From 6f2c8a9bf84f20742ab47b6181ce81cecd31a5b4 Mon Sep 17 00:00:00 2001 From: abhijeet1999 <38234788+abhijeet1999@users.noreply.github.com> Date: Wed, 17 Jun 2020 21:41:35 +0530 Subject: [PATCH 1/3] task3-4 --- Tasks/daily tasks/Abhijeet/image/index.jpeg | Bin 0 -> 6191 bytes Tasks/daily tasks/Abhijeet/task3.py | 195 ++++++++++++++++++++ Tasks/daily tasks/Abhijeet/task4.py | 32 ++++ 3 files changed, 227 insertions(+) create mode 100644 Tasks/daily tasks/Abhijeet/image/index.jpeg create mode 100644 Tasks/daily tasks/Abhijeet/task3.py create mode 100644 Tasks/daily tasks/Abhijeet/task4.py diff --git a/Tasks/daily tasks/Abhijeet/image/index.jpeg b/Tasks/daily tasks/Abhijeet/image/index.jpeg new file mode 100644 index 0000000000000000000000000000000000000000..aea8524cf569ce6d1eb67302dca6d47244c9cb8b GIT binary patch literal 6191 zcmbVwbx<73yY?)Lh2R9&EOxNPB{&E7;K2g~0xV9D1WgDoi$idCg2SQ-9$;}_oWMe` z06`N7mz?`MRp0l=ty^{9o_hP4e!Ac3nx2|h?iTLW0b(^JRV4rf0szo`1MZf9_rL>e z95OOeaxzj2030^#A|5fTv65);$%urjjo+za%N;^F#7LwR|4?yo<>`wxH$|M%S={SUnR z43OXgEg&*52m)Y`fWRc6yFP&KeuEfb(4W2jE0|ayFg6Ab?ma6>41mBGn3!N}Fb*d8 z&z$?&B;d!GSfuEmm>{fsikk$$z_>S!1;zybhX>soCVkA0sRI#^vvN`lBD|gkuYlD$RRS>X1Vr>Neuv!n3AO{!j|9$9;1cQmskV35oh={;|FyTf7Lm>Yv z1Wzd726sO*=ED8Yk}r7j$0!=Q+p*Cd^c$=Z@sxyKwU!ZoQHusIA>q6OGnJeREVU6g zrZ7Lb-tPnmxcaHllT_rEGJdto;&l3<1VAVo>ir8cl+hx>K!0Z zKVF^aplI^zhK6}cv9x^p7b7u*+mLd>{h0_F0EgLI-2vV>jrOAPx7R)oQ%__LHaoGS zlEIaFXdta&!mk&>5bZIfU)*qLryTi%ezLb<=pkND-v9K1h~$VNU@WT_RZO_`7-xGg zTwOmUf_u*9NQa(JwO0mH|%k~bmwLJoHa5;iiHg^`~-7lI3w(D{7?f@)p zut&j`EQ}@k;b_-&MG{&u)-5iC`Y9e$HhSubx6Tb8I-`k8GNI&icGy}nPYNfFa9^C+ zPvs%Sk=i1i)J%PM`oW-zd|t5P;nlRbe-bIo;C2Ho%i6dk0{#$JY&Ms-Z0lYBdoz$;c@_?u<^-61N<=lt3HUQZy$~ zsRAN2Vx|*_gO$`6Eg!WH)2v5p@?!9dJAm^^pGY)dqrUn>VxW*z9j^Y$!g1b~zq-3B zBB=-KXL?IUm`2_EDaXkdHth6K9Xrgo7n&NZB8l8rQzv(To5G+xtU}WA;Pt>+9m(Rl zM9S6s07?UOnc}CxsMvr$VmZ-s)T8AQ30pQwslo7+njZ&M0UC3Yv4MUmfjLCp2Uiy_ ze~BUO$M1lw89=K-LB^#wdaKoOCTq$Bor-Y5WrFh=p}t+E(VHcO7d;!_Vh}u7>gWlJl0WhFM0Y;OAV>uP417X%n7h=KxJr&SRF;m3qi z!v$?ZF@!4NOT+k&?u*_PE@Wj15@4J}_=d*w%_1Lc)9b2nE;kQ&ezCQhs!DX0l_GW! zL9hoj`o=Iui6OIml8284N3%fl`)<4VOh|7xV%PinqdbmcSY^6Z{unVE=6Gph7+pqM z8*3_!<&gV_tAJ5^PZc+a^N`0glwt~K-|HNE2HzgG01;)}_Q(+$DQ}APW3e0$-0Psu zOieY;B-Lp&5_HXYn~HdMaeJmG8@zyKl`VWZBjZ0jP2TXAe}RigD-2+a=-CrM<2gAO z331Gnv_ff%P1FR*FsaFYlq z&Q)LWtt^ph`8eNeBPZ-jKb!C?I)oX#+0}Ca zkGI#ujU%UR;{+Ewmu~<~Nh$VJ32hU&^T895`BpP{1b<9`+G_XuQwJL_eclRAeM}Vo zh-+)^D`WfK87*xM^ZBE$&fmpP_~m#sgW!Em#bMh__k-}9T3TUYN`79>&c9{RyOA|pU*TQ98s>$h-ObexgA>Q%f2p3q4L1fLCMB8 zhQYeg00Fxn#OOraSs03!%T799O@Du3B<-Qv
