[英]Getting different accuracy on test data in MNIST digit recognition in Keras
我做手寫數字識別使用Keras和我有兩個文件:predict.py和train.py。
train.py訓練模型(如果它還沒有訓練過)並將其保存到一個目錄中,否則它只會從它保存到的目錄中加載經過訓練的模型並打印Test Loss
和Test Accuracy
。
def getData():
(X_train, y_train), (X_test, y_test) = mnist.load_data()
y_train = to_categorical(y_train, num_classes=10)
y_test = to_categorical(y_test, num_classes=10)
X_train = X_train.reshape(X_train.shape[0], 784)
X_test = X_test.reshape(X_test.shape[0], 784)
# normalizing the data to help with the training
X_train /= 255
X_test /= 255
return X_train, y_train, X_test, y_test
def trainModel(X_train, y_train, X_test, y_test):
# training parameters
batch_size = 1
epochs = 10
# create model and add layers
model = Sequential()
model.add(Dense(64, activation='relu', input_shape=(784,)))
model.add(Dense(10, activation = 'softmax'))
# compiling the sequential model
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='adam')
# training the model and saving metrics in history
history = model.fit(X_train, y_train,
batch_size=batch_size, epochs=epochs,
verbose=2,
validation_data=(X_test, y_test))
loss_and_metrics = model.evaluate(X_test, y_test, verbose=2)
print("Test Loss", loss_and_metrics[0])
print("Test Accuracy", loss_and_metrics[1])
# Save model structure and weights
model_json = model.to_json()
with open('model.json', 'w') as json_file:
json_file.write(model_json)
model.save_weights('mnist_model.h5')
return model
def loadModel():
json_file = open('model.json', 'r')
model_json = json_file.read()
json_file.close()
model = model_from_json(model_json)
model.load_weights("mnist_model.h5")
return model
X_train, y_train, X_test, y_test = getData()
if(not os.path.exists('mnist_model.h5')):
model = trainModel(X_train, y_train, X_test, y_test)
print('trained model')
print(model.summary())
else:
model = loadModel()
print('loaded model')
print(model.summary())
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
loss_and_metrics = model.evaluate(X_test, y_test, verbose=2)
print("Test Loss", loss_and_metrics[0])
print("Test Accuracy", loss_and_metrics[1])
這是輸出(假設模型之前訓練過,這次模型將被加載):
('測試損失',1.741784990310669)
('測試精度',0.414)
predict.py,在另一方面,預計手寫號碼:
def loadModel():
json_file = open('model.json', 'r')
model_json = json_file.read()
json_file.close()
model = model_from_json(model_json)
model.load_weights("mnist_model.h5")
return model
model = loadModel()
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
(X_train, y_train), (X_test, y_test) = mnist.load_data()
y_test = to_categorical(y_test, num_classes=10)
X_test = X_test.reshape(X_test.shape[0], 28*28)
loss_and_metrics = model.evaluate(X_test, y_test, verbose=2)
print("Test Loss", loss_and_metrics[0])
print("Test Accuracy", loss_and_metrics[1])
在這種情況下,令我驚訝的是,得到以下結果:
('測試損失',1.8380377866744995)
('測試精度',0.8856)
在第二個文件中,我得到了 0.88 的Test Accuracy
(是我之前得到的兩倍多)。
此外, model.summery()
在這兩個文件中是相同的:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense_1 (Dense) (None, 64) 50240
_________________________________________________________________
dense_2 (Dense) (None, 10) 650
=================================================================
Total params: 50,890
Trainable params: 50,890
Non-trainable params: 0
_________________________________________________________________
我無法弄清楚這種行為背后的原因。 正常嗎? 或者我錯過了什么?
造成這種差異的原因是,一次您使用標准化數據(即除以 255)調用evaluate()
方法,而另一次(即在“predict.py”文件中)您使用非標准化數據調用它。 在推理時間(即測試時間)中,您應該始終使用與訓練數據相同的預處理步驟。
此外,首先將數據轉換為浮點數,然后將其除以 255(否則,使用/
,在 Python 2.x 和 Python 3.x 中進行真正的除法,您會在運行X_train /= 255
和X_test /= 255
):
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255.
X_test /= 255.
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.