如果 MNIST 数据集中有 60000 张图像，为什么模型只在 1875 张训练集图像上进行训练?

问题描述

我正在尝试创建一个简单的 CNN 来对 MNIST 数据集中的图像进行分类.该模型达到了可接受的精度，但我注意到该模型在每个 epoch 中仅在 1875 张图像上进行了训练.可能是什么原因造成的?怎么修?

I am trying to create a simple CNN to classify images in MNIST dataset. The model achieved an acceptable accuracy but I noticed that the model is trained only on 1875 images in each epoch. What could be the cause of it? How can it be fixed?

model=models.Sequential()

model.add(layers.Conv2D(filters=32,kernel_size=(3,3),activation='relu',input_shape=(28,28,1)))
model.add(layers.MaxPooling2D((2,2)))
model.add(layers.Conv2D(filters=64,kernel_size=(3,3),activation='relu'))
model.add(layers.MaxPooling2D((2,2)))
model.add(layers.Conv2D(filters=64,kernel_size=(3,3),activation='relu'))
model.add(layers.Flatten())
model.add(layers.Dense(64,activation='relu'))
model.add(layers.Dense(10,activation='softmax'))

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d (Conv2D)              (None, 26, 26, 32)        320       
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 13, 13, 32)        0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 11, 11, 64)        18496     
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 5, 5, 64)          0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 3, 3, 64)          36928     
_________________________________________________________________
flatten (Flatten)            (None, 576)               0         
_________________________________________________________________
dense (Dense)                (None, 64)                36928     
_________________________________________________________________
dense_1 (Dense)              (None, 10)                650  

=================================================================
Total params: 93,322
Trainable params: 93,322
Non-trainable params: 0

model.compile(optimizer='adam',loss='sparse_categorical_crossentropy',metrics=['accuracy'])

model.compile(optimizer='adam',loss='sparse_categorical_crossentropy',metrics=['accuracy'])

model.fit(train_images,train_labels,epochs=5)

model.fit(train_images,train_labels,epochs=5)

Epoch 1/5
1875/1875 [==============================] - 55s 29ms/step - loss: 0.0760 - accuracy: 0.9776
Epoch 2/5
1875/1875 [==============================] - 54s 29ms/step - loss: 0.0576 - accuracy: 0.9825
Epoch 3/5
1875/1875 [==============================] - 55s 29ms/step - loss: 0.0454 - accuracy: 0.9862
Epoch 4/5
1875/1875 [==============================] - 55s 29ms/step - loss: 0.0396 - accuracy: 0.9879
Epoch 5/5
1875/1875 [==============================] - 55s 29ms/step - loss: 0.0336 - accuracy: 0.9900
<tensorflow.python.keras.callbacks.History at 0x7f3e0ff43b70>

colab 中的模型截图

训练模型截图

推荐答案

培训没有问题.模型正在接受 1875 个批次的训练，每批次 32 张图像，而不是 1875 张图像.

There's no problem with the training. Model is being trained on 1875 batches of 32 images each, not 1875 images.

1875*32 = 60000 张图片

1875*32 = 60000 images

这篇关于如果 MNIST 数据集中有 60000 张图像，为什么模型只在 1875 张训练集图像上进行训练?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！