import os
os.environ['KERAS_BACKEND'] = 'torch'

import keras

import numpy as np
from skimage import io
import random

from modules.AE5_builder    import AE5_builder
from modules.MNIST          import MNIST
from modules.ImagesCallback import ImagesCallback

import fidle


# Init Fidle environment
run_id, run_dir, datasets_dir = fidle.init('K3AE5')

Version              : 2.3.2
Run id               : K3AE5
Run dir              : ./run/K3AE5
Datasets dir         : /lustre/fswork/projects/rech/mlh/uja62cb/fidle-project/datasets-fidle
Start time           : 22/12/24 21:30:22
Hostname             : r3i6n0 (Linux)
Tensorflow log level : Info + Warning + Error  (=0)
Update keras cache   : False
Update torch cache   : False
Save figs            : ./run/K3AE5/figs (True)
keras                : 3.7.0
numpy                : 2.1.2
sklearn              : 1.5.2
yaml                 : 6.0.2
skimage              : 0.24.0
matplotlib           : 3.9.2
pandas               : 2.2.3
torch                : 2.5.0

prepared_dataset = './data/mnist-noisy.h5'
dataset_seed     = None

scale            = .1

train_prop       = .8
batch_size       = 128
epochs           = 10
fit_verbosity    = 1

fidle.override('prepared_dataset', 'dataset_seed', 'scale')
fidle.override('train_prop', 'batch_size', 'epochs', 'fit_verbosity')

** Overrided parameters : **
scale                : 1
** Overrided parameters : **
epochs               : 30
fit_verbosity        : 2

clean_train,clean_test, noisy_train,noisy_test, class_train,class_test = MNIST.reload_prepared_dataset(
                                                                                    scale      = scale, 
                                                                                    train_prop = train_prop,
                                                                                    seed       = dataset_seed,
                                                                                    shuffle    = True,
                                                                                    filename   = prepared_dataset )

Loaded.
rescaled (1).
Seeded (None)

Shuffled.
splited (0.8).

clean_train shape is :  (56000, 28, 28, 1)
clean_test  shape is :  (14000, 28, 28, 1)
noisy_train shape is :  (56000, 28, 28, 1)
noisy_test  shape is :  (14000, 28, 28, 1)
class_train shape is :  (56000,)
class_test  shape is :  (14000,)
Blake2b digest is    :  296f23be5f05c00ca9e9

builder = AE5_builder( ae   = { 'latent_dim':10 }, 
                       cnn1 = { 'lc1':8,  'lc2':16, 'ld':100 }, 
                       cnn2 = { 'lc1':32, 'lc2':64, 'ld':50 } )

model = builder.create_model()

model.compile(optimizer='rmsprop', 
              loss={'ae':'binary_crossentropy', 'classifier':'sparse_categorical_crossentropy'},
              loss_weights={'ae':1., 'classifier':1.},
              metrics={'classifier':'accuracy'} )

# ---- Callback : Images
#
fidle.utils.mkdir( run_dir + '/images')
filename = run_dir + '/images/image-{epoch:03d}-{i:02d}.jpg'

encoder = model.get_layer('ae').get_layer('encoder')
decoder = model.get_layer('ae').get_layer('decoder')

callback_images = ImagesCallback(filename, x=clean_test[:5], encoder=encoder,decoder=decoder)

chrono = fidle.Chrono()
chrono.start()

history = model.fit(noisy_train, [clean_train, class_train],
                 batch_size      = batch_size,
                 epochs          = epochs,
                 verbose         = fit_verbosity,
                 validation_data = (noisy_test, [clean_test, class_test]),
                 callbacks       = [ callback_images ] ) 


chrono.show()

Epoch 1/30

/lustre/fswork/projects/rech/mlh/uja62cb/local/fidle-k3/lib/python3.12/site-packages/keras/src/backend/common/backend_utils.py:91: UserWarning: You might experience inconsistencies across backends when calling conv transpose with kernel_size=3, stride=2, dilation_rate=1, padding=same, output_padding=1.
  warnings.warn(

1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 10ms/step


1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 11ms/step

1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step


1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 5ms/step

438/438 - 11s - 26ms/step - ae_loss: 0.2621 - classifier_accuracy: 0.6411 - classifier_loss: 1.0617 - loss: 1.3238 - val_ae_loss: 0.2087 - val_classifier_accuracy: 0.8189 - val_classifier_loss: 0.5657 - val_loss: 0.7744

