From 5f757ad9397fe84c024ac9a849975fae05032e44 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=AD=8F=E9=81=87=E5=8D=BF?= <358614401@qq.com>
Date: Sat, 18 Mar 2023 16:23:57 +0800
Subject: [PATCH] load two layer of cnn

---
 ...t.tfevents.1679127816.WEIYUQING.46432.0.v2 | Bin 0 -> 60775 bytes
 _mian_tensorflow_keras_.py                    |  92 --------------
 _mian_tensorflow_twoLayerCNN.py               | 113 ++++++++++++++++++
 noise_take_ecg.py                             |  31 -----
 requirements.txt                              |  11 ++
 some-test/noise_take_ecg.py                   |  31 +++++
 .../pytorch_gpu_test.py                       |   0
 .../test_plt_show.py                          |   0
 .../tf_run_in_gpu.py                          |   0
 wfdb_use.py => some-test/wfdb_use.py          |   4 +-
 utils.py                                      |   2 +-
 11 files changed, 158 insertions(+), 126 deletions(-)
 create mode 100644 Number-Of-CNN-Layers/Two/logs/20230318-162330/train/events.out.tfevents.1679127816.WEIYUQING.46432.0.v2
 delete mode 100644 _mian_tensorflow_keras_.py
 create mode 100644 _mian_tensorflow_twoLayerCNN.py
 delete mode 100644 noise_take_ecg.py
 create mode 100644 requirements.txt
 create mode 100644 some-test/noise_take_ecg.py
 rename pytorch_gpu_test.py => some-test/pytorch_gpu_test.py (100%)
 rename test_plt_show.py => some-test/test_plt_show.py (100%)
 rename tf_run_in_gpu.py => some-test/tf_run_in_gpu.py (100%)
 rename wfdb_use.py => some-test/wfdb_use.py (90%)

diff --git a/Number-Of-CNN-Layers/Two/logs/20230318-162330/train/events.out.tfevents.1679127816.WEIYUQING.46432.0.v2 b/Number-Of-CNN-Layers/Two/logs/20230318-162330/train/events.out.tfevents.1679127816.WEIYUQING.46432.0.v2
new file mode 100644
index 0000000000000000000000000000000000000000..d3f29c620f5d0deef2332f3b82ddb37527d128b8
GIT binary patch
literal 60775
zcmeHw33OY<xv(TJu_sP&ZWf%I5L_of5FxhZEMN#$oE1ny$O4ZoLa}5=M3#&sI|(Vp
zP)Y+0OQ5ub^3$*d2$U`Cp@b!`w7d|u*R;^4Wodi50in=W+CIwrX70?rGxyHDx>u6j
z^PfY`iS2JRn)&A2zgg>i+P^z4Ikll0{%k+5;;q^0u+^DpA~khhUp$p-4P89>@zkY5
zwR+3{UOB(I=8R#aUhuDD&|k)&inZ}fG~2#!Ow|y@*Z$I&jSU^iXf_*3MZ4n-t@RDd
z;}`ZqLy2gzVM={NM>^G+=z{W%4Xi>|sE~|qh-b1;;T&^AC#QOPbBplDriNBWa~*3U
z3H)&+yC&L$yFDk>n@morZ)s|pQr~<YbR5fVARjbzCezVeO9;1-?TKcxxOQhWnT<n1
zCfd~%k8uSIN3HSZhKnzr0+@>foRd!VHP1ES#J&jQ?Q4$V4|ABP(bY-ZUoO*&yOZJ6
znMmd|0!)J%K-*M28ObItB7+K%p=5KJL@Z8dMBtuiES5-NqBdkP(Q(VsTr|>|&U8m}
zxVU3YGzINsBfyy)`8<(~<`U^tBoob%mPtchnRIUtZnqhlh<4->eWVg@Arnvb;xG1Q
z<B`>gD6T{YK~YSk5}3z;Xa+tr(`Z35ok{0brV<z@+zuxP**GCNW*8=K18yF;>D1iW
z@k}}^HbcHjammEHdXv!%#YK|@ty$?OWTc7QhKTf2+9n_jbO#n<g7QsTK9I@C;^_LN
z>2wmfWGgA%(e;rYTE~mPaMBRMf{xqJ1*V0Rc$5#>0OsTu@<=o0$d_XNrI@=Gb59~O
zID$SO3}Y^y5{--Qt2&KOT?)FRC6;O0+;|Fnl4v5CH;J*&Tz1|IR+QND&~eb<mlmDG
