我已经使用 word2vec 训练了一个模型来预测主题类别，并使用 keras 训练了一个 lstm 模型，并且在训练过程中获得了大约 98% 的准确率，我保存了模型，然后将其加载到另一个文件中以尝试测试集，我使用model.evaluate and model.predict结果却截然不同。
我使用 keras 和tensorflow作为后端，模型摘要是：
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
lstm_1 (LSTM) (None, 22) 19624
_________________________________________________________________
dropout_1 (Dropout) (None, 22) 0
_________________________________________________________________
dense_1 (Dense) (None, 40) 920
_________________________________________________________________
activation_1 (Activation) (None, 40) 0
=================================================================
Total params: 20,544
Trainable params: 20,544
Non-trainable params: 0
_________________________________________________________________
None
代码：
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.load_weights(os.path.join('model', 'lstm_model_weights.hdf5'))
score, acc = model.evaluate(x_test, y_test, batch_size=batch_size)
print()
print('Score: %1.4f' % score)
print('Evaluation Accuracy: %1.2f%%' % (acc*100))
predicted = model.predict(x_test, batch_size=batch_size)
acc2 = np.count_nonzero(predicted.argmax(1) == y_test.argmax(1))/y_test.shape[0]
print('Prediction Accuracy: %1.2f%%' % (acc2*100))
这段代码的输出是
39680/40171 [============================>.] - ETA: 0s
Score: 0.1192
Evaluation Accuracy: 97.50%
Prediction Accuracy: 9.03%
谁能告诉我我错过了什么？
