def __init__(self,nhidden, n_object_cats , n_predicate_cats, n_vocab, voc_sign,
max_word_length, MPS_iter, use_language_loss, object_loss_weight,
predicate_loss_weight,
dropout=False,
use_kmeans_anchors=True,
gate_width=128,
nhidden_caption=256,
nembedding = 256,
rnn_type='LSTM_normal',
rnn_droptout=0.0, rnn_bias=False,
use_region_reg=False, use_kernel=False):
super(faster_rcnn, self).__init__(nhidden, n_object_cats, n_predicate_cats, n_vocab, voc_sign,
max_word_length, MPS_iter, use_language_loss, object_loss_weight, predicate_loss_weight,
dropout, use_kmeans_anchors, nhidden_caption, nembedding, rnn_type, use_region_reg)
self.rpn = RPN(use_kmeans_anchors)
# self.roi_pool_object = RoIPool(7, 7, 1.0/16)
# self.roi_pool_phrase = RoIPool(7, 7, 1.0/16)
self.roi_pool_region = RoIPool(7, 7, 1.0/16)
# self.fc6_obj = FC(512 * 7 * 7, nhidden, relu=True)
# self.fc7_obj = FC(nhidden, nhidden, relu=False)
# self.fc6_phrase = FC(512 * 7 * 7, nhidden, relu=True)
# self.fc7_phrase = FC(nhidden, nhidden, relu=False)
self.fc6_region = FC(512 * 7 * 7, nhidden, relu=True)
self.fc7_region = FC(nhidden, nhidden, relu=False)
# if MPS_iter == 0:
# self.mps = None
# else:
# self.mps = Hierarchical_Message_Passing_Structure(nhidden, dropout,
# gate_width=gate_width, use_kernel_function=use_kernel) # the hierarchical message passing structure
# network.weights_normal_init(self.mps, 0.01)
# self.score_obj = FC(nhidden, self.n_classes_obj, relu=False)
# self.bbox_obj = FC(nhidden, self.n_classes_obj * 4, relu=False)
# self.score_pred = FC(nhidden, self.n_classes_pred, relu=False)
# if self.use_region_reg:
self.bbox_region = FC(nhidden, 4, relu=False)
network.weights_normal_init(self.bbox_region, 0.01)
# else:
# self.bbox_region = None
self.objectiveness = FC(nhidden, 2, relu=False)
# if use_language_loss:
# self.caption_prediction = \
# Language_Model(rnn_type=self.rnn_type, ntoken=self.n_vocab, nimg=self.nhidden, nhidden=self.nhidden_caption,
# nembed=self.nembedding, nlayers=2, nseq=self.max_word_length, voc_sign = self.voc_sign,
# bias=rnn_bias, dropout=rnn_droptout)
# else:
# self.caption_prediction = Language_Model(rnn_type=self.rnn_type, ntoken=self.n_vocab, nimg=1, nhidden=1,
# nembed=1, nlayers=1, nseq=1, voc_sign = self.voc_sign) # just to make the program run
# network.weights_normal_init(self.score_obj, 0.01)
# network.weights_normal_init(self.bbox_obj, 0.005)
# network.weights_normal_init(self.score_pred, 0.01)
network.weights_normal_init(self.objectiveness, 0.01)
self.objectiveness_loss = None
def __init__(self, nhidden, dropout):
super(Concat, self).__init__()
self.conv1 = Conv2d(3 * nhidden, nhidden, 1)
self.conv2 = Conv2d(nhidden, 256, 1)
self.conv3 = Conv2d(256, 128, 1)
self.compress = FC(640, nhidden, relu=True)
self.compress_r = FC(640, nhidden, relu=True)
self.dropout = dropout
def __init__(self, nhidden, dropout):
super(ConcatEmbedding, self).__init__()
self.linear = nn.Linear(3 * nhidden, nhidden)
self.fc1 = FC(nhidden, 256, relu=True)
self.fc2 = FC(256, 128, relu=True)
self.fc3 = FC(128, 128, relu=True)
self.compress = FC(640, nhidden, relu=True)
self.compress_r = FC(640, nhidden, relu=True)
self.dropout = dropout
def __init__(self, nhidden):
super(DualMask, self).__init__()
self.conv1 = Conv2d(2, 96, kernel_size=5)
self.conv2 = Conv2d(96, 128, kernel_size=5)
self.conv3 = Conv2d(128, 64, kernel_size=8)
self.fc1_dm = FC(18496, nhidden, relu=True)
self.fc2_dm = FC(25600, 2 * nhidden, relu=True)
faster_rcnn.network.weights_normal_init(self.fc1_dm, 0.01)
faster_rcnn.network.weights_normal_init(self.fc2_dm, 0.01)
