为 ResNet50 重塑 MNIST

如何解决为 ResNet50 重塑 MNIST

我正在尝试使用 Keras 库在 ResNet50 上训练 mnist 数据集。 mnist 的形状是 (28,28,1) 但是 resnet50 要求形状是 (32,32,3)

如何将 mnist 数据集转换为所需的形状？

(x_train,y_train),(x_test,y_test) = mnist.load_data()

x_train = x_train.reshape(x_train.shape[0],x_train.shape[1],x_train.shape[2],1)
x_test = x_test.reshape(x_test.shape[0],x_test.shape[1],x_test.shape[2],1)
x_train = x_train/255.0
x_test = x_test/255.0

from keras.utils import to_categorical
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)

model = models.Sequential()
# model.add(InputLayer(input_shape=(28,28)))
# model.add(Reshape(target_shape=(32,3)))
# model.add(Conv2D())
model.add(conv_base)
model.add(Flatten())
model.add(BatchNormalization())
model.add(Dense(128,activation='relu'))
model.add(Dropout(0.5))
model.add(BatchNormalization())
model.add(Dense(64,activation='relu'))
model.add(Dropout(0.5))
model.add(BatchNormalization())
model.add(Dense(10,activation='softmax'))

model.compile(optimizer=optimizers.RMSprop(lr=2e-5),loss='binary_crossentropy',metrics=['acc'])

history = model.fit(x_train,y_train,epochs=5,batch_size=20,validation_data=(x_test,y_test))

ValueError: Input 0 is incompatible with layer sequential_10: expected shape=(None,3),found shape=(20,1) 

解决方法

您需要调整 MNIST 数据集的大小。请注意，最小尺寸实际上取决于 ImageNet 模型。例如：Xception 至少需要 72，其中 ResNet 要求 32。除此之外，MNIST 是灰度图像，但如果您使用这些模型的预训练权重，它可能会发生冲突。因此，好的和安全的一面是调整灰度并将灰度转换为 RGB。

---

为您提供完整的工作代码。

数据集

我们会将 MNIST 的大小从 28 调整为 32。此外，制作 3 个通道而不是保留 1 个。

import tensorflow as tf 
import numpy as np 

(x_train,y_train),(_,_) = tf.keras.datasets.mnist.load_data()

# expand new axis,channel axis 
x_train = np.expand_dims(x_train,axis=-1)

# [optional]: we may need 3 channel (instead of 1)
x_train = np.repeat(x_train,3,axis=-1)

# it's always better to normalize 
x_train = x_train.astype('float32') / 255

# resize the input shape,i.e. old shape: 28,new shape: 32
x_train = tf.image.resize(x_train,[32,32]) # if we want to resize 

# one hot 
y_train = tf.keras.utils.to_categorical(y_train,num_classes=10)

print(x_train.shape,y_train.shape)

(60000,32,3) (60000,10)

ResNet 50

input = tf.keras.Input(shape=(32,3))
efnet = tf.keras.applications.ResNet50(weights='imagenet',include_top = False,input_tensor = input)
# Now that we apply global max pooling.
gap = tf.keras.layers.GlobalMaxPooling2D()(efnet.output)

# Finally,we add a classification layer.
output = tf.keras.layers.Dense(10,activation='softmax',use_bias=True)(gap)

# bind all
func_model = tf.keras.Model(efnet.input,output)

训练

func_model.compile(
          loss  = tf.keras.losses.CategoricalCrossentropy(),metrics = tf.keras.metrics.CategoricalAccuracy(),optimizer = tf.keras.optimizers.Adam())
# fit 
func_model.fit(x_train,y_train,batch_size=128,epochs=5,verbose = 2)

Epoch 1/5
469/469 - 56s - loss: 0.1184 - categorical_accuracy: 0.9690
Epoch 2/5
469/469 - 21s - loss: 0.0648 - categorical_accuracy: 0.9844
Epoch 3/5
469/469 - 21s - loss: 0.0503 - categorical_accuracy: 0.9867
Epoch 4/5
469/469 - 21s - loss: 0.0416 - categorical_accuracy: 0.9888
Epoch 5/5
469/469 - 21s - loss: 0.1556 - categorical_accuracy: 0.9697
<tensorflow.python.keras.callbacks.History at 0x7f316005a3d0>