📑 Processing & Classification of Horse Breeds` Images

🌐   DL_PP5_0_SMC.html
🌐   breed_recognition2.ipynb

📑 Deep Learning. Practice Project 5_0:
Processing & Classification of Horse Breeds` Images

✒️ Code Modules, Helpful Functions, & Settings

xxxxxxxxxx

 

1

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

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

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

8

import os,h5py,urllib,sys,warnings

9

warnings.filterwarnings('ignore'); sys.path.append(path)

10

import torch,pandas as pd,numpy as np

11

import tensorflow as tf,pylab as pl

12

import tensorflow.keras.layers as tkl

13

import tensorflow.keras.callbacks as tkc

14

from torch.utils.data import DataLoader as tdl

15

from torch.utils.data import Dataset as tds

16

from torchvision import transforms,utils,models

17

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

18

from IPython.core.magic import register_line_magic

19

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

20

          'OlgaBelitskaya/data_kitchen/main/'

21

file_name='HorseBreeds160.h5'

22

dev=torch.device(

23

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

24

img_size=int(64)

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

---

Messages

✒️ Data Loading

xxxxxxxxxx

 

1

def get_file(file_path,file_name):

2

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

3

    output_file=open(file_name,'wb')

4

    output_file.write(input_file.read())

5

    output_file.close(); input_file.close()

6

get_file(file_path,file_name)

7

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

8

    keys=list(f.keys())

9

    pretty_print(html(

10

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

11

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

12

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

13

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

14

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

15

    f.close()

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','label shape','label type'])

15

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

16

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

17

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

18

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

19

        ax.set_title(

20

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

21

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

22

        ax.imshow((images[i]))

23

    pl.tight_layout(); pl.show()

24

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

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

---

Messages

xxxxxxxxxx

 

1

class TData(tds):

2

    def __init__(self,x,y):   

3

        self.x=torch.tensor(x,dtype=torch.float32)

4

        self.y=torch.tensor(y,dtype=torch.int32)

5

    def __getitem__(self,index):

6

        img,lbl=self.x[index],self.y[index]

7

        return img,lbl

8

    def __len__(self):

9

        return self.y.shape[0]

10

batch_size2=int(6)

11

n_train=batch_size2*(x_train.shape[0]//batch_size2)

12

x_train2=np.transpose(x_train,(0,3,1,2))[:n_train]

13

print(x_train2.mean(),x_train2.std())

14

n_valid=batch_size2*(x_valid.shape[0]//batch_size2)

15

x_valid2=np.transpose(x_valid,(0,3,1,2))[:n_valid]

16

n_test=batch_size2*(x_test.shape[0]//batch_size2)

17

x_test2=np.transpose(x_test,(0,3,1,2))[:n_test]

18

random_seed=23

19

train2=TData(x_train2,y_train[:n_train])

20

valid2=TData(x_valid2,y_valid[:n_valid])

21

test2=TData(x_test2,y_test[:n_test])

22

dataloaders={'train':tdl(dataset=train2,shuffle=True,

23

                         batch_size=batch_size2), 

24

             'valid':tdl(dataset=valid2,shuffle=True,

25

                         batch_size=batch_size2),

26

             'test':tdl(dataset=test2,shuffle=True,

27

                        batch_size=batch_size2)}

28

del train2,valid2,test2

29

@register_line_magic

30

def display_data_imgs(data):

31

    global names

32

    for images,labels in dataloaders[data]:  

33

        print('Image dimensions: %s'%str(images.shape))

34

        print('Label dimensions: %s'%str(labels.shape))

35

        images=[np.transpose(images[i],(1,2,0)) 

36

                for i in range(len(images))]

37

        display_imgs(images,labels,names,int(1))

38

        break

39

%display_data_imgs valid

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

---

Messages

✒️ Keras

xxxxxxxxxx

 

1

def kmodel(leaky_alpha,num_classes,img_size):

2

    model=tf.keras.Sequential()

3

    model.add(tkl.Conv2D(int(32),(int(5),int(5)),padding='same', 

4

                         input_shape=(img_size,img_size,int(3))))

5

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

6

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

7

    model.add(tkl.Dropout(float(.25)))

8

    model.add(tkl.Conv2D(int(96),(int(5),int(5))))

9

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

10

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

11

    model.add(tkl.Dropout(float(.25)))   

12

    model.add(tkl.GlobalMaxPooling2D())     

13

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

14

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

15

    model.add(tkl.Dropout(float(.5)))     

16

    model.add(tkl.Dense(num_classes))

17

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

18

    model.compile(loss='sparse_categorical_crossentropy',

19

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

20

    return model

21

kmodel=kmodel(float(.005),num_classes,img_size)

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

---

Messages

xxxxxxxxxx

 

1

fw='/tmp/checkpoint'

2

early_stopping=tkc.EarlyStopping(

3

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

4

checkpointer=tkc.ModelCheckpoint(

5

    filepath=fw,verbose=int(0),save_weights_only=True,

6

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

7

lr_reduction=tkc.ReduceLROnPlateau(

8

    monitor='val_loss',patience=int(5),

9

    verbose=int(0),factor=float(.8))

10

history=kmodel.fit(

11

    x_train,y_train,epochs=int(4),batch_size=int(16),verbose=int(2),

12

    validation_data=(x_valid,y_valid),

13

    callbacks=[checkpointer,early_stopping,lr_reduction])

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

---

Messages

xxxxxxxxxx

 

1

def keras_history_plot(fit_history,fig_size=8,color='#348ABD'):

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],grid=True)

11

    ax2=fig.add_subplot(2,1,2)

12

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

13

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

14

    pl.tight_layout(); pl.show()

15

keras_history_plot(history); del history

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

---

Messages

xxxxxxxxxx

 

1

kmodel.load_weights(fw)

2

print(kmodel.evaluate(x_test,y_test,verbose=int(0)))

3

y_test_predict=np.argmax(kmodel.predict(x_test),axis=-1)

4

os.remove(fw)

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

---

Messages

✒️ PyTorch

xxxxxxxxxx

 

1

class FilterResponseNorm(tnn.Module):

2

    def __init__(self,num_features,eps=float(1e-6)):

3

        super(FilterResponseNorm,self).__init__()        

4

        self.register_parameter('beta',\

5

        tnn.Parameter(torch.empty([int(1),num_features,

6

                                   int(1),int(1)]).normal_()))

7

        self.register_parameter('gamma',\

8

        tnn.Parameter(torch.empty([int(1),num_features,

9

                                   int(1),int(1)]).normal_()))      

10

        self.register_parameter('tau',\

11

        tnn.Parameter(torch.empty([int(1),num_features,

12

                                   int(1),int(1)]).normal_()))     

13

        self.eps=torch.Tensor([eps])

14

    def forward(self,x):

15

        n,c,h,w=x.size()        

16

        self.eps=self.eps.to(self.tau.device)

17

        nu2=torch.mean(x.pow(int(2)),(int(2),int(3)),keepdims=True)

18

        x=x*torch.rsqrt(nu2+torch.abs(self.eps))

19

        return torch.max(self.gamma*x+self.beta,self.tau)

20

def convfrn(x,y,k,s,p):

21

    return tnn.Sequential(

22

        tnn.Conv2d(x,y,kernel_size=k,stride=s,padding=p),\

23

        FilterResponseNorm(y))

24

class FRN_NNinNN(tnn.Module):

25

    def __init__(self,num_classes):

26

        super(FRN_NNinNN,self).__init__()

27

        self.num_classes=num_classes

28

        d=int(192); d2=int(256)

