Weak image headers

Question

I am trying to create an image subtitle model.

modelV = createVGG16()
modelV.trainable = False
# DISCARD LAST 2 LAYERS
modelV.layers.pop()
modelV.layers.pop()

print 'LOADED VISION MODULE'

modelL = Sequential()
# CONVERTING THE INPUT PARTIAL CAPTION INDEX VECTOR TO DENSE VECTOR REPRESENTATION
modelL.add(Embedding(self.vocab_size, 256, input_length=self.max_cap_len))
modelL.add(LSTM(128,return_sequences=True))
modelL.add(TimeDistributed(Dense(128)))

print 'LOADED LANGUAGE MODULE'

# REPEATING IMAGE VECTOR TO TURN INTO A SEQUENCE
modelV.add(RepeatVector(self.max_cap_len))

print 'LOADED REPEAT MODULE'

model = Sequential()
model.add(Merge([modelV, modelL], mode='concat', concat_axis=-1))
# ENCODING THE VECTOR SEQ INTO A SINGLE VECTOR
# WHICH WILL BE USED TO COMPUTE THE PROB DISTRIB OF THE NEXT WORD
# IN THE CAPTION
model.add(LSTM(256,return_sequences=False))
model.add(Dense(self.vocab_size))
model.add(Activation('softmax'))

if(ret_model==True):
    return model

model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])

print 'COMBINED MODULES'
# OUTPUT WILL BE OF SHAPE (samples, max_caption_len, 128)
return model 

I tried to run this model on all 5 signatures of the first 100 images of the FLickr8k test dataset over 50 eras. All signatures are added and merged. To generate the title, I give the input image and as the initial word. With each iteration, I predict the probability distribution by vocabulary and get the next word. In the next iteration, I give PredictedWord as an input and again generate a probability distribution.

What happens is that I get the same probability distribution in each time value.

My question is:

1. Is my model too small to create captions?
2. Are training data too small?
3. Is the number of eras too small?
4. ?

Answer 1

, , ?

What happens is that I get the same probability distribution in every iteration.

, , , , (, EOC), .

• ?

"", , .

2. ?

, 100 .

3. ?

, 50 . , , , !

4. ?

, . . , , , .