z1k9;g3^$O7_#Vp#QZ{AMJ?UQJOrgFxrimG!x?~k~#7$E}fJQ2v06)uO8R~6Je$wn>
z^U94UWn+>v-6A*HbY~8H6_(I1g8>)8z<D^Pfgl2cnm!2ZAn3yJRA_2*)6^zR#MRM`
zweb`VIvc?5WYZZ4P}enFd`cY}gGO{^qCIOO+PAyYv3OGPH~+T(8_zxck`|EHy*}~z
z>Yto=DhbFNesFCW>PA%w2q2@mbVeDvG#TxPuSq9k@l0?isvrWT1X_K;1~e)H+{;9=
zJ@Jl2XCfXW@w$Q({oD8pBtTUHO{0Qi(C`R|yB=a^m2w0Pp*Q^KkdtYD3*xyY@%1^y
zT%a0ljzKlF6&#Ldl}c0|3i!){Gte-x^&`;4Rz(?F^#%LqSIVmH53~*w%7WuiWrRfI
z$_R9bGAx<yXbrRB2WMJvcGoJ3p|M6%(l~E@Pc#*qo9NCq#uD911%yJ`9Q0h#7ftrY
z6{Wqls!Z{<B8KS~ex7t?wxqk>k48(oQIOH4Y9XdQYC(j`S6~zaO=ZC$$iD*q@CT<@
zsGy>{)-eJd32l`?l^<o$Q5;TS*&usqgb_oA<C+kkGfKE5#FKtB(M6{MS>%*c-6Ah1
zRg;BO6VUipRU{Qq$spI)&@302N17X##iOw^ASJ;G;AuULnRqtco9T!<sHiLTd)$wv
z6@q{=TtrAMZWz44`@y)FZAC2_-dY3lH5$tp{4Ymq(b4Yk=2T8$Dp%b;gs7a~$9HV6
zX|May5w3a@M64jfs_us+m%$?~#2bZ_)>=w9gMbeOP@UbFluE3zp}DFXwNl-YCO8^Z
z$LOp<R;fajYPlc&8Fpqg8p_4GN~Kc1WZ{`}f+Nuo8n|;`8iQ(a?9kC0OQj+(3(?in
zs{|(dgNLFK@%25)L`NbQp|cuUC4hXv5oid7al^}JFP<0ls;uSc7C)-DBU$5en5Bwe
z6jz4OKU7=l1}C7JtX4Y$(wS9;qZ$=)Mz0{#TMnkT*@|5|Ooq&k#RkfLe8-O_yY19s
zGrXhAtE)e#T0|Yhs<oWhhiCnQ52lWYQbQR+|4{StQ*}MOyprt2k(Q$#G{#EUWiX4T
zl;fW&@5aT^8Hjl6F(J5aVLHjibz2Q;faj3CL48W}*mivh=G2B9g3GpR2nSwrbLq+o
z;K)(;JpUtF0kO-)+B}^yg#IB|P_e2JqZtfyYXbvdI2~+V#acY!OYLPD)GgHfl~sKQ
zyIalWe$Q#(7W2nzmN;-q8gK}r8LU8Msy|>5!=>~R49ihY5)eS#G{B+fOR~s7)~z7Q
z_OxNn!x{z18ZA<+wMdlGuiuZ_ECxr`DU^w^U&(^er~PO~VJKK!OR+=Y%~-yGRC74p
z=oq)Smm(znnP0Hhng@`xOAx&R39Nb<oZQmp4@@;eJ{~}-Jtg(f)EaflMlW~=CnDty
zPo;6FjlH%t&318Xq4rtO;B9`?U{5$}fa*Zyl830ek#3P;IKV;b&3+Vg->t=#6oRs7
zKb!*9J$^LK0XZX7b-`QJ!!Qj$Ya_&7-LEy@A)Z1HSe-^`Amgo9aTY)bGoW)L!r~|1
z3JzL#i@x5zH^JcAl10e$?Heo7#|shM-$e^y?sTy^c;#)Zxw1iAgLxJkiQ`lo@v^m%
zBVb2J{_wTYlKUNo#<h+$Pqm$@N3XX!kKGc#^6F+DJ0(=!2=*8Yl4H@Kt)pc~mZO9)
zA43-kar~Oiu{q<z*aX(7b_FJ|u)hp6kSXpdexGSB%iiV$(4Bt4#j?JZ#kC3kA@mQ`
zi3TiE<>i|-M36Sbq6Ss2pi2iZu{_yAlrd<OY_1+s;6~0elC{gm#nIg2-sC_<pf~x^
zk?y**cnPnliXNigLKK)3YDL;aaak1v=P;phs10gLrA8H%_vnlljF&FQ1*zgtSaD2c
zd(wEP4$P|g3`V+ST|Z7ZxmKdM6?7qLvfw|!j{in6NY*4s-lv71o{<$9I?lq-YBZ#^
z0vHOse9$lGx`3DA@a@<w#I(Y9O=@8<&c+72<|n#9SZdNb<tC$eBOqX8py0l*xG>8~
zSHc_FZ^0mrW(KjQ9l<PxFIevLZEF)bVYl+Q#g8WN0;#RI>-~V0QOe+l%C8g|0~clv
z8E)*i$^N+?davWqm*c&ON(K34gO)+>;iw8$L?d{al&t4D`GXhzXr==xz#PQV-4R&Q
z$Gh(uml2Te#Z!g}pd(ob;y5|PI}wyXoo-pmM2@+p7ycS<D})<EDPabP@q+zckcq=q
z#mu}5d!xz54a}oj1?ZK%i%t^Ju@j(uChKAnAihJThKJNbi7kYTY+&p+-$UaDLl9h3
z6W#7dhdYSD9N7D*l;fYG1#%cSX7=(-2VO`<L6FE5nch?fuz|Q0_-t-Ar!6wON76J4
z$wtq9gT_XhHO0-N-D<wE7D7UC4ThKtNJIuUXaS1wixiHXTHGAJ2IKfmeU?vDj>9c}
zZWtQcT21^Mgr^k<W=Q#^3b7A8a^Yu087tXu!ct)!Mr_3F^@P~N6u}6ek+>vylw|~?
z(a6>j<{-TSWl@ON4!o5Pcq<PlbZQm5Ko1cqKNrkKF7MUC-2xC6*=z4LD$t{17GXlo
zh-2*8FWNIlf*Q(b6U%sDBOfL+te0!M(qQ>k`$LGOStUw!0~gnwo`r@R2{S(%QT#Tb
z4T#(BBTPMvFm0@AZB|WK$YyHG+-ig$UFk=Yv@;M9Y}LEcnM6l48R>w{^;tNw0ghoq
zBj+_ZJUPcu=HM8r-Q#izY|$XcG3-$h;wPC9SorHDh=REO*nAk!WUMi(MRHo4csL7U
