AI勉強会_Kerasハンズオン#1_分類

社内勉強会資料

Keras
Google Colaboratory

(修正中...)
- precision, recallの説明追加

Transcript

1. AI  
    #1 (classification)
2. Keras  
   
3.  $# Google%   Jupyter notebook$# Google Colaboratory (https://colab.research.google.com/)
   12!
   "
   GPU, TPU!
   Google Drive  &! … etc
4. Google Colab   PYTHON    Notebook  Colab!
5. (%"# )  :    !  : $ !  
   Notebook 
6. 
      $"
    !%
   
   GPU%
   # 
     GPU 
7. %# & ’shift + enter’    "$ !     
8.  $’!’ "  Linux   !# Linux 
9. ColabDrive&+ Google Drive!  
   drive" Colb)' 
   drive"%*  from google.colab import drive drive.mount('/content/drive') "(
   google.colabdrive !
   Drive.mount$#  Google Drive! 
10.   
     ' !# URL (&  ) Google Drive% "$ (1)
11. $ # %! & ' "
     (’enter’   Google Drive  (2)
12. E@$#%"! <; *(7- ?.=384 :E@ 96
     <;
    7 
    <;&'!
    Slack> 1, 
    PLAYGROUND /  0C   D5)+A -
    $# -
    2B  
13. ,89 Team Drives*(@2)/$#!7 "'  
    10Team Drives$#!5< (3:-  …) # [001] Install use items &% !.+  Team Drives $#!"' .+46 =;  >? # [002] Mount GoogleDrive # [003] Copy data from google drive # [004] Check directory structure
14.   Keras")* $&! 
     
     '&   % $  )*#(   )* $ 
15. :'<$  /1 !%   '<9
    '<7
    *)0 
     (C 
    F ) '<!%  '<93"
      
      !5 '<9
    > (,?) 
    '<  8) CF'<9
    A'<  
     D+('24)
    (6.  8) FBC;&C'<
    -= (@+ #E)
16. Keras PythonA 8<BNNW0!,01 +($"4*TensorFlow, CNTK, Theano ; ID-3)'!- @  CPUGPU6%.2&;@ … etc :>A =?7#&&/ (=?7   ) 59 (JH)  E : =?7 GCF
17. #$ # [005] Define constant value # [006] Make data file list # [007] Check dog data # [008] Check cat data   
    
    "   ! " ‘_t_XXX.png’ &(Train) ‘_v_XXX.png’  (Validation) ‘_e_XXX.png’ %(Evaluate)
18. +.0  )C57 ,? %98 /- %98%:=>E04 @) H*(:[1, 0], G*(:[0, 1] ,? ;F %98G or H OneHotVector )CA("$%&#!),? 6 2 %98'.(B1D ) numpy>E04<3 
19. !#'% KerasOneHotVactor -*' &#$  import keras.utils as ku class_ids = np.array([1, 0, 1, 1, 2, 0]) one_hots = ku.to_categorical(class_ids) print(one_hots) > [[0, 1, 0], [1, 0, 0], [0, 1, 0], [0, 0, 1], [1, 0, 0]] # [009] Make input and teacher data   "  (,cv2imread  Numpy)+ OK
20. !$ Keras!$ 1) Sequential " 2) functional API# "    Keras!$ "  2) &(  " 2)functional API# "'%  
21. #&
    ) %   functional API$ % input_layer = Input((64, 64, 1)) cv_1_layer = Conv2D(32, 3)(input_layer) cv_2_layer = Conv2D(64, 3)(cv_1_layer) max_layer = MaxPooling2D()(cv_2_layer) flat_layer = Flatten()(max_layer) output_layer = Dense(2)(flat_layer) *'("
    Keras !  
22.  Input&!    input_layer = Input((64, 64, 1)) ( Input(input_shape) #% input_shape '    $ "
23. Convolution!Conv2D1)  Convolution! cv_1_layer = Conv2D(32, 3)(input_layer) 4 Conv2D(filters, kernel_size, strides=(1, 1), padding=‘valid’, activation=None) *,- filters ( ) (30/%.-) kernel_size  - 5 #"+% strides  - 5 #"+% padding’valid’padding3 ’same’ 2('&$  activation
24. MaxPoolingMaxPooling2D.&  MaxPooling max_layer = MaxPooling2D()(cv_layer) 3 MaxPooling2D(pool_size=(2, 2), strides=None) ')* pool_size  *4 " (# strides  *4 " (# ,%2+$ . /5610-! 
25.  Flatten#   flat_layer = Flatten()(max_layer) % Flatten()      "! $& 
26.  
    Dense     output_layer = Dense(2)(flat_layer)  Dense(units, activation=None) 
    units  activation
27. 
      ! 
    
