[英]Low accuracy after training a CNN
我嘗試使用 Keras 訓練一個對手寫數字進行分類的 CNN 模型,但我在訓練中的准確率很低(低於 10%)並且出現了很大的錯誤。 我嘗試了一個沒有結論的簡單神經網絡,但效果不佳。
這是我的代碼。
import tensorflow as tf
from tensorflow import keras
import numpy as np
import matplotlib.pyplot as plt
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
#Explore data
print(y_train[12])
print(np.shape(x_train))
print(np.shape(x_test))
#we have 60000 imae for the training and 10000 for testing
# Scaling data
x_train = x_train/255
y_train = y_train/255
#reshape the data
x_train = x_train.reshape(60000,28,28,1)
x_test = x_test.reshape(10000,28,28,1)
y_train = y_train.reshape(60000,1)
y_test = y_test.reshape(10000,1)
#Create a model
model = keras.Sequential([
keras.layers.Conv2D(64,(3,3),(1,1),padding = "same",input_shape=(28,28,1)),
keras.layers.MaxPooling2D(pool_size = (2,2),padding = "valid"),
keras.layers.Conv2D(32,(3,3),(1,1),padding = "same"),
keras.layers.MaxPooling2D(pool_size = (2,2),padding = "valid"),
keras.layers.Flatten(),
keras.layers.Dense(128,activation = "relu"),
keras.layers.Dense(10,activation = "softmax")])
model.compile(optimizer = "adam",
loss = "sparse_categorical_crossentropy",
metrics = ['accuracy'])
model.fit(x_train,y_train,epochs=10)
test_loss,test_acc = model.evaluate(x_test,y_test)
print("\ntest accuracy:",test_acc)
誰能建議我如何改進我的模型?
你的問題在這里:
x_train = x_train/255
y_train = y_train/255 # makes no sense
您應該重新縮放x_test
,而不是y_train
。
x_train = x_train/255
x_test = x_test/255
那可能只是您的錯字。 更改這些行,您將獲得 95% 以上的准確度。
你的模型有一些縮放問題並嘗試使用 tf 2.0
x_train /= 255
x_test /= 255
您不需要像您所做的那樣縮放所有測試數據:
x_train = x_train/255
y_train = y_train/255
之后,我們可以將標簽轉換為單熱編碼
from tensorflow.keras.utils import to_categorical
y_train = to_categorical(y_train, 10)
y_test = to_categorical(y_test, 10)
這有助於:
loss='categorical_crossentropy',
Sequential API 允許我們將層堆疊在彼此之上。 唯一的缺點是我們在使用這些模型時不能有多個輸出或輸入。 盡管如此,我們可以創建一個 Sequential 對象並使用 add() 函數向我們的模型添加層。 嘗試使用更多的 API 使您的模型更加平滑和准確,因為在 Tf 2.0 上使用添加功能我們可以給 Conv2D 4 時間來使其平滑:
seq_model.add(Conv2D(filters=32, kernel_size=(5,5), activation='relu',
input_shape=x_train.shape[1:]))
seq_model.add(Conv2D(filters=32, kernel_size=(5,5), activation='relu'))
seq_model.add(Conv2D(filters=64, kernel_size=(3, 3), activation='relu'))
seq_model.add(Conv2D(filters=64, kernel_size=(3, 3), activation='relu'))
在代碼中你可以使用 dropout:
seq_model.add(Dropout(rate=0.25))
完整型號:
%tensorflow_version 2.x
from tensorflow.keras.datasets import mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)
x_test = x_test.reshape(x_test.shape[0], 28, 28, 1)
from tensorflow.keras.utils import to_categorical
y_train = to_categorical(y_train, 10)
y_test = to_categorical(y_test, 10)
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPool2D, Dense, Flatten, Dropout
seq_model = Sequential()
seq_model.add(Conv2D(filters=32, kernel_size=(5,5), activation='relu',
input_shape=x_train.shape[1:]))
seq_model.add(Conv2D(filters=32, kernel_size=(5,5), activation='relu'))
seq_model.add(MaxPool2D(pool_size=(2, 2)))
seq_model.add(Dropout(rate=0.25))
seq_model.add(Conv2D(filters=64, kernel_size=(3, 3), activation='relu'))
seq_model.add(Conv2D(filters=64, kernel_size=(3, 3), activation='relu'))
seq_model.add(MaxPool2D(pool_size=(2, 2)))
seq_model.add(Dropout(rate=0.25))
seq_model.add(Flatten())
seq_model.add(Dense(256, activation='relu'))
seq_model.add(Dropout(rate=0.5))
seq_model.add(Dense(10, activation='softmax'))
seq_model.compile(
loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy']
)
epochsz = 3 # number of epch
batch_sizez = 32 # the batch size ,can be 64 , 128 so other
seq_model.fit(x_train,y_train, batch_size=batch_sizez, epochs=epochsz)
結果:
Train on 60000 samples
Epoch 1/3
60000/60000 [==============================] - 186s 3ms/sample - loss: 0.1379 - accuracy: 0.9588
Epoch 2/3
60000/60000 [==============================] - 187s 3ms/sample - loss: 0.0677 - accuracy: 0.9804
Epoch 3/3
60000/60000 [==============================] - 187s 3ms/sample - loss: 0.0540 - accuracy: 0.9840
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.