29

        self.classifier=tnn.Sequential(

30

            convfrn(int(3),d,int(5),int(1),int(2)),

31

#            convfrn(d,d,int(1),int(1),int(0)),

32

            convfrn(d,d2,int(1),int(1),int(0)),

33

            tnn.MaxPool2d(kernel_size=int(3),

34

                          stride=int(2),padding=int(1)),

35

            tnn.Dropout(float(.5)),

36

            convfrn(d2,d,int(5),int(1),int(2)),

37

#            convfrn(d,d,int(1),int(1),int(0)),

38

            convfrn(d,d,int(1),int(1),int(0)),

39

            tnn.AvgPool2d(kernel_size=int(3),

40

                          stride=int(2),padding=int(1)),

41

            tnn.Dropout(float(.5)),

42

            convfrn(d,d,int(3),int(1),int(1)),

43

            convfrn(d,d,int(1),int(1),int(0)),

44

            tnn.Conv2d(d,self.num_classes,kernel_size=int(1),

45

                       stride=int(1),padding=int(0)),

46

            tnn.ReLU(),

47

            tnn.AvgPool2d(kernel_size=int(16),

48

                          stride=int(1),padding=int(0)))

49

    def forward(self,x):

50

        x=self.classifier(x)

51

        logits=x.view(x.size(int(0)),self.num_classes)

52

        probs=torch.softmax(logits,dim=int(1))

53

        return logits,probs

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

---

Messages

xxxxxxxxxx

 

1

def model_acc(model,data_loader):

2

    correct_preds,num_examples=int(0),int(0)

3

    for features,targets in data_loader:

4

        features=features.to(dev)

5

        targets=targets.to(dev).long()

6

        logits,probs=model(features)

7

        _,pred_labels=torch.max(logits,int(1))

8

        num_examples+=targets.size(int(0))

9

        correct_preds+=(pred_labels==targets).sum()        

10

    return correct_preds.float()/num_examples*int(100)

11

def epoch_loss(model,data_loader):

12

    model.eval()

13

    curr_loss,num_examples=float(0.),int(0)

14

    with torch.no_grad():

15

        for features,targets in data_loader:

16

            features=features.to(dev)

17

            targets=targets.to(dev).long()

18

            logits,probs=model(features)

19

            loss=tnnf.cross_entropy(

20

                logits,targets,reduction='sum')

21

            num_examples+=targets.size(int(0))

22

            curr_loss+=loss

23

        return curr_loss/num_examples

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

---

Messages

xxxxxxxxxx

 

1

@register_line_magic

2

def train_run(epochs):

3

    epochs=int(epochs)

4

    st1='epoch: %03d/%03d || batch: %03d/%03d || cost: %.4f'

5

    for epoch in range(epochs):

6

        tmodel.train()

7

        for batch_ids,(features,targets) \

8

        in enumerate(dataloaders['train']):        

9

            features=features.to(dev)

10

            targets=targets.to(dev).long()

11

            logits,probs=tmodel(features)

12

            cost=tnnf.cross_entropy(logits,targets)

13

            optimizer.zero_grad(); cost.backward()

14

            optimizer.step()

15

            if not batch_ids%int(20):

16

                print(st1%(epoch+int(1),epochs,batch_ids,

17

                      len(dataloaders['train']),cost))

18

        tmodel.eval()

19

        with torch.set_grad_enabled(False):

20

            print('epoch: %03d/%03d'%(epoch+int(1),epochs))

21

            print('valid acc/loss: %.2f%%/%.2f'%\

22

                  (model_acc(tmodel,dataloaders['valid']),

23

                   epoch_loss(tmodel,dataloaders['valid'])))

24

torch.manual_seed(random_seed); learning_rate=float(.0001)

25

tmodel=FRN_NNinNN(num_classes)

26

tmodel.to(dev)

27

optimizer=torch.optim.Adam(tmodel.parameters(),lr=learning_rate)

28

%train_run 1

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

---

Messages

xxxxxxxxxx

 

1

tmodel.eval()

2

with torch.set_grad_enabled(False):

3

    print('test acc: %.2f%%'%model_acc(tmodel,dataloaders['test']))

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

---

Messages

✒️ Models` Predictions

xxxxxxxxxx

 

1

fig=pl.figure(figsize=(6,3))

2

randch=np.random.choice(x_test.shape[0],size=6,replace=False)

3

for i,idx in enumerate(randch):

4

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

5

    ax.imshow(np.squeeze(x_test[idx]))

6

    pred_idx=y_test_predict[idx]; true_idx=y_test[idx]

7

    ax.set_title('{} \n({})'.format(names[pred_idx],names[true_idx]),

8

                 color=('#aaf' if pred_idx==true_idx else '#faa'))

9

pl.tight_layout(); pl.show()

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

---

Messages

xxxxxxxxxx

 

1

def show_image(img):

2

    npimg=img.numpy(); tr=(1,2,0)

3

    pl.figure(figsize=(6,2))

4

    pl.imshow(np.transpose(npimg,tr))

5

    pl.xticks([]); pl.tight_layout(); pl.show()

6

with torch.no_grad():

7

    for i,(images,labels) in enumerate(dataloaders['test']):

8

        show_image(utils.make_grid(images[:3]))

9

        print('\ntrue labels: ',

10

              ''.join('%18s'%names[labels[j]] for j in range(3)))

11

        images=images.to(dev)

12

        labels=labels.to(dev).long()

13

        logits,probs=tmodel(images)

14

        _,preds=torch.max(logits,int(1))

15

        print('\npredictions: ',

16

             ''.join('%18s'%names[preds[j]] for j in range(3)))

17

        if i==1: break

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

---

Messages

📑 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

📑 Processing & Classification of Tomato Cultivars` Images

🌐   DL_PP6_0_SMC.html

📑 Deep Learning. Practice Project 6_0:
Processing & Classification of Tomato Cultivars` Images

✒️ Code Modules, Helpful Functions, & Settings

xxxxxxxxxx

 

1

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

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

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

8

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

9

warnings.filterwarnings('ignore')

10

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

11

from sklearn.ensemble import RandomForestClassifier as sRFC

12

from sklearn.metrics import accuracy_score,hamming_loss

13

from sklearn.metrics import classification_report

14

import torch,tensorflow as tf,pylab as pl

15

import tensorflow.keras.layers as tkl

16

import tensorflow.keras.callbacks as tkc

17

from torch.utils.data import DataLoader as tdl

18

from torch.utils.data import Dataset as tds

19

from torchvision import transforms,utils,models

20

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

21

dev=torch.device(

22

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

23

from IPython.core.magic import register_line_magic

24

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='TomatoCultivars160.h5'; img_size=int(64)

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(

13

        '<p>'+10*'&nbsp;'+'file keys: '+', '.join(keys)+'</p>'))

14

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

15

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

16

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

17

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

18

    f.close()

19

@interact(layout=dict(top=[['get_img_size']]))

20

def _get_data_resize(get_img_size=slider([64,60,..,32],default=32)):

21

    global img_size,images

22

    img_size=int(get_img_size)

23

    pretty_print(html('<p>image size: %d<'%img_size+'/p>'))

24

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

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

---

Messages

✒️ Data Processing

xxxxxxxxxx

 

1

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

2

num_classes=len(names) 

3

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

4

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

5

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

6

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

7

df=pd.DataFrame(

8

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

9

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

10

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

11

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

12

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

13

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

14

def display_imgs(images,labels,names,n=12):

15

    fig=pl.figure(figsize=(10,3))

16

    for i in range(0,n):

17

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

18

        ax.set_title(

19

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

20

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

21

        ax.imshow((images[i]))

22

    pl.tight_layout(); pl.show()

23

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

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

---

Messages

xxxxxxxxxx

 

1

class TData(tds):

2

    def __init__(self,x,y):   

3

        self.x=torch.tensor(x,dtype=torch.float32)

4

        self.y=torch.tensor(y,dtype=torch.int32)

5

    def __getitem__(self,index):

6

        img,lbl=self.x[index],self.y[index]

7

        return img,lbl

8

    def __len__(self):

