Keras Sequential to Functional API

Question

我是深度学习的新手，一直在尝试将Keras顺序应用程序接口转换为在CIFAR10图像数据集上运行的函数式应用程序接口，但遇到了一些困难。我已经转换了模型，它看起来除了输入层之外都是一样的，但是序列的平均精度约为70%，我的泛函的平均精度约为10%。我真的很感激在找出哪里出了问题方面的一些帮助。下面是我的函数代码：

import tensorflow as tf
from tensorflow import keras

from keras import datasets, layers, models
from keras.models import Model, Input, Sequential
import matplotlib.pyplot as plt

下载并准备：

(train_images, train_labels), (test_images, test_labels) = datasets.cifar10.load_data()

# Normalize pixel values to be between 0 and 1
train_images, test_images = train_images / 255.0, test_images / 255.0
input_shape = train_images[0,:,:,:].shape

创建模型：

input = layers.Input(shape=input_shape)

x = layers.Conv2D(32, (3, 3), activation='relu',padding='valid')(input)
x = layers.MaxPooling2D((2,2))(x)
x = layers.Conv2D(64, (3, 3), activation='relu')(x)
x = layers.MaxPooling2D((2,2))(x)
x = layers.Conv2D(64, (3, 3), activation='relu')(x)

x = layers.Flatten()(x)
x = layers.Dense(64, activation='relu')(x)
x = layers.Dense(10)(x)

model = Model(input, x, name='Functional')

编译和训练：

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

history = model.fit(train_images, train_labels, epochs=10, 
                    validation_data=(test_images, test_labels))

Here is a link to the original sequential CNN，这是一款谷歌协作笔记本。如果您能帮助我了解并修复问题所在，我将不胜感激。提前谢谢你。

Answer 1

SparseCategoricalCrossentropy loss似乎存在一些问题。

检查这个：https://github.com/tensorflow/tensorflow/issues/38632

以下模型提供了良好的准确性：

import tensorflow as tf
from tensorflow import keras

from keras import datasets, layers, models
from keras.models import Model, Input, Sequential
import matplotlib.pyplot as plt


(train_images, train_labels), (test_images, test_labels) = datasets.cifar10.load_data()

# Normalize pixel values to be between 0 and 1
train_images, test_images = train_images / 255.0, test_images / 255.0
train_labels, test_labels = tf.keras.utils.to_categorical(train_labels, 10) , tf.keras.utils.to_categorical(test_labels, 10)
input_shape = train_images[0,:,:,:].shape


input = layers.Input(shape=input_shape)

x = layers.Conv2D(32, (3, 3), activation='relu',padding='valid')(input)
x = layers.MaxPooling2D((2,2))(x)
x = layers.Conv2D(64, (3, 3), activation='relu')(x)
x = layers.MaxPooling2D((2,2))(x)
x = layers.Conv2D(64, (3, 3), activation='relu')(x)

x = layers.Flatten()(x)
x = layers.Dense(64, activation='relu')(x)
x = layers.Dense(10, activation='softmax')(x)

model = Model(input, x, name='Functional')

model.summary()

model.compile(optimizer='adam',
              loss=loss=tf.keras.losses.CategoricalCrossentropy(),
              metrics=['accuracy'])

history = model.fit(train_images, train_labels, epochs=10, 
                    validation_data=(test_images, test_labels))

conv2d_16 (Conv2D)           (None, 30, 30, 32)        896       
_________________________________________________________________
max_pooling2d_11 (MaxPooling (None, 15, 15, 32)        0         
_________________________________________________________________
conv2d_17 (Conv2D)           (None, 13, 13, 64)        18496     
_________________________________________________________________
max_pooling2d_12 (MaxPooling (None, 6, 6, 64)          0         
_________________________________________________________________
conv2d_18 (Conv2D)           (None, 4, 4, 64)          36928     
_________________________________________________________________
flatten_6 (Flatten)          (None, 1024)              0         
_________________________________________________________________
dense_11 (Dense)             (None, 64)                65600     
_________________________________________________________________
dense_12 (Dense)             (None, 10)                650       
=================================================================
Total params: 122,570
Trainable params: 122,570
Non-trainable params: 0
_________________________________________________________________
Train on 50000 samples, validate on 10000 samples
Epoch 1/10
50000/50000 [==============================] - 15s 305us/step - loss: 1.4870 - accuracy: 0.4600 - val_loss: 1.2874 - val_accuracy: 0.5488
Epoch 2/10
50000/50000 [==============================] - 15s 301us/step - loss: 1.1365 - accuracy: 0.5989 - val_loss: 1.0789 - val_accuracy: 0.6191
Epoch 3/10
50000/50000 [==============================] - 15s 301us/step - loss: 0.9869 - accuracy: 0.6547 - val_loss: 0.9506 - val_accuracy: 0.6700
Epoch 4/10
50000/50000 [==============================] - 15s 301us/step - loss: 0.8896 - accuracy: 0.6907 - val_loss: 0.9509 - val_accuracy: 0.6695
Epoch 5/10
50000/50000 [==============================] - 16s 311us/step - loss: 0.8135 - accuracy: 0.7151 - val_loss: 0.8688 - val_accuracy: 0.7046
Epoch 6/10
50000/50000 [==============================] - 15s 303us/step - loss: 0.7566 - accuracy: 0.7351 - val_loss: 0.8411 - val_accuracy: 0.7141