSH$XSH$`RH$RH$RH$RH$RH$RH$RH$RH$RH$RH$vRH$iRH$P\RH$H$H$PHEPHHH$H[]A\A]A^A_H}8H+$Hu@aH$H$hMH$`H$XL$xHD$@HL$PHt$HH$H$H|$0H$XHT$(HH\$8H?HL$ Ht$H|$HH$pH$`H$LHHl$H$蔲H$H$@A1PH$H$$zDHƄ$HDŽ$~%ȻAePH~;!Ƅ$HDŽ$H$UH}xtH$E1H9wH~0H$H> HtA1OH=78!ZQM`H$H$PH$H$H$H$PH|$XHL$@H$H$@HT$HH$HD$PHt$0H$XH|$(HL$H$`L$xL$pH$HH$HT$LHD$ H\$8Hl$L,$2H$H1MHDŽ$HH$H$H<tHHHL9uH$H$HHH HH4H$HHLH$H+$HH7H$1f.EP$H$H$Lp^L+$H$IHBH?9!H|H$H9u HdAAMH=/6!ROH$10AMH$H$H8!H$H$MPf.EP$f.UH$HDŽ$AHU@MH$IgfffffffIH$H?HH)HHH9$H$d\HH$IH$H?HHH)g\H$XH$H$L$pL$H$HHL$ H$H4$HLd$HD$Ll$LH$H)HH$H$H;C@H$L{PL+$IH$H?HHH)[I9H{PH$HHH+$H+$L1g[LHLHfr.DKH=3!Mf.H}8H+$Hu@ [H$H$hMH$`H$L$xH\$8H|$PHL$@H$XH$Ht$0H$XHT$HH$H|$(HL$Ht$H$pH$`H$HT$ LHl$H$H$DHHx%H$HDHHBHHyH$1MHDŽ$H~^H$H$X1H$H9tH<t fWfA.ztAHǟHHL9uH$H}(@M@fWH$1fH* AY HL9Xu1f(fTf.0H$H$H$8DYA4\f.HI9~mf(fTf.0v[H* YfWf.vA f(f.vH8[HH*$f(Yf.w\fWA HI9H$H$H$11fDH<tHHHI9HH H4HH$HHH7HgMH$H$X1H$`DH<tH<tHHHL9u@YE1AHDŽ$EP6f(gH HM1[AGoH$AH$HHK0H9H1#H9IHH,HHH9HkH1HDŽ$ML$XH$`E1H$DK<JuQJ<uJH`C \0f.r*H$KH=1!1fDIM9H$H$H1!uH$H:cI@LEPPoM~HIML$H$PE1H$XH$`L$pH$J|C CKuIJ<uB\H*YfWf.r+H$JDH=0!XfDIM9HLMMmHfW1H$L$PH$XH$`L$p=H<u=AH*A\@Yf.v!HHL9t"f.f(H<tHf(L9uHH$XH$HH/!HDŽ$H7L(A1QDH=,!EH/!HDŽ$IHC8H{JL$/HC(J HsHH4HKPL4N4LsRH$HC HJ4JH$]HL$IA1.fDEt5I9t0HHCLAHH9}QHHCHHHuH$H$HH$5YfHKPfZAHH9|L$L(A1HT$hCH=+!DHT$hL(A1HT$hH$LD$xLL$pBH=A+!dDLL$pLD$xH$HT$h[HDŽ$HDŽ$HDŽ$H$HH>ItBH1LIHH,Mt'HH9H1HC8111IHC8J 1fDAWIAVAUATMUHHH~XMFIv LL$xL$@IHI II I\XHH9|L,L$@LHL$hLHAHT$hLHB HL$hHL$@HqHy HA(HHH~L1I*fDIL L M H HIH9L tfA. zuHHH9uHL$`HD$hIH$HHHHh8H@HHP0H@HT$hHǀHHB@HAHBHHAHBPHAHBXHA HB`HA(HBhHA0HBpHA8HBxHA@HHAHHHAPHHAXHHLHHLHHHH$H|$xH$H$t&H$Ld$p1I<ܾHH9H|$pHĸL1[]A\A]A^A_@f.HL$`H9Hz Hp ND$ LD$8W,D$ 1H1LbHT$pLD$8JH$IN RfHx D$ 1HHHB(JDHB HT$@Hx 1HT$@I?ND$ LH(H1LHP 1LD$8LL$@HL$pLL$@LD$8JHx D$ 1IHH@ LX(JDHT$@Hx 0HT$@NI?D$ HLP(1LHP 1LD$8$HL$pLD$8JE1E1HDŽ$1fWEȡHv fWHtifWHD$LD$DH^(HLD$T$Ht"DHHZY HHXuYHv HXu\G@H?HfWHHtHHtH9}HHu~HHDOHYJHHZXffffff.HG HtHfHw ff.H?WHH(HtHHtH9}.@uPzNHHu~.Wu0z.HHDO.HuzHHHfD1DHx|HHNHH9HGHtdH9HtVII)MIMMt,fWL 1fHHHI9fA) wLM9tfHHH9}1fHHHt)DHHHZYX  HHuf.HfWHHt HHZY HHXufWfff.H9HHNDH9HHMDH`A:A0A&(A]AHfDHHHD3HtHÿhAffff.StWHX% [fffff.HoH*Y^ HH,AWAVAUIATUSHHH=l ~xA1H= RAHuHI HǺќAA1EIU@AL12IUHAL1AEPALAEXALAE` ALIUh*AL1IU0DAL1IU81pALI]H~-IuHH@ HtH@ HHuHH9uܾAL1SAEAL;IEHAIUN4JHj HfIE bALB0YE(HEHHt8fD@nALZHHEHHHuHU1iALHm H{IEII9KL:H=B ~H[A[]A\A]A^A_H[]A\A]A^A_H!ffffff.HH H?vAf.H$0AfDH6HfWWHfDHtHHtH9*HHuYXG H/HH6HfWHHtHHtH9HHuH6LGHfWWHfHtHHtH9HHuI*YXG Hrf.GH>^H fWH7fHtHHtH9}~HHuYM fWXXRHY~VHHf.HH.fDHHfD~6HH7bfNHYJHHZXD@OHYIH7HZX@NHYJHHZX@NHYJHHZX$@AUfWIATIUSH(Hn Ht|fWI] Hu]DH[ HtOHCH9EuM(HHLT$YK( $ $H[ T$YHXufDHm HuH(f([]A\A]AWAVAUIATIUHSHiAHHIIEE1H1I$(f $D$ $HT$DH u t#LtEH…uI uHIEH9HLImM;4$.LE11iu@HL[]A\A]A^A_fM4$HAWAVAUATUHSHH(HLD$HD$L$pHt$ HHL$LL$(HH?II11 t;HHH4t-р#uI8uHT;I uI8L$ 1AHL$ t%<:IT$ <:Hu<:w1HxAH{t31HD$H DH+ЅtQ u*1H([]A\A]A^A_I0>Q utH+ЅuLl$0L$E1fH<+1L⾃AL;$h{sHD$H@H+ЅtQ u Q utH+Ѕu1LL|ALTuH$HL$HRf1LLAL#u&H$HGHT$HH$1L龐ALuH$HL$(H@H$1MLALH$HM~IVHL$ HH; L$IHHT$ fZHB[HT$ LIHHH$`L08A,AH1AۿAAHL1`A뮿AAWfWIAVAUATIUSHHHHEfWHD$8D$HT$8IO HH\$8IWD$0HH\$(AN,HT$(BHD$Hj D$ HtwI] Hu]DH[ HtOHCH9EuM(HHLYK( $ $H[ YHXD$D$uf.Hm HuID$ II9YD$0YD$XD$D$} IO IW.HD$8H9D$8QD$f.zt D$HH[]A\A]A^A_AWIAVAUIATUSHHH@HHH^ fWHtbfWT$Ht$H[(HHt$L$Ht'f.