9

        return self.y.shape[0]

10

batch_size2=int(16)

11

n_train=batch_size2*(x_train.shape[0]//batch_size2)

12

x_train2=np.transpose(x_train,(0,3,1,2))[:n_train]

13

print(x_train2.mean(),x_train2.std())

14

n_valid=batch_size2*(x_valid.shape[0]//batch_size2)

15

x_valid2=np.transpose(x_valid,(0,3,1,2))[:n_valid]

16

n_test=batch_size2*(x_test.shape[0]//batch_size2)

17

x_test2=np.transpose(x_test,(0,3,1,2))[:n_test]

18

random_seed=23

19

train2=TData(x_train2,y_train[:n_train])

20

valid2=TData(x_valid2,y_valid[:n_valid])

21

test2=TData(x_test2,y_test[:n_test])

22

dataloaders={'train':tdl(dataset=train2,shuffle=True,

23

                         batch_size=batch_size2), 

24

             'valid':tdl(dataset=valid2,shuffle=True,

25

                         batch_size=batch_size2),

26

             'test':tdl(dataset=test2,shuffle=True,

27

                        batch_size=batch_size2)}

28

del train2,valid2,test2

29

@register_line_magic

30

def display_data_imgs(data):

31

    global names

32

    for images,labels in dataloaders[data]:  

33

        print('image dimensions: %s'%str(images.shape))

34

        print('label dimensions: %s'%str(labels.shape))

35

        images=[np.transpose(images[i],(1,2,0)) 

36

                for i in range(len(images))]

37

        display_imgs(images,labels,names,int(8))

38

        break

39

%display_data_imgs valid

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

---

Messages

✒️ Sklearn

xxxxxxxxxx

 

1

def classifier_fit_score(classifier,x_train,x_test,y_train,y_test):

2

    classifier.fit(x_train,y_train)     

3

    y_clf_train=classifier.predict(x_train)

4

    y_clf_test=classifier.predict(x_test)        

5

    acc_clf_train=round(accuracy_score(y_train,y_clf_train),int(4))

6

    acc_clf_test=round(accuracy_score(y_test,y_clf_test),int(4))

7

    loss_clf_train=round(hamming_loss(y_train,y_clf_train),int(4))

8

    loss_clf_test=round(hamming_loss(y_test,y_clf_test),int(4))  

9

    return [y_clf_train,y_clf_test,acc_clf_train,acc_clf_test,

10

            loss_clf_train,loss_clf_test]

11

[y_srfc_train,y_srfc_test,acc_srfc_train,

12

 acc_srfc_test,loss_srfc_train,loss_srfc_test]=\

13

classifier_fit_score(

14

    sRFC(),x_train.reshape(-int(1),int(3)*img_size**2),

15

    x_test.reshape(-int(1),int(3)*img_size**2),y_train,y_test)

16

print(classification_report(y_test,y_srfc_test))

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

---

Messages

xxxxxxxxxx

 

1

def plot_predict(y_predict,label_predict,t=30,fig_size=6):

2

    pl.figure(figsize=(fig_size,fig_size//4)); x=range(t)

3

    pl.scatter(x,y_test[:t],marker='*',s=100,

4

               color='slategray',label='Real data')

5

    pl.scatter(x,y_predict[:t],marker='v',s=50,

6

               color='#348ABD',label=label_predict)

7

    pl.xlabel('Observations'); pl.ylabel('Targets') 

8

    pl.title('Classifiers. Test Results',color='slategray',

9

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

10

    pl.legend(loc=2,fontsize=10)

11

    pl.tight_layout; pl.show()

12

plot_predict(y_srfc_test,'Random Forest')

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

---

Messages

✒️ Keras

xxxxxxxxxx

 

1

def kmodel(leaky_alpha,num_classes,img_size):

2

    model=tf.keras.Sequential()

3

    model.add(tkl.Conv2D(int(32),(int(5),int(5)),padding='same', 

4

                         input_shape=(img_size,img_size,int(3))))

5

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

6

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

7

    model.add(tkl.Dropout(float(.25)))

8

    model.add(tkl.Conv2D(int(96),(int(5),int(5))))

9

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

10

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

11

    model.add(tkl.Dropout(float(.25)))   

12

    model.add(tkl.GlobalMaxPooling2D())     

13

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

14

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

15

    model.add(tkl.Dropout(float(.5)))     

16

    model.add(tkl.Dense(num_classes))

17

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

18

    model.compile(loss='sparse_categorical_crossentropy',

19

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

20

    return model

21

kmodel=kmodel(float(.005),num_classes,img_size)

22

fw='/tmp/checkpoint'

23

checkpointer=tkc.ModelCheckpoint(

24

    filepath=fw,verbose=int(0),save_weights_only=True,

25

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

26

history=kmodel.fit(

27

    x_train,y_train,epochs=int(3),batch_size=int(16),verbose=int(2),

28

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

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

---

Messages

xxxxxxxxxx

 

1

kmodel.load_weights(fw)

2

print(kmodel.evaluate(x_test,y_test,verbose=int(0)))

3

y_cnn_test=np.argmax(kmodel.predict(x_test),axis=-1)

4

os.remove(fw)

5

plot_predict(y_cnn_test,'CNN Keras')

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

---

Messages

✒️ PyTorch

xxxxxxxxxx

 

1

class FilterResponseNorm(tnn.Module):

2

    def __init__(self,num_features,eps=float(1e-6)):

3

        super(FilterResponseNorm,self).__init__()        

4

        self.register_parameter('beta',\

5

        tnn.Parameter(torch.empty([int(1),num_features,

6

                                   int(1),int(1)]).normal_()))

7

        self.register_parameter('gamma',\

8

        tnn.Parameter(torch.empty([int(1),num_features,

9

                                   int(1),int(1)]).normal_()))      

10

        self.register_parameter('tau',\

11

        tnn.Parameter(torch.empty([int(1),num_features,

12

                                   int(1),int(1)]).normal_()))     

13

        self.eps=torch.Tensor([eps])

14

    def forward(self,x):

15

        n,c,h,w=x.size()        

16

        self.eps=self.eps.to(self.tau.device)

17

        nu2=torch.mean(x.pow(int(2)),(int(2),int(3)),keepdims=True)

18

        x=x*torch.rsqrt(nu2+torch.abs(self.eps))

19

        return torch.max(self.gamma*x+self.beta,self.tau)

20

def convfrn(x,y,k,s,p):

21

    return tnn.Sequential(

22

        tnn.Conv2d(x,y,kernel_size=k,stride=s,padding=p),\

23

        FilterResponseNorm(y))

24

class FRN_NNinNN(tnn.Module):

25

    def __init__(self,num_classes):

26

        super(FRN_NNinNN,self).__init__()

27

        self.num_classes=num_classes

28

        self.classifier=tnn.Sequential(

29

            convfrn(int(3),int(192),int(5),int(1),int(2)),

30

            convfrn(int(192),int(160),int(1),int(1),int(0)),

31

            convfrn(int(160),int(96),int(1),int(1),int(0)),

32

            tnn.MaxPool2d(kernel_size=int(3),

33

                          stride=int(2),padding=int(1)),

34

            tnn.Dropout(float(.5)),

35

            convfrn(int(96),int(192),int(5),int(1),int(2)),

36

            convfrn(int(192),int(192),int(1),int(1),int(0)),

37

            convfrn(int(192),int(192),int(1),int(1),int(0)),

38

            tnn.AvgPool2d(kernel_size=int(3),

39

                          stride=int(2),padding=int(1)),

40

            tnn.Dropout(float(.5)),

41

            convfrn(int(192),int(192),int(3),int(1),int(1)),

42

            convfrn(int(192),int(192),int(1),int(1),int(0)),

43

            tnn.Conv2d(int(192),self.num_classes,

44

                kernel_size=int(1),stride=int(1),

45

                padding=int(0)),

46

            tnn.ReLU(),

47

            tnn.AvgPool2d(kernel_size=int(8),

48

                          stride=int(1),padding=int(0)))

