upd

configs/server/server_train_config.yaml

@@ -7,9 +7,9 @@ runner:
     parallel: False
     
   experiment:
-    name: train_ab_global_only
+    name: train_ab_global_only_with_accept_probability
     root_dir: "experiments"
-    use_checkpoint: True
+    use_checkpoint: False
     epoch: -1 # -1 stands for last epoch
     max_epochs: 5000
     save_checkpoint_interval: 1
@@ -96,6 +96,9 @@ module:
     global_feat: True
     feature_transform: False
 
+  pointnet++_encoder:
+    in_dim: 3
+
   transformer_seq_encoder:
     embed_dim: 256
     num_heads: 4

core/nbv_dataset.py

@@ -4,6 +4,7 @@ import PytorchBoot.namespace as namespace
 import PytorchBoot.stereotype as stereotype
 from PytorchBoot.config import ConfigManager
 from PytorchBoot.utils.log_util import Log
+
 import torch
 import os
 import sys
@@ -50,7 +51,7 @@ class NBVReconstructionDataset(BaseDataset):
                 scene_name_list.append(scene_name)
         return scene_name_list
 
-    def get_datalist(self):
+    def get_datalist(self, bias=False):
         datalist = []
         for scene_name in self.scene_name_list:
             seq_num = DataLoadUtil.get_label_num(self.root_dir, scene_name)
@@ -79,16 +80,18 @@ class NBVReconstructionDataset(BaseDataset):
                     for data_pair in label_data["data_pairs"]:
                         scanned_views = data_pair[0]
                         next_best_view = data_pair[1]
-                        datalist.append(
-                            {
-                                "scanned_views": scanned_views,
-                                "next_best_view": next_best_view,
-                                "seq_max_coverage_rate": max_coverage_rate,
-                                "scene_name": scene_name,
-                                "label_idx": seq_idx,
-                                "scene_max_coverage_rate": scene_max_coverage_rate,
-                            }
-                        )
+                        accept_probability = scanned_views[-1][1]
+                        if accept_probability > np.random.rand():
+                            datalist.append(
+                                {
+                                    "scanned_views": scanned_views,
+                                    "next_best_view": next_best_view,
+                                    "seq_max_coverage_rate": max_coverage_rate,
+                                    "scene_name": scene_name,
+                                    "label_idx": seq_idx,
+                                    "scene_max_coverage_rate": scene_max_coverage_rate,
+                                }
+                            )
         return datalist
 
     def preprocess_cache(self):
@@ -227,9 +230,10 @@ if __name__ == "__main__":
     torch.manual_seed(seed)
     np.random.seed(seed)
     config = {
-        "root_dir": "/data/hofee/data/packed_preprocessed_data",
+        "root_dir": "/data/hofee/data/new_full_data",
+        "model_dir": "../data/scaled_object_meshes",
         "source": "nbv_reconstruction_dataset",
-        "split_file": "/data/hofee/data/OmniObject3d_train.txt",
+        "split_file": "/data/hofee/data/new_full_data_list/OmniObject3d_train.txt",
         "load_from_preprocess": True,
         "ratio": 0.5,
         "batch_size": 2,

core/seq_dataset.py

@@ -50,11 +50,12 @@ class SeqReconstructionDataset(BaseDataset):
                 if not os.path.exists(os.path.join(self.root_dir, scene_name)):
                     continue
                 scene_name_list.append(scene_name)
-        return scene_name_list
+        return scene_name_list    
     
     def get_scene_name_list(self):
         return self.scene_name_list
 
+
     def get_datalist(self):
         datalist = []
         total = len(self.scene_name_list)