@HZYHHXuYH[ HXuf(A\GHH[]A\A]A^A_IHfWMg@AD$0JHD$(HT$8IWJHj HtmI] HuUDH[ HtGHKH9MuM(HHLYK(L$L$H[ YHXD$(D$(uHm HuIIW HL$8ID$(I9Y XD$0D$0?D$0A\GfWD$0f.H\$Hl$HLd$Ll$Lt$L|$HXHH?H{HtHk HH}H}HtLe M`I<$jI|$Ht[Ml$ M2I}DI}Ht6Mu MI>!I~HtM~ MI?IHtIG HHD$H8HT$HzHtHD$H@ HHD$tsH8HT$HzHt HT$HB Ht@H8HD$zHD$HxHt gHD$Hx HD$lHD$HGH|$=H|$3L+L#LLH HHl$0H\$(Ld$8Ll$@Lt$HL|$PHXfH\$(Hl$0Ld$8Ll$@Lt$HL|$PHXffff.HSHtHtH HtH[[fDATUSHHHt uD_H{ HtQH{(HtCHHt2H[]A\&fDHH~f.L$MtI|$ HtLHH{HH9|off.SHG0HH<HHDgHH{0HHxwHHwHH9HG1HtH9HtOII)MIMMt(fWL 1HHHI9fA)1wLM9tHHH9}L I~|LSAKJ<Hp HtTH{ H@HN(YHHt(@@HHZYXHHuHv HuIM9|[ÿhA6@AU1AATUHSHHH?D$t@HHHH<uLh0HIPLHHHDH/HI$11 fDHH<HH<H|H|HL9|HfWH@HtHHtH9HHuAT$1}tH|uHÿHHE(HID$1 fDID$L HH9|D$ID$ID$ LAD$(H[]A\A]D~HH:fHHYIHHZXhAz`H\$Hl$HLd$Ll$(H8HI$IEH$t-HHh@L`Lh H\$Hl$ Ld$(Ll$0H8ÿhAfAVAUIiAATUSHHIJ<HHDHIH= ~A1)H= L1'fDHAL tHL9}HLtL9uFLH= ~[AH=3 V[]A\A]LA^H AhAAWAVAUIATUSHH= ~A1>H= H$H$H$LAH$HGH HHH$IDH$KHHH$HID+HIHHuiAL HHD$HLl$PHǾA1LќAL\H|$HHU@A1]H|$HHUHA1HH|$HHUPA13H|$HHUXA1H|$HHU`A1 H|$HHUhA1H|$HHU0A1H|$HHU8A1H|$HHA1H|$HHUA1H}HHIDH@H}HEHHIDHH}HE HE(HDžtAADHT$H$LN,H$HU L$L$H$HHD$H$LLHD$H$H$<1H;HUHT$@H$tfDHHHH< uHp0HT$(Ht$0HHT$(Ht$0HHT$(Ht$0HHD$8HIDHHT$(HL$8Ht$0IH1E1@IL;IM9LT;MT9HI9|LfWH@MtH7HtL9RHMuI1:tH<uHLHHEHT$(HL$8Ht$0HHT$(HL$8Ht$0 HA1@HAD:D8HH9|H?HAHA HQ((HL$8eHHL$8HH@IH@L9eHT$@H@HH J*H|$HLKHCH=ۿ ~HUH= A1HH[]A\A]A^A_f~HLf@HYGLHZXdhAz`ALLFHAL2L: AWAVIAUATUSHHH= Ht$PHL$HLD$X~A1H= HL$xH$H$HH$H$HD$xHH= H$~[A\H= H$HHHDsHH$HT$PHHHHDJHH|$xIHHD-HIfiAH$HIH$H HHHDHH%H= ~A1ZH=˺ HL$H1HL`3t$xLLHA<$#tH$H$LL$hL$H$HHD$H$LH$HT$pHD$VIHT$pH HL$@HH$H3HL$HHHHHH9HH=(HL$P1H;L$H HL$8tDHHHH<uHH0HL$ HHHL$ HϸHT$(HHL$ HHDPHHT$(HL$ IH11 fIL 3HM 0LL3ML0HH9|H8fWH@HtHHtH9HHuJ1A?t%f.HA<uHHHEHT$(HL$ HHT$(HL$ HB1HBA<7@<0HH9|H?HBH$HJ(H$(HB HT$(Ht$0L|$hHL$ HHT$(HL$ Ht$0;H(HH=Ǻ HHHP HL$8HT$@HpLxHH ףp= ףHHH?HHH)HHHH9HA1H= L-L-LHH=% ~H=D HA1-HT$XH*Hĸ[]A\A]A^A_~HH8 f.@HYFH8HZX@HHT$HHhA A]AL1dALHJHR8ATIUSHHHH)H8HH8HHHVHtH9(HH)HHH9uHzHHHDHHH I$WHHt,H2HtXH9H0HZHHXHHHuH:tJfDHHHZHHXHH:uH9t"fDHHHQHHPHH9uH1H}tHHHH|uHX0HIH߸HHHDHHI$11DHH|HH<H|H|HH9|HfWHHtHHtH9HHuAL$`H H?ID$HI\$(ID$ID$ f[]LA\fD}FHHYHHXH>fD~^HHZfHHH)H8DHHYHXHX@XB.@HEHJHHf@HYAHHZX@HuHHH8u[hA3AWAVAUATUSHH8HIH1W(H8t#HHH8uHzHHHD$HH$HH:tJWH HHJHHHH@ZYffZ.@HEHJHH:uHsC(HH(HIH[ HSAf.H1MK(H8t%HHH8uHzHHID $HI $0HH:tJH WHHJHHHH@ZYffZ.@HEHJHH:uHsC(LH=LHLHMIt(I}I}HtI} LoHt(H}aH}HtSH} bHBH[ HH?Iv(H8L[]A\A]A^A_H|$@wfAHD$}IɿhA|@ATIUSHHHH)H8HH8HHHVHtH9HHH)HHH9uHzHHHDHHH I$ VWHHt9H2HtpH9H0HZHHXH@W@HHuH:tU HHHZHHX@W@HH:uH9tHHHQHHPHH9uH1H}tHHHH|uHX0HIH߸HHHDHHI$11DHH|HH<H|H|HH9|HfWHHtHHtH9HHuAL$H H?ID$I|$(ID$HID$ []LA\fD}FHHYHHXH&fD~^HHZfHHH)H8DHHYHXHX@\B.