Epoch 2/30

1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step


1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step

os.makedirs(f'{run_dir}/models', exist_ok=True)

model.save_weights(f'{run_dir}/models/model.weights.h5')

fidle.scrawler.history(history,  plot={'Loss':['loss', 'val_loss'],
                                 'Accuracy':['classifier_accuracy','val_classifier_accuracy']}, save_as='01-history')

imgs=[]
for epoch in range(0,epochs,4):
    for i in range(5):
        filename = run_dir + '/images/image-{epoch:03d}-{i:02d}.jpg'.format(epoch=epoch, i=i)
        img      = io.imread(filename)
        imgs.append(img)      

fidle.utils.subtitle('Real images (clean_test) :')
fidle.scrawler.images(clean_test[:5], None, indices='all', columns=5, x_size=2,y_size=2, interpolation=None, save_as='02-original-real')

fidle.utils.subtitle('Noisy images (noisy_test) :')
fidle.scrawler.images(noisy_test[:5], None, indices='all', columns=5, x_size=2,y_size=2, interpolation=None, save_as='03-original-noisy')

fidle.utils.subtitle('Evolution during the training period (denoised_test) :')
fidle.scrawler.images(imgs, None, indices='all', columns=5, x_size=2,y_size=2, interpolation=None, y_padding=0.1, save_as='04-learning')

fidle.utils.subtitle('Noisy images (noisy_test) :')
fidle.scrawler.images(noisy_test[:5], None, indices='all', columns=5, x_size=2,y_size=2, interpolation=None, save_as=None)

fidle.utils.subtitle('Real images (clean_test) :')
fidle.scrawler.images(clean_test[:5], None, indices='all', columns=5, x_size=2,y_size=2, interpolation=None, save_as=None)

builder = AE5_builder( ae   = { 'latent_dim':10 }, 
                       cnn1 = { 'lc1':8,  'lc2':16, 'ld':100 }, 
                       cnn2 = { 'lc1':32, 'lc2':64, 'ld':50 } )

model = builder.create_model()

model.load_weights(f'{run_dir}/models/model.weights.h5')

outputs = model.predict(noisy_test, verbose=0)

denoised = outputs['ae']
classcat = outputs['classifier']

print('Denoised images   (denoised_test) shape : ', denoised.shape)
print('Predicted classes (classcat_test) shape : ', classcat.shape)

Denoised images   (denoised_test) shape :  (14000, 28, 28, 1)
Predicted classes (classcat_test) shape :  (14000, 10)

i=random.randint(0,len(denoised)-8)
j=i+8

fidle.utils.subtitle('Noisy test images (input):')
fidle.scrawler.images(noisy_test[i:j], None, indices='all', columns=8, x_size=2,y_size=2, interpolation=None, save_as='05-test-noisy')

fidle.utils.subtitle('Denoised images (output):')
fidle.scrawler.images(denoised[i:j], None, indices='all', columns=8, x_size=2,y_size=2, interpolation=None, save_as='06-test-predict')

fidle.utils.subtitle('Real test images :')
fidle.scrawler.images(clean_test[i:j], None, indices='all', columns=8, x_size=2,y_size=2, interpolation=None, save_as='07-test-real')

# We need to (re)compile our resurrected model (to specify loss and metrics)
#
model.compile(optimizer='rmsprop', 
              loss={'ae':'binary_crossentropy', 'classifier':'sparse_categorical_crossentropy'},
              loss_weights={'ae':1., 'classifier':1.},
              metrics={'classifier':'accuracy'} )


# Get an evaluation
#
score = model.evaluate(noisy_test, [clean_test, class_test], verbose=0)

# And show results
#
fidle.utils.subtitle("Accuracy :")
print(f'Classification accuracy : {score[1]:4.4f}')

fidle.utils.subtitle("Few examples :")
classid_test  = np.argmax(classcat, axis=-1)
fidle.scrawler.images(noisy_test, class_test, range(0,200), columns=12, x_size=1, y_size=1, y_pred=classid_test, save_as='04-predictions')

Classification accuracy : 0.1482

fidle.end()

[K3AE5] - Advanced denoiser and classifier model¶

Objectives :¶

What we're going to do :¶

Data Terminology :¶

Step 1 - Init python stuff¶

1.1 - Init¶

1.2 - Parameters¶

Step 2 - Retrieve dataset¶

Step 3 - Build model¶

Step 4 - Train¶

Step 5 - History¶

Step 6 - Denoising progress¶

Step 7 - Evaluation¶

7.1 - Reload our best model¶

7.2 - Let's make a prediction¶

7.3 - Denoised images¶

7.4 - Class prediction¶