Keras ValueError，同時編譯一個加載的模型

Question

我訓練了下面的網絡並保存它。編譯重新加載的網絡時，會出現以下錯誤：

ValueError: Error when checkingModelTarget: expected dense_3 to haveFast (None, 1) but got array with shape (10000, 10) 

可能是什麼原因？許多類似問題的解決方案並不能真正幫助我。

代碼：

#!/usr/bin/env python 
# -*- coding: utf-8 -*- 
import numpy 
from keras.datasets import mnist 
from keras.models import Sequential 
from keras.layers import Dense 
from keras.layers import Dropout 
from keras.layers import Flatten 
from keras.layers.convolutional import Convolution2D 
from keras.layers.convolutional import MaxPooling2D 
from keras.utils import np_utils 
from keras import backend as K 
from keras.models import model_from_json 

K.set_image_dim_ordering('th') 

# fix random seed for reproducibility 
seed = 7 
numpy.random.seed(seed) 

# load data 
(X_train, y_train), (X_test, y_test) = mnist.load_data() 
# reshape to be [samples][pixels][width][height] 
X_train = X_train.reshape(X_train.shape[0], 1, 28, 28).astype('float32') 
X_test = X_test.reshape(X_test.shape[0], 1, 28, 28).astype('float32') 

# normalize inputs from 0-255 to 0-1 
X_train = X_train/255 
X_test = X_test/255 
# one hot encode outputs 
y_train = np_utils.to_categorical(y_train) 
y_test = np_utils.to_categorical(y_test) 
num_classes = y_test.shape[1] 

def larger_model(): 
    # create model 
    model = Sequential() 
    model.add(Convolution2D(30, 5, 5, border_mode='valid', input_shape=(1, 28, 28), activation='relu')) 
    model.add(MaxPooling2D(pool_size=(2, 2))) 
    model.add(Convolution2D(15, 3, 3, activation='relu')) 
    model.add(MaxPooling2D(pool_size=(2, 2))) 
    model.add(Dropout(0.2)) 
    model.add(Flatten()) 
    model.add(Dense(128, activation='relu')) 
    model.add(Dense(50, activation='relu')) 
    model.add(Dense(num_classes, activation='softmax')) 
    # Compile model 
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) 
    return model 

# build the model 
model = larger_model() 
# Fit the model 
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=1, batch_size=200, verbose=2) 
# Final evaluation of the model 
scores = model.evaluate(X_test, y_test, verbose=0) 
print("Baseline Error: %.2f%%" % (100-scores[1]*100)) 


# save model and weights 
print("Saving model...") 
model_json = model.to_json() 
with open('mnist_model.json', 'w') as json_file: 
    json_file.write(model_json) 
model.save_weights("mnist_weights.h5") 
print("model saved to disk") 

# load model and weights 
print("Laoding model...") 
with open('mnist_model.json') as json_file: 
    model_json = json_file.read() 

model = model_from_json(model_json) 
model.load_weights('mnist_weights.h5') 
print("mode loaded from disk") 

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

scores = model.evaluate(X_test, y_test, verbose=0) 
print("Baseline Error: %.2f%%" % (100-scores[1]*100)) 

Answer 1

你爲什麼加載模型後這樣做嗎？ ：

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

你的基礎模型使用categorical_crossentropy，所不同的是，最新的預計範疇，一個炎熱的編碼目標，稀疏版本預計指數，並在後臺調用np.utils.to_categorical()。因此，在這裏，keras抱怨，因爲你使用稀疏版本，它期望索引如此形狀(?, 1)，但你飼料y_test，編碼爲一個熱形狀(?, 10)。

解決方案，要麼不改變損耗和使用的類型：

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

加載模型後，或反向熱編碼y_test之一：

y_test = np.argmax(y_test) 

我希望這有助於： - ）