@HEHJHHf@HYAHHZX@HUHHH8u;hAS9AV1AUATUHSHHH8t#HHH8uHzHHHD$ HH$HUH:tIWfDH HHJHHHHHZYffZ.HHEHJHH:uH1H;Lu(AHmtHHHH<uLh0hHIXLHHHDDH7HI$11 fDHH<HH<H|H|HL9|H0fWH@HtHHtH9HHuAL$1}At"H|uIſIIEHID$1 fDID$L HL9|HMt$(ID$ID$ HL[]A\A]A^~HH02f@HYAH0HZX hAAWIAVAUATU1SH8HL'1LoG(AI<$D$(tHHHI<uLp0HHLHHHDdHHHH11@HI<HH<I|H|HL9|H0fWH@HtHHtH9ZHHuK1A}At$HA|uIĿIIEH:HC1 fDHCAL HI9HC Mo E1D$(HCMC(IuI}AE(Mu E1IMsIvI>AF(M~ E1IMJIwI?AG(IW E1IH!HrH:B(HT$HT$IHJ 1HHqH9A(HL$ tHL$ E1HHI HHqH9A(HL$ HD$AHL$ E1IHT$HI HHqH9A(HL$ HD$ HL$ 1IHT$LD$HI HtFHqH9A(HL$ HD$HL$ HD$ Hy Ht$ LL$LD$HT$HF Iq MH LB IW M~ Mu Ml$ Lc H8H[]A\A]A^A_~HH0f@HYAH0HZX\hAZ@AWAVAUATUSHH8=HHHǹHHAH;HHID HcH;HEHHIDHCHUHE HE(HT$H1H;HH$Hl$ HHf.H HB HD$HL$H $HQ HHHAHHh HLe1LmE(AI<$D$(tHHHI<uLx0HIfLHHHDHELt$HI11 f.HI<HH<I|H|HL9|H0fWH@HtHHtH9"HHuAN1A}At#HA|uIĿIIE7HIF1 fDIFAL HL9|IF H} D$(IFAF(H$IF HL$HBH(HhL`L(軼HHT$HL$HL(L`H@HhHP HT$H H $H9~[HD$ HT$ H@HD$~HH0f.@HYAH0HZX@Hl$ HHt^HC0H<HHDHtNHs0HHx,H1fHH H HH9~H8H[]A\A]A^A_ÿhA脼jAWHAVAUATUSH|$HL$JHfWL IIHD$E1E1E1HT$fDL؃HH9HGH H9ItZII)LHIMt'I,1HHHH9f)LwLM9tID HHLHH9H?IMIILt$I9[HL$HJ H-xLd-H|$HD$HHL$HL$L1AH\$HL$MnJ|{H\$f(fTf.`L9MHHOLD$Lt$IH\$IH\$HL$DAL9f(^f(~8LL|$L DAHIY\HH9H(H;\$Mtf(11ff(H4fTftf(f(fYf\f) HH9wI9Lt6JN<1HN\$IL|$D!eH\$@=$eLD$HLL$PH$If.M9L|$HT$~L$1MH$L,1f.#HY$HH9XuA!H$4LL$hLD$pY\fAW^f(_$f(\$,HH9fT_f(5dH$H\$@LD$HLL$PHH$H$1L$L$A+A$\/\&HAY,XAX$A$HH9u\$L$L|$5c1DHDL|$Ll$1&HAY$HH9XlfWlAdf.s A$f.rdHIH9H$fD(~H$H$DD\HHD$HHD$P5bH$A)H4fDWLT$P=SIA HAYIHt$@X5qjH|$`11L\$HIX@H9~'MHDlHAY/IH9XE >l=fE(D\fD.fD(D\fD.vrfA(\XHH9A,H<A$MAY1XXflHAY/IH9X|LT$@I7EL=fE(DXfA.vfD(DXfA.nf(HH9A\XaL\$HLT$P1DAldfD(DXfD.sA,fD(D\fA.rlHH9uA)LT$xA LT$@AYHL$@HL$`XD hHD$P1HD$H1Xf.H9}'IHDlHAY/IH9XA,>t=A\f.)f(\f.HD$HHD$PHH9tSA,H<A$MAY1XXfDlHAY/IH9X|LI9LT$xHL$@H$H$`5_H/fW~1A$YdHH9Xu%_fTf.-[gvnHD$HH|$XO H$tH|$XHD$Xf.vC^&gAl=AXf.f(Xf.H|$PuH|$HH\$H$H|$L5^-f1HDH|$HL$1HAYHH9XLufWLADf(Xf.sAf(\f.rDHLH9uf(1XDHH9H$~YL$L$HDHA"A ~H$HLH HHuH$X`XT$0\$ (T$0Ҹ\$ uH|$Huf. H([]A\A]A^A_HPH ID$A H$HI9L;$"IpI9%H$H$L$1L$1fD,HA4flfBtf(f\A4fAtfXfA)$HL9rH$H9L$H4I4L$\&HAX$A$HH9L;$JLLL1H8HH:fWfWH8HHHfIt1HHHH9fwH$H$H9$tIDHH9H$f(LLH$LD$xL$LT$pL\$hTH$LD$xL$LT$pL\$hH$ H$H$(HHIH$H$(H H$I HH ШHAH9HHHHH$Y11HfTf\f(f)f)HH9wH$H9t?H$HIHIf.H2H8HH:H0HHH9H$L1HH$IfDH2HxHH:HpLLH9uH$IEH$LH HH$IUHI2H$I1H I4H2I HHH9uH$1ILfH2H8HH:H0LLH9uH$IEHIUHH$H$$ICH9$H$HHHH$11fDAHfATf)HH9rH9$Ht%H$H$@IHHH9$M 1HH$~|f.H1AYAYHXHH9uHLH9uH$H$1DYAYXAHH9H$~$H$ SOH$@fW1HH$Ƅ$HDŽ$fH$@I|tVH1I|uAYAXAHHH9uH$~A AY \HLH9uL$L$1H$ HDŽ$111L$HM\MuTIH$IIHH$HH$HH$HH$HIIH1MH@HH9uHH,+H9vL$H$ HL$H$$H=z $H$H$8HxfHDIHHuHĨ[]A\A]A^A_HH$H$HH$H1H$HHHH$fDH;$u!HH9tH9uH*H9uH$I 3L$L$1I4;H$DL9tKH9tF1fL9uA YXHH9t$H9uA HH9Y XuHLLH9uL$H$HKHH$IH$H$HI4f.5KƄ$0HDŽ$8f(fWf.H$HEfA.H$H$H$EH$HHE fE.zf(Xf. Jf. JruTH$Ƅ$0HDŽ$8f(\HD=H$H$\ 8]\f(AH$ \A : Jf(fTf.H$HAf(fTf.H$fEWHH$A4fA.zjfA.z DX^^\fTf.>Ƅ$ RM"H$HE fA.H$H$H$AH$HH$H$M4] $0J HHxJH$"HI I I HHtI|tI I I HHufWHf(fEWL$L%GLMMfA(1f.THALf(YYXYAYXt'L1@LHYY LH9XuHMIH9uH$fA(1AHTYXf(YYAYXt(H1DAHYYLH9XuHMHH9uf(H=s H$0\xֿpA$P$TH0H$wA1LD$xL$LT$pL\$h L\$hLT$pL$LD$xH$HH$`HH I4$$HVH$QH$H >H9$HHHHBH$XH$11H$fTfdf(f)$f)HH9wH$XH9HtJH$`H$H$XHHH2H file with training data model_file -> file to store learned decision rule in -? -> this help -v [0..3] -> verbosity level (default 1) -z {c,r,p} -> select between classification (c), regression (r), and preference ranking (p) (default classification) -c float -> C: trade-off between training error and margin (default [avg. x*x]^-1) -w [0..] -> epsilon width of tube for regression (default 0.1) -j float -> Cost: cost-factor, by which