49

    def forward(self,x):

50

        x=self.classifier(x)

51

        logits=x.view(x.size(int(0)),self.num_classes)

52

        probs=torch.softmax(logits,dim=int(1))

53

        return logits,probs

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

---

Messages

xxxxxxxxxx

 

1

def model_acc(model,data_loader):

2

    correct_preds,num_examples=int(0),int(0)

3

    for features,targets in data_loader:

4

        features=features.to(dev)

5

        targets=targets.to(dev).long()

6

        logits,probs=model(features)

7

        _,pred_labels=torch.max(logits,int(1))

8

        num_examples+=targets.size(int(0))

9

        correct_preds+=(pred_labels==targets).sum()        

10

    return correct_preds.float()/num_examples*int(100)

11

def epoch_loss(model,data_loader):

12

    model.eval()

13

    curr_loss,num_examples=float(0.),int(0)

14

    with torch.no_grad():

15

        for features,targets in data_loader:

16

            features=features.to(dev)

17

            targets=targets.to(dev).long()

18

            logits,probs=model(features)

19

            loss=tnnf.cross_entropy(logits,targets,reduction='sum')

20

            num_examples+=targets.size(int(0))

21

            curr_loss+=loss

22

        return curr_loss/num_examples

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

---

Messages

xxxxxxxxxx

 

1

@register_line_magic

2

def train_run(epochs):

3

    epochs=int(epochs)

4

    st1='epoch: %03d/%03d || batch: %03d/%03d || cost: %.4f'

5

    for epoch in range(epochs):

6

        tmodel.train()

7

        for batch_ids,(features,targets) \

8

        in enumerate(dataloaders['train']):        

9

            features=features.to(dev)

10

            targets=targets.to(dev).long()

11

            logits,probs=tmodel(features)

12

            cost=tnnf.cross_entropy(logits,targets)

13

            optimizer.zero_grad(); cost.backward()

14

            optimizer.step()

15

            if not batch_ids%int(20):

16

                print(st1%(epoch+int(1),epochs,batch_ids,

17

                      len(dataloaders['train']),cost))

18

        tmodel.eval()

19

        with torch.set_grad_enabled(False):

20

            print('epoch: %03d/%03d'%(epoch+int(1),epochs))

21

            print('valid acc/loss: %.2f%%/%.2f'%\

22

                  (model_acc(tmodel,dataloaders['valid']),

23

                   epoch_loss(tmodel,dataloaders['valid'])))

24

torch.manual_seed(random_seed); learning_rate=float(.00005)

25

tmodel=FRN_NNinNN(num_classes)

26

tmodel.to(dev)

27

optimizer=torch.optim.Adam(tmodel.parameters(),lr=learning_rate)

28

%train_run 2

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

---

Messages

xxxxxxxxxx

 

1

tmodel.eval()

2

with torch.set_grad_enabled(False):

3

    print('test acc: %.2f%%'%model_acc(tmodel,dataloaders['test']))

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

---

Messages

📑 Exercises with White Flowers` Images

🌐   DL_PP7_1_SMC.html

📑 Deep Learning. Practice Project 7_1:
Exercises with White Flowers` Images

✒️ Code Modules, Helpful Functions, & Settings

xxxxxxxxxx

 

1

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

2

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

3

!python3 -m pip install tensorflow_hub \

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

from IPython.display import display,HTML

9

from IPython.core.magic import register_line_magic

10

import tensorflow as tf,tensorflow_hub as hub,numpy as np

11

import os,h5py,urllib,cv2,pandas as pd,pylab as pl

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

---

Messages

xxxxxxxxxx

 

1

def get_data(file_path,file_name,img_size):

2

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

3

    output_file=open(file_name,'wb')

4

    output_file.write(input_file.read())

5

    output_file.close(); input_file.close()

6

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

7

        keys=list(f.keys())

8

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

9

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

10

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

11

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

12

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

13

        f.close()

14

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

15

    return images,labels,names

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

def get_file(file_path,file_name):

26

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

27

    output_file=open(file_name,'wb')

28

    output_file.write(input_file.read())

29

    output_file.close(); input_file.close()

30

def highpass_xy(img):

31

    x_var=img[:,:,int(1):,:]-img[:,:,:-int(1),:]

32

    y_var=img[:,int(1):,:,:]-img[:,:-int(1),:,:]

33

    return x_var,y_var

34

def clip01(img):

35

    return tf.clip_by_value(

36

        img,clip_value_min=float(0.),clip_value_max=float(1.))

37

def load_img(file_name,max_dim=int(512)):

38

    img=tf.io.read_file(file_name)

39

    img=tf.image.decode_image(img,channels=int(3))

40

    img=tf.image.convert_image_dtype(img,tf.float32)

41

    shape=tf.cast(tf.shape(img)[:-int(1)],tf.float32)

42

    scale=max_dim/max(shape)

43

    new_shape=tf.cast(shape*scale,tf.int32)

44

    img=tf.image.resize(img,new_shape)

45

    return img[tf.newaxis,:]

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(64)

4

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','label shape','label type'])

15

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

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

---

Messages

✒️ Super Resolution

xxxxxxxxxx

 

1

def esrgantf2_superresolution(img,img_size=int(50)):

2

    model=hub.load('https://tfhub.dev/captain-pool/esrgan-tf2/1')

3

    func=model.signatures[tf.saved_model\

4

    .DEFAULT_SERVING_SIGNATURE_DEF_KEY]

5

    func.inputs[int(0)].set_shape([int(1),img_size,img_size,int(3)])

6

    converter=tf.lite.TFLiteConverter.from_concrete_functions([func])

7

    converter.optimizations=[tf.lite.Optimize.DEFAULT]

8

    tflite_model=converter.convert()

9

    with tf.io.gfile.GFile('ESRGAN.tflite','wb') as f:

10

        f.write(tflite_model)

11

    esrgan_model_path='./ESRGAN.tflite'

12

    if img.mean()<float(1): img=img*float(255)

13

    lr=tf.image.resize(img,[img_size,img_size])

14

    lr=tf.expand_dims(lr.numpy()[:,:,:int(3)],axis=int(0))

15

    lr=tf.cast(lr,tf.float32)

16

    interpreter=tf.lite.Interpreter(model_path=esrgan_model_path)

17

    interpreter.allocate_tensors()

18

    input_details=interpreter.get_input_details()

19

    output_details=interpreter.get_output_details()

20

    interpreter.set_tensor(input_details[int(0)]['index'],lr)

21

    interpreter.invoke()

22

    output_data=interpreter.get_tensor(

23

        output_details[int(0)]['index'])

24

    sr=tf.squeeze(output_data,axis=int(0))

25

    sr=tf.clip_by_value(sr,int(0),int(255))

26

    sr=tf.round(sr); sr=tf.cast(sr,tf.uint8)

27

    lr=tf.cast(tf.squeeze(lr,axis=int(0)),tf.uint8)

28

    return lr,sr

29

lr,sr=esrgantf2_superresolution(images[start],img_size)

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

---

Messages

xxxxxxxxxx

 

1

def low2superbicubic_imgs(lr,sr):

2

    pl.figure(figsize=(6,3)); pl.title(f'lr')

3

    pl.imshow(lr.numpy()); pl.show()

4

    pl.figure(figsize=(6,3))

5

    pl.subplot(1,2,1); pl.title(f'esrgan x4')

6

    pl.imshow(sr.numpy())

7

    img_size=lr.shape[int(1)]

8

    bicubic=tf.image.resize(

9

        lr,[img_size*int(4),img_size*int(4)],

10

        tf.image.ResizeMethod.BICUBIC)

