 Visualizza su TensorFlow.org |  Esegui in Google Colab |  Visualizza la fonte su GitHub |  Scarica taccuino |
Panoramica
Questo notebook mostra come utilizzare Moving Average Optimizer insieme al Model Average Checkpoint dal pacchetto di componenti aggiuntivi tensorflow.
Media mobile
Il vantaggio di Moving Averaging è che sono meno inclini a spostamenti di perdita dilaganti o rappresentazione irregolare dei dati nell'ultimo batch. Dà un'idea più fluida e più generale dell'addestramento del modello fino a un certo punto.
Media stocastica
La media ponderale stocastica converge verso ottimi più ampi. In tal modo, assomiglia all'incastonatura geometrica. SWA è un metodo semplice per migliorare le prestazioni del modello quando viene utilizzato come involucro attorno ad altri ottimizzatori e per calcolare la media dei risultati da diversi punti di traiettoria dell'ottimizzatore interno.
Punto di controllo medio del modello
callbacks.ModelCheckpointnon ti dà la possibilità di salvare in movimento pesi medi nel bel mezzo di formazione, che è il motivo per cui Girl media ottimizzatori richiesto un callback personalizzato. Utilizzandoupdate_weightsparametro,ModelAverageCheckpointconsente di:
- Assegnare i pesi della media mobile al modello e salvarli.
- Mantieni i vecchi pesi non medi, ma il modello salvato utilizza i pesi medi.
Impostare
pip install -U tensorflow-addons
import tensorflow as tf
import tensorflow_addons as tfa
import numpy as np
import os
Costruisci modello
def create_model(opt):
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(64, activation='relu'),
tf.keras.layers.Dense(64, activation='relu'),
tf.keras.layers.Dense(10, activation='softmax')
])
model.compile(optimizer=opt,
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
return model
Prepara set di dati
#Load Fashion MNIST dataset
train, test = tf.keras.datasets.fashion_mnist.load_data()
images, labels = train
images = images/255.0
labels = labels.astype(np.int32)
fmnist_train_ds = tf.data.Dataset.from_tensor_slices((images, labels))
fmnist_train_ds = fmnist_train_ds.shuffle(5000).batch(32)
test_images, test_labels = test
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-labels-idx1-ubyte.gz 32768/29515 [=================================] - 0s 0us/step 40960/29515 [=========================================] - 0s 0us/step Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-images-idx3-ubyte.gz 26427392/26421880 [==============================] - 0s 0us/step 26435584/26421880 [==============================] - 0s 0us/step Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-labels-idx1-ubyte.gz 16384/5148 [===============================================================================================] - 0s 0us/step Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-images-idx3-ubyte.gz 4423680/4422102 [==============================] - 0s 0us/step 4431872/4422102 [==============================] - 0s 0us/step
Confronteremo tre ottimizzatori qui:
- SGD non confezionato
- SGD con media mobile
- SGD con peso medio stocastico
E guarda come si comportano con lo stesso modello.
#Optimizers
sgd = tf.keras.optimizers.SGD(0.01)
moving_avg_sgd = tfa.optimizers.MovingAverage(sgd)
stocastic_avg_sgd = tfa.optimizers.SWA(sgd)
Entrambi MovingAverage e StocasticAverage optimers utilizzano ModelAverageCheckpoint .