    Z_45C5a#EPG5kz_0O~O+S`=4?% zc2<-ZtZ7b;S_h}gQrLT+6%tx4CPs2Jdjh_9ZG0+A2f&WaAaiP2H2143khBWQ}lSsL~V3*Sr&L?s}o59x;|p z1rz%t3L3_SzS+5-nSHT;8=3e^-T@m5D`C<&qc26Pxp}s+9=+OLLU?op)gfVFwHJ6o zcR+F_-qF@XBo^%L5fytb!0eRmRSw&8A6?U^fSFk$(_xd zGQ8N}dA<@<;39E3;&lxQgp*%rJ8RY2Dx>Q0t0ZinWq5+w_s|ni4T8nl`3|svl@Gqy znzwyp5)z}$Wjs3ed7#k=45dM{ zhU+IZbVN``SVb(?6rZMYpB2@gu1y)4n69lq@tIOE}(8w>WuNs zn)<>cKE(44Hpm5)c&LbEdMDqKVEthC@1+o=38QfLs|Yq%G*7F+i>QnOcNccs^s5l! zOCr0u$bAiBpLfjJzs;wK(&tL%;z)G*(%3yELZ9DzY4k4IR>I`D;8s%JREt z&Ial1wpG>iRC#gaE2eNxKCZGsID}J)BM)Io9$k8&FY%9HLFJUd4uG!(9GUfGxM#kTPd2y-|Iqa_b_=`gj|bx+cq+1r~_ zpyUfDVs5?z#NQaKM1c@dO|;>jwi{J8>q5Uqo%V^a^7?O$R6lg3Xecq0#rFDHJSgBy zqnN}enAbe(=1C`X^HjygJt&v4e`1%VC^o|}Q!pGKw8W+Ya~_e4e^XxN7HvX#Mz_s! z9yGo4qy%5L0*wL-G;<`{{~KfVolz9lTbvOXhM!f{;Ts^RC#O5J3MrqlTc-S zDF?W8CCz$Ruz75|sf%lDk6}+`E!1gK@r$bh|2#Kq(YR)$p0SdgL*~!JpdrWMUB3w* z(H%^l?`~w0UB7SUjN6k6704Coeks>~+>jK;9Ar}3gT6F%d$c@TAm6^IXU(aex(qW= z85K2*5bAHdsW|Owkl*n32`O@G@t&f;!gY#K=-}DWV zk@vLVD@SUFOoBPwTHwems!hd>pQ|f>GuXb_W#h~F{zLTUs6rQSAyxHGeaS#{?&It7&3*=z7ef%5mGBBVdQkdN6O#$D ztkdPMfwh8emwb{HzT_q$hEFNUHFhS0?eUD{*^LOHqD6beJY-NnS7b<}T(}c6n zWg#|2Wgn#I)E)SH9~}OLY?BpV5>U{%hR)NfKa48XoY|)^$nSH`KeWPrc4!EIJCRTe~%%b=Qpo$2T&}lXI#t%n3yQ2 zxOoy3H^AOu(js41Z653P7H>~sE*^P;C@xa7mED+Rv0rm`BxaV=^MBH^Y1jN+k=?jf z0abrQ^aX2ezF#2o<1}F{L|wiH zu~J%hOOEZ3oZ9RV&mk84qi+X?ng>?R_bTy;ieRnYx9#>%y7UU(2D>`5A^0T^=&ip? z*_6sQwI#bKoKebfVL7?|G%ao;(!G50b}-KeS6WNQQ8!4O;A|!^&J_PWMtqBOm8ram zf27PWwV55V)?}RIKM@~j7lJA4)!GYQP~N0uh`IyV2VgdIM31H4>dXR&5^Yn32H4V< z4;HV!R*)~8F>_{TW9wO7rGzb;jUI`fo1PR2DXn~b^U?ER%yfiX?(0vAGL$j;--BfOVILDp3#GoTmV^)st#Lb(lXoHBbDl}+PxPpca7Lr z=;3w_BXMm$HzIn+$SH}k1u|##X*)tC-uHJ{=re#h6mp$2b%5HP5z* z$iq@+;CnxX21ogav-ySXcgz=Us|~$spMtGVJkPJkyM3KSYE_x1_O%K{62JC5voiST zG}3y1jK=G0rNqN7R*#n=B-?K0nZrgc)$#(MRDwI`t}tXz81v$M5n3egGW{#P;__2S`G8&9;zkXd= z(WI#bQ(-t0FTCcHh(~Gn?9EggE%AK|3t_3HhZII)yil1F*~zcL z53Aca8*jTLaQ4r6KHlKAnSM~X>DDJs-!lfN(*O=L5E@OCrn!zF!6)IsoA=Umqo4sV zsTv8gm-;1F>7?9F#>b^BBu;F@S$guzKV32vP8?%335f&bemoSToC+i?t9rmxOFW?( zf6R>|t9qZ3k16V;ds~AQ)sl;wsCwkQczPouX^41&*|y|_T2n=0*-|CNXktNUBlpzP zb+dIRUpeq9#i9{aXSw(95tdmATR{Po7NIvoVKx~Pu{j+&GnlpAOnYFMf-}VWROkm~ zY?XKt^QXb?