training errors on positive examples outweight errors on negative examples (default 1) (see [4]) -b [0,1] -> use biased hyperplane (i.e. x*w+b>0) instead of unbiased hyperplane (i.e. x*w>0) (default 1) -i [0,1] -> remove inconsistent training examples and retrain (default 0)Performance estimation options: -x [0,1] -> compute leave-one-out estimates (default 0) (see [5]) -o ]0..2] -> value of rho for XiAlpha-estimator and for pruning leave-one-out computation (default 1.0) (see [2]) -k [0..100] -> search depth for extended XiAlpha-estimator (default 0)Transduction options (see [3]): -p [0..1] -> fraction of unlabeled examples to be classified into the positive class (default is the ratio of positive and negative examples in the training data) -t int -> type of kernel function: 0: linear (default) 1: polynomial (s a*b+c)^d 2: radial basis function exp(-gamma ||a-b||^2) 3: sigmoid tanh(s a*b + c) 4: user defined kernel from kernel.h -d int -> parameter d in polynomial kernel -g float -> parameter gamma in rbf kernel -s float -> parameter s in sigmoid/poly kernel -r float -> parameter c in sigmoid/poly kernel -u string -> parameter of user defined kernelOptimization options (see [1]): -q [2..] -> maximum size of QP-subproblems (default 10) -n [2..q] -> number of new variables entering the working set in each iteration (default n = q). Set n size of cache for kernel evaluations in MB (default 40) The larger the faster... -e float -> eps: Allow that error for termination criterion [y [w*x+b] - 1] >= eps (default 0.001) -y [0,1] -> restart the optimization from alpha values in file specified by -a option. (default 0) -h [5..] -> number of iterations a variable needs to be optimal before considered for shrinking (default 100) -f [0,1] -> do final optimality check for variables removed by shrinking. Although this test is usually positive, there is no guarantee that the optimum was found if the test is omitted. (default 1) -y string -> if option is given, reads alphas from file with given and uses them as starting point. (default 'disabled') -# int -> terminate optimization, if no progress after this number of iterations. (default 100000) -l string -> file to write predicted labels of unlabeled examples into after transductive learning -a string -> write all alphas to this file after learning (in the same order as in the training set)[1] T. Joachims, Making Large-Scale SVM Learning Practical. Advances in Kernel Methods - Support Vector Learning, B. Schlkopf and C. Burges and A. Smola (ed.), MIT Press, 1999.[2] T. Joachims, Estimating the Generalization performance of an SVM Efficiently. International Conference on Machine Learning (ICML), 2000.[3] T. Joachims, Transductive Inference for Text Classification using Support Vector Machines. International Conference on Machine Learning (ICML),[4] K. Morik, P. Brockhausen, and T. Joachims, Combining statistical learning with a knowledge-based approach - A case study in intensive care monitoring. International Conference on Machine Learning (ICML), 1999.