    Activate   act_layer = Activate(activation='relu’)(cv_layer) " Activate(activation=None)  
    activation
28. ;5F(%'- #! (%'- #!3D CB 14,"* (Input)!G.E7<,"*  9:input_shape==3A8 CB @?& $!6>/ 0/2 & $!)+%'( @?)A8  3D # [010] Define Network
29. 
     input_layer = Input(IMAGE_SHAPE) cv1_1 = Conv2D(32, 3, padding='same', input_shape=IMAGE_SHAPE)(input_layer) cv1_1 = Activation(activation='relu')(cv1_1) cv1_2 = Conv2D(32, 3, padding='same')(cv1_1) cv1_2 = Activation(activation='relu')(cv1_2) cv1_max = MaxPooling2D()(cv1_2) cv2_1 = Conv2D(64, 3, padding='same')(cv1_max) cv2_1 = Activation(activation='relu')(cv2_1) cv2_2 = Conv2D(64, 3, padding='same')(cv2_1) cv2_2 = Activation(activation='relu')(cv2_2) cv2_max = MaxPooling2D()(cv2_2) flat_layer = Flatten()(cv2_max) fc = Dense(2)(flat_layer) output_layer = Activation(activation='softmax')(fc)
30.  " 
    Model#  Keras  model = Model(inputs=[input_layer], outputs=[output_layer]) Model  !
    inputs (  ) outputs   ( )(  )   % $
      
31. ()'#  
    ! & '# model.summary()  +*$ from keras.utils import plot_model plot_model(model, to_file=MODEL_PNG_NAME) to_file "  dot ()%
32. !-  !-
    
       model.compile(optimizer=Adam(), loss='categorical_crossentropy', metrics=['accuracy']) " %&
    optimizer   loss metrics "
    [’accuracy’]( $ ,#' +*&
    crossentropy) 
33.  
    fit   history = model.fit(train_inputs, train_teachers, batch_size=20, epochs=100 , validation_data=(valid_inputs, valid_teachers) , shuffle=True, verbose=1, callbacks=callbacks) 
    train_inputs$*#! train_teachers$*#') batch_size  epochs  % validation_data&(# (!, ')) shuffle!   verbose$*!" (1 ) callbacks %()
34. + 
    "&  + model.save_weights(save_file_name) $+ &  
    ' )*%#(!  model.save(save_file_name) )* $+ &  
    , & 
35.  +  # [012] Train    
    !*
    Adam )'$
    categorical_crossentropy & % (# +",
36. +./, # [013] Check loss and acc  '  &#(3loss41
    acc41$  )%
    loss((3loss) %  
    (3
    )% val loss(*-loss) 5% 
     "!
    0(32
37. 0, 0,&
    "#$ +(  "#$ from keras.models import load_model model = load_model(model_file) !%-. '/  $ 
      model = Model(inputs=[input_layer], outputs=[output_layer]) model.load_weights(model_file) )'/  $ 
    
    "#-.* $ 
38. 
    predict   model.predict(predict_inputs) 
    predict_inputs  (  )  
        # [014] Load trained model    # [015] Predict (Train data)  # [016] Predict (Valid data) # [017] Predict (Evaluate data)
39. '43 51$
    
    (-".
    0 
    '43  ,
    #!///+ )*//&2 1% //&2
40. ,+
    #%3417  #%3417 0.68 
    !'" 5/ 2 3+-4+-Convolution&$*
    Dropout0.55/
    .6  ,+
    0.6 ()  
     
41.   
    Dropout      drop_layer = Dropout()(cv_layer)  Dropout(rate) 
    rate
42. ;JIL0
    '$)8H  
    "&*<F'$)G 8H"&*BK Keras
     Callback(!:=  64
    A;J-.  
    A;J1 lossE N28H
    </ Callback
    ;J+C%#M(O
    @3 %#M)
    ) 
    D97,  ;J(fit)5?callbacls>?@3 
43. #
    "
    ModelCheckpoint " import keras.callbacks as kc kc.ModelCheckpoint( filepath=MODEL_FILE_NAME, save_weights_only=True , save_best_only=True, period=1)  
    filepath (  ) save_weights_only   save_best_only  period  ! val_loss!   
44.  
      
    AutoEncoder  etc …
45.      Keras