I have a seq to seq model trained of some clever bot data:
justphrases_X is a list of sentences and justphrases_Y is a list of responses to those sentences.
maxlen = 62
#low is a list of all the unique words.
def Convert_To_Encoding(just_phrases):
encodings = []
for sentence in just_phrases:
onehotencoded = one_hot(sentence, len(low))
encodings.append(np.array(onehotencoded))
encodings_padded = pad_sequences(encodings, maxlen=maxlen, padding='post', value = 0.0)
return encodings_padded
encodings_X_padded = Convert_To_Encoding(just_phrases_X)
encodings_y_padded = Convert_To_Encoding(just_phrases_y)
model = Sequential()
embedding_layer = Embedding(len(low), output_dim=8, input_length=maxlen)
model.add(embedding_layer)
model.add(GRU(128)) # input_shape=(None, 496)
model.add(RepeatVector(numberofwordsoutput)) #number of characters?
model.add(GRU(128, return_sequences = True))
model.add(Flatten())
model.add(Dense(62, activation = 'softmax'))
model.compile(loss = 'categorical_crossentropy', optimizer= 'adam', metrics=['accuracy'])
model.summary()
model.fit(encodings_X_padded, encodings_y_padded, batch_size = 1, epochs=1) #, validation_data = (testX, testy)
model.save("cleverbottheseq-uel.h5")
When I use this model for prediction, the output will be between 0 and 1 because of my use of softmax. However as I have around 3000 unique words, each with a separate integer assigned to it, how do I essentially repeat what the model did during training and convert the output back to an integer which has a word assigned to it?
