预测新结果时检查模型输入角点时出错

时间:2018-08-17 12:59:28

标签: python tensorflow machine-learning keras word-embedding

我尝试使用基于新数据构建的keras模型,除了在尝试预测预测时出现输入错误。

这是我的模型代码:

def build_model(max_features, maxlen):
    """Build LSTM model"""
    model = Sequential()
    model.add(Embedding(max_features, 128, input_length=maxlen))
    model.add(LSTM(128))
    model.add(Dropout(0.5))
    model.add(Dense(1))
    model.add(Activation('sigmoid'))

    model.compile(loss='binary_crossentropy',
                  optimizer='rmsprop')

    return model

还有用于预测新数据的输出预测的代码:

LSTM_model = load_model('LSTMmodel.h5')
data = pickle.load(open('traindata.pkl', 'rb'))


#### LSTM ####

"""Run train/test on logistic regression model"""

# Extract data and labels
X = [x[1] for x in data]
labels = [x[0] for x in data]

# Generate a dictionary of valid characters
valid_chars = {x:idx+1 for idx, x in enumerate(set(''.join(X)))}

max_features = len(valid_chars) + 1
maxlen = np.max([len(x) for x in X])

# Convert characters to int and pad
X = [[valid_chars[y] for y in x] for x in X]
X = sequence.pad_sequences(X, maxlen=maxlen)

# Convert labels to 0-1
y = [0 if x == 'benign' else 1 for x in labels]


y_pred = LSTM_model.predict(X)

运行此代码时出现的错误:

ValueError: Error when checking input: expected embedding_1_input to have shape (57,) but got array with shape (36,)

我的错误来自maxlen,因为对于我的训练数据maxlen=57和新数据maxlen=36

所以我尝试设置预测代码maxlen=57,但随后出现此错误:

tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[31,53] = 38 is not in [0, 38)
     [[Node: embedding_1/embedding_lookup = GatherV2[Taxis=DT_INT32, Tindices=DT_INT32, Tparams=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](embedding_1/embeddings/read, embedding_1/Cast, embedding_1/embedding_lookup/axis)]]

我应该怎么做才能解决这些问题?更改我的嵌入层?

1 个答案:

答案 0 :(得分:1)

可以将“嵌入”层的input_length设置为您将在数据集中看到的最大长度,或者仅使用在maxlen中构建模型时使用的相同pad_sequences值。在这种情况下,将填充任何短于maxlen的序列,并截短任何长于maxlen的序列。

进一步确保在训练和测试时间中使用的功能相同(即,其编号不应更改)。