z$Fz^4S-szWH<-Of`Vqu&N4Z2n(UW{v98|pxjcG`AP|W=&T5K(ByEE;{Ls$4wOTJNP
zTS8)yEbR4&H)eCN2a<(!r6cDhXnFy7K=?to_`%sGZHwQq_Mtjs&3lfV_*ozVA!h_k
zyXu?}*jkofrUh0gHOtB2qS$iG7}y%*MkUok*sT`Eo5H>p!d~&@R4l%p-y4bdH`Hd=
zWD=>hk?8tFHqsr<u7y;@51W>T#goZIPu3{(1#1yn9q&q{ST!H6mWr<vzU#x*5VrFg
zmF&`wuflepJk+J;2BH*Va2lJKU=;6l-t@!doVV_k@};1rs&}mO8y`Uinei#ZP6qRZ
zrJ76NkATCjp#XXwM_X=3WtdP0U!r=Y62snaGM%nNjfec`<a}dTPR2+>ojKTD&(qxX
znTgz*Md>a$_0cGJOSf)?VPB2K*ya3#A3YL4T_r&||FD#aF2)XVsaqj{RM=frMj3x_
z7#gx78C?y>DZ!Xj!`5~4Zr4eu!Q>NV>B##0UUFSL(X}QAd-IdPVR0$JI`QH2^}C!o
zyF8HJ^oU*SlWBv+=KL;2M9?&2=PFKd;hiO&lrTJa$M2O7%X_<(GWe0-2#c8GdC<K6
zR{RQ~XrwuK2&!HikN0RhUGZuH808g-nBYkLwr3o+`%!B?1rz&C^>#<%$#^&9A8^KG
zIqZWgV6cX=n$4J<H-^x=t#Cy7EUAd`I%ZWinB(uTX*k$K7xFd;nEcfPZ|lOkX-U!s
z1GEtx@2yvuknSQ;e@0&#9qi8GC{-@X!YOO#rWo69<eLLtjW`*)QUP@DimQc_O)Y@W
zg>^>=B`AHJ#o@szuGWC!LtxPIrUIh2gDu0;y#<&w{1uO#5!wqwu^2af>%JYw_j?|q
zmO@s|P4q2EFNvnSB26fy7HgXfgJ?If(~!0>#nz|z$sS4-GSlNSC=8(U&`2Sy7qk4L
zbL$AKXlkh{KZ%gfJDc>{DR;K%pmfPO?B*FJ48fFq(}hAA6=C&IHg<Wj*W_24=UUU@
zqLSZp5Lt+#%TXd39K9gt?QDaNPJ|bJwM8V4CW0udN^r}sGV@V6*zw~1=VCOJm?o?t
zCGd!PbEWZdD^LZ&jyWwJSCtSzrA1y`#R`OtzGnH!GQHMGk=FS<G=6qAo9Ifxk*NVV
zZFx2tDQRAj6{?PisCe+gN)1|wDzPvb2Fx0ixD3ZmL&FHe@U&4$1d400G$M5_8bUE-
zLM39XQc|dTu@})g3p|+-R%i>}tiK}DnFyL75da``rbOp?`_O1<2XYz9gN&-tK^?V9
z(xxbV{{fO6i*`45WumbJPQ4n_DL9@_C&G)FY`Dsg7O++$IoJS`cS22!5Q#-*lUZ7t
z4?9e0P}N=u^YRdR@`EW0+6SncVQ#HN$QX)RI6BV<(3!=f)1FC3V;!)qV*zE}>`Yfy
z87(bVOT`PdbaZ5nwk#O3WES;kf_W-Uya58e>PL%;r(rD77fGez4vdsyMCvk?7=%dt
z;Q*Rf{D^e#T2kt$10}CT8s-}UrBH0T-eN2al!gx_Q#z(8=CuX8oDMdGm0$!*;$2D^
z{3s}MHBh!g^6LS#q<C>R6c`M%p~9sZ{vaql%p{eT3L%aPrER%+5Xb@73YCC$-7E`~
zTJq9TC6r&%9|)8r6f$Dl(vV0!t9bR31{<x-MW%CG1L)M^ano1P4ZB{7C<wD*0HPqb
zw!PR;mQqFB$|QucaBF}VS^FI#>udbQu}VOv6tVS<0W_x=*|Ed|B?x$Fn`%))ZK9N6
zcEqh(cJB6aKbl<(T}TSX5<@{=JY{0w^~1%Wu_BR-E3gomjH{(!vsye&@cy6`;Bj(^
zo+PBs!X0dO%zy(<rH}=-L5Q(MKDq8;?)&;8QxGbnpvU?)#iF@g60KpBveO!;1%XG3
z)Er?$PTpNq;w%WvXB#M+*R-9G{&oPh7prH$MorU-iZ^tbC{EW16`gd=)!vT}V7b2-
zvgqpzB_OWXysD7BF8BG-`QFC6JpW!Sn*;jAZ%+KL06KRdu@!dN7b^$qfD@KP(fHCC
z!Kb*~Q0PZL3!s&yr>34;4JfD7M82IRZsgQO9mrMmwSSkCtw2}9W&n?r<&S_mY&$iO
zac}Gc2qqDxd&7qsWy4JmjHIZAkjbEd7}>gJ5564LL=OF_kw(**Aa)LH0nDK*L+L>h
z45)=s)Ii?mypz4tu0VhBqp5ijr-u@?U;073!musobRKsFsOwXpvik+z_oF6ngNC?-
z-JFpB{9$2)5fL>VM$C71Qv5PLt>{OPwmY!abQD*J81o#5H3ZI!#kkgy=rVM0Zcgy>
zaQ@Z{MsPjjN%mr3!bm#pWViI?k?yL4G@8&L^nksx`aY>b7P6l3qbaTjuE(DagQDj#
z1v}w^X|9zSz3T;YeO=1aVAUdJ!sSGy&B}3|AHD5GQ7m57{aArKssm4Dg2%+pJag!t
zfzNm`N+5b*1IV5o_ZmVe;&{D;DX(#l{tw{Tq`l@~HGm`L$=(InwO6sfJW!d8IPZlW
z?(x0bk3xCyW#_}WKtzm6+z!|f4x2c{@uC~p(CZ+&gtCHp(fzSo^wff{HS!*I+#j$y
zWFLZCKpgbVIz%q$;Ny4mbxm#wAfjXnF!J6iC4O6rFgC#*Shmu|&=evI7uSRtV&vYJ
zm!VhSW{bS2crlh%cBn4LY79V3COlp7cAb-~m@k=gO=5N%ot}TXCviDC;N+LgC|OAD
znmZ2G(%cCdw;j1XU;FoA0G((nLgub1CE>mn^4i`4lFM;`@YI3%%f|f<j`!x#<{Y9!
zbHkMC21#rzvGn%EBClC=c|AIJOE{Phd$(>L8V!6|M!;Vq)<K?*f%$gqaE-CMm+dl~
