def __init__(self,
in_channel=3,
num_joint=25,
num_person=2,
out_channel=64,
window_size=64,
num_class = 60,
):
super(HCN, self).__init__()
self.num_person = num_person
self.num_class = num_class
# position
self.conv1 = nn.Sequential(
nn.Conv2d(in_channels=in_channel,out_channels=out_channel,kernel_size=1,stride=1,padding=0),
nn.PReLU(),
)
self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=window_size, kernel_size=(3,1), stride=1, padding=(1,0))
self.conv3 = nn.Sequential(
nn.Conv2d(in_channels=num_joint, out_channels=out_channel//2, kernel_size=3, stride=1, padding=1),
nn.MaxPool2d(2))
self.conv4 = nn.Sequential(
nn.Conv2d(in_channels=out_channel//2, out_channels=out_channel, kernel_size=3, stride=1, padding=1),
nn.Dropout2d(p=0.5),
nn.MaxPool2d(2))
# motion
self.conv1m = nn.Sequential(
nn.Conv2d(in_channels=in_channel,out_channels=out_channel,kernel_size=1,stride=1,padding=0),
nn.PReLU(),
)
self.conv2m = nn.Conv2d(in_channels=out_channel, out_channels=window_size, kernel_size=(3,1), stride=1, padding=(1,0))
self.conv3m = nn.Sequential(
nn.Conv2d(in_channels=num_joint, out_channels=out_channel//2, kernel_size=3, stride=1, padding=1),
nn.MaxPool2d(2))
self.conv4m = nn.Sequential(
nn.Conv2d(in_channels=out_channel//2, out_channels=out_channel, kernel_size=3, stride=1, padding=1),
nn.Dropout2d(p=0.5),
nn.MaxPool2d(2))
# concatenate motion & position
self.conv5 = nn.Sequential(
nn.Conv2d(in_channels=out_channel*2, out_channels=out_channel*2, kernel_size=3, stride=1, padding=1),
nn.PReLU(),
nn.Dropout2d(p=0.5),
nn.MaxPool2d(2)
)
self.conv6 = nn.Sequential(
nn.Conv2d(in_channels=out_channel*2, out_channels=out_channel*4, kernel_size=3, stride=1, padding=1),
nn.PReLU(),
nn.Dropout2d(p=0.5),
nn.MaxPool2d(2)
)
self.fc7= nn.Sequential(
nn.Linear((out_channel * 4)*(window_size//16)*(window_size//16),256*2), # 4*4 for window=64; 8*8 for window=128
nn.PReLU(),
nn.Dropout2d(p=0.5))
self.fc8 = nn.Linear(256*2,num_class)
# initial weight
utils.initial_model_weight(layers = list(self.children()))
print('weight initial finished!')
def __init__(
self,
in_channel=3,
num_joint=25,
num_person=2,
out_channel=64,
window_size=300,
num_class=60,
):
super(AIF_CNN, self).__init__()
self.num_person = num_person
self.num_class = num_class
self.num_joint = num_joint
self.out_channel = out_channel
# position
# metric1_numpy = np.eye(self.num_joint, 26).astype('float32') + 0.01 * np.random.randn(
# self.num_joint, 26).astype('float32')
# self.adat_metrices1 = nn.Parameter(torch.from_numpy(metric1_numpy))
self.adat_metrices1 = nn.Parameter(torch.from_numpy(ntu_metrics))
self.relu1 = nn.ReLU()
self.conv1 = nn.Sequential(
nn.Conv2d(in_channels=in_channel * 2,
out_channels=out_channel // 2,
kernel_size=1,
stride=1,
padding=0),
nn.ReLU(),
)
self.conv2 = nn.Sequential(
nn.Conv2d(in_channels=out_channel // 2,
out_channels=out_channel // 2,
kernel_size=(3, 1),
stride=1,
padding=(1, 0)))
metric_r1_numpy = np.eye(25).astype(
'float32') + 0.01 * np.random.randn(25).astype('float32')
self.adat_metrices_r1 = nn.Parameter(torch.from_numpy(metric_r1_numpy))
self.conv_resize1 = nn.Sequential(
nn.Conv2d(in_channels=out_channel // 2,
out_channels=out_channel // 2,
kernel_size=(3, 1),
stride=1,
padding=(1, 0)), nn.MaxPool2d((2, 1)))
metric_r2_numpy = np.eye(25).astype(
'float32') + 0.01 * np.random.randn(25).astype('float32')
self.adat_metrices_r2 = nn.Parameter(torch.from_numpy(metric_r2_numpy))
self.conv_resize2 = nn.Sequential(
nn.Conv2d(in_channels=out_channel // 2,
out_channels=out_channel // 2,
kernel_size=(3, 1),
stride=1,
padding=(1, 0)))
metric3_numpy = np.eye(25, 26).astype(
'float32') + 0.01 * np.random.randn(25, 26).astype('float32')
self.adat_metrices3 = nn.Parameter(torch.from_numpy(metric3_numpy))
# self.adat_metrices3_O = torch.from_numpy(metric3_numpy).cuda()
self.conv3 = nn.Sequential(