[5] T. Joachims, Learning to Classify Text Using Support Vector Machines: Methods, Theory, and Algorithms. Dissertation, Kluwer, Not enough input parameters! Unknown type '%s': Valid types are 'c' (classification), 'r' regession, and 'p' preference ranking. It does not make sense to skip the final optimality check for linear kernels. It is necessary to do the final optimality check when removing inconsistent examples. Maximum size of QP-subproblems not in valid range: %ld [2..] Maximum size of QP-subproblems [%ld] must be larger than the number of new variables [%ld] entering the working set in each iteration. Maximum number of iterations for shrinking not in valid range: %ld [1,..] The C parameter must be greater than zero! The fraction of unlabeled examples to classify as positives must The COSTRATIO parameter must be greater than zero! The epsilon parameter must be greater than zero! The parameter rho for xi/alpha-estimates and leave-one-out pruning mustbe greater than zero (typically 1.0 or 2.0, see T. Joachims, Estimating theGeneralization Performance of an SVM Efficiently, ICML, 2000.)! The parameter depth for ext. xi/alpha-estimates must be in [0..100] (zerofor switching to the conventional xa/estimates described in T. Joachims,Estimating the Generalization Performance of an SVM Efficiently, ICML, 2000.)0@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@8@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@,@@@@@@`@@@ @@@@@@`@@@ @@@@@@X@8@@@`@?sid %ld: dist=%.2f, target=%.2f, slack=%.2f, a=%f, alphaslack=%f xacrit>=1: labeledpos=%.5f labeledneg=%.5f default=%.5f xacrit>=1: unlabelpos=%.5f unlabelneg=%.5f xacrit>=1: labeled=%.5f unlabled=%.5f all=%.5f xacritsum: labeled=%.5f unlabled=%.5f all=%.5f r_delta_sq=%.5f xisum=%.5f asum=%.5f Computing qp-matrices (type %ld kernel [degree %ld, rbf_gamma %f, coef_lin %f, coef_const %f])... Number of inactive variables = %ld Error: Kernel cache full! => increase cache sizeObjective function (over active variables): %.16f WARNING: Relaxing KT-Conditions due to slow progress! Terminating! Checking optimality of inactive variables... => (%ld SV (incl. %ld SV at u-bound), max violation=%.5f) POS=%ld, ORGPOS=%ld, ORGNEG=%ld POS=%ld, NEWPOS=%ld, NEWNEG=%ld Classifying unlabeled data as %ld POS / %ld NEG. %ld positive -> Added %ld POS / %ld NEG unlabeled examples. Model-length = %f (%f), loss = %f, objective = %f Increasing influence of unlabeled examples to %f%% .%ld positive -> Switching labels of %ld POS / %ld NEG unlabeled examples. Moving training errors to inconsistent examples... Now %ld inconsistent examples. Setting default regularization parameter C=%.4f WARNING: Using a kernel cache for linear case will slow optimization down!Optimization finished (maxdiff=%.5f). Runtime in cpu-seconds: %.2f (%.2f%% for kernel/%.2f%% for optimizer/%.2f%% for final/%.2f%% for update/%.2f%% for model/%.2f%% for check/%.2f%% for select) Number of SV: %ld (plus %ld inconsistent examples) Number of SV: %ld (including %ld at upper bound) Norm of weight vector: |w|=%.5f Norm of longest example vector: |x|=%.5f Number of kernel evaluations: %ld Error: Missing shared slacks