1. Deep Learning
딥러닝의 구분
- AI (인공지능)
- Mimic human intelligence, 사람의 지능을 모방
- ML (기계학습)
- Data-driven approach, 데이터를 기반으로 무언가를 (기계)학습
- DL (딥러닝)
- Neural Networks, 그 안에서 뉴럴 네트워크를 사용하여 데이터를 가지고 무언가를 학습하는 세부 분야
딥러닝의 Key Components
- data
- the model can learn from
- model
- how to transform the data
- loss function
- quantifies the bbadness of the model
- algorithm
- to adjust the parameters to minimize the loss
- to adjust the parameters to minimize the loss
기타
- loss function을 줄이기만 하는 것이 목적이 아니라, 모델이 학습하지 않았던 테스트 데이터/실제 사용 환경에서 잘 동작하는 것이 목적..! -> 해당 parameter 값(weight, bias)을 찾는 것이 중요할 것
- 모델의 layer를 깊게 쌓으면 문제가 생기는 이유 또한, train error는 적게 나오지만, test data에서 성능이 잘 안 나오기 때문 (+ 이는 ResNet 등장 후 보완이 됨)
Neural Networks
- 인간의 뇌 구조를 모방한 구조
- 뉴럴 네트워크는 함수를 근사하는 모델(
Function Approximator) - 비선형 변환의 연속
Neural networks are function approximators that stack affine transformations followed by nonlinear transformations.
MLP(다층퍼셉트론) PyTorch로 구현해보기
- Evaluate Function 정의
Eval과정은with torch.no_grad():설정해줘야 함- 전체 Dataset에서 정의한
iterator통해, 돌면서Batch Size만큼 뽑아내며eval과정 처리 .to(device)이용해Batch Size만큼의 X 데이터/y 데이터로부터 예측 값/정답 값 정의view()함수 : 필요 시, reshape
def func_eval(model,data_iter,device):
with torch.no_grad():
model.eval() # evaluate (affects DropOut and BN)
n_total,n_correct = 0,0
for batch_in,batch_out in data_iter:
y_trgt = batch_out.to(device)
model_pred = model(batch_in.view(-1, 28*28).to(device))
_,y_pred = torch.max(model_pred.data,1)
n_correct += (y_pred == y_trgt).sum().item()
n_total += batch_in.size(0)
val_accr = (n_correct/n_total)
model.train() # back to train mode
return val_accr
print ("Done")- Train 코드
-
전체 Dataset에서 정의한
iterator통해, 돌면서Batch Size만큼 뽑아내며train과정 처리 -
[1] 포워드 과정
- (1)위에서 정의한
CustomModel의forward(self, x)함수와 (2)선택한loss함수(크로스엔트로피 등)에 배치를 돌면서피드포워드
- (1)위에서 정의한
-
[2] 옵티마이저 및 로스 업데이트 과정 (
backpropagation)- (1)
옵티마이저.zero_grad()로 값 리셋, (2)출력로스.backward()로 미분값 백워드, (3)옵티마이저.step()로 값 업데이트
- (1)
- code
print ("Start training.")
M.init_param() # initialize parameters
M.train()
EPOCHS,print_every = 10,1
for epoch in range(EPOCHS):
loss_val_sum = 0
for batch_in,batch_out in train_iter:
# Forward path
y_pred = M.forward(batch_in.view(-1, 28*28).to(device))
loss_out = loss(y_pred,batch_out.to(device))
# Update
optm.zero_grad() # reset gradient
loss_out.backward() # backpropagate
optm.step() # optimizer update
loss_val_sum += loss_out
loss_val_avg = loss_val_sum/len(train_iter)
# Print
if ((epoch%print_every)==0) or (epoch==(EPOCHS-1)):
train_accr = func_eval(M,train_iter,device)
test_accr = func_eval(M,test_iter,device)
print ("epoch:[%d] loss:[%.3f] train_accr:[%.3f] test_accr:[%.3f]."%
(epoch,loss_val_avg,train_accr,test_accr))
print ("Done") 2. Optimization
-
Generalization
- 일반화 성능을 높이자
- 학습 데이터 - 테스트 데이터 간 성능의 차이(Generalization Gap)가 적을 때를 지향
- underfitting vs. overfitting 용어와 관련
-
Cross-validations
- 학습 데이터 / 테스트 데이터를 k개로 나누어서, (k-1)개로 training, 1개로 validation 일부만 학습에 사용
- Cross-validations을 이용해 최적의 하이퍼 파라미터 값을 찾고, 이 하이퍼 파라미터 값을 가지고 모델을 학습하는 방법
-
Bias와 Variance
- 편향과 분산
- bias와 variance는 Trade-off 관계를 갖는다.
