File size: 7,999 Bytes
912c7e2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 | """ Adapted from https://github.com/dyson-ai/hdp/blob/main/rk_diffuser/models/pointnet.py """
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.nn.parallel
import torch.utils.data
from torch.autograd import Variable
from diffusion_policy.common.pytorch_util import replace_submodules
class STN3d(nn.Module):
def __init__(self):
super(STN3d, self).__init__()
self.conv1 = torch.nn.Conv1d(3, 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)
self.bn4 = nn.LayerNorm(512)
self.bn5 = nn.LayerNorm(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 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.bn4 = nn.LayerNorm(512)
self.bn5 = nn.LayerNorm(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 PointNetfeat(nn.Module):
def __init__(self, input_channels: int, input_transform: bool, feature_transform=False):
super(PointNetfeat, self).__init__()
self.input_transform = input_transform
if self.input_transform:
self.stn = STNkd(k=input_channels)
self.conv1 = torch.nn.Conv1d(input_channels, 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.feature_transform = feature_transform
if self.feature_transform:
self.fstn = STNkd(k=64)
def forward(self, x):
b = x.size(0)
if len(x.shape) == 4:
x = x.view(b, -1, 3).permute(0, 2, 1).contiguous()
if self.input_transform:
trans = self.stn(x)
x = x.transpose(2, 1)
x = torch.bmm(x, trans)
x = x.transpose(2, 1)
else:
trans = None
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
x = F.relu(self.bn2(self.conv2(x)))
x = self.bn3(self.conv3(x))
x = torch.max(x, 2, keepdim=True)[0]
x = x.view(-1, 1024)
return x
class PointNetCls(nn.Module):
def __init__(self, k=2, feature_transform=False):
super(PointNetCls, self).__init__()
self.feature_transform = feature_transform
self.feat = PointNetfeat(global_feat=True, feature_transform=feature_transform)
self.fc1 = nn.Linear(1024, 512)
self.fc2 = nn.Linear(512, 256)
self.fc3 = nn.Linear(256, k)
self.dropout = nn.Dropout(p=0.3)
self.bn1 = nn.BatchNorm1d(512)
self.bn2 = nn.BatchNorm1d(256)
self.relu = nn.ReLU()
def forward(self, x):
x, trans, trans_feat = self.feat(x)
x = F.relu(self.bn1(self.fc1(x)))
x = F.relu(self.bn2(self.dropout(self.fc2(x))))
x = self.fc3(x)
return F.log_softmax(x, dim=1), trans, trans_feat
class PointNetDenseCls(nn.Module):
def __init__(self, k=2, feature_transform=False):
super(PointNetDenseCls, self).__init__()
self.k = k
self.feature_transform = feature_transform
self.feat = PointNetfeat(global_feat=False, feature_transform=feature_transform)
self.conv1 = torch.nn.Conv1d(1088, 512, 1)
self.conv2 = torch.nn.Conv1d(512, 256, 1)
self.conv3 = torch.nn.Conv1d(256, 128, 1)
self.conv4 = torch.nn.Conv1d(128, self.k, 1)
self.bn1 = nn.BatchNorm1d(512)
self.bn2 = nn.BatchNorm1d(256)
self.bn3 = nn.BatchNorm1d(128)
def forward(self, x):
batchsize = x.size()[0]
n_pts = x.size()[2]
x, trans, trans_feat = self.feat(x)
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 = self.conv4(x)
x = x.transpose(2, 1).contiguous()
x = F.log_softmax(x.view(-1, self.k), dim=-1)
x = x.view(batchsize, n_pts, self.k)
return x, trans, trans_feat
class PointNetBackbone(nn.Module):
def __init__(
self,
embed_dim: int,
input_channels: int,
input_transform: bool,
use_group_norm: bool = False,
):
super().__init__()
assert input_channels in [3, 6], "Input channels must be 3 or 6"
self.backbone = nn.Sequential(
PointNetfeat(input_channels, input_transform),
nn.Mish(),
nn.Linear(1024, 512),
nn.Mish(),
nn.Linear(512, embed_dim),
)
if use_group_norm:
self.backbone = replace_submodules(
root_module=self.backbone,
predicate=lambda x: isinstance(x, nn.BatchNorm1d),
func=lambda x: nn.GroupNorm(
num_groups=x.num_features // 16, num_channels=x.num_features
),
)
return
def forward(self, pcd: torch.Tensor, robot_state_obs: torch.Tensor = None) -> torch.Tensor:
B = pcd.shape[0]
# Flatten the batch and time dimensions
pcd = pcd.float().reshape(-1, *pcd.shape[2:])
robot_state_obs = robot_state_obs.float().reshape(-1, *robot_state_obs.shape[2:])
# Permute [B, P, C] -> [B, C, P]
pcd = pcd.permute(0, 2, 1)
# Encode all point clouds (across time steps and batch size)
encoded_pcd = self.backbone(pcd)
nx = torch.cat([encoded_pcd, robot_state_obs], dim=1)
# Reshape back to the batch dimension. Now the features of each time step are concatenated
nx = nx.reshape(B, -1)
return nx
|