#build the whole model and run it
#modelBuilder = ModelBuilder(batch_size, question_dim, obj_dim, dictSize)
modelBuilder = ModelBuilder(batch_size, macro_batch_size, question_dim,
obj_dim, dictSize, args.questionAwareContext,
args.f_layers, args.f_inner_layers, args.g_layers,
args.h_layers, args.appendPosVec)
(inputContext, inputContextLengths, inputContextSentenceLengths, inputQuestion,
inputQuestionLengths, objects,
question) = modelBuilder.buildWordProcessorLSTMs()
if modelToUse == 1:
print("Using model I")
rnOutput = modelBuilder.buildRN_I(objects, question)
elif modelToUse == 2:
print("Using model II")
rnOutput = modelBuilder.buildRN_II(objects, question)
elif modelToUse == 3:
print("Using model III")
rnOutput = modelBuilder.buildRN_III(objects, question)
elif modelToUse == 4:
print("Using model IV")
rnOutput = modelBuilder.buildRN_IV(objects, question)
elif modelToUse == 5:
print("Using model V")
rnOutput = modelBuilder.buildRN_V(objects, question)
elif modelToUse == 6:
print("Using model VI")
rnOutput = modelBuilder.buildRN_VI(objects, question)
contextInput = sum([[sentence + [0]*(maxContextSentenceLen - len(sentence)) for sentence in context] for context, question, answer in samples], [])#concatenated
#contextInput = [[sentence + [0]*(maxContextSentenceLen - len(sentence)) for sentence in context] + [emptySentence]*(maxContextLen - len(context)) for context, question, answer in samples]
contextSentenceLengths = sum(contextSentenceLengths, [])#concatenated
#contextSentenceLengths = [sentenceLengths + [1]*(maxContextLen - len(sentenceLengths)) for sentenceLengths in contextSentenceLengths]#apply padding for tensorflow tensor - padding with 1 instead of 0 so sequence-end-selectors dont fail with bufferunderrun
questionInput = [question + [0]*(maxQuestionLen - len(question)) for context, question, answer in samples]
answerInput = [answer for context, question, answer in samples]
yield contextInput, contextLengths, contextSentenceLengths, questionInput, questionLengths, answerInput
#build the whole model and run it
modelBuilder = ModelBuilder(batch_size, macro_batch_size, question_dim, obj_dim, dictSize, args.questionAwareContext, args.f_layers, args.f_inner_layers, args.g_layers, args.h_layers, args.appendPosVec, args.batchNorm, args.layerNorm, args.weightPenalty)
(inputContext, inputContextLengths, inputContextSentenceLengths, inputQuestion, inputQuestionLengths, objects, question) = modelBuilder.buildWordProcessorLSTMs()
if modelToUse == 1:
print("Using model I")
(rnOutput, isTraining) = modelBuilder.buildRN_I(objects, question)
elif modelToUse == 2:
print("Using model II")
(rnOutput, isTraining) = modelBuilder.buildRN_II(objects, question)
elif modelToUse == 3:
print("Using model III")
(rnOutput, isTraining) = modelBuilder.buildRN_III(objects, question)
elif modelToUse == 4:
print("Using model IV")
(rnOutput, isTraining) = modelBuilder.buildRN_IV(objects, question)
elif modelToUse == 5:
print("Using model V")
(rnOutput, isTraining) = modelBuilder.buildRN_V(objects, question)
elif modelToUse == 6:
print("Using model VI")
(rnOutput, isTraining) = modelBuilder.buildRN_VI(objects, question)