z2HX2dGb)tIV4n3QhoS_>1A{3Qj6sSf#@m&syWp~0TY(pdO2pfUX9^&d<c$jp!@OaC
zzuz(gWlXu~*yoLIJW#-(x{X@dPqdUH5O#a#ucJFhd;Ul;=)CVYRWvYiFYM*`?3BIU
znR)=7%94phUDQ1g%)ykKyCEYsh9io#E7Kxea1G&rzQLGo1(pa0Pwgd2CBb2dV7bj`
za+cfr{u2l^ZPBP^r0RalId|~F+C2mE;EUXGPTwfGt<1qUnUTaugyy!x4GKMw#F4j*
zm64J{)hmgF%iPSp@?&<eXy&gmmsQF)e{4P3fL^K&H=xYQZ%#2E;DIxd9rMXc%*rTP
zsatt$cHOro=WxZ7XDg8R>U$f*Xo)xQb55n;lG~R8Ae?qTSVA9T@{ynL6+!`aPrhNc
z+*{#1A%~5YxC=SVUlyf`*aHu&r_?Y8DcWXlPWv0)`JkVI{0cjZQP)0(-jP(+P%|1{
zr-Z9q$$#-|hP^i~Lw|6J_ssNT@m|P?_li?=&(!C3e2Ua}e*aE;B?Hz0>}OU?0?n@(
z+ROc7E$J~t!oA#=qu)3MLLxer*uy^XwBuQ`>S^r8kVHDWia>-5^nVvXt+p0f93~~F
zeJ;trttWofaJs^Lr&x)$?+}fN^_ff7X9?U|^}%~<ihE=Wb{X0S*5bfShTZ0wFhd61
zi**_Lvy){L(O~w3%O8sn71wMnjUgwLFGr6#&9`aFD4PklcfvL#Qu8v&r30dP-(%fJ
zVNML#`aJthl3!t+-hM92G;%|fY*fhJN0lQGY<t^9JDMZO7p+qxG%Yc(aWB~Acsa^m
zzeF@F_S!X}9IUk11rcInAO%=yEl;H409OtlYip$?JsVjfZ<ED}oK5CmMX{??q6`tT
z4|^jb_C3dKe&~%fl0-$84?EZ^5l!ZX@@0n7<ibYZN|AH8iUl|+^P??g=meKiCi2EH
zFLWh=`BHqwA);4HASd*w>v=OmFWj+9&uzITc?>OoMhJ&Z;8p0ayEkik*Z|Cd=h*G@
z5O`U~V;<tT6G^HLd<s~MP`PGwp0L3=1JP)`8hwQv`NtPLLsT#z&y#0Ron0T6yUz1t
z!)KEASI%7q*Xoc?PlhdixkPS*QpNsKZLw*X(s)67b!##W_g}9`13@xz{0w!pwW%=&
zm%_rYSiBEz#BH6kbY*Lk;p*%TcHoOh@O=scMAtR+x(2a%3rQVu;Hg<{dza2d2$6wA
z;SFl`>V`*R2^X1EE52ng&BQ%!Z{PQ&epJOeS1Rz8E+KWKgsduuqDS0lHf4{)xBO@*
z=@P36sJV8Xh>n)W?%?(!`kY3!!>#G|vK>Pc4P-(CC0%_;weQ6uWNt9x`E5TsxH$X}
z(lOIlptqsB4mf$_f}TR#X|F)$mO&x2xfdrgo9pVg&lE~#I4jObu5x5H_fu*zf0e5D
z()2o|41TC)?yJ1&mAdz@QOgD$gPh6w4-IJl7t{W;y{jA7)02B1$5_n0Jbje-&^^9|
zYc(~Z1RMG{p^QhA^6J(FsG8{b@(barvvT}X)vPJ>T<X3qK{cc=Xd0FQ{|!W5Z}1q)
z7$&oT5gj@Zy3|9zm<~Oc>5aqP7<iIAnuI$jRfGBl$0N<9?tUYcF8!2{7?M#cP~=M8
zInykX8I(%1Zrr`U#hrcSr7raEkh)7asSBB<4luIV*-|rrr$EcUn*uFn3IIlC3WQ2c
zfs4$MObh2??dMx<l1n4saFf{en){x{^=&?g<z}AM=-z2&^sDA>r*qwUUnAmH*PI8f
zt*5Os_dbK`-F)`PJZNwZk}XN@hTUiGcqZ4e{k#o1e#Rb_)AmsFbB^-OC;WS|7A_yh
z^=nUVtzXB{I_?O!(D`_-TYJG~r|pE@;{1T~ouxwSP^~F9XySS<=$xM$23MecRcN@-
z^Ae?+MaxU_E*i6`Jbih|aum`mj51MF?HQ_>3}crQ>nLP7xM=Q3F7*ymP*Rz7K+RUx
z9H?d^C~83rcId~((tgPuIPvOPjSJ&W@Mtt5qR+smd$hN1M=8pj-fS-2jaT^aRiwvG
zpFT4<7Wr2wqmUA+g-uGrzu*IY%dL^{qUKHh)*6^n9u5D=bf>muPcP%P@$s*8(+8fp
z_b<u!D)jG_pe^)Ucy*5$6!N3DCk9XN!5l+2-J9u%&+h3-ZXh3Y3r|ma3{ddHx@6l(
zpw$;#iYg-=$!IpK%tv#Tc9`UB4RbGHimG5Nl!1K^=NF~(45MtP4qcA3@BjC4ZZ1a+
z`T41gu&`L2RTLLgS5oAvR-ciG^0~ii%GxaRGp2$N{qh{VB%_+VraFC9A;a}3`0zk%
zFTCptGQKvE>cU5^4KH7MJy1{$?hUR=hNr31efU{q^b0tDWfljbN&~0hb9Du8MaL;K
zY!sXYeMKp?>(P}?tp{;*2g|IcS;jk=GV?DnQ<Iv9;;KtIaanIblvoV9@mloJ5;c|&
zw1lc#8X1tOD{MNovH>rx44k?y)75n$ny<{2t1E~dm{Ghdy>uSg^;k=%y#Kbb-drwG
zWeHzps@!IARNlBDQCLaOjomKm4T@ri)R|Vrb~Wr0s`)@ji%jX^)T~wM@p9L|DgAt1
z=}$zh%5k<zFE^zgLvPpPE1jYb>iGUg=BFk6lPPzLOu6$=U81Ox-lPgGt2ZbL-J%{N
zRcQH8OQ^)9k_4IJz9m!KX#=Xb?YiO~hh`|#%!(^aiWL=FyB=HVly=a@_D7k*O86#I
z*hWra-B4SitdgFj$||cjD9SobJ&IRWhhdgbQA@#nnUcchbgOrrKA=iEM_1D0(M)B!
