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
python类FC的实例源码
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(1024 * 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, 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, bn=False, num_classes=10):
super(CMTL, self).__init__()
self.num_classes = num_classes
self.base_layer = nn.Sequential(Conv2d( 1, 16, 9, same_padding=True, NL='prelu', bn=bn),
Conv2d(16, 32, 7, same_padding=True, NL='prelu', bn=bn))
self.hl_prior_1 = nn.Sequential(Conv2d( 32, 16, 9, same_padding=True, NL='prelu', bn=bn),
nn.MaxPool2d(2),
Conv2d(16, 32, 7, same_padding=True, NL='prelu', bn=bn),
nn.MaxPool2d(2),
Conv2d(32, 16, 7, same_padding=True, NL='prelu', bn=bn),
Conv2d(16, 8, 7, same_padding=True, NL='prelu', bn=bn))
self.hl_prior_2 = nn.Sequential(nn.AdaptiveMaxPool2d((32,32)),
Conv2d( 8, 4, 1, same_padding=True, NL='prelu', bn=bn))
self.hl_prior_fc1 = FC(4*1024,512, NL='prelu')
self.hl_prior_fc2 = FC(512,256, NL='prelu')
self.hl_prior_fc3 = FC(256, self.num_classes, NL='prelu')
self.de_stage_1 = nn.Sequential(Conv2d( 32, 20, 7, same_padding=True, NL='prelu', bn=bn),
nn.MaxPool2d(2),
Conv2d(20, 40, 5, same_padding=True, NL='prelu', bn=bn),
nn.MaxPool2d(2),
Conv2d(40, 20, 5, same_padding=True, NL='prelu', bn=bn),
Conv2d(20, 10, 5, same_padding=True, NL='prelu', bn=bn))
self.de_stage_2 = nn.Sequential(Conv2d( 18, 24, 3, same_padding=True, NL='prelu', bn=bn),
Conv2d( 24, 32, 3, same_padding=True, NL='prelu', bn=bn),
nn.ConvTranspose2d(32,16,4,stride=2,padding=1,output_padding=0,bias=True),
nn.PReLU(),
nn.ConvTranspose2d(16,8,4,stride=2,padding=1,output_padding=0,bias=True),
nn.PReLU(),
Conv2d(8, 1, 1, same_padding=True, NL='relu', bn=bn))
def __init__(self, classes=None, debug=False, arch='vgg16'):
super(FasterRCNN, self).__init__()
if classes is not None:
self.classes = classes
self.n_classes = len(classes)
print('n_classes: {}\n{}'.format(self.n_classes, self.classes))
if arch == 'vgg16':
cnn_arch = models.vgg16(pretrained=False) # w/o bn
self.rpn = RPN(features=cnn_arch.features)
self.fcs = nn.Sequential(
nn.Linear(512 * 7 * 7, 4096),
nn.ReLU(True),
nn.Dropout(),
nn.Linear(4096, 4096),
nn.ReLU(True),
nn.Dropout()
)
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,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=False,
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(Hierarchical_Descriptive_Model, 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