definitions in some of the examples.'remove inconsistent' not available in this mode. Switching option off!Number of non-zero slack variables: %ld (out of %ld) %ld positive, %ld negative, and %ld unlabeled examples. Deactivating Shrinking due to an incompatibility with the transductive learner in the current version. Cannot compute leave-one-out estimates for transductive learner. Cannot compute leave-one-out estimates when removing inconsistent examples. Cannot compute leave-one-out with only one example in one class. Optimization finished (%ld misclassified, maxdiff=%.5f). Estimated VCdim of classifier: VCdim<=%.5f Computing XiAlpha-estimates...Runtime for XiAlpha-estimates in cpu-seconds: %.2f XiAlpha-estimate of the error: error<=%.2f%% (rho=%.2f,depth=%ld) XiAlpha-estimate of the recall: recall=>%.2f%% (rho=%.2f,depth=%ld) XiAlpha-estimate of the precision: precision=>%.2f%% (rho=%.2f,depth=%ld) Leave-One-Out test on example %ld Leave-one-out estimate of the error: error=%.2f%% Leave-one-out estimate of the recall: recall=%.2f%% Leave-one-out estimate of the precision: precision=%.2f%% Actual leave-one-outs computed: %ld (rho=%.2f) Runtime for leave-one-out in cpu-seconds: %.2f Constructing %ld rank constraints... (single %f) (joint %f) inconsistent(%ld)..Writing alpha file...w%.18g doneWriting prediction file...%.8g:+1 %.8g:-1 %.8g:-1 %.8g:+1 Calculating model... Cache-size in rows = %ld Kernel evals so far: %ld Reorganizing cache...done.%ld..done Running optimizer... Shrinking...Iteration %ld: Selecting working set... (i-step)(j-step on %ld) %ld vectors chosen pos ratio = %f (%f). Retraining.Number of switches: %ld Optimizingdone. (%ld iterations) Runtime in cpu-seconds: %.2f L1 loss: loss=%.5f Computing starting state...Number of SV: %ld Computing leave-one-out(?[%ld]-)+) Retrain on full problem?ffffff?333333?Y@dA333333?ii@-C6?? Copyright: Thorsten Joachims, thorsten@joachims.org This software is available for non-commercial use only. It must notbe modified and distributed without prior permission of the author.The author is not responsible for implications from the use of this%ld # number of training documents %ld # number of support vectors plus 1 %.8g # threshold b, each following line is a SV (starting with alpha*y) Error: Unknown kernel functionLine must start with label or 0!!! Slack-id must be greater or equal to 1!!! Feature numbers must be larger or equal to 1!!! Features must be in increasing order!!! Cannot parse feature/value pair!!! Not enough values in alpha file!Version of model-file does not match version of svm_classify! Parsing error while reading model file in SV %ld! %sOK. (%d support vectors read) Reading examples into memory... Parsing error in line %ld! %s Maximum feature number exceeds limit defined in MAXFEATNUM!software. Out of memory! Writing model file...SVM-light Version %s %ld # kernel type %ld # kernel parameter -d %.8g # kernel parameter -g %.8g # kernel parameter -s %.8g # kernel parameter -r %s# kernel parameter -u %ld # highest feature index %.32g #%s %ld:%.8g %lfqid:%ld%ssid:%ld%scost:%lf%s%ld:%lf%s'%s' in LINE: %s Reading alphas...