zTuJ4Y&!cN~J-E_o>EI3S1DTpiI44unCX1Tpp|?a&C0$ANR90_L^mMv9*{Y}Vah6a~
zOCkU=O_k2(%otEj&6CNS)_;m}sIEs>I#nIS(Mjj3B)pU9DnD1{j^Yw!mGmW5R$0A4
zQPvsaT$STMOQ@}-kpY>y{!->xXAY>k&eI+13Fvrbrqr>*EP>nvdUUO>hgUj%9n9f<
zB6F@1?#UE3WOlCkX)e)NNoP`xmDL**jh(3mE$-EJq$O0@5{ZFKXZy?0C}TOOE0gZ+
ziNxYPS*3hQ`m`Q(;ws}qyQN_D2umd(ie<7&R!uVPD61x!q>xpUq(`!9lIToUP2v}1
z)g;2`jq_*?-J(S(P1YvqrciY>M_7Y3!Gce$zzK%K41P*pU6sG%>Ud6v?o~99$M3mX
z&ld4}Q>)QAs8(1uz^@0;$6Sklo&ok2^NkCyDU3K7Rzjn>bY?+3w<Nwk2Mb0POl0pF
zlm%U0>+VP0s8TqLBOrs@rbleb9FN$z?rt#}qMtP+f2g#3V`16-$?X6L<B;VS_QvBE
z#TE94-rxjOlhr<p0K>A%a8#qBFW5hBCEL{-Cm;jx671sW`bKCBZq7`kQ>BvuI2To^
zwXV?LDt{#!i?x=gJ9BV}fNH@+xR6;tGytpj>E2vVZ%*3_6lkgrx*BQ+6^Rf%pG8sP
zgu!~=%1y(#fw|e-3V3+~%U#913wxtUMf;_i*cS>;Ky`^!N4mQwnoF!s#v^10P9&bm
zq%-111UFry)pSfPbWB>W+>nq(zTLDd45<UL8{~{zbTsL1f#Kl|MEo92@m#-a1zL-$
zsl>w>2%TuGW1w0oh5j_8nK>ru@~5y&4@TQ>Yxbjawb#VSKKgFe7>P>FDM-kQL~K2I
zo8=Hxy*3^P|BjUx_JSA|!tSJ*&4c10J#rQ{M`0UJgi68Ny0|lx_M5QImp>>Tk~<>l
zgW?7<+JoXDzGpu?TwlIC0oIKC<OpO8-fSN2h_Ql7{4^@@q(x5Ptp?quB|*k*NZe8~
z5^s=`xWxmB4P>Y<n5K@AJ=z{I(H?Fi8Ed?J3n3wYiraF8aJ(cS(W&6#m3Z5oe(=Wo
zI9oJ8>4%GmsZud(Hc*j|y;+buTV&D*8Mttd;Mx;Pbwb_{V;f;Zvypy!lG~BaA(6ic
zk$@z)cjTm$fSjJn2`CDWEdk+bvcn7tT99$ePfn)g=(s#i)r)F)Y&ec`Y_njgIu9W~
zOXeZOcKO4Ibq=cnGWnZ10}UY=2ehF%40Y%#qus(Y4I8UAO;@5~9mi_9Rh#C)su{?r
zj0n66SEExn8uMq6Im)XQt8kv2pU?}rw)n$V2It(i^nMj0xjD_yCvZ8U#DIR8!3*2g
zU1sp=SdFTZ%SY64#zzr6f5BTq;X^!YA$%xJjOC8a#=kb(l!t7}TWrdwskN(2nXsy^
zGVGWc^YQkd!7J1Jr&dchf%~rIQ~0*~4VwjS(e|{_q~L94?pNMiucdpLZ4}AK@>_bI
zO_al60~#NRcElo`y{V2Iq}>tN51h-SlMyYs#mQhpS=D3J%a7~&QwXjn!v7|XJ>$>S
zS3i3B{PQZ_nhld7M<5jMNq4M)t?b!sJAzXzzJ~I%Dz821l%c2^4aveqHPKAAGB~|)
zhSq@Zv@<t<RQ-z=XbZ=nqtS4!g=j}dZzkHYfwj_jTe3}PCH3{`Z;mh1nt5Z(k<+So
zKk+RMkLxPY)s<*0;NRCAYg`-8q~gg)Q{$QhoX~-zJKgQSuBZwqRdC8?0{ky)c&!3j
zsXzO>Z|t5sckZaC7rnk)YqcuO;7yx0RjGm3^l}E@ymjl}KS{kp%SVM7+|bbQ-p;pP
zrscjcgLmxM@p5+Vk7;>rn87VAEjwEt{7=1{!O!g4^}SEVzNoj)V8HA0otHmH%L$$Y
zzG>^$w|@7lU9|jQ8-t;r9i5LpuD8!%Xm8{1u6$T8XE1zk>)vPY(c5Qm&$@N%ZhG?;
zy_~`QP~Nz_UoYq3H+)yNY4jWw#=kNA&Vd65rro$rFK6&`yLO#0{f|3nxi8G%*Y@t+
zd-L}nq2&kL7!3ISQ+@dfT3#Dw@clb>1i$y`GkQ6L_wC(#|J8>)ueZZspy!@f?tGD!
z`!L@L4DJ15SnH4Ub{IUZrR9^wul|_T_c0jyLD$6oORvx1Ngx3G{{9LrKiI}#=zsh-
z7rdsIGZ^G+@=@2n&e{(%81S0*(l6g&<vtD$cOCWLdON4UBpgDzz-KR?vgIU|>Pppp
zUFFr|CvDbr<(f+Ltx9w#)s@wWXg05=gewj_xEm;O&J}Opw_D@v!8Qi32T2(6^Sf!e
z&&Obp=o>cu^bWn8!M{3i;JlIBzps}w_>7e+ZybHwclGuej3u%0xNG(L46Yq9V#Jzr
zzowV#FqD71{)9FSPxwh;_}<tTf7`E@GkC?yl`DU}?mE4k!M{9k;IIQ<y-6=;FmOKm
zL6}Lh4@&}pVccgX=iI5+XE4y|gg?!@M=$5#`U@7`Ps<PD-vkE1xh!|YLwbD%1Lr^8
zc_h;aAC?3Hcf!9<j(SwD&tQ<CpNEcqTrX!ZSb|eB!6)@{27|&q^YAfG>*Wmo@WT(M
zemsR~me0pvp!aP}Q=irAGZ-vl^^=D_r<XJMz8yPWIJ1svqR+=*pvT6))xDtCXYea~
z_fGrnSY1PX3<i1mV1~L!ug~C*KKyX|e)T`~at=PfZyeL;gKcI_Irh>Mf)l8wyq|o2
zNcDys)s*Wi(Y2LmoTe!dvbgjs{f}S1Z#S0qjfd~utx4hdFoS_R+rv-)gqGKZ84Of<
zs$%6!dO3q()O%n4Xb&x)9OmG6uD$97y*~6qU~HFG9KrlVFw9`EGd0utnV*;*W-xr-
z^6X>GPfWt~2@L(8weU~OPlT|a)8V^j@1Xr28OGzoFxclsPu;(bmQM;ZxCaI}BeI#6
zH-#De9E|JW@3U?A`=CQ%244r-K5`P%x=CRU?*HrdyY%|-B?31AzVDv!AT6IBW-$ED
zcCKMs5yIsJhHe-AGV~O!-w<YSth4jTWuO0$mQM}y@NYVp)J_XyY%vVq`}2gKFzK9v
z+aWMmmAB5C%B1bcFoS^%Kl=6!%zsSAd?#=S;(%8_dztooWSGJK`r?c4qgBj*)P)%g
z{cN81;;Xd&DBLfB;rEH*QHK9uFmCU_eC9u@Nc$KDypG<u;Z52Oi5nQat?qv2SA1c!
