連接h5fy重量有一個錯誤

錯誤：

File "merge.py", line 48, in <module> 
    model.fit(X_train, y_train, batch_size=128, nb_epoch=1, validation_split=0.2) 
    File "/home/ngxin/anaconda2/lib/python2.7/site-packages/keras/engine/training.py", line 1117, in fit 
    batch_size=batch_size) 
    File "/home/ngxin/anaconda2/lib/python2.7/site-packages/keras/engine/training.py", line 1034, in _standardize_user_data 
    exception_prefix='model target') 
    File "/home/ngxin/anaconda2/lib/python2.7/site-packages/keras/engine/training.py", line 112, in standardize_input_data 
    str(array.shape)) 
ValueError: Error when checking model target: expected dense_1 to have 4 dimensions, but got array with shape (31000, 1)

謝謝

來源

2017-04-20 ngxin

如果您希望人們提供幫助，您應該包含您的代碼，而不是它的圖片。 – ted

請看看代碼，可以保存該模型識別率在開始時是好的，但連接模型的第二階段（連接相同的兩個模型）非常糟糕，我認爲它應該是m y保存模型和連接問題的過程，但控制檯中沒有錯誤，謝謝！

(X_train, y_train), (X_test, y_test) = faces_load_data()#the data is an numpy array 
model = Sequential()the procedure is not being given 
model.add(Convolution2D(32, 3, 3, 
        border_mode='valid', 
        input_shape=(48, 48,1))) 
model.add(Activation('relu')) 
model.add(Convolution2D(32, 3,3)) 
model.add(Activation('relu')) 
model.add(MaxPooling2D(pool_size=(2, 2))) 
model.add(Dropout(0.25)) 
model.add(Flatten()) 
model.add(Dense(256)) 
model.add(Activation('relu')) 
model.add(Dropout(0.25)) 
model.add(Dense(7)) 
model.add(Activation('softmax')) 

gen = ImageDataGenerator() 
gen.fit(X_train) 
train_generator =gen.flow(X_train,Y_train,batch_size=32,shuffle=False) 
test_generator = gen.flow(X_test, Y_test, batch_size=32,shuffle=False) 
train = model.predict_generator(train_generator, 31000) 
test= model.predict_generator(test_generator, 3589) 
with h5py.File("model_common.h5") as h: 
    h.create_dataset("train", data=train) 
    h.create_dataset("test", data=test) 
    h.create_dataset("label", data=y_train)#sava mode ,there should hava a problem 

for filename in ["model_common.h5","model_common.h5"]: 
    with h5py.File(filename, 'r') as h: 
     X_train.append(np.array(h['train'])) 
     X_test.append(np.array(h['test'])) 
     y_train = np.array(h['label']) 
X_train = np.concatenate(X_train, axis=1) 
X_test = np.concatenate(X_test, axis=1) 
X_train, y_train = shuffle(X_train, y_train) 
input_tensor = Input(X_train.shape[1:]) 
x = input_tensor 
x = Dropout(0.5)(x) 
x = Dense(1, activation='relu')(x) 
model = Model(input_tensor, x) 
model.fit(X_train,y_train, batch_size=32, nb_epoch=1,  validation_split=0.2)

來源

2017-04-21 11:33:48 ngxin

連接h5fy重量有一個錯誤

回答

相關問題