📑 Simple Neural Networks for Image Classification

🌐   DL_PP7_0_SMC.html

📑 Deep Learning. Practice Project 7_0:
Simple Neural Networks for Image Classification

✒️ Code Modules, Helpful Functions, & Settings

xxxxxxxxxx

 

1

!python3 -m pip install --upgrade pip \

2

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

3

#!python3 -m pip install torch==1.8.0 \

4

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

5

!python3 -m pip install torchvision==0.9.0 \

6

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

7

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

8

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

9

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

10

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

11

warnings.filterwarnings('ignore')

12

import os,h5py,urllib,torch,pandas as pd,numpy as np

13

import tensorflow as tf,pylab as pl

14

import tensorflow.keras.layers as tkl

15

import tensorflow.keras.callbacks as tkc

16

from torch.utils.data import DataLoader as tdl

17

from torch.utils.data import Dataset as tds

18

from torchvision import transforms,utils,models

19

import torch.nn.functional as tnnf,torch.nn as tnn

20

dev=torch.device(

21

    'cuda:0' if torch.cuda.is_available() else 'cpu')

22

from IPython.core.magic import register_line_magic

23

from IPython.display import HTML

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

---

Messages

✒️ Data Loading

xxxxxxxxxx

 

1

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

2

          'OlgaBelitskaya/data_kitchen/main/'

3

file_name='WhiteFlowers128.h5'; img_size=int(48)

4

def get_data(file_path,file_name,img_size):

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

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

10

        keys=list(f.keys())

11

        pretty_print(html(

12

            '<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

    pretty_print(html('<p>%s'%names+'</p>'))

19

    return images,labels,names

20

images,labels,names=get_data(file_path,file_name,img_size)

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

---

Messages

✒️ Data Processing

xxxxxxxxxx

 

1

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

2

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

3

shuffle_ids=np.arange(N)

4

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

5

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

6

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

7

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

8

df=pd.DataFrame(

9

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

10

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

11

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

12

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

13

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

14

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

15

           'label shape','label type'])

16

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

17

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

18

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

19

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

20

        ax.set_title(

21

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

22

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

23

        ax.imshow((images[i]))

24

    pl.tight_layout(); pl.show()

25

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

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

---

Messages

✒️ Keras Models

xxxxxxxxxx

 

1

def keras_history_plot(fit_history,fig_size,color):

2

    keys=list(fit_history.history.keys())

3

    list_history=[fit_history.history[keys[i]] 

4

                  for i in range(len(keys))]

5

    dfkeys=pd.DataFrame(list_history).T

6

    dfkeys.columns=keys

7

    fig=pl.figure(figsize=(fig_size,fig_size//2))

8

    ax1=fig.add_subplot(2,1,1)

9

    dfkeys.iloc[:,[int(0),int(2)]].plot(

10

        ax=ax1,color=['slategray',color])

11

    pl.grid(); ax2=fig.add_subplot(2,1,2)

12

    dfkeys.iloc[:,[int(1),int(3)]].plot(

13

        ax=ax2,color=['slategray',color])

14

    pl.grid(); pl.show()

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

---

Messages

xxxxxxxxxx

 

1

def cnn_model(num_classes):

2

    model=tf.keras.Sequential(); dr=float(.25)

3

    model.add(tkl.Conv2D(int(32),(int(3),int(3)),padding='same', 

4

                         input_shape=x_train.shape[int(1):]))

5

    model.add(tkl.LeakyReLU(alpha=.02))

6

    model.add(tkl.MaxPooling2D(pool_size=(int(2),int(2))))

7

    model.add(tkl.Dropout(dr))

8

    model.add(tkl.GlobalMaxPooling2D())    

9

    model.add(tkl.Dense(int(512)))

10

    model.add(tkl.LeakyReLU(alpha=.02))

11

    model.add(tkl.Dropout(2*dr))      

12

    model.add(tkl.Dense(num_classes))

13

    model.add(tkl.Activation('softmax'))

14

    model.compile(loss='sparse_categorical_crossentropy', 

15

                  optimizer='nadam',metrics=['accuracy'])    

16

    return model

17

model=cnn_model(num_classes)

18

checkpointer=tkc.ModelCheckpoint(

19

    filepath='/tmp/checkpoint',verbose=int(2),save_weights_only=True,

20

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

21

history=model.fit(

22

    x_train,y_train,batch_size=int(16),epochs=int(5),verbose=int(2),

23

    validation_data=(x_valid,y_valid),callbacks=[checkpointer])

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

---

Messages

xxxxxxxxxx

 

1

model.load_weights('/tmp/checkpoint')

2

print('[loss, accuracy] => %s'%\

3

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

4

keras_history_plot(history,6,'#348ABD')

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

---

Messages