11

    bicubic_contrast=tf.image.adjust_contrast(bicubic,float(.8))

12

    bicubic_contrast=tf.cast(bicubic_contrast,tf.uint8)

13

    pl.subplot(1,2,2); pl.title(f'bicubic & contrast')

14

    pl.imshow(bicubic_contrast.numpy())

15

    pl.tight_layout(); pl.show()

16

low2superbicubic_imgs(lr,sr)

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

---

Messages

✒️ OpenCV Image Manipulations

xxxxxxxxxx

 

1

file_path2='https://raw.githubusercontent.com/'+\

2

           'OlgaBelitskaya/data/main/white_flowers/'

3

file_name2='01_036.png'

4

get_file(file_path2,file_name2)

5

img=cv2.imread(file_name2)

6

img=cv2.resize(img,(int(256),int(192)))

7

gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)

8

rgb=cv2.cvtColor(img,cv2.COLOR_BGR2RGB)

9

hsv=cv2.cvtColor(img,cv2.COLOR_BGR2HSV)

10

edge_img=rgb.copy()

11

edge=cv2.Canny(gray,int(80),int(210))

12

edge_img[edge!=0]=(255,0,255) 

13

lower=np.array([10,200,150]); upper=np.array([30,255,255])

14

mask=cv2.inRange(hsv,lower,upper)

15

result=cv2.bitwise_and(img,img,mask=mask)

16

kernel=np.ones((11,11),np.uint8)

17

gradient=cv2.morphologyEx(img,cv2.MORPH_GRADIENT,kernel)

18

sobel=cv2.Sobel(

19

    gray,cv2.CV_64F,int(1),int(0),ksize=int(27))

20

laplacian=cv2.Laplacian(img,cv2.CV_64F)

21

pl.figure(figsize=(6,10)); pl.subplot(521)

22

pl.imshow(cv2.bitwise_not(rgb))

23

pl.title('bitwise_not'),pl.subplot(522)

24

pl.imshow(cv2.cvtColor(hsv,cv2.COLOR_HSV2RGB))

25

pl.title('hsv2rgb'),pl.subplot(523)

26

pl.imshow(gray,cmap='bone')

27

pl.title('gray2bone'),pl.subplot(524)

28

pl.imshow(edge_img)

29

pl.title('edges2magenta'),pl.subplot(525)

30

pl.imshow(edge,cmap='flag_r')

31

pl.title('edges2flag_r'),pl.subplot(526)

32

pl.imshow(gradient)

33

pl.title('morphology_gradient'),pl.subplot(527)

34

pl.imshow(cv2.cvtColor(result,cv2.COLOR_BGR2RGB))

35

pl.title('hsv_mask'),pl.subplot(528)

36

pl.imshow(sobel,cmap='bone')

37

pl.title('sobel'),pl.subplot(529)

38

pl.imshow(laplacian,cmap='bone')

39

pl.title('laplacian'),pl.tight_layout(); pl.show()

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

---

Messages

xxxxxxxxxx

 

1

values=[0,1,..,255]

2

@interact

3

def _(red=slider(values,default=15),

4

      green=slider(values,default=127),

5

      blue=slider(values,default=15),

6

      step=[15,14,..,1]):

7

    [r,g,b]=[red,green,blue]

8

    min_rgb=[max(0,x-4*step) for x in [r,g,b]]

9

    max_rgb=[min(255,x+4*step) for x in [r,g,b]]

10

    pretty_print('min rgb: %s; \n'%str(min_rgb)+\

11

                 'rgb: %s; \n'%str([r,g,b])+\

12

                 'max rgb: %s; '%str(max_rgb))

13

    m=[[[r+i*step,g,b] for i in range(-4,5,1)],

14

       [[r,g+i*step,b] for i in range(-4,5,1)],

15

       [[r,g,b+i*step] for i in range(-4,5,1)],

16

       [[r+i*step,g+i*step,b] for i in range(-4,5,1)],

17

       [[r,g+i*step,b+i*step] for i in range(-4,5,1)],

18

       [[r+i*step,g,b+i*step] for i in range(-4,5,1)],

19

       [[r+i*step,g+i*step,b+i*step] for i in range(-4,5,1)]]

20

    tf=[[-4,-3,-2,-1,0,1,2,3,4],['r','g','b','rg','gb','rb','rgb']]

21

    p=matrix_plot(np.array(m)/255,

22

                  ticks=[[0..8],[0..6]],tick_formatter=tf)

23

    p.show()

24

    hsv=cv2.cvtColor(np.uint8([[[r,g,b]]]),cv2.COLOR_BGR2HSV)

25

    min_hsv=cv2.cvtColor(np.uint8([[min_rgb]]),cv2.COLOR_BGR2HSV)

26

    max_hsv=cv2.cvtColor(np.uint8([[max_rgb]]),cv2.COLOR_BGR2HSV)

27

    pretty_print('min rgb -> hsv: %s; \n'%str(min_hsv[0][0])+\

28

                 'rgb -> hsv: %s; \n'%str(hsv[0][0])+\

29

                 'max rgb -> hsv: %s; '%str(max_hsv[0][0]))

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

---

Messages

xxxxxxxxxx

 

1

@interact(layout=dict(

2

    top=[['file'],['lower_red','lower_green','lower_blue'],

3

         ['upper_red','upper_green','upper_blue']]))

4

def _rgb2hsv(file=[1,2,3,6,7],

5

             lower_red=slider(values,default=0),

6

             lower_green=slider(values,default=0),

7

             lower_blue=slider(values,default=0),

8

             upper_red=slider(values,default=50),

9

             upper_green=slider(values,default=127),

10

             upper_blue=slider(values,default=50)):

11

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

12

              'OlgaBelitskaya/data/main/white_flowers/'

13

    file_name='01_00%s'%(file)+'.png'

14

    get_file(file_path,file_name)

15

    img=cv2.imread(file_name)

16

    rgb=cv2.cvtColor(img,cv2.COLOR_BGR2RGB)

17

    hsv=cv2.cvtColor(img,cv2.COLOR_BGR2HSV)

18

    [lr,lg,lb]=[lower_red,lower_green,lower_blue]

19

    [ur,ug,ub]=[upper_red,upper_green,upper_blue]

20

    lower_hsv=cv2.cvtColor(

21

        np.uint8([[[lr,lg,lb]]]),cv2.COLOR_BGR2HSV)[0][0]

22

    upper_hsv=cv2.cvtColor(

23

        np.uint8([[[ur,ug,ub]]]),cv2.COLOR_BGR2HSV)[0][0]

24

    mask=cv2.inRange(hsv,np.array(lower_hsv),np.array(upper_hsv))   

25

    result=cv2.bitwise_and(img,img,mask=mask)

26

    result_rgb=cv2.cvtColor(result,cv2.COLOR_BGR2RGB)

27

    pretty_print('lower rgb -> hsv: %s; '%str(lower_hsv)+\

28

                 'upper rgb -> hsv: %s; '%str(upper_hsv))

29

    for el in [rgb,mask,result_rgb]:

30

         matrix_plot(el/255).show(frame=False,figsize=(3.5,3.5))

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

---

Messages

✒️ TensorFlow Image Manipulations

xxxxxxxxxx

 

1

@interact(layout=dict(top=[['file'],['contrast','brightness']]))

2

def _tfimg(file=slider([1..60],default=30),

3

           contrast=slider([.05,.1,..,1.95],default=1.5),

4

           brightness=slider([.05,.1,..,1.05],default=.5)):

5

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

6

              'OlgaBelitskaya/data/main/white_flowers/'

7

    file_name='02_%03d'%(file)+'.png'

8

    get_file(file_path,file_name)

9

    original_img=load_img(file_name)

10

    gray_img=np.dot(original_img[...,:int(3)],[.299,.587,.114])

