|
- import torch.nn as nn
- import torch.utils.data
- import torch.nn.functional as F
- from ClsNetwork.PointNet import feature_transform_reguliarzer
- from torch.autograd import Variable
- import numpy as np
-
-
- class STNkd(nn.Module):
- def __init__(self, k=64):
- super(STNkd, self).__init__()
- self.conv1 = torch.nn.Conv1d(k, 64, 1)
- self.conv2 = torch.nn.Conv1d(64, 128, 1)
- self.conv3 = torch.nn.Conv1d(128, 1024, 1)
- self.fc1 = nn.Linear(1024, 512)
- self.fc2 = nn.Linear(512, 256)
- self.fc3 = nn.Linear(256, k * k)
- self.relu = nn.ReLU()
-
- self.bn1 = nn.BatchNorm1d(64)
- self.bn2 = nn.BatchNorm1d(128)
- self.bn3 = nn.BatchNorm1d(1024)
- self.bn4 = nn.BatchNorm1d(512)
- self.bn5 = nn.BatchNorm1d(256)
-
- self.k = k
-
- def forward(self, x):
- batchsize = x.size()[0]
- x = F.relu(self.bn1(self.conv1(x)))
- x = F.relu(self.bn2(self.conv2(x)))
- x = F.relu(self.bn3(self.conv3(x)))
- x = torch.max(x, 2, keepdim=True)[0]
- x = x.view(-1, 1024)
-
- x = F.relu(self.bn4(self.fc1(x)))
- x = F.relu(self.bn5(self.fc2(x)))
- x = self.fc3(x)
-
- iden = Variable(torch.from_numpy(np.eye(self.k).flatten().astype(np.float32))).view(1, self.k * self.k).repeat(
- batchsize, 1)
- if x.is_cuda:
- iden = iden.cuda()
- x = x + iden
- x = x.view(-1, self.k, self.k)
- return x
-
- class STN3d(nn.Module):
- def __init__(self, channel):
- super(STN3d, self).__init__()
- self.conv1 = torch.nn.Conv1d(channel, 64, 1)
- self.conv2 = torch.nn.Conv1d(64, 128, 1)
- self.conv3 = torch.nn.Conv1d(128, 1024, 1)
- self.fc1 = nn.Linear(1024, 512)
- self.fc2 = nn.Linear(512, 256)
- self.fc3 = nn.Linear(256, 9)
- self.relu = nn.ReLU()
-
- self.bn1 = nn.BatchNorm1d(64)
- self.bn2 = nn.BatchNorm1d(128)
- self.bn3 = nn.BatchNorm1d(1024)
- self.bn4 = nn.BatchNorm1d(512)
- self.bn5 = nn.BatchNorm1d(256)
-
- def forward(self, x):
- batchsize = x.size()[0]
- x = F.relu(self.bn1(self.conv1(x)))
- x = F.relu(self.bn2(self.conv2(x)))
- x = F.relu(self.bn3(self.conv3(x)))
- x = torch.max(x, 2, keepdim=True)[0]
- x = x.view(-1, 1024)
-
- x = F.relu(self.bn4(self.fc1(x)))
- x = F.relu(self.bn5(self.fc2(x)))
- x = self.fc3(x)
-
- iden = Variable(torch.from_numpy(np.array([1, 0, 0, 0, 1, 0, 0, 0, 1]).astype(np.float32))).view(1, 9).repeat(
- batchsize, 1)
- if x.is_cuda:
- iden = iden.cuda()
- x = x + iden
- x = x.view(-1, 3, 3)
- return x
-
- class PointNetEncoder(nn.Module):
- def __init__(self, global_feat=True, feature_transform=False, channel=3):
- super(PointNetEncoder, self).__init__()
- self.stn = STN3d(channel)
- self.conv1 = torch.nn.Conv1d(channel, 64, 1)
- self.conv2 = torch.nn.Conv1d(64, 128, 1)
- self.conv3 = torch.nn.Conv1d(128, 1024, 1)
- self.bn1 = nn.BatchNorm1d(64)
- self.bn2 = nn.BatchNorm1d(128)
- self.bn3 = nn.BatchNorm1d(1024)
- self.global_feat = global_feat
- self.feature_transform = feature_transform
- if self.feature_transform:
- self.fstn = STNkd(k=64)
-
- def forward(self, x):
- B, D, N = x.size()
- trans = self.stn(x)
- x = x.transpose(2, 1)
- if D >3 :
- x, feature = x.split(3,dim=2)
- x = torch.bmm(x, trans)
- if D > 3:
- x = torch.cat([x,feature],dim=2)
- x = x.transpose(2, 1)
- x = F.relu(self.bn1(self.conv1(x)))
-
- if self.feature_transform:
- trans_feat = self.fstn(x)
- x = x.transpose(2, 1)
- x = torch.bmm(x, trans_feat)
- x = x.transpose(2, 1)
- else:
- trans_feat = None
-
- pointfeat = x
- x = F.relu(self.bn2(self.conv2(x)))
- maxbefore_feaute = self.bn3(self.conv3(x))
- x = torch.max(maxbefore_feaute, 2, keepdim=True)[0]
- x = x.view(-1, 1024)
- if self.global_feat:
- return x, trans, trans_feat,maxbefore_feaute
- else:
- x = x.view(-1, 1024, 1).repeat(1, 1, N)
- return torch.cat([x, pointfeat], 1), trans, trans_feat
-
- class PoiintNet(nn.Module):
- def __init__(self, k=40, normal_channel=True):
- super(PoiintNet, self).__init__()
- if normal_channel:
- channel = 6
- else:
- channel = 3
- self.feat = PointNetEncoder(global_feat=True, feature_transform=True, channel=channel)
- self.fc1 = nn.Linear(1024, 512)
- self.fc2 = nn.Linear(512, 256)
- self.fc3 = nn.Linear(256, k)
- self.dropout = nn.Dropout(p=0.4)
- self.bn1 = nn.BatchNorm1d(512)
- self.bn2 = nn.BatchNorm1d(256)
- self.relu = nn.ReLU()
-
- def forward(self, x):
- gbfeature, trans, trans_feat,maxbefore_feaute = self.feat(x)
- x = F.relu(self.bn1(self.fc1(gbfeature)))
- x = F.relu(self.bn2(self.dropout(self.fc2(x))))
- cls_before_feaute = x
- x = self.fc3(x)
- #x = F.log_softmax(x, dim=1)
- return x, gbfeature,maxbefore_feaute
-
- class get_loss(torch.nn.Module):
- def __init__(self, mat_diff_loss_scale=0.001):
- super(get_loss, self).__init__()
- self.mat_diff_loss_scale = mat_diff_loss_scale
-
- def forward(self, pred, target, trans_feat):
- loss = F.nll_loss(pred, target)
- mat_diff_loss = feature_transform_reguliarzer(trans_feat)
-
- total_loss = loss + mat_diff_loss * self.mat_diff_loss_scale
- return total_loss
-
-
- if __name__=="__main__":
-
- params={
- "up_ratio":4,
- "patch_num_point":100
- }
- clsnet=PoiintNet(10,normal_channel=False).cuda()
- point_cloud=torch.rand(2,3,1024).cuda()
- output,_,_=clsnet(point_cloud)
- print(output.shape)
|