zwoG{9>4QQHHtBJyEkX<i+TzNy)L&n}bvIbJH=euYhTWL9KHtGM244v=*sq(J?D%{P
z2H8!X7`&9$_xTvS5KLm%RcrKe2Hyj*!NhNO(6Rb_4E`|?>5R87(aRZJ-_Q_P^66E2
zIfKFSE&1&8>uLGHHU>j8xBTQ%CbK>tgTb=?@#czK^>!ExXpVn;&uw}+gMn8s-g<@M
zK^P45xZs-$@7C)x7<;@Pq{mJ^4u0}K_6nYbz<}?n+1D^#A(ouLP#zdP`C+|%27`>A
zQGKQ1aTpAt+`XUwVW(c7!Qe<g|M-;0^l}CRJ(m9NKEo3+7{-0)+ckzKV(_kAyZ*MX
zo9U>}$6%nxsW0v`JQRb0uD3qXXm}_F1D*bI-*rr<eLe<*?9bcwvEjKG3?6dPDMuTg
zi@|_b-=4ROat_{h(pAhhSUt<i={q-#qn@RH*0Cp5|K^UXwHOTC%H~Q`N76I5ZY4bJ
z4{z=Uj=wwZ(l>T9Rbem;?Xt45ERC6h(+>gz%jWNozDny)$7YAXFtkl~ZDH;yjKfU=
z1L<DQJ<r_JB9g9P7~D?H+>d{xwX^Mf?1l&oPIk%2uTb~2EfZ!i;I-wwrO(s)mxUP&
z{crE^|4=Kh`hUdzVHo-i2BJ@B<(J)s`z0`l;se{Bqi*Qdd%_G}0}XvGOw*NfcZ3;?
z(~7<?wrcJCV@H_5I6e91M{Bk6XYLF0@Qr0Rv=Ms#@xCzrjbR+bUi|`9#q#^Y42It`
z@A1>%?Dl(cIf21#?ySC@ivF^Du^T1uK?t7Kw(ru~KW=-N!4TZ8?7WbQRPx3!gW-E4
zzdM_{m4)BH?GRWQG2-=?MliRsF3ezP@0!ovrEcZ?7;c}ypkj-TeuSna&#fSC4#PM-
zIs3AG8a}?`!wd$Ij?KIGHCjFir$YpW{$D(A1alwt7#{+Id^Pmx?t`Se1O~h=z2;rr
zefT)|o$V*@r|nza%A#2#W{st)vL*WTi0a#qzD83O$m_4FL}N5napzMee)iOE5X5Jz
z_fdfYpTc0AZ5+JgvE78>K3|x@K(PPazhNgWKZyN1fgu|G-VaZs0toFe82Hz_@YDzN
z`V0n}v~%>|?xp3m#NT2VZ1czO-F}x|&R`JesSho=O)qCKjvM~*DHUX2Er}yAjI)y)
z7j2>SgJA}PkGegwkom;cunxZiBiVoOByGG6VIPG*`|!imjI%Cn)5>eZ42JxBmv7}3
zT3&_oaR!GwKi^8r>%#Co0z+Q=-fx#NUsfAtF!<g(>+Zgb)*lsSFjmx4|9P+8FM~Hj
z{`<Al9-!sp!wd$+=>7TW%s16xMIkVJZ~w;|nGdSP27tg=A%||Kis-8%3X0*YHf_3T
z(rawqz!zrlEij)m>mSV59BgASD8|`mPGUZ#7Ap#Yp9OmKEHQisgS$FAhtE5a`G~48
zgFzvmJ^ggUM=%)hOt0!RvK|huU%QdTl~$kf?sxvY`Y@^}XCK}(y!s!vP(|5Ni6FIC
z*_5B#WM%9LKgW|`d!D&_|87kf$m9}%!6{UoKkBD?IfKFaFDkqAO<G=uy#ax-mEZos
z>$H3lvHBPWnf>X>XTPSGGZ<p`mbb5FlWCK2l0;xovR(CEY%*;+p5!4g;5oM|{1R<v
z7Pe9Z1`*%;gR#^L`DSBlM_}k@<)?q4$xwed%wXJJ?@cTjnn&8lF#cZPRAwCJkajTq
zB-B6rpFg1e&I~gcdza(SXUaR1cpC;U9sPA$e-2g_ABM5lS#ZX+Z5o}ACte7{SjpD)
zu)wdKC>@6Jq}K!Apxy@XXE4V9D{r!Zs*T`}VGz<C->zo?Pb(H$0^@O&Jwb&K+F>xJ
z-wzM$q4<OeJu!^i?<;4?%52g;hQa!`G#$exyG|g<B8G84e>k0al_{iO41@LGa{4pO
zt4zgSi@*@DFM8lK=2dEOGD=`9Uqj!2lj2i_qY?rGntQtXeoD*9)CYt6_f-Fkm0OaP
zU)}q9hY*0xDZkblfVs_8&cEW0XLbYY7Ct(QiOxaXHG`Yp``J_YbM}wHb+wr%`EngT
zsfPI{?JE@i{o3tJ1W7rAU)vgfly8T@Prmf_Beb00!{BXy%{|Q5XYi(phdjiWGx(j`
zmoX71{WAEWe_gSIug~EAvv=Limos?j;~(A0movCtnRGi}&fs@`@zAY&IfMIe7|Z-0
z!H2>1r(SjgU!TGK75l%%moxae+}-_rxej0Vew;7&F?i?x&NhuB+D{7i&-zV2U(Vq0
zK4mj4C-i4<|AX6Z5b9I-oxjawew5T_a5(&`kt;&a3|>07<#xUu2KWE|U(94^^r7%W
an_o6^Mfill?=*df<%(9na&bfZmj44p)t)Z^

literal 0
HcmV?d00001

diff --git a/_mian_tensorflow_keras_.py b/_mian_tensorflow_keras_.py
deleted file mode 100644
index 6ac1ebc..0000000
--- a/_mian_tensorflow_keras_.py
+++ /dev/null
@@ -1,92 +0,0 @@
-import numpy as np
-import pywt
-import wfdb
-import tensorflow as tf
-
-ECGDATAPATH= "mit-bih-arrhythmia-database-1.0.0/"
-
-
-def denoise(date):
-    # Wavelet db5 level9
-    coeffs = pywt.wavedec(data=date, wavelet='db5', level=9)
-    cA9, cD9, cD8, cD7, cD6, cD5, cD4, cD3, cD2, cD1 = coeffs
-    # noice del
-    threshold = (np.median(np.abs(cD1)) / 0.6745) * (np.sqrt(2 * np.log(len(cD1))))
-    # take cD 1,2 turn 0 to denoise
-    cD1.fill(0)
-    cD2.fill(0)
-    for i in range(1, len(coeffs) - 2):
-        coeffs[i] = pywt.threshold(coeffs[i], threshold)
-    # get signal that before wavelet
-    rdata = pywt.waverec(coeffs=coeffs, wavelet='db5')
-    return rdata
-
-
-# get ECG data,date type and denoise
-# this function without return
-# use append take return data to pass data
-def getDataSet(number, X_data, Y_data):
-    ecgClassSet = ['N', 'A', 'V', 'l', 'R']
-    print('get' + number + ' ECG data')
-    record = wfdb.rdrecord(ECGDATAPATH + number, channel_names=['MLII'])
-    data = record.p_signal.flatten()
-    # use def denoise
-    rdata = denoise(date=data)
-
-    # get type of ECG data
-    annotation = wfdb.rdann(ECGDATAPATH + number, 'atr')
-    Rlocation = annotation.sample  # annotation.sample:get R
-    Rclass = annotation.symbol
-
-    # delete stable date near R
-    start = 10
-    end = 5
-    i = start
-    j = len(annotation.symbol) - end
-
-    # get NAVLR type data
-    while i < j:
-        try:
-            lable = ecgClassSet.index(Rclass[i])
-            x_train = rdata[Rlocation[i] - 99:Rlocation[i] + 201]
-            X_data.append(x_train)
-            Y_data.append(lable)
-            i += 1
-        except ValueError:
-            i += 1
-        return
-
-
-# RATIO=The ratio of the training set to the test set，usually is 0.3
-def loadData(RATIO):
-    numberSet = [
-        '100', '101', '103', '105', '106', '107', '108', '109', '111', '112', '113', '114', '115', '116', '117', '119',
-        '121', '122', '123', '124', '200', '201', '202', '203', '205', '208', '210', '212', '213', '214', '215', '217',