modules/module_lib/pointnet2_modules.py

@@ -0,0 +1,162 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from . import pointnet2_utils
+from . import pytorch_utils as pt_utils
+from typing import List
+
+
+class _PointnetSAModuleBase(nn.Module):
+
+    def __init__(self):
+        super().__init__()
+        self.npoint = None
+        self.groupers = None
+        self.mlps = None
+        self.pool_method = 'max_pool'
+
+    def forward(self, xyz: torch.Tensor, features: torch.Tensor = None, new_xyz=None) -> (torch.Tensor, torch.Tensor):
+        """
+        :param xyz: (B, N, 3) tensor of the xyz coordinates of the features
+        :param features: (B, N, C) tensor of the descriptors of the the features
+        :param new_xyz:
+        :return:
+            new_xyz: (B, npoint, 3) tensor of the new features' xyz
+            new_features: (B, npoint, \sum_k(mlps[k][-1])) tensor of the new_features descriptors
+        """
+        new_features_list = []
+
+        xyz_flipped = xyz.transpose(1, 2).contiguous()
+        if new_xyz is None:
+            new_xyz = pointnet2_utils.gather_operation(
+                xyz_flipped,
+                pointnet2_utils.furthest_point_sample(xyz, self.npoint)
+            ).transpose(1, 2).contiguous() if self.npoint is not None else None
+
+        for i in range(len(self.groupers)):
+            new_features = self.groupers[i](xyz, new_xyz, features)  # (B, C, npoint, nsample)
+
+            new_features = self.mlps[i](new_features)  # (B, mlp[-1], npoint, nsample)
+
+            if self.pool_method == 'max_pool':
+                new_features = F.max_pool2d(
+                    new_features, kernel_size=[1, new_features.size(3)]
+                )  # (B, mlp[-1], npoint, 1)
+            elif self.pool_method == 'avg_pool':
+                new_features = F.avg_pool2d(
+                    new_features, kernel_size=[1, new_features.size(3)]
+                )  # (B, mlp[-1], npoint, 1)
+            else:
+                raise NotImplementedError
+
+            new_features = new_features.squeeze(-1)  # (B, mlp[-1], npoint)
+            new_features_list.append(new_features)
+
+        return new_xyz, torch.cat(new_features_list, dim=1)
+
+
+class PointnetSAModuleMSG(_PointnetSAModuleBase):
+    """Pointnet set abstraction layer with multiscale grouping"""
+
+    def __init__(self, *, npoint: int, radii: List[float], nsamples: List[int], mlps: List[List[int]], bn: bool = True,
+                 use_xyz: bool = True, pool_method='max_pool', instance_norm=False):
+        """
+        :param npoint: int
+        :param radii: list of float, list of radii to group with
+        :param nsamples: list of int, number of samples in each ball query
+        :param mlps: list of list of int, spec of the pointnet before the global pooling for each scale
+        :param bn: whether to use batchnorm
+        :param use_xyz:
+        :param pool_method: max_pool / avg_pool
+        :param instance_norm: whether to use instance_norm
+        """
+        super().__init__()
+
+        assert len(radii) == len(nsamples) == len(mlps)
+
+        self.npoint = npoint
+        self.groupers = nn.ModuleList()
+        self.mlps = nn.ModuleList()
+        for i in range(len(radii)):
