the accuracy of the answer

[BoatInTheRiver]

I run your code,and why the accuracy of the answer is so low ？Please tell me how you train it.

[BoatInTheRiver]

Like this.

[lianglili]

Hello, please tell me how to solve the following error information, thanks a lot!

Function：

def get_VQA_model(VQA_weights_file_name): ''' Given the VQA model and its weights, compiles and returns the model ''' vqa_model = VQA_MODEL()

vqa_model.load_weights(VQA_weights_file_name)     **Here，i got a  error!**
vqa_model.compile(loss=keras.losses.categorical_crossentropy,
                  optimizer=keras.optimizers.Adadelta(),
                  metrics=['accuracy'])
return vqa_model

Error Information：

Traceback (most recent call last): File "E:/pycharm-workspace/VQA-Demo-GUI-master/VQA-VGG-16+LSTM-GUI.py", line 246, in start_prediction vqa_model = get_VQA_model(model,VQA_weights_file_name) File "E:/pycharm-workspace/VQA-Demo-GUI-master/VQA-VGG-16+LSTM-GUI.py", line 73, in get_VQA_model vqa_model.load_weights(VQA_weights_file_name) File "C:\Users\lucky\Anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py", line 162, in load_weights return super(Model, self).load_weights(filepath, by_name) File "C:\Users\lucky\Anaconda3\lib\site-packages\tensorflow\python\keras\engine\network.py", line 1411, in load_weights self._assert_weights_created() File "C:\Users\lucky\Anaconda3\lib\site-packages\tensorflow\python\keras\engine\network.py", line 1673, in _assert_weights_created self.name) ValueError: Weights for model sequential_2 have not yet been created. Weights are created when the Model is first called on inputs or build() is called with an input_shape.