📑 TensorFlow Workout 01. Classification

tensorflow_01.html

📑 TensorFlow Workout 01

Code Modules

xxxxxxxxxx

 

1

!python3 -m pip install tensorflow_hub \

2

--user --quiet --no-warn-script-location

3

#!python3 -m pip install tensorflow==2.6.0 \

4

#--user --quiet --no-warn-script-location

5

path='/home/sc_work/.sage/local/lib/python3.9/site-packages'

6

import sys,warnings; sys.path.append(path)

7

warnings.filterwarnings('ignore')

8

import tensorflow_hub as th,tensorflow as tf

9

import numpy as np,pandas as pd,pylab as pl,h5py,urllib

10

import tensorflow.keras.callbacks as tkc,\

11

tensorflow.keras.utils as tku,tensorflow.keras.layers as tkl

Language: Sage Gap GP HTML Macaulay2 Maxima Octave Python R Singular

---

Messages

Image Data

xxxxxxxxxx

 

1

path='https://raw.githubusercontent.com/'+\

2

     'OlgaBelitskaya/data_kitchen/main/'

3

zf='Flowers128.h5'

4

input_file=urllib.request.urlopen(path+zf)

5

output_file=open(zf,'wb')

6

output_file.write(input_file.read())

7

output_file.close(); input_file.close()

8

with h5py.File(zf,'r') as f:

9

    keys=list(f.keys())

10

    pretty_print(html(

11

        '<p style="color:darkorange">'+\

12

        'file keys: '+', '.join(keys)+'</p>'))

13

    images=np.array(f[keys[0]])

14

    labels=np.array(f[keys[1]])

15

    names=[el.decode('utf-8')for el in f[keys[2]]]

16

    f.close()

17

N=labels.shape[0]; n=int(.1*N); shuffle_ids=np.arange(N)

18

np.random.RandomState(12).shuffle(shuffle_ids)

19

images=images[shuffle_ids]; labels=labels[shuffle_ids]

20

x_test,x_valid,x_train=images[:n],images[n:2*n],images[2*n:]

21

y_test,y_valid,y_train=labels[:n],labels[n:2*n],labels[2*n:]

22

df=pd.DataFrame(

23

    [[x_train.shape,x_valid.shape,x_test.shape],

24

     [x_train.dtype,x_valid.dtype,x_test.dtype],

25

     [y_train.shape,y_valid.shape,y_test.shape],

26

     [y_train.dtype,y_valid.dtype,y_test.dtype]],

27

    columns=['train','valid','test'],

28

    index=['image shape','image type',

29

           'label shape','label type'])

30

fig=pl.figure(figsize=(6,4)); n=randint(1,100)

31

for i in range(n,n+6):

32

    ax=fig.add_subplot(2,3,i-n+1,xticks=[],yticks=[])

33

    ax.set_title(

34

        names[labels[i]],color='slategray',

35

        fontdict={'fontsize':'large'})

36

    ax.imshow((images[i]))

37

pl.tight_layout(); pl.show(); display(df)

Language: Sage Gap GP HTML Macaulay2 Maxima Octave Python R Singular

---

Messages

Helpful Functions

xxxxxxxxxx

 

1

def premodel(pix,den,mh,lbl,activ,loss):

2

    model=tf.keras.Sequential([

3

        tkl.Input((pix,pix,int(3)),name='input'),

4

        th.KerasLayer(mh,trainable=True),

5

        tkl.Flatten(),

6

        tkl.Dense(den,activation='relu'),

7

        tkl.Dropout(rate=.5),

8

        tkl.Dense(lbl,activation=activ)])

9

    model.compile(optimizer='adam',metrics=['accuracy'],loss=loss)

10

    return model

11

def cb(fw):

12

    early_stopping=tkc.EarlyStopping(

13

        monitor='val_loss',patience=int(20),verbose=int(2))

14

    checkpointer=tkc.ModelCheckpoint(

15

        filepath=fw,verbose=int(2),save_weights_only=True,

16

        monitor='val_accuracy',mode='max',save_best_only=True)

17

    lr_reduction=tkc.ReduceLROnPlateau(

18

        monitor='val_loss',verbose=int(2),

19

        patience=int(5),factor=.8)

20

    return [checkpointer,early_stopping,lr_reduction]

Language: Sage Gap GP HTML Macaulay2 Maxima Octave Python R Singular

---

Messages

Model Training

xxxxxxxxxx

 

1

fw='/tmp/checkpoint'

2

[handle_base,pixels]=['mobilenet_v2_100_128',int(128)]

3

mhandle='https://tfhub.dev/google/imagenet/{}/classification/4'\

4

.format(handle_base)

5

model=premodel(pixels,int(512),mhandle,int(20),

6

               'softmax','sparse_categorical_crossentropy')

7

history=model.fit(x=x_train,y=y_train,batch_size=int(32),

8

                  epochs=int(1),callbacks=cb(fw),verbose=int(0),

9

                  validation_data=(x_valid,y_valid))

Language: Sage Gap GP HTML Macaulay2 Maxima Octave Python R Singular

---

Messages

Model Evaluation

xxxxxxxxxx

 

1

model.load_weights(fw)

2

model.evaluate(x_test,y_test,verbose=int(0))

Language: Sage Gap GP HTML Macaulay2 Maxima Octave Python R Singular

---

Messages