def convgru_forward(x, CGRU):
len_r = len(reset_group)
if len_r > 0:
yyy = []
if reset_group[0][0] > 0:
temp_x = x[0:reset_group[0][0]]
xx = temp_x.view(-1, temp_x.size(0), temp_x.size(1),
temp_x.size(2), temp_x.size(3))
xxx = CGRU(xx)
yyy.append(xxx[1])
for item in reset_group:
temp_x = x[item[0]:item[1]]
xx = temp_x.view(-1, temp_x.size(0), temp_x.size(1),
temp_x.size(2), temp_x.size(3))
xxx = CGRU(xx)
yyy.append(xxx[1])
yyy = torch.cat(yyy, 0)
yyy = F.relu(yyy, inplace=True)
x = yyy.view(x.size())
return x
else:
xx = x.view(-1, x.size(0), x.size(1), x.size(2), x.size(3))
xxx = CGRU(xx)
yyy = xxx[1]
yyyy = F.relu(yyy, inplace=True)
x = yyyy.view(x.size())
return x
def convgru_forward(x, CGRU, hidden_states, hi):
len_r = len(reset_group)
if len_r > 0:
yyy = []
if reset_group[0][0] > 0:
temp_x = x[0:reset_group[0][0]]
xx = temp_x.view(-1, temp_x.size(0), temp_x.size(1),
temp_x.size(2), temp_x.size(3))
len_hid = len(hidden_states[hi])
if len_hid > 0:
temp = [(Variable(hidden_states[hi]).cuda())]
xxx = CGRU(xx, temp)
else:
xxx = CGRU(xx)
hidden_states[hi] = xxx[0][0].data
yyy.append(xxx[1].data)
for item in reset_group:
hidden_states[hi] = []
temp_x = x[item[0]:item[1]]
xx = temp_x.view(-1, temp_x.size(0), temp_x.size(1),
temp_x.size(2), temp_x.size(3))
xxx = CGRU(xx)
hidden_states[hi] = xxx[0][0].data
yyy.append(xxx[1].data)
third_tensor = yyy[0]
if len(yyy) > 1:
for yitem in yyy[1:]:
third_tensor = torch.cat((third_tensor, yitem), 0)
yyyy = Variable(third_tensor).cuda()
yyyy = F.relu(yyyy, inplace=True)
x = yyyy.view(x.size())
return x
else:
xx = x.view(-1, x.size(0), x.size(1), x.size(2), x.size(3))
len_hid = len(hidden_states[hi])
if len_hid > 0:
temp = [(Variable(hidden_states[hi]).cuda())]
xxx = CGRU(xx, temp)
else:
xxx = CGRU(xx)
yyy = xxx[1]
hidden_states[hi] = xxx[0][0].data
yyyy = F.relu(yyy, inplace=True)
x = yyyy.view(x.size())
return x
def __init__(self, base, extras, head, num_classes, use_gru = False):
super(SSD, self).__init__()
self.num_classes = num_classes
# TODO: implement __call__ in PriorBox
self.priorbox = PriorBox(v2)
self.priors = Variable(self.priorbox.forward(), volatile=True)
self.num_priors = self.priors.size(0)
self.size = 300
self.hidden_states = [[]]
# SSD network
self.vgg = nn.ModuleList(base)
clstm = [CLSTM(512, 512, 3, 1)]
cgru = [CGRU(512, 512, 3, 1)]
self.clstm = nn.ModuleList(clstm)
self.use_gru = use_gru
if self.use_gru:
self.cgru = nn.ModuleList(cgru)
print ("ConvGRU is used")
else:
print("ConvLSTM is used")
# if self.use_gru:
# self.hidden_states = []
# Layer learns to scale the l2 normalized features from conv4_3
self.L2Norm = L2Norm(512, 20)
self.extras = nn.ModuleList(extras)
self.loc = nn.ModuleList(head[0])
self.conf = nn.ModuleList(head[1])
self.softmax = nn.Softmax().cuda()
def multibox(vgg, extra_layers, cfg, num_classes):
loc_layers = []
conf_layers = []
vgg_source = [24, -2]
for k, v in enumerate(vgg_source):
loc_layers += [
nn.Conv2d(vgg[v].out_channels,
cfg[k] * 4,
kernel_size=3,
padding=1)
]
conf_layers += [
nn.Conv2d(vgg[v].out_channels,
cfg[k] * num_classes,
kernel_size=3,
padding=1)
]
for k, v in enumerate(extra_layers[1::2], 2):
loc_layers += [
nn.Conv2d(v.out_channels, cfg[k] * 4, kernel_size=3, padding=1)
]
conf_layers += [
nn.Conv2d(v.out_channels,
cfg[k] * num_classes,
kernel_size=3,
padding=1)
]
clstm = [CLSTM(512, 512, 3, 1)]
cgru = [CGRU(512, 512, 3, 1)]
return vgg, extra_layers, clstm, cgru, (loc_layers, conf_layers)