طبقات إضافات TensorFlow: تسوية الوزن

ملخص

سيوضح هذا الكمبيوتر الدفتري كيفية استخدام طبقة تسوية الوزن وكيف يمكنها تحسين التقارب.

الوزن: التطبيع

إصلاح بسيط للمعاملات لتسريع تدريب الشبكات العصبية العميقة:

تيم ساليمانز ، ديدريك ب.كينجما (2016)

من خلال إعادة معاملات الأوزان بهذه الطريقة ، يمكنك تحسين تكييف مشكلة التحسين وتسريع تقارب نزول التدرج العشوائي. تم استلهام عملية إعادة المعاملات الخاصة بنا من تسوية الدُفعات ولكنها لا تقدم أي تبعيات بين الأمثلة الموجودة في الدفعة الصغيرة. هذا يعني أنه يمكن أيضًا تطبيق طريقتنا بنجاح على النماذج المتكررة مثل LSTMs والتطبيقات الحساسة للضوضاء مثل التعلم المعزز العميق أو النماذج التوليدية ، والتي يكون تطبيع الدُفعات أقل ملاءمة لها. على الرغم من أن طريقتنا أبسط بكثير ، إلا أنها لا تزال توفر الكثير من تسريع تطبيع الدُفعات الكاملة. بالإضافة إلى ذلك ، فإن النفقات الحسابية لطريقتنا أقل ، مما يسمح باتخاذ المزيد من خطوات التحسين في نفس الوقت.

https://arxiv.org/abs/1602.07868

اقامة

pip install -q -U tensorflow-addons

import tensorflow as tf
import tensorflow_addons as tfa

import numpy as np
from matplotlib import pyplot as plt

# Hyper Parameters
batch_size = 32
epochs = 10
num_classes=10

بناء النماذج

# Standard ConvNet
reg_model = tf.keras.Sequential([
    tf.keras.layers.Conv2D(6, 5, activation='relu'),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Conv2D(16, 5, activation='relu'),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(120, activation='relu'),
    tf.keras.layers.Dense(84, activation='relu'),
    tf.keras.layers.Dense(num_classes, activation='softmax'),
])

# WeightNorm ConvNet
wn_model = tf.keras.Sequential([
    tfa.layers.WeightNormalization(tf.keras.layers.Conv2D(6, 5, activation='relu')),
    tf.keras.layers.MaxPooling2D(2, 2),
    tfa.layers.WeightNormalization(tf.keras.layers.Conv2D(16, 5, activation='relu')),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Flatten(),
    tfa.layers.WeightNormalization(tf.keras.layers.Dense(120, activation='relu')),
    tfa.layers.WeightNormalization(tf.keras.layers.Dense(84, activation='relu')),
    tfa.layers.WeightNormalization(tf.keras.layers.Dense(num_classes, activation='softmax')),
])

تحميل البيانات

(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()

# Convert class vectors to binary class matrices.
y_train = tf.keras.utils.to_categorical(y_train, num_classes)
y_test = tf.keras.utils.to_categorical(y_test, num_classes)

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255

Downloading data from https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz
170500096/170498071 [==============================] - 11s 0us/step

نماذج القطارات

reg_model.compile(optimizer='adam', 
                  loss='categorical_crossentropy',
                  metrics=['accuracy'])

reg_history = reg_model.fit(x_train, y_train,
                            batch_size=batch_size,
                            epochs=epochs,
                            validation_data=(x_test, y_test),
                            shuffle=True)