+            radius = radii[i]
+            nsample = nsamples[i]
+            self.groupers.append(
+                pointnet2_utils.QueryAndGroup(radius, nsample, use_xyz=use_xyz)
+                if npoint is not None else pointnet2_utils.GroupAll(use_xyz)
+            )
+            mlp_spec = mlps[i]
+            if use_xyz:
+                mlp_spec[0] += 3
+
+            self.mlps.append(pt_utils.SharedMLP(mlp_spec, bn=bn, instance_norm=instance_norm))
+        self.pool_method = pool_method
+
+
+class PointnetSAModule(PointnetSAModuleMSG):
+    """Pointnet set abstraction layer"""
+
+    def __init__(self, *, mlp: List[int], npoint: int = None, radius: float = None, nsample: int = None,
+                 bn: bool = True, use_xyz: bool = True, pool_method='max_pool', instance_norm=False):
+        """
+        :param mlp: list of int, spec of the pointnet before the global max_pool
+        :param npoint: int, number of features
+        :param radius: float, radius of ball
+        :param nsample: int, number of samples in the ball query
+        :param bn: whether to use batchnorm
+        :param use_xyz:
+        :param pool_method: max_pool / avg_pool
+        :param instance_norm: whether to use instance_norm
+        """
+        super().__init__(
+            mlps=[mlp], npoint=npoint, radii=[radius], nsamples=[nsample], bn=bn, use_xyz=use_xyz,
+            pool_method=pool_method, instance_norm=instance_norm
+        )
+
+
+class PointnetFPModule(nn.Module):
+    r"""Propigates the features of one set to another"""
+
+    def __init__(self, *, mlp: List[int], bn: bool = True):
+        """
+        :param mlp: list of int
+        :param bn: whether to use batchnorm
+        """
+        super().__init__()
+        self.mlp = pt_utils.SharedMLP(mlp, bn=bn)
+
+    def forward(
+            self, unknown: torch.Tensor, known: torch.Tensor, unknow_feats: torch.Tensor, known_feats: torch.Tensor
+    ) -> torch.Tensor:
+        """
+        :param unknown: (B, n, 3) tensor of the xyz positions of the unknown features
+        :param known: (B, m, 3) tensor of the xyz positions of the known features
+        :param unknow_feats: (B, C1, n) tensor of the features to be propigated to
+        :param known_feats: (B, C2, m) tensor of features to be propigated
+        :return:
+            new_features: (B, mlp[-1], n) tensor of the features of the unknown features
+        """
+        if known is not None:
+            dist, idx = pointnet2_utils.three_nn(unknown, known)
+            dist_recip = 1.0 / (dist + 1e-8)
+            norm = torch.sum(dist_recip, dim=2, keepdim=True)
+            weight = dist_recip / norm
+
+            interpolated_feats = pointnet2_utils.three_interpolate(known_feats, idx, weight)
+        else:
+            interpolated_feats = known_feats.expand(*known_feats.size()[0:2], unknown.size(1))
+
+        if unknow_feats is not None:
+            new_features = torch.cat([interpolated_feats, unknow_feats], dim=1)  # (B, C2 + C1, n)
+        else:
+            new_features = interpolated_feats
+
+        new_features = new_features.unsqueeze(-1)
+
+        new_features = self.mlp(new_features)
+
+        return new_features.squeeze(-1)
+
+
+if __name__ == "__main__":
+    pass