11

    contrast_img=tf.image.adjust_contrast(

12

        original_img,float(contrast))

13

    brightness_img=tf.image.adjust_brightness(

14

        original_img,float(brightness))

15

    x_deltas,y_deltas=highpass_xy(original_img)

16

    sobel=tf.image.sobel_edges(original_img)

17

    pl.figure(figsize=(6,10))

18

    pl.subplot(4,2,1),pl.imshow(tf.squeeze(clip01(original_img)))

19

    pl.title('rgb || original')

20

    pl.subplot(4,2,2)

21

    pl.imshow(tf.squeeze(clip01(gray_img)),cmap='bone')

22

    pl.title('gray || original')

23

    pl.subplot(4,2,3),pl.imshow(tf.squeeze(clip01(brightness_img)))

24

    pl.title('brightness || original')

25

    pl.subplot(4,2,4),pl.imshow(tf.squeeze(clip01(contrast_img)))

26

    pl.title('contrast || original')

27

    pl.subplot(4,2,5)

28

    pl.imshow(tf.squeeze(clip01(int(2)*y_deltas+float(.5))))

29

    pl.title('horizontal deltas || original')

30

    pl.subplot(4,2,6)

31

    pl.imshow(tf.squeeze(clip01(int(2)*x_deltas+float(.5))))

32

    pl.title('vertical deltas || original')

33

    pl.subplot(4,2,7)

34

    pl.imshow(tf.squeeze(clip01(sobel[...,int(0)]/int(4)+float(.5))))

35

    pl.title('horizontal sobel-edges')

36

    pl.subplot(4,2,8)

37

    pl.imshow(tf.squeeze(clip01(sobel[...,int(1)]/int(4)+float(.5))))

38

    pl.title('vertical sobel-edges');

39

    pl.tight_layout(); pl.show()

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

---

Messages

📑 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

📑 Exercises with Drawing Images

🌐   DL_PP8_2_SMC.html

📑 Deep Learning. Practice Project 8_2:
Exercises with Drawing Images

✒️ Code Modules, Helpful Functions, & Settings

xxxxxxxxxx

 

1

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

2

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

3

!python3 -m pip install tensorflow_hub \

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 os,h5py,urllib,pandas as pd

9

import numpy as np,pylab as pl,seaborn as sn

10

import tensorflow as tf,tensorflow_hub as hub

11

style_hub_path='https://tfhub.dev/google/magenta/'+\

12

               'arbitrary-image-stylization-v1-256/2'

13

super_hub_path='https://tfhub.dev/captain-pool/esrgan-tf2/1'

14

os.environ['TFHUB_MODEL_LOAD_FORMAT']='COMPRESSED'

15

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

16

          'OlgaBelitskaya/data_kitchen/main/'

17

file_name='Pictograms64.h5'

18

img_size=int(64); max_dim=int(224); lr_size=int(32)

19

style_model=hub.load(style_hub_path)

20

from tensorflow.keras.applications import vgg19,VGG19

21

mvgg19=VGG19(include_top=True,weights='imagenet')

22

super_model=hub.load(super_hub_path)

23

func=super_model.signatures[tf.saved_model\

24

.DEFAULT_SERVING_SIGNATURE_DEF_KEY]

25

func.inputs[0].set_shape([1,lr_size,lr_size,3])

26

converter=tf.lite.TFLiteConverter.from_concrete_functions([func])

27

converter.optimizations=[tf.lite.Optimize.DEFAULT]

28

tflite_super_model=converter.convert()

29

with tf.io.gfile.GFile('ESRGAN.tflite','wb') as f:

30

    f.write(tflite_super_model)

31

esrgan_model_path='./ESRGAN.tflite'

32

from IPython.display import display,HTML

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

---

Messages

xxxxxxxxxx

 

1

def img2tensor(img,max_dim=max_dim):

2

    shape=tf.cast(tf.shape(img)[:-int(1)],tf.float32)

3

    scale=max_dim/max(shape)

4

    new_shape=tf.cast(shape*scale,tf.int32)

5

    img=tf.image.resize(img,new_shape)

6

    return tf.constant(img[tf.newaxis,:])

7

def tensor2img(tensor,frame=False,fig_size=2):

8

    if np.ndim(tensor)>int(3):

9

        assert tensor.shape[int(0)]==int(1); tensor=tensor[int(0)]

10

    return matrix_plot(tensor,frame=frame,

11

                       figsize=(fig_size,fig_size))

12

def interpolate_hypersphere(v1,v2,steps):

13

    v1norm=tf.norm(v1); v2norm=tf.norm(v2); vectors=[]

14

    v2normalized=v2*(v1norm/v2norm)

15

    for step in range(steps):

16

        interpolated=v1+(v2normalized-v1)*step/(steps-int(1))

17

        interpolated_norm=tf.norm(interpolated)

18

        interpolated_normalized=\

19

        interpolated*(v1norm/interpolated_norm)

20

        vectors.append(interpolated_normalized)

21

    return tf.stack(vectors)

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

---

Messages

xxxxxxxxxx

 

1

def pd_style():

2

    return [dict(selector='th',

3

                 props=[('font-size','12pt'),

4

                        ('min-width','150px')]),

5

            dict(selector='td',

6

                 props=[('padding','0em 0em'),

7

                        ('min-width','150px')]),

8

            dict(selector='tr:hover th:hover',

9

                 props=[('font-size','14pt'),

10

                        ('max-width','150px'),

11

                        ('text-shadow','3px 3px 3px #aaa')]),

12

            dict(selector='tr:hover td:hover',

13

                 props=[('font-size','12pt'),

14

                        ('max-width','150px'),

15

                        ('text-shadow','3px 3px 3px #aaa')])]

16

def display_images(images,labels,names,n):

17

    fig=pl.figure(figsize=(6,n/2))

18

    randch=np.random.choice(

19

        images.shape[0],size=n,replace=False)

20

    for i,idx in enumerate(randch):

21

        ax=fig.add_subplot(int(n//3)+1,3,i+1,

22

                           xticks=[],yticks=[])

23

        ax.imshow(images[idx],cmap='bone')

24

        label=[labels[:,idx]]

25

        name=[names[i][labels[i][idx]] 

26

                       for i in range(labels.shape[0])]

27

        ti='{} \n {}'.format(str(label),str(name))

28

        ax.set_title(ti,fontsize=8)

29

    pl.tight_layout(); pl.show()

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

---

Messages

xxxxxxxxxx

 

1

def h5file2data(h5file,cmap,img_size,resize=False):

2

    with h5py.File(h5file,'r') as f:

3

        keys=list(f.keys())

4

        pretty_print('file keys: '+', '.join(keys))

5

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

6

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

7

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

8

               for i in range(int(2),len(keys))]

9

        f.close()

10

    if resize:

11

        images=tf.image.resize(

12

            images,[img_size,img_size]).numpy()

13

    N=images.shape[0]; shuffle_ids=np.arange(N)

14

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

15

    images=images[shuffle_ids]

16

    labels=np.array([labels[i][shuffle_ids] 

17

                     for i in range(labels.shape[int(0)])])

18

    pretty_print('data outputs: ')

19

    df=pd.DataFrame([[images.shape,images.dtype],

20

                     [labels.shape,labels.dtype]],

21

                    columns=['shape','dtype'],

22

                    index=['images','labels'])

23

    display(df.style.set_table_styles(pd_style()))

24

    pretty_print('distribution of labels: ')

25

    idx=['labels %d'%(i+int(1)) for i in range(labels.shape[int(0)])]

26

    df=pd.DataFrame(labels,index=idx).T

27

    for i in range(labels.shape[int(0)]):

28

        df['name %d'%(i+int(1))]=[names[i][l] for l in labels[i]]

29

    fig=pl.figure(figsize=(6,6))    

30

    for i in range(labels.shape[int(0)]):

