📑 TensorFlow Hub Models

🌐   DL_PP6_1_SMC.html

📑 Deep Learning. Practice Project 6_1:
TensorFlow Hub Models

✒️ Code Modules, Helpful Functions, & Settings

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

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

6

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

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

12

from IPython.display import HTML

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

---

Messages

✒️ Image Data

xxxxxxxxxx

 

1

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

2

          'OlgaBelitskaya/data_kitchen/main/'

3

file_name='TomatoCultivars160.h5'; img_size=int(96)

4

def get_file(file_path,file_name):

5

    input_file=urllib.request.urlopen(file_path+file_name)

6

    output_file=open(file_name,'wb')

7

    output_file.write(input_file.read())

8

    output_file.close(); input_file.close()

9

get_file(file_path,file_name)

10

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

11

    keys=list(f.keys())

12

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

13

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

14

    images=tf.image.resize(images,[img_size,img_size]).numpy()

15

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

16

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

17

    f.close()

18

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

19

num_classes=len(names); start=int(100) 

20

shuffle_ids=np.arange(N)

21

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

22

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

23

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

24

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

25

df=pd.DataFrame(

26

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

27

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

28

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

29

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

30

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

31

    index=['image shape','image type','label shape','label type'])

32

def display_imgs(images,labels,names,start):

33

    fig=pl.figure(figsize=(6,3)); n=randint(0,start-1)

34

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

35

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

36

        ax.set_title(

37

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

38

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

39

        ax.imshow((images[i]))

40

    pl.tight_layout(); pl.show()

41

display_imgs(images,labels,names,start); display(df)

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

---

Messages

✒️ Model 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),patience=int(5),factor=.8)

19

    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_96',int(96)]

3

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

4

.format(handle_base)

5

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

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