Saya telah melakukan kode ini dan saya perlu memuat model agar berfungsi nanti, tetapi ketika saya mencoba menggunakan load_model() kesalahannya adalah Tidak ada model yang ditemukan di file konfigurasi. Dan ketika saya mencoba memuat bobot kesalahannya adalah Tidak dapat memuat bobot yang disimpan dalam format HDF5 ke dalam Model subkelas yang belum membuat variabelnya. Panggil Model terlebih dahulu, lalu muat bobotnya.
Ini kode saya
class Sampling(layers.Layer):
"""Uses (z_mean, z_log_var) to sample z, the vector encoding a digit."""
def call(self, inputs):
z_mean, z_log_var = inputs
batch = tf.shape(z_mean)[0]
dim = tf.shape(z_mean)[1]
epsilon = tf.keras.backend.random_normal(shape=(batch, dim))
return z_mean + tf.exp(0.5 * z_log_var) * epsilon
Saya mendefinisikan encoder dan decoder yang akan saya gunakan nanti
class VAE(keras.Model):
def __init__(self, encoder, decoder, **kwargs):
super(VAE, self).__init__(**kwargs)
self.encoder = encoder
self.decoder = decoder
def train_step(self, data):
if isinstance(data, tuple):
data = data[0]
with tf.GradientTape() as tape:
z_mean, z_log_var, z = encoder(data)
reconstruction = decoder(z)
reconstruction_loss = tf.reduce_mean(
keras.losses.binary_crossentropy(data, reconstruction)
)
reconstruction_loss *= 64 * 64 * 3
kl_loss = 1 + z_log_var - tf.square(z_mean) - tf.exp(z_log_var)
kl_loss = tf.reduce_mean(kl_loss)
kl_loss *= -0.5
total_loss = reconstruction_loss + kl_loss
grads = tape.gradient(total_loss, self.trainable_weights)
self.optimizer.apply_gradients(zip(grads, self.trainable_weights))
return {
"loss": total_loss,
"reconstruction_loss": reconstruction_loss,
"kl_loss": kl_loss,
}
def test_step(self, data):
if isinstance(data, tuple):
data = data[0]
with tf.GradientTape() as tape:
z_mean, z_log_var, z = encoder(data)
reconstruction = decoder(z)
reconstruction_loss = tf.reduce_mean(
keras.losses.binary_crossentropy(data, reconstruction)
)
reconstruction_loss *= 64 * 64 * 3
kl_loss = 1 + z_log_var - tf.square(z_mean) - tf.exp(z_log_var)
kl_loss = tf.reduce_mean(kl_loss)
kl_loss *= -0.5
total_loss = reconstruction_loss + kl_loss
grads = tape.gradient(total_loss, self.trainable_weights)
self.optimizer.apply_gradients(zip(grads, self.trainable_weights))
return {
"loss": total_loss,
"reconstruction_loss": reconstruction_loss,
"kl_loss": kl_loss,
}
Akhirnya beginilah cara saya menggunakannya dan membuat model
model_name = 'car_racing_VAE.h5'
vae = VAE(encoder, decoder)
vae.compile(optimizer=keras.optimizers.Adam(0.001))
checkpointer = keras.callbacks.ModelCheckpoint(filepath=model_name, monitor='val_loss', verbose=1, save_best_only=True, mode='min', save_freq='epoch')
history = vae.fit(train, train,
epochs=150,
batch_size = 128,
shuffle=True,
validation_data=(val, val), validation_batch_size=128,
callbacks=[checkpointer])
Jadi, bagaimana cara memuat model dan menggunakannya nanti?
model = load_model(model_name)
vae.load_weights(model_name)
Tak satu pun dari mereka yang bekerja
Unable to load weights saved in HDF5 format into a subclassed Model which has not created its variables yet. Call the Model first, then load the weights.
AtauNo model found in config file.
saat menggunakanmodel = load_model('my_model.h5')
- person Marisol Rodriguez   schedule 18.11.2020