Menu
I am developing autoencoder on the dataset https://www.kaggle.com/jessicali9530/celeba-dataset.
import tensorflow
tensorflow.__version__
Output:
'2.2.0-rc3'
from tensorflow.keras.preprocessing import image
data_gen = image.ImageDataGenerator(rescale=1.0/255)
batch_size = 20
train_data_gen = data_gen.flow_from_directory(directory=train_dest_path,
target_size=(256, 256),
batch_size=batch_size,
shuffle=True,
class_mode = 'input')
test_data_gen = data_gen.flow_from_directory(directory=test_dest_path,
target_size=(256,256),
batch_size=batch_size,
shuffle=True,
class_mode= 'input')
# autoencoder
from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, UpSampling2D
from tensorflow.keras import Model
from tensorflow.keras.optimizers import Adam, SGD
#parameters
inchannel = 3
x, y = 256, 256
input_img = Input(shape=(x,y,inchannel))
def autoencoder_model(input_img):
#encoder
conv1 = Conv2D(32, kernel_size=(3,3), activation='relu', padding='same')(input_img)
pool1 = MaxPooling2D(pool_size=(2,2))(conv1)
conv2 = Conv2D(64, kernel_size=(3,3), activation='relu', padding='same')(pool1)
pool2 = MaxPooling2D(pool_size=(2,2))(conv2)
conv3 = Conv2D(128, kernel_size=(3,3), activation='relu', padding='same')(pool2)
#decoder
conv4 = Conv2D(128, kernel_size=(3,3), activation='relu', padding='same')(conv3)
pool3 = UpSampling2D(size=(2,2))(conv4)
conv5 = Conv2D(64, kernel_size=(3,3), activation='relu', padding='same')(pool3)
pool4 = UpSampling2D(size=(2,2))(conv5)
decoded = Conv2D(3, kernel_size=(3,3), activation='relu', padding='same')(pool4)
return decoded
model = Model(inputs=input_img, outputs=autoencoder_model(input_img))
model.compile(loss='mean_squared_error', optimizer=Adam())
model.summary()
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 256, 256, 3)] 0
_________________________________________________________________
conv2d (Conv2D) (None, 256, 256, 32) 896
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 128, 128, 32) 0
_________________________________________________________________
conv2d_1 (Conv2D) (None, 128, 128, 64) 18496
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 64, 64, 64) 0
_________________________________________________________________
conv2d_2 (Conv2D) (None, 64, 64, 128) 73856
_________________________________________________________________
conv2d_3 (Conv2D) (None, 64, 64, 128) 147584
_________________________________________________________________
up_sampling2d (UpSampling2D) (None, 128, 128, 128) 0
_________________________________________________________________
conv2d_4 (Conv2D) (None, 128, 128, 64) 73792
_________________________________________________________________
up_sampling2d_1 (UpSampling2 (None, 256, 256, 64) 0
_________________________________________________________________
conv2d_5 (Conv2D) (None, 256, 256, 3) 1731
=================================================================
Total params: 316,355
Trainable params: 316,355
Non-trainable params: 0
from tensorflow.keras.callbacks import ModelCheckpoint
epochs = 2
num_training_steps = train_data_gen.samples/batch_size
checkpoint_directory = '/gdrive/My Drive/Colab Notebooks'
checkpoint = ModelCheckpoint(checkpoint_directory, verbose=1, save_weights_only=False, save_freq='epoch')
model.fit(train_data_gen, epochs=epochs, verbose=1, callbacks=[checkpoint])
Output:
Epoch 1/2
103/Unknown - 8s 80ms/step - loss: 0.0175
After spending a lot of time, I am still not able to understand why I am getting "Unknown" in the output of model.fit(). Also, model.fit() keeps running forever even though if I take only 1000 images from the training dataset in flow_from_directory(). It goes above 1000 and I am not able to understand why it is acting like that.
662
A number of epochs mean how many times you go through your training set. The model is updated each time a batch is processed, which means that it can be updated multiple times during one epoch. If batch_size is set equal to the length of x, then the model will be updated once per epoch. Hope this answer helps.
Epoch: In terms of artificial neural networks, an epoch refers to one cycle through the full training dataset. Usually, training a neural network takes more than a few epochs. Loss: A scalar value that we attempt to minimize during our training of the model.
Traditionally, the steps per epoch is calculated as train_length // batch_size, since this will use all of the data points, one batch size worth at a time. If you are augmenting the data, then you can stretch this a tad (sometimes I multiply that function above by 2 or 3 etc.
By default Keras' model. fit() returns a History callback object. This object keeps track of the accuracy, loss and other training metrics, for each epoch, in the memory.
When executing model.fit with a generator as input you have to set the steps_per_epoch argument. For generators you can't know the number of images they output (and in this case they go on forever), so set it to the number of images in your dataset divided by your batch size.
81
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With