-        '219', '220', '221', '222', '223', '228', '230', '231', '232', '233', '234'
-    ]
-    dataSet = []
-    labelSet = []
-    for n in numberSet:
-        getDataSet(n, dataSet, labelSet)
-
-    dataSet = np.array(dataSet).reshape(-1, 300)
-    labelSet = np.array(labelSet).reshape(-1, 1)
-    train_ds = np.hstack((dataSet, labelSet))
-    np.random.shuffle(train_ds)
-
-    X = train_ds[:, :300].reshape(-1, 300, 1)
-    Y = train_ds[:, 300]
-    # cut test and train data from ECG data
-    shuffle_index = np.random.permutation(len(X))
-    test_length = int(RATIO * len(shuffle_index))
-    test_index = shuffle_index[:test_length]
-    train_index = shuffle_index[test_index:]
-    X_test, Y_test = X[test_index:], Y[test_index]
-    X_train, Y_train = X[train_index], Y[train_index]
-    return X_train, Y_test, X_test, Y_train
-
-
-class CNN_model_level_one():
-    def __init__(self):
-        super().__init__()
-        self.conv1 = tf.layers.Conv1d(filter=4)
diff --git a/_mian_tensorflow_twoLayerCNN.py b/_mian_tensorflow_twoLayerCNN.py
new file mode 100644
index 0000000..7daaec7
--- /dev/null
+++ b/_mian_tensorflow_twoLayerCNN.py
@@ -0,0 +1,113 @@
+import datetime
+import os
+
+import numpy as np
+import pywt
+import wfdb
+import tensorflow as tf
+from tensorflow import keras
+from utils import loadData, plot_history_tf, plot_heat_map
+
+#from ECG_read_weiyuqing_without_wfdb import ECGDATAPATH
+#PATH of this test
+Project_PATH = "./Number-Of-CNN-Layers/Two/"
+#PICTUREPATH= Project_PATH + "picture/"
+log_dir = Project_PATH + "logs/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
+model_Path_one = Project_PATH  + "model/ecg_model_one_layer.h5"
+#model_Path_one = Project_PATH + "ecg_model_one_layer.h5"
+
+RATIO = 0.3
+RANDOM_SEED = 42
+BATCH_SIZE = 128
+NUM_EPOCHS = 30
+
+
+def CNN_model_level_one():
+    leavlOneModel = tf.keras.models.Sequential([
+
+        # #four CNN layers test
+        # tf.keras.layers.InputLayer(input_shape=(300,)),
+        # # reshape the tensor with shape (batch_size, 300) to (batch_size, 300, 1)
+        # tf.keras.layers.Reshape(target_shape=(300, 1)),
+        # # the first convolution layer, 4 21x1 convolution kernels, output shape (batch_size, 300, 4)
+        # tf.keras.layers.Conv1D(filters=4, kernel_size=21, strides=1, padding='SAME', activation='relu'),
+        # # the first pooling layer, max pooling, pooling size=3 , stride=2, output shape (batch_size, 150, 4)
+        # tf.keras.layers.MaxPool1D(pool_size=3, strides=2, padding='SAME'),
+        # # the second convolution layer, 16 23x1 convolution kernels, output shape (batch_size, 150, 16)
+        # tf.keras.layers.Conv1D(filters=16, kernel_size=23, strides=1, padding='SAME', activation='relu'),
+        # # the second pooling layer, max pooling, pooling size=3, stride=2, output shape (batch_size, 75, 16)
+        # tf.keras.layers.MaxPool1D(pool_size=3, strides=2, padding='SAME'),
+        # # the third convolution layer, 32 25x1 convolution kernels, output shape (batch_size, 75, 32)
+        # tf.keras.layers.Conv1D(filters=32, kernel_size=25, strides=1, padding='SAME', activation='relu'),
+        # # the third pooling layer, average pooling, pooling size=3, stride=2, output shape (batch_size, 38, 32)
+        # tf.keras.layers.AvgPool1D(pool_size=3, strides=2, padding='SAME'),
+        # # the fourth convolution layer, 64 27x1 convolution kernels, output shape (batch_size, 38, 64)
+        # tf.keras.layers.Conv1D(filters=64, kernel_size=27, strides=1, padding='SAME', activation='relu'),
+        # # flatten layer, for the next fully connected layer, output shape (batch_size, 38*64)
+        # tf.keras.layers.Flatten(),
+        # # fully connected layer, 128 nodes, output shape (batch_size, 128)
+        # tf.keras.layers.Dense(128, activation='relu'),
+        # # Dropout layer, dropout rate = 0.2
+        # tf.keras.layers.Dropout(rate=0.2),
+        # # fully connected layer, 5 nodes (number of classes), output shape (batch_size, 5)
+        # tf.keras.layers.Dense(5, activation='softmax')
+
+        #take test for one CNN layers model
+
+        tf.keras.layers.InputLayer(input_shape=(300, 1)),
+
+        # ECG data cant add 0 in edge, will broken data ,take false answer. So we need padding same data in edge.
+
+        # take four 21*1 conv excitation function used RElu
+        tf.keras.layers.Conv1D(filters=4, kernel_size=21, strides=1, padding='same', activation='relu'),
+        # take four 3*1 pool,take strids 2.