modules/module_lib/pointnet2_utils.py

@@ -0,0 +1,291 @@
+import torch
+from torch.autograd import Variable
+from torch.autograd import Function
+import torch.nn as nn
+from typing import Tuple
+import sys
+
+import pointnet2_cuda as pointnet2
+
+
+class FurthestPointSampling(Function):
+    @staticmethod
+    def forward(ctx, xyz: torch.Tensor, npoint: int) -> torch.Tensor:
+        """
+        Uses iterative furthest point sampling to select a set of npoint features that have the largest
+        minimum distance
+        :param ctx:
+        :param xyz: (B, N, 3) where N > npoint
+        :param npoint: int, number of features in the sampled set
+        :return:
+             output: (B, npoint) tensor containing the set
+        """
+        assert xyz.is_contiguous()
+
+        B, N, _ = xyz.size()
+        output = torch.cuda.IntTensor(B, npoint)
+        temp = torch.cuda.FloatTensor(B, N).fill_(1e10)
+
+        pointnet2.furthest_point_sampling_wrapper(B, N, npoint, xyz, temp, output)
+        return output
+
+    @staticmethod
+    def backward(xyz, a=None):
+        return None, None
+
+
+furthest_point_sample = FurthestPointSampling.apply
+
+
+class GatherOperation(Function):
+
+    @staticmethod
+    def forward(ctx, features: torch.Tensor, idx: torch.Tensor) -> torch.Tensor:
+        """
+        :param ctx:
+        :param features: (B, C, N)
+        :param idx: (B, npoint) index tensor of the features to gather
+        :return:
+            output: (B, C, npoint)
+        """
+        assert features.is_contiguous()
+        assert idx.is_contiguous()
+
+        B, npoint = idx.size()
+        _, C, N = features.size()
+        output = torch.cuda.FloatTensor(B, C, npoint)
+
+        pointnet2.gather_points_wrapper(B, C, N, npoint, features, idx, output)
+
+        ctx.for_backwards = (idx, C, N)
+        return output
+
+    @staticmethod
+    def backward(ctx, grad_out):
+        idx, C, N = ctx.for_backwards
+        B, npoint = idx.size()
+
+        grad_features = Variable(torch.cuda.FloatTensor(B, C, N).zero_())
+        grad_out_data = grad_out.data.contiguous()
+        pointnet2.gather_points_grad_wrapper(B, C, N, npoint, grad_out_data, idx, grad_features.data)
+        return grad_features, None
+
+
+gather_operation = GatherOperation.apply
+
+
+class ThreeNN(Function):
+
+    @staticmethod
+    def forward(ctx, unknown: torch.Tensor, known: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
+        """
+        Find the three nearest neighbors of unknown in known
+        :param ctx:
+        :param unknown: (B, N, 3)
+        :param known: (B, M, 3)
+        :return:
+            dist: (B, N, 3) l2 distance to the three nearest neighbors
+            idx: (B, N, 3) index of 3 nearest neighbors
+        """
+        assert unknown.is_contiguous()
+        assert known.is_contiguous()
+
+        B, N, _ = unknown.size()
+        m = known.size(1)
+        dist2 = torch.cuda.FloatTensor(B, N, 3)
+        idx = torch.cuda.IntTensor(B, N, 3)
+
+        pointnet2.three_nn_wrapper(B, N, m, unknown, known, dist2, idx)
+        return torch.sqrt(dist2), idx
+
+    @staticmethod
+    def backward(ctx, a=None, b=None):
+        return None, None
+
+
+three_nn = ThreeNN.apply
+
+
+class ThreeInterpolate(Function):
+
+    @staticmethod
