pointnet2.py

import os.path
import numpy as np
import os,sys,copy,time,cv2
code_dir = os.path.dirname(os.path.realpath(__file__))
from collections import OrderedDict
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchvision
from PIL import Image


def square_distance(src, dst):
    """
    Calculate Euclid distance between each two points.
    src^T * dst = xn * xm + yn * ym + zn * zm；
    sum(src^2, dim=-1) = xn*xn + yn*yn + zn*zn;
    sum(dst^2, dim=-1) = xm*xm + ym*ym + zm*zm;
    dist = (xn - xm)^2 + (yn - ym)^2 + (zn - zm)^2
         = sum(src**2,dim=-1)+sum(dst**2,dim=-1)-2*src^T*dst
    Input:
        src: source points, [B, N, C]
        dst: target points, [B, M, C]
    Output:
        dist: per-point square distance, [B, N, M]
    """
    B, N, _ = src.shape
    _, M, _ = dst.shape
    dist = -2 * torch.matmul(src, dst.permute(0, 2, 1))
    dist += torch.sum(src ** 2, -1).view(B, N, 1)
    dist += torch.sum(dst ** 2, -1).view(B, 1, M)
    return dist

def index_points(points, idx):
    """
    Input:
        points: input points data, [B, N, C]
        idx: sample index data, [B, S]
    Return:
        new_points:, indexed points data, [B, S, C]
    """
    device = points.device
    B = points.shape[0]
    view_shape = list(idx.shape)
    view_shape[1:] = [1] * (len(view_shape) - 1)
    repeat_shape = list(idx.shape)
    repeat_shape[0] = 1
    batch_indices = torch.arange(B, dtype=torch.long).to(device).view(view_shape).repeat(repeat_shape)
    new_points = points[batch_indices, idx, :]
    return new_points


def farthest_point_sample(xyz, npoint):
    """
    Input:
        xyz: pointcloud data, [B, N, 3]
        npoint: number of samples
    Return:
        centroids: sampled pointcloud index, [B, npoint]
    """
    device = xyz.device
    B, N, C = xyz.shape
    centroids = torch.zeros(B, npoint, dtype=torch.long).to(device)
    distance = torch.ones(B, N).to(device) * 1e10
    farthest = torch.randint(0, N, (B,), dtype=torch.long).to(device)
    batch_indices = torch.arange(B, dtype=torch.long).to(device)
    for i in range(npoint):
        centroids[:, i] = farthest
        centroid = xyz[batch_indices, farthest, :].view(B, 1, 3)
        dist = torch.sum((xyz - centroid) ** 2, -1)
        mask = dist < distance
        distance[mask] = dist[mask]
        farthest = torch.max(distance, -1)[1]
    return centroids


def query_ball_point(radius, nsample, xyz, new_xyz):
    """
    Input:
        radius: local region radius
        nsample: max sample number in local region
        xyz: all points, [B, N, 3]
        new_xyz: query points, [B, S, 3]
    Return:
        group_idx: grouped points index, [B, S, nsample]
    """
    device = xyz.device
    B, N, C = xyz.shape
    _, S, _ = new_xyz.shape
    group_idx = torch.arange(N, dtype=torch.long).to(device).view(1, 1, N).repeat([B, S, 1])
    sqrdists = square_distance(new_xyz, xyz)
    group_idx[sqrdists > radius ** 2] = N
    group_idx = group_idx.sort(dim=-1)[0][:, :, :nsample]
    group_first = group_idx[:, :, 0].view(B, S, 1).repeat([1, 1, nsample])
    mask = group_idx == N
    group_idx[mask] = group_first[mask]
    return group_idx


def sample_and_group(npoint, radius, nsample, xyz, points, returnfps=False):
    """
    Input:
        npoint:
        radius:
        nsample:
        xyz: input points position data, [B, N, 3]
        points: input points data, [B, N, D]
    Return:
        new_xyz: sampled points position data, [B, npoint, nsample, 3]
        new_points: sampled points data, [B, npoint, nsample, 3+D]
    """
    B, N, C = xyz.shape
    S = npoint
    fps_idx = farthest_point_sample(xyz, npoint) # [B, npoint, C]
    new_xyz = index_points(xyz, fps_idx)
    idx = query_ball_point(radius, nsample, xyz, new_xyz)
    grouped_xyz = index_points(xyz, idx) # [B, npoint, nsample, C]
    grouped_xyz_norm = grouped_xyz - new_xyz.view(B, S, 1, C)

