deep learning - i am doing project on image captioning using cnn and lstm i got error

Question

InvalidArgumentError:  Matrix size-incompatible: In[0]: [47,1000],
In[1]: [4096,256]    [[node model_1/dense_4/Relu (defined at
<ipython-input-23-4876d7977fbf>:10) ]]
[Op:__inference_train_function_14686]

my code:

def define_model(vocab_size, max_length):
    # feature extractor model
    inputs1 = Input(shape=(4096,))
    fe1 = Dropout(0.5)(inputs1)
    fe2 = Dense(256, activation='relu')(fe1)
    fe3 = RepeatVector(max_length)(fe2)
    #embedding
    inputs2 = Input(shape=(max_length,))
    emb2 = Embedding(vocab_size,256,mask_zero =True)(inputs2)
    #merge inputs
    merged = concatenate([fe3, emb2])
    #language model(decoder)
    lm2 = LSTM(500,return_sequences=False)(merged)
    #lm3 = Dense(500,activation='relu')(lm2)
    outputs = Dense(vocab_size,activation='softmax')(lm2)
    # tie it together [image, seq] [word]
    model = Model(inputs=[inputs1, inputs2], outputs=outputs)
    model.compile(loss='categorical_crossentropy', optimizer='adam',metrics=['accuracy'])
  
    # summarize model
    print(model.summary())
    return model

question from:https://stackoverflow.com/questions/65913215/i-am-doing-project-on-image-captioning-using-cnn-and-lstm-i-got-error

Answer 1

Waitting for answers