31

        ax=fig.add_subplot(labels.shape[int(0)],int(1),i+int(1))

32

        sn.countplot(y='name %s'%(i+1),data=df,

33

                     palette=cmap,alpha=.5,ax=ax)

34

    pl.tight_layout(); pl.show()       

35

    return [names,images,labels]

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

---

Messages

✒️ Data Loading & Processing

xxxxxxxxxx

 

1

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

2

output_file=open(file_name,'wb')

3

output_file.write(input_file.read())

4

output_file.close(); input_file.close()

5

[names,images,labels]=h5file2data(file_name,'tab20',img_size)

6

num_classes=len(names[int(1)])

7

display_images(images,labels,names,6)

8

os.remove(file_name)

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

---

Messages

✒️ Color Interpolation

xxxxxxxxxx

 

1

@interact(layout=dict(top=[['interpolation_steps'],

2

                           ['image_type1','image_object1'],

3

                           ['image_type2','image_object2']]))

4

def _pictograms(interpolation_steps=slider([20,30,..,60]),

5

                image_type1=selector(names[0],default='pictogram'),

6

                image_object1=selector(names[1],default='flower'),

7

                image_type2=selector(names[0],default='pictogram'),

8

                image_object2=selector(names[1],default='bird')):

9

    steps=int(interpolation_steps); global names,images,labels

10

    names1=[names[0].index(image_type1),

11

            names[1].index(image_object1)]

12

    names2=[names[0].index(image_type2),

13

            names[1].index(image_object2)]

14

    cond1=np.intersect1d(np.where(labels[0]==names1[0]),

15

                         np.where(labels[1]==names1[1]))

16

    cond2=np.intersect1d(np.where(labels[0]==names2[0]),

17

                         np.where(labels[1]==names2[1]))

18

    images1=images[cond1]; len1=images1.shape[0]

19

    images2=images[cond2]; len2=images2.shape[0]

20

    img1=images1[randint(0,len1-1)]

21

    img2=images2[randint(0,len2-1)]

22

    tensor2img(img1).show(); tensor2img(img2).show()

23

    imgs=np.vstack([interpolate_hypersphere(img1,img2,steps),

24

                    interpolate_hypersphere(img2,img1,steps)])

25

    animate([tensor2img(imgs[i]) for i in range(2*steps)]).show()

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

---

Messages

✒️ Style Transfer

xxxxxxxxxx

 

1

@interact(layout=dict(

2

    top=[['original_type','original_object'],

3

         ['style_type','style_object']]))

4

def _pictograms(

5

    original_type=selector(names[0],default='contour'),

6

    original_object=selector(names[1],default='butterfly'),

7

    style_type=selector(names[0],default='pictogram'),

8

    style_object=selector(names[1],default='butterfly')):

9

    global names,images,labels,style_model

10

    original_names=[names[0].index(original_type),

11

                    names[1].index(original_object)]

12

    style_names=[names[0].index(style_type),

13

                 names[1].index(style_object)]

14

    original_cond=np.intersect1d(

15

        np.where(labels[0]==original_names[0]),

16

        np.where(labels[1]==original_names[1]))

17

    style_cond=np.intersect1d(

18

        np.where(labels[0]==style_names[0]),

19

        np.where(labels[1]==style_names[1]))

20

    original_images=images[original_cond]

21

    original_len=original_images.shape[0]

22

    style_images=images[style_cond]; style_len=style_images.shape[0]

23

    original_img=original_images[randint(0,original_len-1)]

24

    style_img=style_images[randint(0,style_len-1)]

25

    tensor2img(original_img).show(); tensor2img(style_img).show()

26

    stylized_img=style_model(

27

        img2tensor(original_img,max_dim=int(256)),

28

        img2tensor(style_img,max_dim=int(256)))[int(0)]

29

    tensor2img(stylized_img).show()

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

---

Messages

✒️ Object Recognition

xxxxxxxxxx

 

1

@interact(layout=dict(

2

    top=[['original_type','original_object']]))

3

def _pictograms(

4

    original_type=selector(names[0],default='pictogram'),

5

    original_object=selector(names[1],default='dog')):

6

    global names,images,labels,mvgg19

7

    original_names=[names[0].index(original_type),

8

                    names[1].index(original_object)]

9

    original_cond=np.intersect1d(

10

        np.where(labels[0]==original_names[0]),

11

        np.where(labels[1]==original_names[1]))

12

    original_images=images[original_cond]

13

    original_len=original_images.shape[0]

14

    original_img=original_images[randint(0,original_len-1)]

15

    original_img=img2tensor(original_img)

16

    x=vgg19.preprocess_input(original_img*(int(255)))

17

    prediction_probabilities=mvgg19(x)

18

    predicted_top5=vgg19.decode_predictions(

19

        prediction_probabilities.numpy())[int(0)]

20

    tensor2img(original_img,frame=True,fig_size=3).show()

21

    t=[[number[1:],name.replace('_',' '),prob] 

22

        for (number,name,prob) in predicted_top5]

23

    display(table(t,frame=True))

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

---

Messages

✒️ Super Resolution

xxxxxxxxxx

 

1

@interact(layout=dict(

2

    top=[['original_type','original_object']]))

3

def _pictograms(

4

    original_type=selector(names[0],default='pictogram'),

5

    original_object=selector(names[1],default='horse')):

6

    global names,images,labels,esrgan_model_path,lr_size

7

    original_names=[names[0].index(original_type),

8

                    names[1].index(original_object)]

9

    original_cond=np.intersect1d(

10

        np.where(labels[0]==original_names[0]),

11

        np.where(labels[1]==original_names[1]))

12

    original_images=images[original_cond]

13

    original_len=original_images.shape[0]

14

    original_img=original_images[randint(0,original_len-1)]

15

    lr=tf.image.resize(original_img,[lr_size,lr_size])

16

    lr=tf.expand_dims(lr.numpy()[:,:,:int(3)],axis=int(0))

17

    lr=tf.cast(lr*int(255),tf.float32)

18

    interpreter=tf.lite.Interpreter(model_path=esrgan_model_path)

19

    interpreter.allocate_tensors()

20

    input_details=interpreter.get_input_details()

21

    output_details=interpreter.get_output_details()

22

    interpreter.set_tensor(input_details[int(0)]['index'],lr)

23

    interpreter.invoke()

24

    output_data=interpreter.get_tensor(output_details[0]['index'])

25

    sr=tf.squeeze(output_data,axis=int(0))

26

    sr=tf.clip_by_value(sr,int(0),int(255))

27

    sr=tf.cast(tf.round(sr),tf.uint8)

28

    lr=tf.cast(tf.squeeze(lr,axis=int(0)),tf.uint8)

29

    print('original 64x64 \n',

30

          '===> lower resolution 32x32 \n',

31

          '===> higher resolution 128x128')

32

    for img in [original_img,lr/int(255),sr/int(255)]: 

33

        tensor2img(img,frame=True,fig_size=3).show()

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

---

Messages

📑 Exercises with Adversarial Regularization

🌐   DL_PP8_1_SMC.html

📑 Deep Learning. Practice Project 8_1:
Exercises with Adversarial Regularization

✒️ Code Modules, Helpful Functions, & Settings

xxxxxxxxxx

 

1

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

2

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

3

!python3 -m pip install --upgrade neural_structured_learning \

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

9

import tensorflow as tf,pylab as pl,seaborn as sn

10

import neural_structured_learning as nsl

11

import tensorflow.keras.layers as tkl

12

import tensorflow.keras.callbacks as tkc

13

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

14

          'OlgaBelitskaya/data_kitchen/main/'

15

file_name='Pictograms64.h5'

16

model_weights='/tmp/checkpoint'

17

img_size=int(32)

18

from IPython.display import display,HTML

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

---

Messages

xxxxxxxxxx

 

1

def pd_style():