    if points is not None:
        grouped_points = index_points(points, idx)
        new_points = torch.cat([grouped_xyz_norm, grouped_points], dim=-1) # [B, npoint, nsample, C+D]
    else:
        new_points = grouped_xyz_norm
    if returnfps:
        return new_xyz, new_points, grouped_xyz, fps_idx
    else:
        return new_xyz, new_points


def sample_and_group_all(xyz, points):
    """
    Input:
        xyz: input points position data, [B, N, 3]
        points: input points data, [B, N, D]
    Return:
        new_xyz: sampled points position data, [B, 1, 3]
        new_points: sampled points data, [B, 1, N, 3+D]
    """
    device = xyz.device
    B, N, C = xyz.shape
    new_xyz = torch.zeros(B, 1, C).to(device)
    grouped_xyz = xyz.view(B, 1, N, C)
    if points is not None:
        new_points = torch.cat([grouped_xyz, points.view(B, 1, N, -1)], dim=-1)
    else:
        new_points = grouped_xyz
    return new_xyz, new_points



class STN3d(nn.Module):
    def __init__(self, channel):
        super().__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 = torch.tensor(np.array([1, 0, 0, 0, 1, 0, 0, 0, 1]).astype(np.float32)).view(1, 9).repeat(batchsize, 1).to(x.device)
        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.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 = torch.tensor(np.eye(self.k).flatten().astype(np.float32)).view(1, self.k * self.k).repeat(batchsize, 1).to(x.device)
        x = x + iden
        x = x.view(-1, self.k, self.k)
        return x


class PointNetEncoder(nn.Module):
    def __init__(self, global_feat=True, feature_transform=False, channel=3):
        super().__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:
            feature = x[:, :, 3:]
            x = x[:, :, :3]
        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)))
        x = self.bn3(self.conv3(x))
        x = torch.max(x, 2, keepdim=True)[0]
        x = x.view(-1, 1024)
        if self.global_feat:
            return x, trans, trans_feat
        else:
            x = x.view(-1, 1024, 1).repeat(1, 1, N)
            return torch.cat([x, pointfeat], 1), trans, trans_feat



class PointNetCls(nn.Module):
    def __init__(self, n_in, n_out):
        '''https://github.com/yanx27/Pointnet_Pointnet2_pytorch/blob/master/models/pointnet_cls.py
        '''
        super().__init__()
        self.feat = PointNetEncoder(global_feat=True, feature_transform=True, channel=n_in)
        self.fc1 = nn.Linear(1024, 512)
        self.fc2 = nn.Linear(512, 256)
        self.fc3 = nn.Linear(256, n_out)
        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):
        '''
        @x: (B,N,D)
        '''
        x = x.permute(0,2,1)   #(B,D,N)
        x, trans, trans_feat = self.feat(x)
        x = F.relu(self.bn1(self.fc1(x)))
        x = self.dropout(x)
        x = F.relu(self.bn2(self.fc2(x)))
        x = self.fc3(x)
        return x, trans_feat


class PointNetSeg(nn.Module):
    def __init__(self, n_in, n_out):
        '''https://github.com/yanx27/Pointnet_Pointnet2_pytorch/blob/master/models/pointnet_sem_seg.py
        '''
        super().__init__()
        self.feat = PointNetEncoder(global_feat=False, feature_transform=True, channel=n_in)
        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, n_out, 1)
        self.bn1 = nn.BatchNorm1d(512)
        self.bn2 = nn.BatchNorm1d(256)
        self.bn3 = nn.BatchNorm1d(128)

    def forward(self, x):
        '''
        @x: (B,N,D)
        '''
        x = x.permute(0,2,1)
        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.permute(0,2,1)  #(B,N,D)
        return x, trans_feat




if __name__=='__main__':
    import torchprof
    code_dir = os.path.dirname(os.path.realpath(__file__))