+    def forward(ctx, features: torch.Tensor, idx: torch.Tensor, weight: torch.Tensor) -> torch.Tensor:
+        """
+        Performs weight linear interpolation on 3 features
+        :param ctx:
+        :param features: (B, C, M) Features descriptors to be interpolated from
+        :param idx: (B, n, 3) three nearest neighbors of the target features in features
+        :param weight: (B, n, 3) weights
+        :return:
+            output: (B, C, N) tensor of the interpolated features
+        """
+        assert features.is_contiguous()
+        assert idx.is_contiguous()
+        assert weight.is_contiguous()
+
+        B, c, m = features.size()
+        n = idx.size(1)
+        ctx.three_interpolate_for_backward = (idx, weight, m)
+        output = torch.cuda.FloatTensor(B, c, n)
+
+        pointnet2.three_interpolate_wrapper(B, c, m, n, features, idx, weight, output)
+        return output
+
+    @staticmethod
+    def backward(ctx, grad_out: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
+        """
+        :param ctx:
+        :param grad_out: (B, C, N) tensor with gradients of outputs
+        :return:
+            grad_features: (B, C, M) tensor with gradients of features
+            None:
+            None:
+        """
+        idx, weight, m = ctx.three_interpolate_for_backward
+        B, c, n = grad_out.size()
+
+        grad_features = Variable(torch.cuda.FloatTensor(B, c, m).zero_())
+        grad_out_data = grad_out.data.contiguous()
+
+        pointnet2.three_interpolate_grad_wrapper(B, c, n, m, grad_out_data, idx, weight, grad_features.data)
+        return grad_features, None, None
+
+
+three_interpolate = ThreeInterpolate.apply
+
+
+class GroupingOperation(Function):
+
+    @staticmethod
+    def forward(ctx, features: torch.Tensor, idx: torch.Tensor) -> torch.Tensor:
+        """
+        :param ctx:
+        :param features: (B, C, N) tensor of features to group
+        :param idx: (B, npoint, nsample) tensor containing the indicies of features to group with
+        :return:
+            output: (B, C, npoint, nsample) tensor
+        """
+        assert features.is_contiguous()
+        assert idx.is_contiguous()
+
+        B, nfeatures, nsample = idx.size()
+        _, C, N = features.size()
+        output = torch.cuda.FloatTensor(B, C, nfeatures, nsample)
+
+        pointnet2.group_points_wrapper(B, C, N, nfeatures, nsample, features, idx, output)
+
+        ctx.for_backwards = (idx, N)
+        return output
+
+    @staticmethod
+    def backward(ctx, grad_out: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
+        """
+        :param ctx:
+        :param grad_out: (B, C, npoint, nsample) tensor of the gradients of the output from forward
+        :return:
+            grad_features: (B, C, N) gradient of the features
+        """
+        idx, N = ctx.for_backwards
+
+        B, C, npoint, nsample = grad_out.size()
+        grad_features = Variable(torch.cuda.FloatTensor(B, C, N).zero_())
+
+        grad_out_data = grad_out.data.contiguous()
+        pointnet2.group_points_grad_wrapper(B, C, N, npoint, nsample, grad_out_data, idx, grad_features.data)
+        return grad_features, None
+
+
+grouping_operation = GroupingOperation.apply
+
+
+class BallQuery(Function):
+
+    @staticmethod
+    def forward(ctx, radius: float, nsample: int, xyz: torch.Tensor, new_xyz: torch.Tensor) -> torch.Tensor:
