0
我在Keras(版本1.2.0)中遇到了很奇怪的問題。 這裏是我的神經網絡模型:Keras輸入問題
model = Sequential()
lindata=302
model.add(Dense(lindata, input_dim=lindata, activation='sigmoid'))
model.add(Dense(60,activation='sigmoid'))
model.add(Dense(30, activation='softplus'))
model.add(Dense(loutdata, activation='softplus'))
model.compile(optimizer='rmsprop',
loss='mean_squared_error',
metrics=['accuracy'])
輸入是302輛彩車一個載體,我對他們有376的訓練樣本。 現在,當我運行model.fit(),我得到錯誤信息:
Traceback (most recent call last):
File "nn.py", line 142, in <module>
model.fit(all_indata,all_outdata,nb_epoch=35, batch_size=4) # nb_epoch=65 - not enough
File "/usr/lib/python2.7/site-packages/keras/models.py", line 664, in fit
sample_weight=sample_weight)
File "/usr/lib/python2.7/site-packages/keras/engine/training.py", line 1068, in fit
batch_size=batch_size)
File "/usr/lib/python2.7/site-packages/keras/engine/training.py", line 981, in _standardize_user_data
exception_prefix='model input')
File "/usr/lib/python2.7/site-packages/keras/engine/training.py", line 54, in standardize_input_data
'...')
ValueError: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 1 arrays but instead got the following list of 376 arrays: [array([[ 1.25000000e+11],
[ 1.20000000e-09],
[ 0.00000000e+00],
[ 0.00000000e+00],
[ 0.00000000e+00],
[ 0.00000000e+00],
[ 0.00000000e+00],
[ ...
這是我創造我的輸入:
for line in datasample:
elems=line.split(",")
indata=np.array([[float(elems[i])] for i in range(2,len(elems)-1)])
all_indata.append(indata)
我已經試過轉換INDATA使用asarray到numpy的陣列等等,但沒有任何作品!你有什麼建議嗎?這是我在尋找一個解決方案第二天...
的Mariusz
右循環後現在,'all_indata'是一個Python列表。當你嘗試'all_indata = np.array(all_indata)'時會發生什麼? –
當我這樣做時,我收到以下錯誤消息: 'Traceback(最近調用最後一個): 文件「nn.py」,第142行,在 model.fit(all_indata,all_outdata,nb_epoch = 35,batch_size = 4) 文件「/usr/lib/python2.7/site-packages/keras/models.py」,行664,in fit sample_weight = sample_weight) 文件「/usr/lib/python2.7/site- (模塊輸入) ValueError:檢查模型輸入時出錯:期望的dense_input_1有形狀(無,302),但有形狀的數組(376) ,1)' –
user3282997
什麼是allindata.shape? – ginge