+        tf.keras.layers.MaxPool1D(pool_size=3, strides=2, padding='same'),
+
+        tf.keras.layers.Conv1D(filters=4, kernel_size=21, strides=1, padding='same', activation='relu'),
+        tf.keras.layers.MaxPool1D(pool_size=3, strides=2, padding='same'),
+        # tf.keras.layers.Conv1D(filters=4, kernel_size=21, strides=1, padding='same', activation='relu'),
+        # tf.keras.layers.MaxPool1D(pool_size=3, strides=2, padding='same'),
+
+        tf.keras.layers.Flatten(),
+        tf.keras.layers.Dense(128, activation='relu'),
+        tf.keras.layers.Dropout(rate=0.2),
+        tf.keras.layers.Dense(5, activation='softmax')
+    ])
+    return leavlOneModel
+
+
+def main():
+    # get traxin test
+    X_train, X_test, y_train, y_test = loadData(RATIO, RANDOM_SEED)
+
+    # get model or create model
+    if os.path.exists(model_Path_one):
+        print(' get model in h5 file')
+        model = tf.keras.models.load_model(filepath=model_Path_one)
+    else:
+        # create new model(if model unexists)
+        model = CNN_model_level_one()
+        model.compile(optimizer='adam',
+                      loss='sparse_categorical_crossentropy',
+                      metrics=['accuracy'])
+        model.summary()
+        # TB make
+        tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir,
+                                                              histogram_freq=1,
+                                                              )
+        # Training and validation
+        history = model.fit(X_train, y_train, epochs=NUM_EPOCHS,
+                            batch_size=BATCH_SIZE,
+                            validation_data=(X_test, y_test),
+                            callbacks=[tensorboard_callback])
+        # validation_split=RATIO,
+        model.save(filepath=model_Path_one)
+        plot_history_tf(history)
+
+    y_pred = np.argmax(model.predict(X_test), axis=-1)
+    plot_heat_map(y_test, y_pred)
+
+
+if __name__ == '__main__':
+    os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
+    main()
diff --git a/noise_take_ecg.py b/noise_take_ecg.py
deleted file mode 100644
index bd4f428..0000000
--- a/noise_take_ecg.py
+++ /dev/null
@@ -1,31 +0,0 @@
-import numpy as np
-import pywt
-import wfdb
-from matplotlib import pyplot as plt
-
-#file error
-
-#use db5 ,level9 do deviose
-from ECG_read_weiyuqing_without_wfdb import ECGDATAPATH
-
-#from ECG_read_weiyuqing_without_wfdb import PATH
-
-record=wfdb.rdrecord(ECGDATAPATH + 100, channel_names=['MLII'])
-data=record.p_signal.flatten()
-
-coeffs=pywt.wavedec(data=data,wavelet='db5',level=9)
-cA9,cD9, cD8, cD7, cD6, cD5, cD4, cD3, cD2, cD1 = coeffs
-
-threshold=(np.median(np.abs(cD1))/0.6745)*(np.sqrt(2*np.log(len(cD1))))
-cD1.fill(0)
-cD2.fill(0)
-for i in range(1,len(coeffs)-2):
-    coeffs[i]=pywt.threshold(coeffs[i],threshold)
-
-rdata=pywt.waverec(coeffs=coeffs,wavelet='db5')
-
-plt.figure(figsize=(20,4))
-plt.plot(data)
-plt.show()
-plt.plot(rdata)
-plt.show()
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..094b32d
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,11 @@
+matplotlib==3.7.0
+numpy==1.23.5
+opencv_python==4.7.0.72
+Pillow==9.4.0
+PyWavelets==1.4.1
+scikit_learn==1.2.1
+seaborn==0.12.2
+tensorflow==2.10.0
+tensorflow_intel==2.11.0
+torch==2.0.0+cu117
+wfdb==4.1.0
diff --git a/some-test/noise_take_ecg.py b/some-test/noise_take_ecg.py
new file mode 100644
index 0000000..a30bdf5
--- /dev/null
+++ b/some-test/noise_take_ecg.py
@@ -0,0 +1,31 @@
+import numpy as np
+import pywt
+import wfdb
+from matplotlib import pyplot as plt
+
+# file error
+
+# use db5 ,level9 do deviose
+ECGDATAPATH = './MIT-BIT/'
+
+# from ECG_read_weiyuqing_without_wfdb import PATH
+# record = wfdb.rdrecord(ECGDATAPATH + number, channel_names=['MLII'])
+record = wfdb.rdrecord(ECGDATAPATH + '100', channel_names=['MLII'])
+data = record.p_signal.flatten()
+
+coeffs = pywt.wavedec(data=data, wavelet='db5', level=9)
+cA9, cD9, cD8, cD7, cD6, cD5, cD4, cD3, cD2, cD1 = coeffs
+
+threshold = (np.median(np.abs(cD1)) / 0.6745) * (np.sqrt(2 * np.log(len(cD1))))
+cD1.fill(0)
+cD2.fill(0)
+for i in range(1, len(coeffs) - 2):
+    coeffs[i] = pywt.threshold(coeffs[i], threshold)
+
+rdata = pywt.waverec(coeffs=coeffs, wavelet='db5')
+
+plt.figure(figsize=(20, 4))
+plt.plot(data)
+plt.show()
+plt.plot(rdata)
+plt.show()
diff --git a/pytorch_gpu_test.py b/some-test/pytorch_gpu_test.py
similarity index 100%
rename from pytorch_gpu_test.py
rename to some-test/pytorch_gpu_test.py
diff --git a/test_plt_show.py b/some-test/test_plt_show.py
similarity index 100%
rename from test_plt_show.py
rename to some-test/test_plt_show.py
diff --git a/tf_run_in_gpu.py b/some-test/tf_run_in_gpu.py
similarity index 100%
rename from tf_run_in_gpu.py
rename to some-test/tf_run_in_gpu.py
diff --git a/wfdb_use.py b/some-test/wfdb_use.py
similarity index 90%
rename from wfdb_use.py
rename to some-test/wfdb_use.py
index 9da84a0..4a68aa6 100644
--- a/wfdb_use.py
+++ b/some-test/wfdb_use.py
@@ -4,14 +4,14 @@ import numpy as np
 import wfdb
 import matplotlib.pyplot
 
-PATH = './mit-bih-arrhythmia-database-1.0.0/'
+PATH = '../MIT-BIT/'
 
 
 # file error with read_ecg_data(data) parameter data false
 
 def read_ecg_data(data):
     # get the data from the ecg data file and set begin and end points
-    record = wfdb.rdrecord(PATH + data, sampfrom=0, sampto=1500)
+    record = wfdb.rdrecord(PATH + 'data', sampfrom=0, sampto=1500)
     # return type record
     print(type(record))
     print(dir(record))
diff --git a/utils.py b/utils.py
index 814fd91..12eac22 100644
--- a/utils.py
+++ b/utils.py
@@ -10,7 +10,7 @@ from sklearn.metrics import confusion_matrix
 from sklearn.model_selection import train_test_split
 
 # from _mian_tensorflow import Project_PATH
-Project_PATH = "./Number-Of-CNN-Layers/One/"
+Project_PATH = "./Number-Of-CNN-Layers/Two/"
 
 PICTUREPATH= Project_PATH +'picture/'