nn.Conv2d(in_channels=out_channel // 2,
out_channels=out_channel // 2,
kernel_size=3,
stride=1,
padding=1), nn.MaxPool2d(2))
metric4_numpy = np.eye(13, 14).astype(
'float32') + 0.01 * np.random.randn(13, 14).astype('float32')
self.adat_metrices4 = nn.Parameter(torch.from_numpy(metric4_numpy))
# self.adat_metrices4_O = torch.from_numpy(metric4_numpy).cuda()
self.conv4 = nn.Sequential(
nn.Conv2d(in_channels=out_channel // 2,
out_channels=out_channel,
kernel_size=3,
stride=1,
padding=1), nn.Dropout2d(p=0.5), nn.MaxPool2d(2))
# motion
# metric1_numpy_m = np.eye(self.num_joint, 26).astype('float32') + 0.01 * np.random.randn(
# self.num_joint, 26).astype('float32')
# self.adat_metrices1_m = nn.Parameter(torch.from_numpy(metric1_numpy_m))
self.adat_metrices1_m = nn.Parameter(torch.from_numpy(ntu_metrics))
self.relu1_m = nn.ReLU()
self.conv1_m = nn.Sequential(
nn.Conv2d(in_channels=in_channel * 2,
out_channels=out_channel // 2,
kernel_size=1,
stride=1,
padding=0),
nn.ReLU(),
)
self.conv2_m = nn.Sequential(
nn.Conv2d(in_channels=out_channel // 2,
out_channels=out_channel // 2,
kernel_size=(3, 1),
stride=1,
padding=(1, 0)))
metric_r1m_numpy = np.eye(25).astype(
'float32') + 0.01 * np.random.randn(25).astype('float32')
self.adat_metrices_r1m = nn.Parameter(
torch.from_numpy(metric_r1m_numpy))
self.conv_resize1_m = nn.Sequential(
nn.Conv2d(in_channels=out_channel // 2,
out_channels=out_channel // 2,
kernel_size=(3, 1),
stride=1,
padding=(1, 0)), nn.MaxPool2d((2, 1)))
metric_r2m_numpy = np.eye(25).astype(
'float32') + 0.01 * np.random.randn(25).astype('float32')
self.adat_metrices_r2m = nn.Parameter(
torch.from_numpy(metric_r2m_numpy))
self.conv_resize2_m = nn.Sequential(
nn.Conv2d(in_channels=out_channel // 2,
out_channels=out_channel // 2,
kernel_size=(3, 1),
stride=1,
padding=(1, 0)))
metric3_numpy_m = np.eye(25, 26).astype(
'float32') + 0.01 * np.random.randn(25, 26).astype('float32')
self.adat_metrices3_m = nn.Parameter(torch.from_numpy(metric3_numpy_m))
# self.adat_metrices3_m_O = torch.from_numpy(metric3_numpy_m).cuda()
self.conv3_m = nn.Sequential(
nn.Conv2d(in_channels=out_channel // 2,
out_channels=out_channel // 2,
kernel_size=3,
stride=1,
padding=1), nn.MaxPool2d(2))
metric4_numpy_m = np.eye(13, 14).astype(
'float32') + 0.01 * np.random.randn(13, 14).astype('float32')
self.adat_metrices4_m = nn.Parameter(torch.from_numpy(metric4_numpy_m))
# self.adat_metrices4_m_o = torch.from_numpy(metric4_numpy_m).cuda()
self.conv4_m = nn.Sequential(
nn.Conv2d(in_channels=out_channel // 2,
out_channels=out_channel,
kernel_size=3,
stride=1,
padding=1), nn.Dropout2d(p=0.5), nn.MaxPool2d(2))
# concatenate motion & position
metric5_numpy = np.eye(7, 8).astype(
'float32') + 0.01 * np.random.randn(7, 8).astype('float32')
self.adat_metrices5 = nn.Parameter(torch.from_numpy(metric5_numpy))
# self.adat_metrices5_o = torch.from_numpy(metric5_numpy).cuda()
self.conv5 = nn.Sequential(
nn.Conv2d(in_channels=out_channel * 2,
out_channels=out_channel * 4,
kernel_size=3,
stride=1,
padding=1), nn.ReLU(), nn.Dropout2d(p=0.5),
nn.MaxPool2d(2))
metric6_numpy = np.eye(
out_channel // 16).astype('float32') + 0.01 * np.random.randn(
out_channel // 16).astype('float32')
self.adat_metrices6 = nn.Parameter(torch.from_numpy(metric6_numpy))
# self.adat_metrices6_o = torch.from_numpy(metric6_numpy).cuda()
self.conv6 = nn.Sequential(
nn.Conv2d(in_channels=out_channel * 4,
out_channels=out_channel * 8,
kernel_size=3,
stride=1,
padding=1), nn.ReLU(), nn.Dropout2d(p=0.5),
nn.MaxPool2d(2))
self.fc7 = nn.Sequential(
nn.Linear((out_channel * 8) * 2 * (out_channel // 32), 512),
# 4*4 for window=64; 8*8 for window=128
nn.ReLU(),
nn.Dropout2d(p=0.5))
self.fc8 = nn.Linear(512, num_class)
utils.initial_model_weight(layers=list(self.children()))
print('weight initial finished!')