+        """
+        :param ctx:
+        :param radius: float, radius of the balls
+        :param nsample: int, maximum number of features in the balls
+        :param xyz: (B, N, 3) xyz coordinates of the features
+        :param new_xyz: (B, npoint, 3) centers of the ball query
+        :return:
+            idx: (B, npoint, nsample) tensor with the indicies of the features that form the query balls
+        """
+        assert new_xyz.is_contiguous()
+        assert xyz.is_contiguous()
+
+        B, N, _ = xyz.size()
+        npoint = new_xyz.size(1)
+        idx = torch.cuda.IntTensor(B, npoint, nsample).zero_()
+
+        pointnet2.ball_query_wrapper(B, N, npoint, radius, nsample, new_xyz, xyz, idx)
+        return idx
+
+    @staticmethod
+    def backward(ctx, a=None):
+        return None, None, None, None
+
+
+ball_query = BallQuery.apply
+
+
+class QueryAndGroup(nn.Module):
+    def __init__(self, radius: float, nsample: int, use_xyz: bool = True):
+        """
+        :param radius: float, radius of ball
+        :param nsample: int, maximum number of features to gather in the ball
+        :param use_xyz:
+        """
+        super().__init__()
+        self.radius, self.nsample, self.use_xyz = radius, nsample, use_xyz
+
+    def forward(self, xyz: torch.Tensor, new_xyz: torch.Tensor, features: torch.Tensor = None) -> Tuple[torch.Tensor]:
+        """
+        :param xyz: (B, N, 3) xyz coordinates of the features
+        :param new_xyz: (B, npoint, 3) centroids
+        :param features: (B, C, N) descriptors of the features
+        :return:
+            new_features: (B, 3 + C, npoint, nsample)
+        """
+        idx = ball_query(self.radius, self.nsample, xyz, new_xyz)
+        xyz_trans = xyz.transpose(1, 2).contiguous()
+        grouped_xyz = grouping_operation(xyz_trans, idx)  # (B, 3, npoint, nsample)
+        grouped_xyz -= new_xyz.transpose(1, 2).unsqueeze(-1)
+
+        if features is not None:
+            grouped_features = grouping_operation(features, idx)
+            if self.use_xyz:
+                new_features = torch.cat([grouped_xyz, grouped_features], dim=1)  # (B, C + 3, npoint, nsample)
+            else:
+                new_features = grouped_features
+        else:
+            assert self.use_xyz, "Cannot have not features and not use xyz as a feature!"
+            new_features = grouped_xyz
+
+        return new_features
+
+
+class GroupAll(nn.Module):
+    def __init__(self, use_xyz: bool = True):
+        super().__init__()
+        self.use_xyz = use_xyz
+
+    def forward(self, xyz: torch.Tensor, new_xyz: torch.Tensor, features: torch.Tensor = None):
+        """
+        :param xyz: (B, N, 3) xyz coordinates of the features
+        :param new_xyz: ignored
+        :param features: (B, C, N) descriptors of the features
+        :return:
+            new_features: (B, C + 3, 1, N)
+        """
+        grouped_xyz = xyz.transpose(1, 2).unsqueeze(2)
+        if features is not None:
+            grouped_features = features.unsqueeze(2)
+            if self.use_xyz:
+                new_features = torch.cat([grouped_xyz, grouped_features], dim=1)  # (B, 3 + C, 1, N)
+            else:
+                new_features = grouped_features
+        else:
+            new_features = grouped_xyz
+
+        return new_features

