def build_baseline_newatt(dataset, num_hid):
w_emb = WordEmbedding(dataset.dictionary.ntoken, 300, 0.0)
q_emb = QuestionEmbedding(300, num_hid, 1, False, 0.0)
v_att = NewAttention(dataset.v_dim, q_emb.num_hid, num_hid)
q_net = FCNet([num_hid, num_hid])
v_net = FCNet([dataset.v_dim, num_hid])
fusion = FCNet([num_hid, num_hid * 2], dropout=0.5)
return BaseModel(w_emb, q_emb, v_att, q_net, v_net, fusion, num_hid,
dataset.num_ans_candidates)
def build_baseline_newatt(dataset, num_hid):
w_emb = WordEmbedding(dataset.dictionary.ntoken, 300, 0.0)
q_emb = QuestionEmbedding(300, num_hid, 1, False, 0.0)
v_att = NewAttention(dataset.v_dim, q_emb.num_hid, num_hid)
q_net = FCNet([num_hid, num_hid])
v_net = FCNet([dataset.v_dim, num_hid])
a_mask = AnswerMask(num_hid, dataset.num_ans_candidates)
classifier = SimpleClassifier(num_hid, num_hid * 2,
dataset.num_ans_candidates, 0.5)
return BaseModel(w_emb, q_emb, v_att, q_net, v_net, classifier, a_mask)
def __init__(self, v_dim, q_dim, num_hid):
super(Attention, self).__init__()
self.nonlinear = FCNet([v_dim + q_dim, num_hid])
self.linear = weight_norm(nn.Linear(num_hid, 1), dim=None)
def __init__(self, v_dim, q_dim, num_hid, dropout=0.2):
super(NewAttention, self).__init__()
self.v_proj = FCNet([v_dim, num_hid])
self.q_proj = FCNet([q_dim, num_hid])
self.dropout = nn.Dropout(dropout)
self.linear = weight_norm(nn.Linear(q_dim, 1), dim=None)