- Cost를 최소화하는 문제는, 즉, bias, variance, noise 세 가지를 최소화하는 것
- Bootstrapping
- 학습 데이터가 고정되어 있을 때, 그 안에서 subsampling을 통해서 학습 데이터를 여러 개로 만들고, 이를 통해 만든 여러 개의 모델/metric을 통해, 전체 모델의 일치성/불확실성을 파악하는 접근법
선형회귀문제(음성신호 데이터) PyTorch로 optimizer 비교해보기
- optimizers 정의
torch.optim라이브러리 활용해 선언momentum옵티마이저는momentum=(확률값)옵션 추가
- code
### 임포트 : import torch.optim as optim
LEARNING_RATE = 1e-2
# Instantiate models
model_sgd = Model(name='mlp_sgd',xdim=1,hdims=[64,64],ydim=1).to(device)
model_momentum = Model(name='mlp_momentum',xdim=1,hdims=[64,64],ydim=1).to(device)
model_adam = Model(name='mlp_adam',xdim=1,hdims=[64,64],ydim=1).to(device)
# Optimizers
loss = nn.MSELoss()
optm_sgd = optim.SGD(model_sgd.parameters(), lr=LEARNING_RATE)
optm_momentum = optim.SGD(model_momentum.parameters(), lr=LEARNING_RATE, momentum=0.9)
optm_adam = optim.Adam(model_adam.parameters(), lr=LEARNING_RATE)
print ("Done.")- 💡 인사이트
-
Adam
Adam은 짧은 학습 시간부터 성능(정확도)이 확보됨Adam에는adaptive learning개념이 반영된 접근법. (adaptive learning: 어떠한 파라미터에 대해서는 lr을 높이고, 다른 어떠한 파라미터에 대해서는 lr을 줄여나감)- 따라서, 똑같은 lr을 선언해주어도 더 빠르게 성능이 확보될 수 있다..! ✨
- Momentum
Momentum은 학습 시간이 조금 길어지면 성능 확보됨. 반면, SGD는 같은 시간까지도 성능이 확보되지 않음Momentum은 이전 배치의gradient정보를 활용해 현재 배치 턴에서 사용하겠다는 접근법- 이러한 점에서 미니배치일 때,
SGD보다 좋다..! ✨
- SGD
SGD는 데이터에서 큰 특징이 되는 파트 위주로 학습이 잘되고, 세부적으로는 잘 놓치는 모양새를 보임- 하지만,
SGD는 오랜 학습 시간이 흘렀을 때에는 더 좋은 성능을 보일 순 있다.
- 결론:
Adam/rAdam을 초기에 사용하면 어느정도의 성능을 짧은 시간에 효율적으로 확보할 수 있다..! ✨
54개의 댓글
Double your deposit with Linebet’s promo code BNB777! Claim a 100% bonus up to €130. Enjoy free spins, sports bets, and exclusive rewards today.code promo linebet cote d'ivoire
You make so many great points here that I read your article a couple of times. Your views are in accordance with my own for the most part. This is great content for your readers. 五反田 英語 アルバイト
POL88 adalah situs slot online gacor terpercaya dengan RTP tinggi dan game dari provider ternama. Daftar sekarang untuk nikmati jackpot besar serta bonus harian yang banyak. slot gacor
This article was written by a real thinking writer. I agree many of the with the solid points made by the writer. I’ll be back. jay rufer
Keep up the good work , I read few posts on this web site and I conceive that your blog is very interesting and has sets of fantastic information. agenolx
Really a great addition. I have read this marvelous post. Thanks for sharing information about it. I really like that. Thanks so lot for your convene. BATMAN138
Thank you for such a well written article. It’s full of insightful information and entertaining descriptions. Your point of view is the best among many. DeepL
This is my first time i visit here and I found so many interesting stuff in your blog especially it's discussion, thank you. sandibet
A very awesome blog post. We are really grateful for your blog post. You will find a lot of approaches after visiting your post. hptoto alternatif
A very awesome blog post. We are really grateful for your blog post. You will find a lot of approaches after visiting your post. pass prop firm
A very awesome blog post. We are really grateful for your blog post. You will find a lot of approaches after visiting your post. toto login
Thanks for a wonderful share. Your article has proved your hard work and experience you have got in this field. Brilliant .i love it reading. olxtoto
Thanks for a wonderful share. Your article has proved your hard work and experience you have got in this field. Brilliant .i love it reading. situs togel terpercaya
I’m going to read this. I’ll be sure to come back. thanks for sharing. and also This article gives the light in which we can observe the reality. this is very nice one and gives indepth information. thanks for this nice article... hptoto situs slot
Thanks for a wonderful share. Your article has proved your hard work and experience you have got in this field. Brilliant .i love it reading. sandibet
You make so many great points here that I read your article a couple of times. Your views are in accordance with my own for the most part. This is great content for your readers.olxtoto
Excellent article. Very interesting to read. I really love to read such a nice article. Thanks! keep rocking. slot qris
It was wondering if I could use this write-up on my other website, I will link it back to your website though.Great Thanks. Bulenox coupon code
Hey what a brilliant post I have come across and believe me I have been searching out for this similar kind of post for past a week and hardly came across this. Thank you very much and will look for more postings from you.gaspol189
It was wondering if I could use this write-up on my other website, I will link it back to your website though.Great Thanks. bandar toto macau
Hey what a brilliant post I have come across and believe me I have been searching out for this similar kind of post for past a week and hardly came across this. Thank you very much and will look for more postings from you.M88
I admire this article for the well-researched content and excellent wording. I got so involved in this material that I couldn’t stop reading. I am impressed with your work and skill. Thank you so much.situs toto
I admire this article for the well-researched content and excellent wording. I got so involved in this material that I couldn’t stop reading. I am impressed with your work and skill. Thank you so much.situs toto
I admire this article for the well-researched content and excellent wording. I got so involved in this material that I couldn’t stop reading. I am impressed with your work and skill. Thank you so much.situs toto