modules/module_lib/pytorch_utils.py

@@ -0,0 +1,236 @@
+import torch.nn as nn
+from typing import List, Tuple
+
+
+class SharedMLP(nn.Sequential):
+
+    def __init__(
+            self,
+            args: List[int],
+            *,
+            bn: bool = False,
+            activation=nn.ReLU(inplace=True),
+            preact: bool = False,
+            first: bool = False,
+            name: str = "",
+            instance_norm: bool = False,
+    ):
+        super().__init__()
+
+        for i in range(len(args) - 1):
+            self.add_module(
+                name + 'layer{}'.format(i),
+                Conv2d(
+                    args[i],
+                    args[i + 1],
+                    bn=(not first or not preact or (i != 0)) and bn,
+                    activation=activation
+                    if (not first or not preact or (i != 0)) else None,
+                    preact=preact,
+                    instance_norm=instance_norm
+                )
+            )
+
+
+class _ConvBase(nn.Sequential):
+
+    def __init__(
+            self,
+            in_size,
+            out_size,
+            kernel_size,
+            stride,
+            padding,
+            activation,
+            bn,
+            init,
+            conv=None,
+            batch_norm=None,
+            bias=True,
+            preact=False,
+            name="",
+            instance_norm=False,
+            instance_norm_func=None
+    ):
+        super().__init__()
+
+        bias = bias and (not bn)
+        conv_unit = conv(
+            in_size,
+            out_size,
+            kernel_size=kernel_size,
+            stride=stride,
+            padding=padding,
+            bias=bias
+        )
+        init(conv_unit.weight)
+        if bias:
+            nn.init.constant_(conv_unit.bias, 0)
+
+        if bn:
+            if not preact:
+                bn_unit = batch_norm(out_size)
+            else:
+                bn_unit = batch_norm(in_size)
+        if instance_norm:
+            if not preact:
+                in_unit = instance_norm_func(out_size, affine=False, track_running_stats=False)
+            else:
+                in_unit = instance_norm_func(in_size, affine=False, track_running_stats=False)
+
+        if preact:
+            if bn:
+                self.add_module(name + 'bn', bn_unit)
+
+            if activation is not None:
+                self.add_module(name + 'activation', activation)
+
+            if not bn and instance_norm:
+                self.add_module(name + 'in', in_unit)
+
+        self.add_module(name + 'conv', conv_unit)
+
+        if not preact:
+            if bn:
+                self.add_module(name + 'bn', bn_unit)
+
+            if activation is not None:
+                self.add_module(name + 'activation', activation)
+
+            if not bn and instance_norm:
+                self.add_module(name + 'in', in_unit)
+
+
+class _BNBase(nn.Sequential):
+
+    def __init__(self, in_size, batch_norm=None, name=""):
+        super().__init__()
+        self.add_module(name + "bn", batch_norm(in_size))
+
+        nn.init.constant_(self[0].weight, 1.0)
+        nn.init.constant_(self[0].bias, 0)
+
+
+class BatchNorm1d(_BNBase):
+
+    def __init__(self, in_size: int, *, name: str = ""):
+        super().__init__(in_size, batch_norm=nn.BatchNorm1d, name=name)
+
+
+class BatchNorm2d(_BNBase):
+
+    def __init__(self, in_size: int, name: str = ""):
+        super().__init__(in_size, batch_norm=nn.BatchNorm2d, name=name)
+
+
+class Conv1d(_ConvBase):
+
+    def __init__(
+            self,
+            in_size: int,
+            out_size: int,
+            *,
+            kernel_size: int = 1,
+            stride: int = 1,
+            padding: int = 0,
+            activation=nn.ReLU(inplace=True),
+            bn: bool = False,
+            init=nn.init.kaiming_normal_,
+            bias: bool = True,
+            preact: bool = False,
+            name: str = "",
+            instance_norm=False
+    ):
+        super().__init__(
+            in_size,
+            out_size,
+            kernel_size,
+            stride,
+            padding,
+            activation,
+            bn,
+            init,
+            conv=nn.Conv1d,
+            batch_norm=BatchNorm1d,
+            bias=bias,
+            preact=preact,
+            name=name,
+            instance_norm=instance_norm,
+            instance_norm_func=nn.InstanceNorm1d
+        )
+
+
+class Conv2d(_ConvBase):
+
+    def __init__(
+            self,
+            in_size: int,
+            out_size: int,
+            *,
+            kernel_size: Tuple[int, int] = (1, 1),
+            stride: Tuple[int, int] = (1, 1),
+            padding: Tuple[int, int] = (0, 0),
+            activation=nn.ReLU(inplace=True),
+            bn: bool = False,
+            init=nn.init.kaiming_normal_,
+            bias: bool = True,
+            preact: bool = False,
+            name: str = "",
+            instance_norm=False
+    ):
+        super().__init__(
+            in_size,
+            out_size,
+            kernel_size,
+            stride,
+            padding,
+            activation,
+            bn,
+            init,
+            conv=nn.Conv2d,
+            batch_norm=BatchNorm2d,
+            bias=bias,
+            preact=preact,
+            name=name,
+            instance_norm=instance_norm,
+            instance_norm_func=nn.InstanceNorm2d
+        )
+
+
+class FC(nn.Sequential):
+
+    def __init__(
+            self,
+            in_size: int,
+            out_size: int,
+            *,
+            activation=nn.ReLU(inplace=True),
+            bn: bool = False,
+            init=None,
+            preact: bool = False,
+            name: str = ""
+    ):
+        super().__init__()
+
+        fc = nn.Linear(in_size, out_size, bias=not bn)
+        if init is not None:
+            init(fc.weight)
+        if not bn:
+            nn.init.constant(fc.bias, 0)
+
+        if preact:
+            if bn:
+                self.add_module(name + 'bn', BatchNorm1d(in_size))
+
+            if activation is not None:
+                self.add_module(name + 'activation', activation)
+
+        self.add_module(name + 'fc', fc)
+
+        if not preact:
+            if bn:
+                self.add_module(name + 'bn', BatchNorm1d(out_size))
+
+            if activation is not None:
+                self.add_module(name + 'activation', activation)
+