%lf Reading model...%ld%*[^ ] %lf%*[^ ] %[^#]%*[^ ] Scanning examples...OK. (%ld examples read) AA A0AA.A%5.2f real_qp_size(%ld)...%f: : a=%.10f < %f: y=%f %f EQ: %f*x0 + %f*x%ld = %f return(%d)...return_srd(%d)...: a=%.30f: nonopti=%ldeq-constraint=%.30f b=%f smallroundcount=%ld SOLVE DUAL: inappropriate number of eq-constrains!before(%.30f)...after(%.30f)...result_sd(%d)... WARNING: Relaxing epsilon on KT-Conditions (%f). ~.AV瞯$@#B ; ?- ?;\j FF G0GHG`0HxHI@IPI`III(JH@J`L`OP0QUV @XpZZ`[\p^P^x`ekXnPqtwPz`~8p H8PzRx 8DU48DLT<# BYB L(A0D8T 8A0A(B BBBE DDBJE A(A0GC 0C(A BBBI GmGG@4HLDLPHBBB B(A0A8n 0G(B BBBI ,(JBDG AB4JBBA A(  ABBA KHL@,pLUDL\Lt8M+PMHML@MBHB B(A0A8J# 8A0A(B BBBI $ QD J d D F<4XRBDD D(G`x (A ABBE 4tSBCC G@v  AABG LSBMB D(D0x (A BBBP A (A BBBA d0TBBE E(D0D8Gp 8F0A(B BBBI D 8A0A(B BBBA LdUWBBB B(A0A8Dpr 8A0A(B BBFB dY BBE B(A0D8GP 8A0A(B BBBB A8A0A(B BBB<`Z~BED D(D@X (A ABBA D\ZBBB I(D0G` 0A(A BBBI Dx[BBB I(D0G` 0A(A BBBA L@\>BBE E(D0G8Q 8A0A(B BBB[ <<0`BBA I(G` (A ABBA |aN0Y I <aBEA A(T0 (D ABBJ LdBEI D(G0" (A ABBE E (A ABBE L,0f>BBB B(D0D8R8A0A(B BBB| jKAELPjgBED D(G0- (F ABBG D (A ABBA plHABd lBIB B(A0A8JD 8A0A(B BBBG w 8F0A(B BBBO LtXq<BBB B(A0A8D 8A0A(B BBBK ,HrBID  ABA Ls6BKB B(A0D8M 8A0A(B BBBE LD yRBBB B(A0C8I 8D0A(B BBBA L | BBB B(A0A8Jh 8A0A(B BBBA L BBB B(A0A8J 8A0A(B BBBG ,4 AG AC  AA Ld |BBB B(D0D8Gp 8A0A(B BBBA D HTBBB B(A0A8 0A(B BBBA D `BBB B(A0A8 0A(B BBBA LD BBB B(D0A8J  8A0A(B BBBB L BEB B(A0D8J 8A0A(B BBBJ L *!BBB E(A0D8G 8A0A(B BBBA L4 BEB B(D0H8K 8A0A(B BBBE , hM[`r F  I L BBE E(A0D8GG 8A0A(B BBBE L / BEB B(D0D8GB 8A0A(B BBBJ LT -BBB B(D0D8J 8F0A(B BBBI  5  5| 5a @6H6{64(76LP74dx7 |p7 h7:Dq73DZ A 7"C^7(D^d7BBB E(A0A8G@8 8F0A(B BBBE D 8A0A(B BBBA ,l:D L L D  O \ L 4`<BID A(DP(E ABBL<BBB E(D0D8LP 8D0A(B BBBG L$=BBB B(A0D8JW 8A0A(B BBBA Lt(AyBIB B(D0A8DV8A0A(B BBBLXBBEB E(A0A8D 8A0A(B BBBA ,C3MX` N bDE*D\ H A,dEBAA F ABK hFLA6 A <GBJA D(G@L (A ABBF $I~MS@I A <pIBBJ A(A0 (A BBEA L\PJBBB E(A0A8G 8D0A(B BBBC LOBBE B(A0A8J 8A0A(B BBBD ,0UBDA , AEG L, XBBB B(A0A8GpD 8D0A(B BBBA ,|pZ?BDA L AEG D]hBDB A(D0D@ 0D(A BBBD L_BEB B(A0C8Dp 8D0A(B BBBD LDbBBB B(A0A8Lp 8D0A(B BBBA DhfBEB B(A0A8% 0A(B BBBE 4lBEA A(  ABBA m$, n D B v A ,To?BDA  ABA pDDpBBB B(D0A8D@Z8F0A(B BBBLpWBBB B(A0A8J6 8A0A(B BBBA L<$BEB B(I0A8J 8C0A(B BBBA LBBE B(D0D8J 8A0A(B BBBA `$XQ_@X@ ` @ Ao`@@@ 6 a@x@H o@oo@(a @ @ @ @ @ @ @ @ @ @. @> @N @^ @n @~ @ @ @ @ @ @ @ @ @ @ @. @> @h㈵>:0yE>GCC: (GNU) 4.4.6 20110731 (Red Hat 4.4.6-3).symtab.strtab.shstrtab.interp.note.ABI-tag.note.gnu.build-id.gnu.hash.dynsym.dynstr.gnu.version.gnu.version_r.rela.dyn.rela.plt.init.text.fini.rodata.eh_frame_hdr.eh_frame.ctors.dtors.jcr.dynamic.got.got.plt.data.bss.comment@#@ 1<@<$Do`@`(N @V@6^o@Bko@`zx@xH@ ` @` x @x P @P HAAp4 A \Aaa a (a(aaa a 0,(4 { @@<@`@@@@@ x@ @ ` @ x @ P @AA AAaa a(aaaaa | @a*a8 aE @[aj ax  @aA a `A O@0a(a$0aFaWaj(as a~ A6 KA ZA .@W z@ A$ P)@? l@T^ P @e @q @Aaz H@H A: p@   0A(( XA?9KXaW pF@gkAq  #@@a "@@ A{a @ @ pW@R `A  A4  ,AL2 E a\  WAi  pA n  @  HA  <@  ZA  @#   `)A3 Ha @a  #@! 3 a8  @@E Y  A3c 8aj ax  0@@  5@  !