%w2)B{ExjffqJd`?BRPX(aqrbf8YO%?lm3@&O@ur$4 zBwQXMS?c|1X{=I3Ne9Z|r;cS-MzaFjyd)-T0W*-1xSQD%MO`~|7u|z%Lx#aC z*Vz8SbS8K~wLQOkU447S@!VSar-Cr$e$w!AlfgTHI2R4--8I}<2>;2jUJcDN;bkavD6aeJY2>>5&Z#BI2z{~21OOvHPYV-ba) z$cn9Mx(^HsTh`40KX~qI7+clUM#MnQ;~xJ(8B<1s2AKkrhd7(w1v0w>@O%Sa>BPaU zh7SXC;-UiDUpUX1X|>fGk@37JS3L1m1Yg(RU$}7F+#0HLH|b~yjOZl-ewYXxbk9`y z$%5feb|hBh6^E6b(~Jk$QNMucGU4ni+p!I4LyCi%4(LS}qE{j`FL=6zOg_2=ZO-x< zs*W+LBp&eFw9+3;=QvY^GB6WH1h2@3we}aOQ1E?qZ%#za&1jL9vjwnhpRKBtO<-3W zEsvGipAs=%5k|*Kb62aP7V%3s8zt0fb{()#UL<{T^GLtWc}3H{@8yb(WmdU|=DmG~ zyjG7#v8JY(?6W_2?e7@JIU5`a?NOCHprJhqX|CCGiybveyws=ck^4$YL*Q> zwm(1q$*Y`F>)$*bCoh5owCoGV1TUGV@-RO=MArD01>i(BC!M8O#lC2~w){S6AmqRr zZoR|{g-%^aQFFR3fBZZ@tJrdQY{E~@ZR7D+p_iWZVE23C08>hnoN>yCjjVr5TT)u@ zI(>gifT&z(S2|OAtzo0#2h=vTgc-D#4BmM2E;kYF&!pAuH2TdkTr_93Bb7sx zn$0m*mAG67tBwpWr$Hu?V6o-uJKisRbve5A8!Nq8u#V)sd*?#NBI&WOoA2-dpOf;& zPx9{=zsZ_M)K>&0=S64K9jR+DO^LhlblP&WT$QW)MkF&Dz7x}eB-Z{~DMSq4aV zTikuXS!UV?rn`8{l-h{FIt4Cy`QFQt-<7qSiM}!P)we8(MT*A_<3- zPC=(Yw5H>2^9D+$oF@d~a7E4rU#CW!B{%(MYP=qtj`})~7qx+$VbWW^XW!0bD!$qq z5U`N@ZFJaWw8;@4o4j<%yZO76n@3>Tv&7Vn5Hz{8SysnQHf!n|*=8OvtFBSO&uM5W z>Jp0}ZB~B7^Gt$N`k@V+bbkx_fQS^QqT&SSr{*1ywxxfdz6yR7xoS6A|28+MXze;s zk-vHp3GW%kR4~=B`u}Q0|9+1DDH~y}g)^2EW(2Nx8=[2, 12000] loss: 1.811 +Test Accuracy of plane: 50% (502/1000) +Test Accuracy of car: 49% (495/1000) +Test Accuracy of bird: 15% (157/1000) +Test Accuracy of cat: 15% (151/1000) +Test Accuracy of deer: 36% (362/1000) +Test Accuracy of dog: 22% (222/1000) +Test Accuracy of frog: 49% (495/1000) +Test Accuracy of horse: 34% (348/1000) +Test Accuracy of ship: 52% (520/1000) +Test Accuracy of truck: 42% (426/1000) + +Test Accuracy (Overall): 36% (3678/10000) + + number of output channels=16, kernel size=5, learning rate=0.01 epoch=2 +final loss ===========>[2, 12000] loss: 1.255 + +Test Accuracy of plane: 60% (609/1000) +Test Accuracy of car: 71% (719/1000) +Test Accuracy of bird: 45% (453/1000) +Test Accuracy of cat: 44% (445/1000) +Test Accuracy of deer: 46% (469/1000) +Test Accuracy of dog: 42% (423/1000) +Test Accuracy of frog: 68% (681/1000) +Test Accuracy of horse: 65% (659/1000) +Test Accuracy of ship: 66% (660/1000) +Test Accuracy of truck: 34% (344/1000) + +Test Accuracy (Overall): 54% (5462/10000) + +number of output channels=16, kernel size=3 learning rate=0.01 epoch=2 +final loss ===========>[2, 12000] loss: 1.270 +Test Accuracy of plane: 63% (632/1000) +Test Accuracy of car: 74% (747/1000) +Test Accuracy of bird: 41% (419/1000) +Test Accuracy of cat: 36% (366/1000) +Test Accuracy of deer: 61% (610/1000) +Test Accuracy of dog: 30% (306/1000) +Test Accuracy of