modules/pointnet++_encoder.py

@@ -0,0 +1,121 @@
+import torch
+import torch.nn as nn
+import os
+import sys
+path = os.path.abspath(__file__)
+for i in range(2):
+    path = os.path.dirname(path)
+PROJECT_ROOT = path                 
+sys.path.append(PROJECT_ROOT)
+import PytorchBoot.stereotype as stereotype
+from modules.module_lib.pointnet2_modules import PointnetSAModuleMSG
+
+
+ClsMSG_CFG_Dense = {
+    'NPOINTS': [512, 256, 128, None],
+    'RADIUS': [[0.02, 0.04], [0.04, 0.08], [0.08, 0.16], [None, None]],
+    'NSAMPLE': [[32, 64], [16, 32], [8, 16], [None, None]],
+    'MLPS': [[[16, 16, 32], [32, 32, 64]],
+             [[64, 64, 128], [64, 96, 128]],
+             [[128, 196, 256], [128, 196, 256]],
+             [[256, 256, 512], [256, 384, 512]]],
+    'DP_RATIO': 0.5,
+}
+
+ClsMSG_CFG_Light = {
+    'NPOINTS': [512, 256, 128, None],
+    'RADIUS': [[0.02, 0.04], [0.04, 0.08], [0.08, 0.16], [None, None]],
+    'NSAMPLE': [[16, 32], [16, 32], [16, 32], [None, None]],
+    'MLPS': [[[16, 16, 32], [32, 32, 64]],
+             [[64, 64, 128], [64, 96, 128]],
+             [[128, 196, 256], [128, 196, 256]],
+             [[256, 256, 512], [256, 384, 512]]],
+    'DP_RATIO': 0.5,
+}
+
+ClsMSG_CFG_Lighter = {
+    'NPOINTS': [512, 256, 128, 64, None],
+    'RADIUS': [[0.01], [0.02], [0.04], [0.08], [None]],
+    'NSAMPLE': [[64], [32], [16], [8], [None]],
+    'MLPS': [[[32, 32, 64]],
+             [[64, 64, 128]],
+             [[128, 196, 256]],
+             [[256, 256, 512]],
+             [[512, 512, 1024]]],
+    'DP_RATIO': 0.5,
+}
+
+
+def select_params(name):
+    if name == 'light':
+        return ClsMSG_CFG_Light
+    elif name == 'lighter':
+        return ClsMSG_CFG_Lighter
+    elif name == 'dense':
+        return ClsMSG_CFG_Dense
+    else:
+        raise NotImplementedError
+
+
+def break_up_pc(pc):
+    xyz = pc[..., 0:3].contiguous()
+    features = (
+        pc[..., 3:].transpose(1, 2).contiguous()
+        if pc.size(-1) > 3 else None
+    )
+
+    return xyz, features
+
+
+@stereotype.module("pointnet++_encoder")
+class PointNet2Encoder(nn.Module):
+    def encode_points(self, pts, require_per_point_feat=False):
+        return self.forward(pts)
+
+    def __init__(self, config:dict):
+        super().__init__()
+
+        channel_in = config.get("in_dim", 3) - 3
+        params_name = config.get("params_name", "light")
+
+        self.SA_modules = nn.ModuleList()
+        selected_params = select_params(params_name)
+        for k in range(selected_params['NPOINTS'].__len__()):
+            mlps = selected_params['MLPS'][k].copy()
+            channel_out = 0
+            for idx in range(mlps.__len__()):
+                mlps[idx] = [channel_in] + mlps[idx]
+                channel_out += mlps[idx][-1]
+
+            self.SA_modules.append(
+                PointnetSAModuleMSG(
+                    npoint=selected_params['NPOINTS'][k],
+                    radii=selected_params['RADIUS'][k],
+                    nsamples=selected_params['NSAMPLE'][k],
+                    mlps=mlps,
+                    use_xyz=True,
+                    bn=True
+                )
+            )
+            channel_in = channel_out
+
+    def forward(self, point_cloud: torch.cuda.FloatTensor):
+        xyz, features = break_up_pc(point_cloud)
+
+        l_xyz, l_features = [xyz], [features]
+        for i in range(len(self.SA_modules)):
+            li_xyz, li_features = self.SA_modules[i](l_xyz[i], l_features[i])
+            l_xyz.append(li_xyz)
+            l_features.append(li_features)
+        return l_features[-1].squeeze(-1)
+
+
+if __name__ == '__main__':
+    seed = 100
+    torch.manual_seed(seed)
+    torch.cuda.manual_seed(seed)
+    net = PointNet2Encoder(config={"in_dim": 3, "params_name": "light"}).cuda()
+    pts = torch.randn(2, 1024, 3).cuda()
+    print(torch.mean(pts, dim=1))
+    pre = net.encode_points(pts)
+    print(pre.shape)

runners/inferencer.py

@@ -142,6 +142,7 @@ class Inferencer(Runner):
             voxel_downsampled_combined_scanned_pts_np, inverse =  self.voxel_downsample_with_mapping(combined_scanned_pts, voxel_threshold)
             output = self.pipeline(input_data)
             pred_pose_9d = output["pred_pose_9d"]
+            import ipdb; ipdb.set_trace()
             pred_pose = torch.eye(4, device=pred_pose_9d.device)
 
             pred_pose[:3,:3] = PoseUtil.rotation_6d_to_matrix_tensor_batch(pred_pose_9d[:,:6])[0]

utils/render.py

@@ -83,8 +83,7 @@ class RenderUtil:
             shutil.copy(scene_info_path, os.path.join(temp_dir, "scene_info.json"))
             params_data_path = os.path.join(temp_dir, "params.json")
             with open(params_data_path, 'w') as f:
-                json.dump(params, f)
-            #import ipdb; ipdb.set_trace()
+                json.dump(params, f) 
             result = subprocess.run([
                 '/home/hofee/blender-4.0.2-linux-x64/blender', '-b', '-P', script_path, '--', temp_dir
             ], capture_output=True, text=True)