code/pointcept_framework/pointcept/models/default copy.py

import torch
import torch.nn as nn
import torch_scatter
import torch_cluster

from pointcept.models.losses import build_criteria
from pointcept.models.utils.structure import Point
from pointcept.models.utils import offset2batch
from .builder import MODELS, build_model


@MODELS.register_module()
class DefaultSegmentor(nn.Module):
    def __init__(self, backbone=None, criteria=None):
        super().__init__()
        self.backbone = build_model(backbone)
        self.criteria = build_criteria(criteria)

    def forward(self, input_dict):
        if "condition" in input_dict.keys():
            # PPT (https://arxiv.org/abs/2308.09718)
            # currently, only support one batch one condition
            input_dict["condition"] = input_dict["condition"][0]
        seg_logits = self.backbone(input_dict)
        # train
        if self.training:
            loss = self.criteria(seg_logits, input_dict["segment"])
            return dict(loss=loss)
        # eval
        elif "segment" in input_dict.keys():
            loss = self.criteria(seg_logits, input_dict["segment"])
            return dict(loss=loss, seg_logits=seg_logits)
        # test
        else:
            return dict(seg_logits=seg_logits)


@MODELS.register_module()
class DefaultSegmentorV2(nn.Module):
    def __init__(
        self,
        num_classes,
        backbone_out_channels,
        backbone=None,
        criteria=None,
        freeze_backbone=False,
    ):
        super().__init__()
        self.seg_head = (
            nn.Linear(backbone_out_channels, num_classes)
            if num_classes > 0
            else nn.Identity()
        )
        self.backbone = build_model(backbone)
        self.criteria = build_criteria(criteria)
        self.freeze_backbone = freeze_backbone
        if self.freeze_backbone:
            for p in self.backbone.parameters():
                p.requires_grad = False

    def forward(self, input_dict, return_point=False):
        point = Point(input_dict)
        point = self.backbone(point)
        # Backbone added after v1.5.0 return Point instead of feat and use DefaultSegmentorV2
        # TODO: remove this part after make all backbone return Point only.
        if isinstance(point, Point):
            while "pooling_parent" in point.keys():
                assert "pooling_inverse" in point.keys()
                parent = point.pop("pooling_parent")
                inverse = point.pop("pooling_inverse")
                parent.feat = torch.cat([parent.feat, point.feat[inverse]], dim=-1)
                point = parent
            feat = point.feat
        else:
            feat = point
        seg_logits = self.seg_head(feat)
        return_dict = dict()
        if return_point:
            # PCA evaluator parse feat and coord in point
            return_dict["point"] = point
        # train
        if self.training:
            loss = self.criteria(seg_logits, input_dict["segment"])
            return_dict["loss"] = loss
        # eval
        elif "segment" in input_dict.keys():
            loss = self.criteria(seg_logits, input_dict["segment"])
            return_dict["loss"] = loss
            return_dict["seg_logits"] = seg_logits
        # test
        else:
            return_dict["seg_logits"] = seg_logits
        return return_dict


@MODELS.register_module()
class DINOEnhancedSegmentor(nn.Module):
    def __init__(
        self,
        num_classes,
        backbone_out_channels,
        backbone=None,
        criteria=None,
        freeze_backbone=False,
    ):
        super().__init__()
        self.seg_head = (
            nn.Linear(backbone_out_channels, num_classes)
            if num_classes > 0
            else nn.Identity()
        )
        self.backbone = build_model(backbone) if backbone is not None else None
        self.criteria = build_criteria(criteria)
        self.freeze_backbone = freeze_backbone
        if self.backbone is not None and self.freeze_backbone:
            for p in self.backbone.parameters():
                p.requires_grad = False

    def forward(self, input_dict, return_point=False):
        point = Point(input_dict)
        if self.backbone is not None:
            if self.freeze_backbone:
                with torch.no_grad():
                    point = self.backbone(point)
            else:
                point = self.backbone(point)
            point_list = [point]
            while "unpooling_parent" in point_list[-1].keys():
                point_list.append(point_list[-1].pop("unpooling_parent"))
            for i in reversed(range(1, len(point_list))):
                point = point_list[i]
                parent = point_list[i - 1]
                assert "pooling_inverse" in point.keys()
                inverse = point.pooling_inverse
                parent.feat = torch.cat([parent.feat, point.feat[inverse]], dim=-1)
            point = point_list[0]
            while "pooling_parent" in point.keys():
                assert "pooling_inverse" in point.keys()
                parent = point.pop("pooling_parent")
                inverse = point.pooling_inverse
                parent.feat = torch.cat([parent.feat, point.feat[inverse]], dim=-1)
                point = parent
            feat = [point.feat]
        else:
            feat = []
        dino_coord = input_dict["dino_coord"]
        dino_feat = input_dict["dino_feat"]
        dino_offset = input_dict["dino_offset"]
        idx = torch_cluster.knn(
            x=dino_coord,
            y=point.origin_coord,
            batch_x=offset2batch(dino_offset),
            batch_y=offset2batch(point.origin_offset),
            k=1,
        )[1]

        feat.append(dino_feat[idx])
        feat = torch.concatenate(feat, dim=-1)
        seg_logits = self.seg_head(feat)
        return_dict = dict()
        if return_point:
            # PCA evaluator parse feat and coord in point
            return_dict["point"] = point
        # train
        if self.training:
            loss = self.criteria(seg_logits, input_dict["segment"])
            return_dict["loss"] = loss
        # eval
        elif "segment" in input_dict.keys():
            loss = self.criteria(seg_logits, input_dict["segment"])
            return_dict["loss"] = loss
            return_dict["seg_logits"] = seg_logits
        # test
        else:
            return_dict["seg_logits"] = seg_logits
        return return_dict


@MODELS.register_module()
class DefaultClassifier(nn.Module):
    def __init__(
        self,
        backbone=None,
        criteria=None,
        num_classes=40,
        backbone_embed_dim=256,
    ):
        super().__init__()
        self.backbone = build_model(backbone)
        self.criteria = build_criteria(criteria)
        self.num_classes = num_classes
        self.backbone_embed_dim = backbone_embed_dim
        self.cls_head = nn.Sequential(
            nn.Linear(backbone_embed_dim, 256),
            nn.BatchNorm1d(256),
            nn.ReLU(inplace=True),
            nn.Dropout(p=0.5),
            nn.Linear(256, 128),
            nn.BatchNorm1d(128),
            nn.ReLU(inplace=True),
            nn.Dropout(p=0.5),
            nn.Linear(128, num_classes),
        )

    def forward(self, input_dict):
        point = Point(input_dict)
        point = self.backbone(point)
        # Backbone added after v1.5.0 return Point instead of feat
        # And after v1.5.0 feature aggregation for classification operated in classifier
        # TODO: remove this part after make all backbone return Point only.
        if isinstance(point, Point):
            point.feat = torch_scatter.segment_csr(
                src=point.feat,
                indptr=nn.functional.pad(point.offset, (1, 0)),
                reduce="mean",
            )
            feat = point.feat
        else:
            feat = point
        cls_logits = self.cls_head(feat)
        if self.training:
            loss = self.criteria(cls_logits, input_dict["category"])
            return dict(loss=loss)
        elif "category" in input_dict.keys():
            loss = self.criteria(cls_logits, input_dict["category"])
            return dict(loss=loss, cls_logits=cls_logits)
        else:
            return dict(cls_logits=cls_logits)