2

    return [dict(selector='th',

3

                 props=[('font-size','12pt'),

4

                        ('min-width','150px')]),

5

            dict(selector='td',

6

                 props=[('padding','0em 0em'),

7

                        ('min-width','150px')]),

8

            dict(selector='tr:hover th:hover',

9

                 props=[('font-size','14pt'),

10

                        ('max-width','150px'),

11

                        ('text-shadow','3px 3px 3px #aaa')]),

12

            dict(selector='tr:hover td:hover',

13

                 props=[('font-size','12pt'),

14

                        ('max-width','150px'),

15

                        ('text-shadow','3px 3px 3px #aaa')])]

16

def display_images(images,labels,names,n):

17

    fig=pl.figure(figsize=(6,n/2))

18

    randch=np.random.choice(

19

        images.shape[0],size=n,replace=False)

20

    for i,idx in enumerate(randch):

21

        ax=fig.add_subplot(int(n//3)+1,3,i+1,

22

                           xticks=[],yticks=[])

23

        ax.imshow(images[idx],cmap='bone')

24

        label=[labels[:,idx]]

25

        name=[names[i][labels[i][idx]] 

26

                       for i in range(labels.shape[0])]

27

        ti='{} \n {}'.format(str(label),str(name))

28

        ax.set_title(ti,fontsize=8)

29

    pl.tight_layout(); pl.show()

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

---

Messages

xxxxxxxxxx

 

1

def h5file2data(h5file,cmap,img_size,resize=True):

2

    with h5py.File(h5file,'r') as f:

3

        keys=list(f.keys())

4

        pretty_print('file keys: '+', '.join(keys))

5

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

6

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

7

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

8

               for i in range(int(2),len(keys))]

9

        f.close()

10

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

11

    if resize:

12

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

13

    shuffle_ids=np.arange(N)

14

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

15

    images=images[shuffle_ids]

16

    labels=np.array([labels[i][shuffle_ids] 

17

                     for i in range(labels.shape[int(0)])])

18

    x_test,x_valid,x_train=\

19

    images[:n],images[n:2*n],images[2*n:]

20

    y_test,y_valid,y_train=\

21

    labels[:,:n],labels[:,n:2*n],labels[:,2*n:]

22

    pretty_print('data outputs: ')

23

    df=pd.DataFrame([[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

    display(df.style.set_table_styles(pd_style()))

31

    pretty_print('distribution of labels: ')

32

    idx=['labels %d'%(i+int(1)) for i in range(labels.shape[int(0)])]

33

    df=pd.DataFrame(labels,index=idx).T

34

    for i in range(labels.shape[int(0)]):

35

        df['name %d'%(i+int(1))]=[names[i][l] for l in labels[i]]

36

    fig=pl.figure(figsize=(6,6))    

37

    for i in range(labels.shape[int(0)]):

38

        ax=fig.add_subplot(labels.shape[int(0)],int(1),i+int(1))

39

        sn.countplot(y='name %s'%(i+1),data=df,

40

                     palette=cmap,alpha=.5,ax=ax)

41

    pl.tight_layout(); pl.show()       

42

    return [names,x_train,x_valid,x_test,y_train,y_valid,y_test]

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

---

Messages

xxxxxxxxxx

 

1

def cb(mw):

2

    early_stopping=tf.keras.callbacks.EarlyStopping(

3

        monitor='val_sparse_categorical_accuracy',

4

        patience=int(20),verbose=int(2),mode='max')

5

    checkpointer=tf.keras.callbacks.ModelCheckpoint(

6

        save_best_only=True,save_weights_only=True,

7

        monitor='val_sparse_categorical_accuracy',

8

        filepath=mw,verbose=int(2),mode='max')

9

    lr_reduction=tf.keras.callbacks.ReduceLROnPlateau(

10

        monitor='val_sparse_categorical_accuracy',

11

        verbose=int(2),patience=int(5),factor=float(.9),mode='max')

12

    return [checkpointer,early_stopping,lr_reduction]

13

def keras_history_plot(

14

    fit_history,fig_size=6,color='#348ABD'):

15

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

16

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

17

                  for i in range(len(keys))]

18

    dfkeys=pd.DataFrame(list_history).T

19

    dfkeys.columns=keys

20

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

21

    ax1=fig.add_subplot(3,1,1)

22

    dfkeys.iloc[:,[0,4]].plot(

23

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

24

    ax2=fig.add_subplot(3,1,2)

25

    dfkeys.iloc[:,[3,7]].plot(

26

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

27

    ax3=fig.add_subplot(3,1,3)

28

    dfkeys.iloc[:,[2,6]].plot(

29

        ax=ax3,color=['slategray',color],grid=True)

30

    pl.tight_layout(); pl.show()

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

---

Messages

✒️ Data Loading & Processing

xxxxxxxxxx

 

1

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

2

output_file=open(file_name,'wb')

3

output_file.write(input_file.read())

4

output_file.close(); input_file.close()

5

[names,x_train,x_valid,x_test,y_train,y_valid,y_test]=\

6

h5file2data(file_name,'tab20',img_size)

7

num_classes=len(names[int(1)])

8

os.remove(file_name)

9

display_images(x_train,y_train,names,6)

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

---

Messages

xxxxxxxxxx

 

1

batch_size=int(16)

2

train=tf.data.Dataset.from_tensor_slices(

3

    {'input':x_train,

4

     'label':np.array(y_train[1],dtype='float32')})\

5

     .batch(batch_size)

6

valid=tf.data.Dataset.from_tensor_slices(

7

    {'input':x_valid,

8

     'label':np.array(y_valid[1],dtype='float32')})\

9

     .batch(batch_size)

10

valid_steps=x_valid.shape[0]//batch_size

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

---

Messages

✒️ Models with Adversarial Regularization => CNN

xxxxxxxxxx

 

1

base_model=tf.keras.Sequential([

2

    tf.keras.Input((img_size,img_size,int(3)),name='input'),

3

    tf.keras.layers.Conv2D(int(32),(int(5),int(5)),padding='same'),

4

    tf.keras.layers.Activation('relu'),

5

    tf.keras.layers.MaxPooling2D(pool_size=(int(2),int(2))),

6

    tf.keras.layers.Dropout(float(.25)),

7

    tf.keras.layers.Conv2D(int(96),(int(5),int(5))),

8

    tf.keras.layers.Activation('relu'),    

9

    tf.keras.layers.MaxPooling2D(pool_size=(int(2),int(2))),

10

    tf.keras.layers.Dropout(float(.25)),

11

    tf.keras.layers.GlobalMaxPooling2D(),    

12

    tf.keras.layers.Dense(int(256)),

13

    tf.keras.layers.Activation('relu'),

14

    tf.keras.layers.Dropout(float(.5)),

15

    tf.keras.layers.Dense(num_classes,activation='softmax')

16

])

17

adv_config=nsl.configs\

18

.make_adv_reg_config(multiplier=float(.2),adv_step_size=float(.05))

19

adv_model=nsl.keras\

20

.AdversarialRegularization(base_model,adv_config=adv_config)

21

adv_model.compile(optimizer='adam',metrics=['accuracy'],

22

                  loss='sparse_categorical_crossentropy')

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

---

Messages

xxxxxxxxxx

 

1

history=adv_model.fit(

2

    train,validation_data=valid,validation_steps=valid_steps,

3

    verbose=int(2),epochs=int(3),callbacks=cb(model_weights));

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

---

Messages

xxxxxxxxxx

 

1

keras_history_plot(history)

2

adv_model.load_weights(model_weights)

3

dict(zip(adv_model.metrics_names,adv_model.evaluate(

4

    {'input':x_test,

5

     'label':np.array(y_test[int(1)],dtype='float32')},

6

     verbose=int(0))))

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

---

Messages

xxxxxxxxxx

 

1

​

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

---

Messages