def __init__(self, vocab, arch, normalization='none', activation='relu',
padding='same', vecs_size=1024, pooling='avg'):
super(AppearanceEncoder, self).__init__()
self.vocab = vocab
cnn_kwargs = {
'arch': arch,
'normalization': normalization,
'activation': activation,
'pooling': pooling,
'padding': padding,
}
cnn, channels = build_cnn(**cnn_kwargs)
self.cnn = nn.Sequential(cnn, GlobalAvgPool(), nn.Linear(channels, vecs_size))
def __init__(self, vocab, arch, normalization='none', activation='relu', padding='same', pooling='avg'):
super(AcDiscriminator, self).__init__()
self.vocab = vocab
cnn_kwargs = {
'arch': arch,
'normalization': normalization,
'activation': activation,
'pooling': pooling,
'padding': padding,
}
cnn, D = build_cnn(**cnn_kwargs)
self.cnn = nn.Sequential(cnn, GlobalAvgPool(), nn.Linear(D, 1024))
num_objects = len(vocab['object_idx_to_name']) #len(vocab['object_to_idx']) #cm Azade
self.real_classifier = nn.Linear(1024, 1)
self.obj_classifier = nn.Linear(1024, num_objects)