def __init__(self, image_feat_dim, ques_emb_dim, **kwargs):
super(two_layer_elmt_multiply, self).__init__()
self.Fa_image1 = nonlinear_layer(image_feat_dim, kwargs['hidden_size'])
self.Fa_image2 = nonlinear_layer(
kwargs['hidden_size'], kwargs['hidden_size'])
self.Fa_txt1 = nonlinear_layer(ques_emb_dim, kwargs['hidden_size'])
self.Fa_txt2 = nonlinear_layer(
kwargs['hidden_size'], kwargs['hidden_size'])
self.dropout = nn.Dropout(kwargs['dropout'])
self.out_dim = kwargs['hidden_size']
def __init__(self, image_feat_dim, ques_emb_dim, **kwargs):
super(two_layer_elmt_multiply, self).__init__()
self.Fa_image1 = nonlinear_layer(image_feat_dim, kwargs["hidden_size"])
self.Fa_image2 = nonlinear_layer(kwargs["hidden_size"],
kwargs["hidden_size"])
self.Fa_txt1 = nonlinear_layer(ques_emb_dim, kwargs["hidden_size"])
self.Fa_txt2 = nonlinear_layer(kwargs["hidden_size"],
kwargs["hidden_size"])
self.dropout = nn.Dropout(kwargs["dropout"])
self.out_dim = kwargs["hidden_size"]
def __init__(self,
image_feat_dim,
txt_rnn_embeding_dim,
hidden_size,
dropout=0.2):
super(project_attention, self).__init__()
self.image_feat_dim = image_feat_dim
self.txt_embeding_dim = txt_rnn_embeding_dim
self.Fa_image = nonlinear_layer(image_feat_dim, hidden_size)
self.Fa_txt = nonlinear_layer(txt_rnn_embeding_dim, hidden_size)
self.dropout = nn.Dropout(dropout)
self.lc = nn.Linear(hidden_size, 1)
def __init__(self,
image_feat_dim,
txt_rnn_embeding_dim,
hidden_size,
dropout=0.2):
super(project_attention, self).__init__()
self.image_feat_dim = image_feat_dim
self.txt_embeding_dim = txt_rnn_embeding_dim
self.Fa_image = nonlinear_layer(image_feat_dim, hidden_size)
self.Fa_txt = nonlinear_layer(txt_rnn_embeding_dim, hidden_size)
self.dropout = nn.Dropout(dropout)
self.lc = nn.Linear(hidden_size, 1)
def __init__(self, image_attention_model, question_embedding_models,
classifier):
super(top_down_bottom_up_model, self).__init__()
self.image_attention_model = image_attention_model
self.question_embedding_models = question_embedding_models
self.classifier = classifier
text_lstm_dim = sum(
[q.text_out_dim for q in question_embedding_models])
joint_embedding_out_dim = classifier.input_dim
image_feat_dim = image_attention_model.image_feat_dim
self.nonLinear_question = nonlinear_layer(text_lstm_dim,
joint_embedding_out_dim)
self.nonLinear_image = nonlinear_layer(image_feat_dim,
joint_embedding_out_dim)
def __init__(self, image_attention_model,
question_embedding_models, classifier):
super(top_down_bottom_up_model, self).__init__()
self.image_attention_model = image_attention_model
self.question_embedding_models = question_embedding_models
self.classifier = classifier
text_lstm_dim = sum(
[q.text_out_dim for q in question_embedding_models])
joint_embedding_out_dim = classifier.input_dim
image_feat_dim = image_attention_model.image_feat_dim
self.nonLinear_question = nonlinear_layer(
text_lstm_dim, joint_embedding_out_dim)
self.nonLinear_image = nonlinear_layer(
image_feat_dim, joint_embedding_out_dim)
def __init__(self, image_feat_dim, txt_rnn_embeding_dim, hidden_size):
super(concatenate_attention, self).__init__()
self.image_feat_dim = image_feat_dim
self.txt_embeding_dim = txt_rnn_embeding_dim
self.Fa = nonlinear_layer(image_feat_dim + txt_rnn_embeding_dim,
hidden_size)
self.lc = nn.Linear(hidden_size, 1)
def __init__(self, image_feat_dim, txt_rnn_embeding_dim, hidden_size):
super(concatenate_attention, self).__init__()
self.image_feat_dim = image_feat_dim
self.txt_embeding_dim = txt_rnn_embeding_dim
self.Fa = nonlinear_layer(
image_feat_dim + txt_rnn_embeding_dim, hidden_size)
self.lc = nn.Linear(hidden_size, 1)
def __init__(self, in_dim, out_dim, **kwargs):
super(logit_classifier, self).__init__()
input_dim = in_dim
num_ans_candidates = out_dim
txt_nonLinear_dim = kwargs['txt_hidden_dim']
image_nonLinear_dim = kwargs['img_hidden_dim']
self.f_o_text = nonlinear_layer(input_dim, txt_nonLinear_dim)
self.f_o_image = nonlinear_layer(input_dim, image_nonLinear_dim)
self.linear_text = nn.Linear(txt_nonLinear_dim, num_ans_candidates)
self.linear_image = nn.Linear(image_nonLinear_dim, num_ans_candidates)
if 'pretrained_image' in kwargs and \
kwargs['pretrained_text'] is not None:
self.linear_text.weight.data.copy_(
torch.from_numpy(kwargs['pretrained_text']))
if 'pretrained_image' in kwargs and \
kwargs['pretrained_image'] is not None:
self.linear_image.weight.data.copy_(
torch.from_numpy(kwargs['pretrained_image']))
def __init__(self, image_feat_dim, ques_emb_dim, **kwargs):
super(non_linear_elmt_multiply, self).__init__()
self.Fa_image = nonlinear_layer(image_feat_dim, kwargs['hidden_size'])
self.Fa_txt = nonlinear_layer(ques_emb_dim, kwargs['hidden_size'])
self.dropout = nn.Dropout(kwargs['dropout'])
self.out_dim = kwargs['hidden_size']
