I am running into problems with my code after I removed the loss function of the compile
step (set it equal to loss=None
) and added one with the intention of adding another, loss function through the add_loss
method. I can call fit
and it trains for one epoch but then I get this error:
ValueError: operands could not be broadcast together with shapes (128,) (117,) (128,)
My batch size is 128. It looks like 117
is somehow dependent on the number of examples that I am using. When I vary the number of examples, I get different numbers from 117
. They are all my number of examples mod my batch size. I am at a loss about how to fix this issue. I am using tf.data.TFRecordDataset
as input.
I have the following simplified model:
class MyModel(Model):
def __init__(self):
super(MyModel, self).__init__()
encoder_input = layers.Input(shape=INPUT_SHAPE, name='encoder_input')
x = encoder_input
x = layers.Conv2D(64, (3, 3), activation='relu', padding='same', strides=2)(x)
x = layers.BatchNormalization()(x)
x = layers.Conv2D(32, (3, 3), activation='relu', padding='same', strides=2)(x)
x = layers.BatchNormalization()(x)
x = layers.Flatten()(x)
encoded = layers.Dense(LATENT_DIM, name='encoded')(x)
self.encoder = Model(encoder_input, outputs=[encoded])
self.decoder = tf.keras.Sequential([
layers.Input(shape=LATENT_DIM),
layers.Dense(32 * 32 * 32),
layers.Reshape((32, 32, 32)),
layers.Conv2DTranspose(32, kernel_size=3, strides=2, activation='relu', padding='same'),
layers.Conv2DTranspose(64, kernel_size=3, strides=2, activation='relu', padding='same'),
layers.Conv2D(3, kernel_size=(3, 3), activation='sigmoid', padding='same')])
def call(self, x):
encoded = self.encoder(x)
decoded = self.decoder(encoded)
# Loss function. Has to be here because I intend to add another, more layer-interdependent, loss function.
r_loss = tf.math.reduce_sum(tf.math.square(x - decoded), axis=[1, 2, 3])
self.add_loss(r_loss)
return decoded
def read_tfrecord(example):
example = tf.io.parse_single_example(example, CELEB_A_FORMAT)
image = decode_image(example['image'])
return image, image
def load_dataset(filenames, func):
dataset = tf.data.TFRecordDataset(
filenames
)
dataset = dataset.map(partial(func), num_parallel_calls=tf.data.AUTOTUNE)
return dataset
def train_autoencoder():
filenames_train = glob.glob(TRAIN_PATH)
train_dataset_x_x = load_dataset(filenames_train[:4], func=read_tfrecord)
autoencoder = Autoencoder()
# The loss function used to be defined here and everything worked fine before.
def r_loss(y_true, y_pred):
return tf.math.reduce_sum(tf.math.square(y_true - y_pred), axis=[1, 2, 3])
optimizer = tf.keras.optimizers.Adam(1e-4)
autoencoder.compile(optimizer=optimizer, loss=None)
autoencoder.fit(train_dataset_x_x.batch(AUTOENCODER_BATCH_SIZE),
epochs=AUTOENCODER_NUM_EPOCHS,
shuffle=True)
CodePudding user response:
If you only want to get rid of the error and don't care about the last "remainder" batch of your dataset, you can use the keyword argument drop_remainder=True
inside of train_dataset_x_x.batch()
, that way all of your batches will be the same size.
FYI, it's usually better practice to batch your dataset outside of the function call for fit
:
data = data.batch(32)
model.fit(data)
CodePudding user response:
the loss function can not be set in the call method . the call method is intended to make a forward pass not to copute the loss .
u need to add the loss function in the compile method or after it