I admire this article for the well-researched content and excellent wording. I got so involved in this material that I couldn’t stop reading. I am impressed with your work and skill. Thank you so much.situs toto
I think this is an informative post and it is very useful and knowledgeable. therefore, I would like to thank you for the efforts you have made in writing this article.olxtoto
Thanks for a very interesting blog. What else may I get that kind of info written in such a perfect approach? I’ve a undertaking that I am simply now operating on, and I have been at the look out for such info. keluaran toto macau
Hey what a brilliant post I have come across and believe me I have been searching out for this similar kind of post for past a week and hardly came across this. Thank you very much and will look for more postings from you.keytoto
Hey what a brilliant post I have come across and believe me I have been searching out for this similar kind of post for past a week and hardly came across this. Thank you very much and will look for more postings from you.keytoto
Hey what a brilliant post I have come across and believe me I have been searching out for this similar kind of post for past a week and hardly came across this. Thank you very much and will look for more postings from you.olxtoto
Thanks for a wonderful share. Your article has proved your hard work and experience you have got in this field. Brilliant .i love it reading. olxtoto link alternatif
Thanks for a wonderful share. Your article has proved your hard work and experience you have got in this field. Brilliant .i love it reading. toto slot 777 login
Hey what a brilliant post I have come across and believe me I have been searching out for this similar kind of post for past a week and hardly came across this. Thank you very much and will look for more postings from you.olxtoto
This is my first time i visit here. I found so many interesting stuff in your blog especially its discussion. From the tons of comments on your articles, I guess I am not the only one having all the enjoyment here keep up the good worktoto togel
This is my first time i visit here and I found so many interesting stuff in your blog especially it's discussion, thank you.toto 4d
Thanks for a wonderful share. Your article has proved your hard work and experience you have got in this field. Brilliant .i love it reading. togel online
Thanks for a very interesting blog. What else may I get that kind of info written in such a perfect approach? I’ve a undertaking that I am simply now operating on, and I have been at the look out for such info.keluaran toto macau
I have read all the comments and suggestions posted by the visitors for this article are very fine,We will wait for your next article so only.Thanks! olxtoto
When your website or blog goes live for the first time, it is exciting. That is until you realize no one but you and your.kantorbola slot
Positive site, where did u come up with the information on this posting? I'm pleased I discovered it though, ill be checking back soon to find out what additional posts you include.situs toto 4d
It was wondering if I could use this write-up on my other website, I will link it back to your website though.Great Thanks. olxtoto login
Thanks For sharing this Superb article.I use this Article to show my assignment in college.it is useful For me Great Work.toto macau
Hey what a brilliant post I have come across and believe me I have been searching out for this similar kind of post for past a week and hardly came across this. Thank you very much and will look for more postings from you. olxtoto
Hey what a brilliant post I have come across and believe me I have been searching out for this similar kind of post for past a week and hardly came across this. Thank you very much and will look for more postings from you. jpdewa
It was wondering if I could use this write-up on my other website, I will link it back to your website though.Great Thanks. slot dax69
I haven’t any word to appreciate this post.....Really i am impressed from this post....the person who create this post it was a great human..thanks for shared this with us. olxtoto link alternatif
Wow, What a Excellent post. I really found this to much informatics. It is what i was searching for.I would like to suggest you that please keep sharing such type of info.Thankssitus slot
Wow, excellent post. I'd like to draft like this too - taking time and real hard work to make a great article. This post has encouraged me to write some posts that I am going to write soon. SoundCloud MP3
I wanted to thank you for this great read!! I definitely enjoying every little bit of it I have you bookmarked to check out new stuff you post. olxtoto link
I wanted to thank you for this great read!! I definitely enjoying every little bit of it I have you bookmarked to check out new stuff you post. toto macau
Great job for publishing such a beneficial web site. Your web log isn’t only useful but it is additionally really creative too.slot dax69
Positive site, where did u come up with the information on this posting? I'm pleased I discovered it though, ill be checking back soon to find out what additional posts you include. bandar togel terpercaya
Thanks for a very interesting blog. What else may I get that kind of info written in such a perfect approach? I’ve a undertaking that I am simply now operating on, and I have been at the look out for such info.olxtoto togel login
i read a lot of stuff and i found that the way of writing to clearifing that exactly want to say was very good so i am impressed and ilike to come again in future..http://wwscc.org/evinfo/pages/1xbet_promo_code_for_registration___sign_up_bonus_india.html