#Callback
checkpoint_path = "./training/cp-{epoch:04d}.ckpt"
checkpoint_dir = os.path.dirname(checkpoint_path)
cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_dir,
save_weights_only=True,
verbose=1)
avg_callback = tfa.callbacks.AverageModelCheckpoint(filepath=checkpoint_dir,
update_weights=True)
Modello di treno
Ottimizzatore SGD vaniglia
#Build Model
model = create_model(sgd)
#Train the network
model.fit(fmnist_train_ds, epochs=5, callbacks=[cp_callback])
Epoch 1/5 1875/1875 [==============================] - 4s 2ms/step - loss: 0.8031 - accuracy: 0.7282 Epoch 00001: saving model to ./training Epoch 2/5 1875/1875 [==============================] - 3s 2ms/step - loss: 0.5049 - accuracy: 0.8240 Epoch 00002: saving model to ./training Epoch 3/5 1875/1875 [==============================] - 3s 2ms/step - loss: 0.4591 - accuracy: 0.8375 Epoch 00003: saving model to ./training Epoch 4/5 1875/1875 [==============================] - 3s 2ms/step - loss: 0.4328 - accuracy: 0.8492 Epoch 00004: saving model to ./training Epoch 5/5 1875/1875 [==============================] - 3s 2ms/step - loss: 0.4128 - accuracy: 0.8561 Epoch 00005: saving model to ./training <keras.callbacks.History at 0x7fc9d0262250>
#Evalute results
model.load_weights(checkpoint_dir)
loss, accuracy = model.evaluate(test_images, test_labels, batch_size=32, verbose=2)
print("Loss :", loss)
print("Accuracy :", accuracy)
313/313 - 0s - loss: 95.4645 - accuracy: 0.7796 Loss : 95.46446990966797 Accuracy : 0.7796000242233276
Media mobile SGD
#Build Model
model = create_model(moving_avg_sgd)
#Train the network
model.fit(fmnist_train_ds, epochs=5, callbacks=[avg_callback])
Epoch 1/5 1875/1875 [==============================] - 4s 2ms/step - loss: 0.8064 - accuracy: 0.7303 2021-09-02 00:35:29.787996: W tensorflow/python/util/util.cc:348] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them. INFO:tensorflow:Assets written to: ./training/assets Epoch 2/5 1875/1875 [==============================] - 4s 2ms/step - loss: 0.5114 - accuracy: 0.8223 INFO:tensorflow:Assets written to: ./training/assets Epoch 3/5 1875/1875 [==============================] - 4s 2ms/step - loss: 0.4620 - accuracy: 0.8382 INFO:tensorflow:Assets written to: ./training/assets Epoch 4/5 1875/1875 [==============================] - 4s 2ms/step - loss: 0.4345 - accuracy: 0.8470 INFO:tensorflow:Assets written to: ./training/assets Epoch 5/5 1875/1875 [==============================] - 4s 2ms/step - loss: 0.4146 - accuracy: 0.8547 INFO:tensorflow:Assets written to: ./training/assets <keras.callbacks.History at 0x7fc8e16f30d0>
#Evalute results
model.load_weights(checkpoint_dir)
loss, accuracy = model.evaluate(test_images, test_labels, batch_size=32, verbose=2)
print("Loss :", loss)
print("Accuracy :", accuracy)
313/313 - 0s - loss: 95.4645 - accuracy: 0.7796 Loss : 95.46446990966797 Accuracy : 0.7796000242233276
Peso stocastico medio SGD
#Build Model
model = create_model(stocastic_avg_sgd)
#Train the network
model.fit(fmnist_train_ds, epochs=5, callbacks=[avg_callback])
Epoch 1/5 1875/1875 [==============================] - 5s 2ms/step - loss: 0.7896 - accuracy: 0.7350 INFO:tensorflow:Assets written to: ./training/assets Epoch 2/5 1875/1875 [==============================] - 5s 2ms/step - loss: 0.5670 - accuracy: 0.8065 INFO:tensorflow:Assets written to: ./training/assets Epoch 3/5 1875/1875 [==============================] - 5s 2ms/step - loss: 0.5345 - accuracy: 0.8142 INFO:tensorflow:Assets written to: ./training/assets Epoch 4/5 1875/1875 [==============================] - 5s 2ms/step - loss: 0.5194 - accuracy: 0.8188 INFO:tensorflow:Assets written to: ./training/assets Epoch 5/5 1875/1875 [==============================] - 5s 2ms/step - loss: 0.5089 - accuracy: 0.8235 INFO:tensorflow:Assets written to: ./training/assets <keras.callbacks.History at 0x7fc8e0538790>
#Evalute results
model.load_weights(checkpoint_dir)
loss, accuracy = model.evaluate(test_images, test_labels, batch_size=32, verbose=2)
print("Loss :", loss)
print("Accuracy :", accuracy)
313/313 - 0s - loss: 95.4645 - accuracy: 0.7796 Loss : 95.46446990966797 Accuracy : 0.7796000242233276