Epoch 1/10
1563/1563 [==============================] - 9s 4ms/step - loss: 1.8336 - accuracy: 0.3253 - val_loss: 1.4039 - val_accuracy: 0.4957
Epoch 2/10
1563/1563 [==============================] - 5s 3ms/step - loss: 1.3773 - accuracy: 0.5039 - val_loss: 1.3419 - val_accuracy: 0.5309
Epoch 3/10
1563/1563 [==============================] - 5s 3ms/step - loss: 1.2510 - accuracy: 0.5497 - val_loss: 1.2108 - val_accuracy: 0.5710
Epoch 4/10
1563/1563 [==============================] - 5s 3ms/step - loss: 1.1606 - accuracy: 0.5858 - val_loss: 1.2134 - val_accuracy: 0.5687
Epoch 5/10
1563/1563 [==============================] - 5s 3ms/step - loss: 1.0971 - accuracy: 0.6100 - val_loss: 1.1534 - val_accuracy: 0.5880
Epoch 6/10
1563/1563 [==============================] - 5s 3ms/step - loss: 1.0420 - accuracy: 0.6296 - val_loss: 1.1944 - val_accuracy: 0.5865
Epoch 7/10
1563/1563 [==============================] - 5s 3ms/step - loss: 1.0014 - accuracy: 0.6445 - val_loss: 1.1386 - val_accuracy: 0.6012
Epoch 8/10
1563/1563 [==============================] - 5s 3ms/step - loss: 0.9550 - accuracy: 0.6623 - val_loss: 1.1659 - val_accuracy: 0.6020
Epoch 9/10
1563/1563 [==============================] - 5s 3ms/step - loss: 0.9196 - accuracy: 0.6737 - val_loss: 1.1539 - val_accuracy: 0.6027
Epoch 10/10
1563/1563 [==============================] - 5s 3ms/step - loss: 0.8768 - accuracy: 0.6889 - val_loss: 1.1509 - val_accuracy: 0.6029

wn_model.compile(optimizer='adam', 
                 loss='categorical_crossentropy',
                 metrics=['accuracy'])

wn_history = wn_model.fit(x_train, y_train,
                          batch_size=batch_size,
                          epochs=epochs,
                          validation_data=(x_test, y_test),
                          shuffle=True)

Epoch 1/10
1563/1563 [==============================] - 14s 8ms/step - loss: 1.8195 - accuracy: 0.3319 - val_loss: 1.4563 - val_accuracy: 0.4721
Epoch 2/10
1563/1563 [==============================] - 10s 7ms/step - loss: 1.4049 - accuracy: 0.4937 - val_loss: 1.3051 - val_accuracy: 0.5301
Epoch 3/10
1563/1563 [==============================] - 10s 6ms/step - loss: 1.2669 - accuracy: 0.5461 - val_loss: 1.2858 - val_accuracy: 0.5425
Epoch 4/10
1563/1563 [==============================] - 10s 6ms/step - loss: 1.1622 - accuracy: 0.5868 - val_loss: 1.2278 - val_accuracy: 0.5587
Epoch 5/10
1563/1563 [==============================] - 10s 6ms/step - loss: 1.0782 - accuracy: 0.6175 - val_loss: 1.1755 - val_accuracy: 0.5825
Epoch 6/10
1563/1563 [==============================] - 10s 6ms/step - loss: 1.0280 - accuracy: 0.6383 - val_loss: 1.1772 - val_accuracy: 0.5827
Epoch 7/10
1563/1563 [==============================] - 10s 6ms/step - loss: 0.9705 - accuracy: 0.6527 - val_loss: 1.1542 - val_accuracy: 0.5895
Epoch 8/10
1563/1563 [==============================] - 10s 6ms/step - loss: 0.9291 - accuracy: 0.6695 - val_loss: 1.1680 - val_accuracy: 0.5924
Epoch 9/10
1563/1563 [==============================] - 10s 6ms/step - loss: 0.8837 - accuracy: 0.6884 - val_loss: 1.1302 - val_accuracy: 0.6039
Epoch 10/10
1563/1563 [==============================] - 10s 6ms/step - loss: 0.8437 - accuracy: 0.7029 - val_loss: 1.1593 - val_accuracy: 0.6018

reg_accuracy = reg_history.history['accuracy']
wn_accuracy = wn_history.history['accuracy']

plt.plot(np.linspace(0, epochs,  epochs), reg_accuracy,
             color='red', label='Regular ConvNet')

plt.plot(np.linspace(0, epochs, epochs), wn_accuracy,
         color='blue', label='WeightNorm ConvNet')

plt.title('WeightNorm Accuracy Comparison')
plt.legend()
plt.grid(True)
plt.show()