Capacitamos a la red generativa competitiva para dibujar imágenes en Azure ML

El aprendizaje profundo a veces parece pura magia, ¡especialmente cuando la computadora aprende a hacer algo realmente creativo, por ejemplo, para pintar cuadros! La tecnología utilizada para esto se llama GAN, una red generativa competitiva, y en este artículo veremos cómo se organizan dichas redes y cómo capacitarlas para generar imágenes usando Azure Machine Learning.

Esta publicación es parte de la iniciativa AI April . Todos los días de abril, mis colegas de Microsoft escriben artículos interesantes sobre inteligencia artificial y aprendizaje automático. Mire el calendario : de repente encontrará otros temas de interés para usted. Los artículos son principalmente en inglés.

Azure ML VS Code ), , Azure ML. , "" MNIST. Azure ML — , , :

, 2019, Art of the Artificial keragan WikiArt:	, 2019, keragan WikiArt:

WikiArt. , , , WikiArt Retriever, WikiArt Dataset GANGogh.

, dataset. , , :

, , ( , ), (, ) .

-

- (GAN).

GAN keragan Keras, .

GAN :

• ,
• , "" ( )

GAN :

1. :
   

   noise = np.random.normal(0, 1, (batch_size, latent_dim))
   gen_imgs = generator.predict(noise)
   imgs = get_batch(batch_size)

2. . ones zeros :
   

   d_loss_r = discriminator.train_on_batch(imgs, ones)
   d_loss_f = discriminator.train_on_batch(gen_imgs, zeros)
   d_loss = np.add(d_loss_r , d_loss_f)*0.5

3. , , :
   

   g_loss = combined.train_on_batch(noise, ones)

, — :

discriminator = create_discriminator()
generator = create_generator()
discriminator.compile(loss='binary_crossentropy',optimizer=optimizer, 
                      metrics=['accuracy'])
discriminator.trainable = False
z = keras.models.Input(shape=(latent_dim,))
img = generator(z)
valid = discriminator(img)
combined = keras.models.Model(z, valid)
combined.compile(loss='binary_crossentropy', optimizer=optimizer)

, (CNN). 64x64 :

discriminator = Sequential()

for x in [16,32,64]: # number of filters on next layer
    discriminator.add(Conv2D(x, (3,3), strides=1, padding="same"))
    discriminator.add(AveragePooling2D())
    discriminator.addBatchNormalization(momentum=0.8))
    discriminator.add(LeakyReLU(alpha=0.2))
    discriminator.add(Dropout(0.3))

discriminator.add(Flatten())
discriminator.add(Dense(1, activation='sigmoid'))

3 :

• 64x64x3 16- , ( AveragePooling2D ) 32x32x16.
• 32x32x16 16x16x32
• 8x8x64.

, ( — Dense ).

. , , — latent_dim=100. , , 100..

— 100 . . UpSampling2D , :

generator = Sequential()
generator.add(Dense(8 * 8 * 2 * size, activation="relu", 
                                      input_dim=latent_dim))
generator.add(Reshape((8, 8, 2 * size)))

for x in [64;32;16]:
    generator.add(UpSampling2D())
    generator.add(Conv2D(x, kernel_size=(3,3),strides=1,padding="same"))
    generator.add(BatchNormalization(momentum=0.8))
    generator.add(Activation("relu"))

generator.add(Conv2D(3, kernel_size=3, padding="same"))
generator.add(Activation("tanh"))

64x64x3, . tanh [-1;1] — , . , , ImageDataset, .

Azure ML

- , Azure ML !

, , . Azure ML , (accuracy) (loss). run.log, , Azure ML.

, , ( ) . , , .. - , .

, Azure ML , . log_image, numpy-, , matplotlib. , , . callbk, keragan :

def callbk(tr):
    if tr.gan.epoch % 20 == 0:
        res = tr.gan.sample_images(n=3)
        fig,ax = plt.subplots(1,len(res))
        for i,v in enumerate(res):
            ax[i].imshow(v[0])
        run.log_image("Sample",plot=plt)

:

gan = keragan.DCGAN(args)
imsrc = keragan.ImageDataset(args)
imsrc.load()
train = keragan.GANTrainer(image_dataset=imsrc,gan=gan,args=args)

train.train(callbk)

, keragan , args, , , , learning rate ..

Azure ML VS Code, , SDK, Azure ML. submit_gan.ipynb, :

• : ws = Workspace.from_config()
• : cluster = ComputeTarget(workspace=ws, name='My Cluster'). GPU, [NC6][AzureVMNC].
• : ds.upload(...).

, , :

exp = Experiment(workspace=ws, name='KeraGAN')
script_params = {
    '--path': ws.get_default_datastore(),
    '--dataset' : 'faces',
    '--model_path' : './outputs/models',
    '--samples_path' : './outputs/samples',
    '--batch_size' : 32,
    '--size' : 512,
    '--learning_rate': 0.0001,
    '--epochs' : 10000
}
est = TensorFlow(source_directory='.',
    script_params=script_params,
    compute_target=cluster,
    entry_script='train_gan.py',
    use_gpu = True,
    conda_packages=['keras','tensorflow','opencv','tqdm','matplotlib'],
    pip_packages=['git+https://github.com/shwars/keragan@v0.0.1']

run = exp.submit(est)

model_path=./outputs/models samples_path=./outputs/samples, ( ) outputs. , , Azure ML.

Estimator, GPU, Tensorflow. Estimator, " " . Estimator- .

— , keragan GitHub. PyPI pip-, , GitHub , commit ID. , PyPI.

, Azure ML Portal:

GAN , . -, learning rate: , — . .

:

• --size , . (64 128) , ( 1024) . 1024 , , progressive growing
• --learning_rate . , .
• --dateset. , , Azure ML datastore, .

, for, . , . .

, , . outputs/models, — outputs/samples. Azure ML Portal :

, , . run, , , ( ):

run.download_files(prefix='outputs/samples')

outputs/samples, .

run ( , ), , run id, :

run = Run(experiment=exp,run_id='KeraGAN_1584082108_356cf603')

. , , . , ( gen_):

fnames = run.get_file_names()
fnames = filter(lambda x : x.startswith('outputs/models/gen_'),fnames)

: outputs/models/gen_0.h5, outputs/models/gen_100.h5 .. :

no = max(map(lambda x: int(x[19:x.find('.')]), fnames))
fname = 'outputs/models/gen_{}.h5'.format(no)
fname_wout_path = fname[fname.rfind('/')+1:]
run.download_file(fname)

, fname_wout_path.

, Keras, , , , :

model = keras.models.load_model(fname_wout_path)
latent_dim=model.layers[0].input.shape[1].value
res = model.predict(np.random.normal(0,1,(10,latent_dim)))

, [-1,1], [0,1], matplotlib:

res = (res+1.0)/2
fig,ax = plt.subplots(1,10,figsize=(15,10))
for i in range(10):
    ax[i].imshow(res[i])

:

, :

Colourful Spring, 2020	Countryside, 2020
Through the Icy Glass, 2020	Summer Landscape, 2020

( ) , — @art_of_artificial, .

, - . , , . , :

- , Azure. , . , — — . ? ...

keragan, , DCGAN, Maxime Ellerbach, GANGogh. GAN Keras .

Azure ML

• Azure ML
• Azure ML
• - Azure ML ( )