def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, k=(5, 9, 13)):
super(SPPCSP, self).__init__()
c_ = int(2 * c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
self.cv3 = Conv(c_, c_, 3, 1)
self.cv4 = Conv(c_, c_, 1, 1)
self.m = nn.ModuleList(
[nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
self.cv5 = Conv(4 * c_, c_, 1, 1)
self.cv6 = Conv(c_, c_, 3, 1)
self.bn = nn.BatchNorm2d(2 * c_)
self.act = Mish()
self.cv7 = Conv(2 * c_, c2, 1, 1)
def __init__(self,
c1,
c2,
n=1,
shortcut=False,
g=1,
e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
super(BottleneckCSP2, self).__init__()
c_ = int(c2) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = nn.Conv2d(c_, c_, 1, 1, bias=False)
self.cv3 = Conv(2 * c_, c2, 1, 1)
self.bn = nn.BatchNorm2d(2 * c_)
self.act = Mish()
self.m = nn.Sequential(
*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
def __init__(self,
c1,
c2,
k=1,
s=1,
p=None,
g=1,
act=True): # ch_in, ch_out, kernel, stride, padding, groups
super(ConvSqu, self).__init__()
self.conv = nn.Conv2d(c1,
c2,
k,
s,
autopad(k, p),
groups=g,
bias=False)
self.act = Mish() if act else nn.Identity()
def __init__(self, d=3, k=10, emb_dims=1024, dropout=0.5):
super(Model, self).__init__()
self.emb_dims = emb_dims
self.k = k
self.dropout = dropout
self.d = d
self.conv1 = nn.Sequential(
nn.Conv2d(2 * self.d, 64, kernel_size=1, bias=False),
nn.BatchNorm2d(64), Mish())
self.conv2 = nn.Sequential(
nn.Conv2d(64, 64, kernel_size=1, bias=False), nn.BatchNorm2d(64),
Mish())
self.conv3 = nn.Sequential(
nn.Conv2d(64 * 2, 64, kernel_size=1, bias=False),
nn.BatchNorm2d(64), Mish())
self.conv4 = nn.Sequential(
nn.Conv2d(64, 64, kernel_size=1, bias=False), nn.BatchNorm2d(64),
Mish())
self.conv5 = nn.Sequential(
nn.Conv2d(64 * 2, 64, kernel_size=1, bias=False),
nn.BatchNorm2d(64), Mish())
self.conv6 = nn.Sequential(
nn.Conv1d(64 * 3, self.emb_dims, kernel_size=1, bias=False),
nn.BatchNorm1d(self.emb_dims), Mish())
self.conv7 = nn.Sequential(
nn.Conv1d(self.emb_dims + 64 * 3, 512, kernel_size=1, bias=False),
nn.BatchNorm1d(512), Mish())
self.conv8 = nn.Sequential(
nn.Conv1d(512, 256, kernel_size=1, bias=False),
nn.BatchNorm1d(256), Mish())
self.conv9 = nn.Conv1d(256, 2, kernel_size=1, bias=False)
print(opt)
# Input
img = torch.zeros((opt.batch_size, 3,
*opt.img_size)) # image size(1,3,320,192) iDetection
# Load PyTorch model
model = attempt_load(opt.weights,
map_location=torch.device('cpu')) # load FP32 model
# Update model
for k, m in model.named_modules():
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatability
if isinstance(m, models.common.Conv) and isinstance(
m.act, models.common.Mish):
m.act = Mish() # assign activation
if isinstance(m, models.common.BottleneckCSP) or isinstance(m, models.common.BottleneckCSP2) \
or isinstance(m, models.common.SPPCSP):
if isinstance(m.bn, nn.SyncBatchNorm):
bn = nn.BatchNorm2d(m.bn.num_features,
eps=m.bn.eps,
momentum=m.bn.momentum)
bn.training = False
bn._buffers = m.bn._buffers
bn._non_persistent_buffers_set = set()
m.bn = bn
if isinstance(m.act, models.common.Mish):
m.act = Mish() # assign activation
# if isinstance(m, models.yolo.Detect):
# m.forward = m.forward_export # assign forward (optional)