@  4@  0VA  p$@   @m$  0!A+  j@|F  A@>b v a}  &Ay   ,@   a  @L  0Q@6  a  *@2  @7  ` @= Q  01A\  `A a  A"o  0Acall_gmon_startcrtstuff.c__CTOR_LIST____DTOR_LIST____JCR_LIST____do_global_dtors_auxcompleted.6347dtor_idx.6349frame_dummy__CTOR_END____FRAME_END____JCR_END____do_global_ctors_auxsvm_learn_main.csvm_learn.cinit_shrink_state.clone.0switchsens.8371switchnum.8378svm_common.csvm_hideo.c_GLOBAL_OFFSET_TABLE___init_array_end__init_array_start_DYNAMICdata_startadd_vector_nscopy_modelexp@@GLIBC_2.2.5printf@@GLIBC_2.2.5lprint_matrixtanh@@GLIBC_2.2.5calculate_svm_modeloptimize_to_convergence_sharedslack__libc_csu_finiidentify_one_misclassifiedselect_next_qp_subproblem_grad_startclear_indexsprod_ss__isoc99_fscanf@@GLIBC_2.7shrink_state_cleanupcopyright_noticecache_kernel_row__gmon_start___Jv_RegisterClassesputs@@GLIBC_2.2.5__isoc99_sscanf@@GLIBC_2.7get_runtimelswitchrk_matrixexit@@GLIBC_2.2.5roundnumberkernel_cache_shrink_finiadd_ssputchar@@GLIBC_2.2.5kernel_cache_clean_and_malloccompute_matrices_for_optimizationmalloc@@GLIBC_2.2.5fopen@@GLIBC_2.2.5svm_learn_optimizationsmult_s__libc_start_main@@GLIBC_2.2.5get_kernel_rowkernel_cache_checksub_sskernel_cache_cleanupadd_list_sscreate_svectornonoptimallswitch_rows_matrixfgets@@GLIBC_2.2.5svm_learn_rankingverbosityread_documentsestimate_spheredocfile_IO_stdin_usedkernel_cache_mallocincorporate_unlabeled_examplesoptimize_qpfree@@GLIBC_2.2.5_IO_getc@@GLIBC_2.2.5__data_startclassify_examplemaxiterappend_svector_listcheck_optimalityfree_example__ctype_b_loc@@GLIBC_2.3create_example__isnan@@GLIBC_2.2.5stdin@@GLIBC_2.2.5write_alphaslinvert_matrixclassify_example_linearcompute_shared_slackscustom_kernelpow@@GLIBC_2.2.5optimize_hildreth_despooptimize_svmsingle_kernelreactivate_inactive_examplesprint_help__dso_handlecheck_optimality_sharedslackbufferclear_vector_nselect_next_qp_subproblem_randstrtol@@GLIBC_2.2.5__DTOR_END____libc_csu_initsmallroundcountestimate_margin_vcdimsvm_learn_classificationkernelkernel_cache_touchselect_top_nsolve_dualupdate_linear_componentparse_documentfree_modelidentify_inconsistentlength_of_longest_document_vectorlindep_sensitivityoptimize_to_convergenceestimate_transduction_qualitykernel_cache_free_lrudualkernel_cache_reset_lrufeatvec_eq__bss_startwait_any_keyshrink_problemwrite_modelsprod_nsadd_weight_vector_to_linear_modelclock@@GLIBC_2.2.5kernel_cache_statisticlcopy_matrixmaxlsvm_learn_regressioncopy_svectorkernel_cache_initcalculate_qp_objectiveread_input_parametersstrcpy@@GLIBC_2.2.5free_svectorprecision_violationsmodelfilekernel_cache_freefeof@@GLIBC_2.2.5_endadd_to_indexfclose@@GLIBC_2.2.5my_mallocprimalopt_precisioninit_shrink_stateestimate_r_deltaselect_next_qp_slacksetestimate_r_delta_averageladd_matrixkernel_cache_space_availablefwrite@@GLIBC_2.2.5compute_objective_functionnol_llcache_multiple_kernel_rowsdistribute_alpha_t_greedilyperror@@GLIBC_2.2.5_edatamodel_length_sfprintf@@GLIBC_2.2.5write_predictionsqrt@@GLIBC_2.2.5restartfilecompute_indexcompute_xa_estimatesstrtod@@GLIBC_2.2.5stdout@@GLIBC_2.2.5identify_misclassifiedmain_initfflush@@GLIBC_2.2.5read_modelminlspace_or_nullread_alphas