Skip to content

Labs for my NCTU course "Deep Learning and Practice"

Notifications You must be signed in to change notification settings

GuanBiao/NCTU_DL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

NCTU DL Labs

Environment

  • Ubuntu 16.04 LTS
  • NVIDIA GTX 1080
  • TensorFlow 1.0
  • Python 3.5 (Lab 3 ~ Lab 6, Lab 9, Lab 10, Final Project)
  • Python 2.7 (Lab 7)
  • C++ (Lab 8)

Lab 3

Implement NIN, all convolutional NIN and train on CIFAR-10.

Method Test Error
NIN + Dropout 10.89%
All Conv. NIN + Dropout + Data Augmentation 10.31%
NIN + Dropout + Data Augmentation 8.88%

Lab 4

Combine NIN with different activation functions, BN, He weight initialization and train on CIFAR-10.

Method Test Error
ReLU NIN + Dropout + Data Augmentation + BN 8.22%
Maxout NIN (k=3) + Dropout + Data Augmentation + BN 7.67%

Lab 5

Use VGG-19 to build an object recognition system, and retrain VGG-19 on CIFAR-10.

Method Test Error
Random initialization + BN 7.97%
Pretrained model + BN 6.94%

Lab 6

Build LSTM to perform the copy task.

Training length 1~20 Training length 30
Test length 10 99% Test length 20 85%
20 99% 30 99%
30 30% 50 7%

Lab 7

Add a hard attention mechanism to this code.

Attention BLEU-1 BLEU-2 BLEU-3 BLEU-4 METEOR
Hard 63.6 42.0 28.2 19.3 19.8
Soft 65.3 43.5 29.2 19.9 20.5

Lab 8

Build an AI to play 2048 through TD(0).

After 1000K training games, the winning rate is 0.974 (averaged over 10K test games).

Lab 9

Train a DQN to play Breakout.

During training, the game score obtained by the agent could achieve 65.

Lab 10

Apply DDPG to the pendulum problem.

Final Project

Real-Time Partial Style Transfer.

About

Labs for my NCTU course "Deep Learning and Practice"

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published