frog: 74% (740/1000) +Test Accuracy of horse: 62% (624/1000) +Test Accuracy of ship: 62% (621/1000) +Test Accuracy of truck: 49% (491/1000) + +Test Accuracy (Overall): 55% (5556/10000) + +number of output channels=32, kernel size=3 learning rate=0.01 epoch=2 +final loss ===========>[2, 12000] loss: 1.170 +Test Accuracy of plane: 64% (644/1000) +Test Accuracy of car: 67% (673/1000) +Test Accuracy of bird: 37% (376/1000) +Test Accuracy of cat: 59% (593/1000) +Test Accuracy of deer: 60% (603/1000) +Test Accuracy of dog: 38% (381/1000) +Test Accuracy of frog: 70% (706/1000) +Test Accuracy of horse: 64% (646/1000) +Test Accuracy of ship: 70% (707/1000) +Test Accuracy of truck: 72% (728/1000) + +Test Accuracy (Overall): 60% (6057/10000) + +number of output channels=32, kernel size=3 learning rate=0.01 epoch=4 +final loss ===========>[[4, 12000] loss: 0.966 + +number of output channels=32, kernel size=3 learning rate=0.01 epoch=4 batch 5 +final loss ===========>[[6, 10000] loss: 0.799 +Test Accuracy of plane: 60% (606/1000) +Test Accuracy of car: 83% (831/1000) +Test Accuracy of bird: 49% (498/1000) +Test Accuracy of cat: 38% (385/1000) +Test Accuracy of deer: 71% (712/1000) +Test Accuracy of dog: 69% (690/1000) +Test Accuracy of frog: 73% (733/1000) +Test Accuracy of horse: 68% (682/1000) +Test Accuracy of ship: 80% (808/1000) +Test Accuracy of truck: 65% (651/1000) + +Test Accuracy (Overall): 65% (6596/10000) + +number of output channels=32, kernel size=3 learning rate=0.01 epoch=4 batch 5 with padding +final loss ===========>[6, 10000] loss: 0.718 +Test Accuracy of plane: 68% (689/1000) +Test Accuracy of car: 64% (645/1000) +Test Accuracy of bird: 57% (573/1000) +Test Accuracy of cat: 48% (481/1000) +Test Accuracy of deer: 58% (588/1000) +Test Accuracy of dog: 63% (633/1000) +Test Accuracy of frog: 83% (838/1000) +Test Accuracy of horse: 65% (653/1000) +Test Accuracy of ship: 82% (829/1000) +Test Accuracy of truck: 75% (755/1000) + +Test Accuracy (Overall): 66% (6684/10000) +''' \ No newline at end of file diff --git a/Tasks/daily tasks/Abhijeet/task4.py b/Tasks/daily tasks/Abhijeet/task4.py new file mode 100644 index 0000000..95ab717 --- /dev/null +++ b/Tasks/daily tasks/Abhijeet/task4.py @@ -0,0 +1,32 @@ + + +from torchvision import transforms +from PIL import Image + +import torchvision.transforms.functional as F +import torch + + + +transform = transforms.Compose([ +transforms.Resize(255), +transforms.CenterCrop(224), +transforms.ColorJitter(brightness=1, contrast=1, saturation=0, hue=0), +transforms.RandomVerticalFlip(), + transforms.ToTensor(), + transforms.Normalize( + (0.5, 0.5, 0.5), + (0.5, 0.5, 0.5) + ), + + +]) + + +img=Image.open('image/index.jpeg') + +img = transform(img) + + +a = F.to_pil_image(img) +a.show() From 4ad27a4a4da56350c2e546b03242f6918a0224b6 Mon Sep 17 00:00:00 2001 From: abhijeet1999 <38234788+abhijeet1999@users.noreply.github.com> Date: Wed, 24 Jun 2020 22:41:03 +0530 Subject: [PATCH 2/3] Update README.md --- projects/README.md | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/projects/README.md b/projects/README.md index 407e4cb..05b181f 100644 --- a/projects/README.md +++ b/projects/README.md @@ -1,2 +1,16 @@ -# Projects -Student projects once finished will be pushed to this monorepo as well! +## Project +# Indian Sign Language Translator + +## Problem Description +The barrier of communication between deaf, mute and others who do not know sign language, as we generally need a translator for understanding their language. +We propose an app which can convert sign language in real time into voice or text + +## DataSet +Dataset will be Indian Sign Language from internet and other sources + +## Model +It will be combination of CNN and RNN + +# Team Members +## [Abhijeet C](https://github.com/abhijeet1999) +## [Bharath T U](https://github.com/5hade5layer) From 4e057648f61d32d8fd190bc7481fe0e56da23f75 Mon Sep 17 00:00:00 2001 From: abhijeet1999 <38234788+abhijeet1999@users.noreply.github.com> Date: Wed, 24 Jun 2020 23:01:10 +0530 Subject: [PATCH 3/3] Update README.md --- projects/README.md | 15 --------------- 1 file changed, 15 deletions(-) diff --git a/projects/README.md b/projects/README.md index 05b181f..dcef38a 100644 --- a/projects/README.md +++ b/projects/README.md @@ -1,16 +1 @@ ## Project -# Indian Sign Language Translator - -## Problem Description -The barrier of communication between deaf, mute and others who do not know sign language, as we generally need a translator for understanding their language. -We propose an app which can convert sign language in real time into voice or text - -## DataSet -Dataset will be Indian Sign Language from internet and other sources - -## Model -It will be combination of CNN and RNN - -# Team Members -## [Abhijeet C](https://github.com/abhijeet1999) -## [Bharath T U](https://github.com/5hade5layer)