def __init__(self, nhidden, dropout):
super(GraphicalModel, self).__init__()
self.f = FC(nhidden, nhidden, relu=True)
self.g = FC(nhidden, nhidden, relu=True)
self.conv1 = Conv2d(3 * nhidden, nhidden, 1)
self.conv2 = Conv2d(nhidden, 256, 1)
self.conv3 = Conv2d(256, 128, 1)
self.conv1_r = Conv2d(3 * nhidden, nhidden, 1)
self.conv2_r = Conv2d(nhidden, 256, 1)
self.conv3_r = Conv2d(256, 128, 1)
self.compress = FC(640, nhidden, relu=True)
self.compress_r = FC(640, nhidden, relu=True)
self.dropout = dropout
def __init__(self, classes=None, debug=False):
super(FasterRCNN, self).__init__()
if classes is not None:
self.classes = classes
self.n_classes = len(classes)
self.rpn = RPN()
self.roi_pool = RoIPool(7, 7, 1.0 / 16)
self.fc6 = FC(512 * 7 * 7, 4096)
self.fc7 = FC(4096, 4096)
self.score_fc = FC(4096, self.n_classes, relu=False)
self.bbox_fc = FC(4096, self.n_classes * 4, relu=False)
# loss
self.cross_entropy = None
self.loss_box = None
# for log
self.debug = debug
def __init__(self, classes=None, debug=False):
super(FasterRCNN, self).__init__()
self.classes = np.asarray(classes)
self.n_classes = len(classes)
self.rpn = RPN(debug=debug)
self.proposal_target_layer = proposal_target_layer_py(self.n_classes)
if cfg.POOLING_MODE == 'align':
self.roi_pool = RoIAlign(7, 7, 1.0 / 16)
elif cfg.POOLING_MODE == 'pool':
self.roi_pool = RoIPool(7, 7, 1.0 / 16)
self.score_fc = FC(4096, self.n_classes, relu=False)
self.bbox_fc = FC(4096, self.n_classes * 4, relu=False)
# loss
self.cross_entropy = 0
self.loss_box = 0
self.triplet_loss = 0
# for log
self.debug = debug
if cfg.TRIPLET.IS_TRUE:
self.fc_sim = FC(512 * 7 * 7, 4096, relu=False)
pos_weight = torch.ones(3)
pos_weight[0] = 2.0
if self.debug:
self.set = 0
self.match = 0
if cfg.TRIPLET.LOSS == 'euc':
self.loss_triplet = tpl.euclidean_distance_loss
elif cfg.TRIPLET.LOSS == 'log':
self.loss_triplet = tpl.cross_entropy_l2_dist
self.relu = nn.ReLU(inplace=True)
self.BCELoss = nn.BCELoss(weight=pos_weight,
size_average=False)
elif cfg.TRIPLET.LOSS == 'cls':
self.loss_triplet = tpl.cross_entropy_cosine_sim
self.relu = nn.ReLU(inplace=True)
self.BCELoss = nn.BCELoss(weight=pos_weight,
size_average=False)
self.init_module = self._init_faster_rcnn_vgg16
def __init__(self, nhidden, dropout):
super(TranslationEmbedding, self).__init__()
self.linear_s = nn.Linear(nhidden, nhidden)
self.linear_o = nn.Linear(nhidden, nhidden)
self.fc = FC(2 * nhidden, nhidden, relu=True)
self.dropout = dropout
def __init__(self, nhidden, dropout):
super(LstmStructure, self).__init__()
self.brnn = nn.LSTM(nhidden, nhidden, 1, bidirectional=True)
self.compress = FC(3 * nhidden, nhidden, relu=True)
self.compress_r = FC(3 * nhidden, nhidden, relu=True)
self.dropout = dropout
def __init__(self, nhidden, dropout):
super(IterativeStructure, self).__init__()
self.linear_s_p_o = FC(nhidden, 128, relu=True)
self.fc_p = FC(768, nhidden, relu=True)
self.linear_p = FC(nhidden, 128, relu=True)
self.linear = FC(640, nhidden, relu=True)
def __init__(self, ninput, nembed, nhidden, nlayers, bias, dropout):
super(Img_Encoder_Structure, self).__init__()
self.image_encoder = FC(ninput, nembed, relu=True)
self.rnn = nn.LSTM(nembed, nhidden, nlayers, bias=bias, dropout=dropout)
def __init__(self, input, nhidden):
super(GaussianMixtureModel, self).__init__()
self.fc_gmm = FC(input, 2 * nhidden, relu=True)
faster_rcnn.network.weights_normal_init(self.fc_gmm, 0.01)
def __init__(self, nhidden, dropout):
super(GeometricSpatialFeature, self).__init__()
self.fc = FC(640, nhidden, relu=True)
self.fc_r = FC(640, nhidden, relu=True)
self.dropout = dropout