diff --git a/classification_ModelNet40/models/__init__.py b/classification_ModelNet40/models/__init__.py index 351cb18..b8815da 100644 --- a/classification_ModelNet40/models/__init__.py +++ b/classification_ModelNet40/models/__init__.py @@ -1,52 +1,3 @@ from __future__ import absolute_import -from .pct import PCT -from .pointConv import PointConv -from .GDANet import GDANET -from .GBNet import GBNet, DGCNN -# from .PAconv import PAConv # could not excuted. -from .CurveNet import CurveNet -from .pctmlp import PCTMLP -from .pointnet_noBN import PointNetNoBN -from .pointnet2_affine import PointNet2Affine -from .pointnet import PointNet -from .pointnet_deep import PointNetDeep -from .pointnet_deep_noBN import PointNetDeepNoBN -from .pointnet2 import PointNet2 -from .pointnet2_noBN import PointNet2NoBN -from .pointnetmlp import PointNetMLP -from .model25 import model25H -from .model26 import model26H, model26A, model26B, model26C, model26D -from .model31 import model31A, model31B, model31C, model31D, model31E, model31F, model31G, model31H, model31I, \ - model31J, model31K, model31L, model31M, model31N -from .model31NoRes import model31CNoRes - -from .model32 import model32A,model32C,model32D, model32E, model32F, model32G, model32H, model32I, model32J, model32K,\ - model32L, model32M, model32N, model32A2, model32A3, model32A4 - -from .model33 import model33A, model33B, model33C, model33D, model33E, model33F, model33G, model33H - - - -from .pointsformer1 import pointsformer1A, pointsformer1B, pointsformer1C, pointsformer1D, pointsformer1H, \ - pointsformer1E, pointsformer1F, pointsformer1G, pointsformer1I - -from .modelelite import modeleliteA, modeleliteB, modeleliteC, modeleliteD, modeleliteE, modeleliteF, modeleliteG -from .modelelite2 import modelelite2A, modelelite2B, modelelite2C, modelelite2D, modelelite2E, modelelite2F, \ - modelelite2G, modelelite2H, modelelite2I, modelelite2J, modelelite2K, modelelite2L, \ - modelelite2A2, modelelite2B2, modelelite2C2, modelelite2D2, modelelite2E2, modelelite2F2, \ - modelelite2G2, modelelite2H2, modelelite2I2, modelelite2J2, modelelite2K2, modelelite2L2, \ - modelelite2A3, modelelite2B3, modelelite2C3, modelelite2D3, modelelite2E3, modelelite2F3, \ - modelelite2G3, modelelite2H3, modelelite2I3, modelelite2J3, modelelite2K3, modelelite2L3 - -from .modelelite3 import modelelite3A1, modelelite3A2, modelelite3B1, modelelite3B2, modelelite3C1, modelelite3C2, \ - modelelite3D1, modelelite3D2, modelelite3E1, modelelite3E2, modelelite3F1, modelelite3F2, modelelite3G1, \ - modelelite3G2, modelelite3H1, modelelite3H2, modelelite3I1, modelelite3I2, modelelite3J1, modelelite3J2, \ - modelelite3K1, modelelite3K2, modelelite3L1, modelelite3L2, modelelite3X1, modelelite3X2, modelelite3X3, \ - modelelite3X4, modelelite3X5, modelelite3X6, modelelite3X7, modelelite3X8, modelelite3X9, modelelite3X10, \ - modelelite3X11, modelelite3X12, modelelite3X13 - -from .pointsformer2 import pointsformer2A, pointsformer2B, pointsformer2C, pointsformer2D, pointsformer2E, \ - pointsformer2F, pointsformer2G, pointsformer2H, pointsformer2I, pointsformer2J, pointsformer2K, \ - pointsformer2L, pointsformer2M, pointsformer2N, pointsformer2O, pointsformer2P, pointsformer2Q, pointsformer2R -# from .pointsformer2 import pointsformer2A, pointsformer2B +from .pointmlp import pointMLP, pointMLPElite diff --git a/classification_ModelNet40/models/modelelite3.py b/classification_ModelNet40/models/modelelite3.py deleted file mode 100644 index b5ae79b..0000000 --- a/classification_ModelNet40/models/modelelite3.py +++ /dev/null @@ -1,624 +0,0 @@ -""" -Based on model31, different configures for elite version. -Based on model30, change the grouper operation by normalization. -Based on model28, only change configurations, mainly the reducer. -Based on model27, change to x-a, reorgnized structure -Based on model25, simple LocalGrouper (not x-a), reorgnized structure -Based on model24, using ReLU to replace GELU -Based on model22, remove attention -Bsed on model21, change FPS to random sampling. -Exactly based on Model10, but ReLU to GeLU -Based on Model8, add dropout and max, avg combine. -Based on Local model, add residual connections. -The extraction is doubled for depth. -Learning Point Cloud with Progressively Local representation. -[B,3,N] - {[B,G,K,d]-[B,G,d]} - {[B,G',K,d]-[B,G',d]} -cls -""" -import torch -import torch.nn as nn -import torch.nn.functional as F -# from torch import einsum -# from einops import rearrange, repeat -from einops.layers.torch import Rearrange - - -from pointnet2_ops import pointnet2_utils - - -def get_activation(activation): - if activation.lower() == 'gelu': - return nn.GELU() - elif activation.lower() == 'rrelu': - return nn.RReLU(inplace=True) - elif activation.lower() == 'selu': - return nn.SELU(inplace=True) - elif activation.lower() == 'silu': - return nn.SiLU(inplace=True) - elif activation.lower() == 'hardswish': - return nn.Hardswish(inplace=True) - elif activation.lower() == 'leakyrelu': - return nn.LeakyReLU(inplace=True) - else: - return nn.ReLU(inplace=True) - - -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) - distance = torch.min(distance, dist) - 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 knn_point(nsample, xyz, new_xyz): - """ - Input: - nsample: max sample number in local region - xyz: all points, [B, N, C] - new_xyz: query points, [B, S, C] - Return: - group_idx: grouped points index, [B, S, nsample] - """ - sqrdists = square_distance(new_xyz, xyz) - _, group_idx = torch.topk(sqrdists, nsample, dim=-1, largest=False, sorted=False) - return group_idx - - -class LocalGrouper(nn.Module): - def __init__(self, channel, groups, kneighbors, use_xyz=True, normalize="center", **kwargs): - """ - Give xyz[b,p,3] and fea[b,p,d], return new_xyz[b,g,3] and new_fea[b,g,k,d] - :param groups: groups number - :param kneighbors: k-nerighbors - :param kwargs: others - """ - super(LocalGrouper, self).__init__() - self.groups = groups - self.kneighbors = kneighbors - self.use_xyz = use_xyz - if normalize is not None: - self.normalize = normalize.lower() - else: - self.normalize = None - if self.normalize not in ["center", "anchor"]: - print(f"Unrecognized normalize parameter (self.normalize), set to None. Should be one of [center, anchor].") - self.normalize = None - if self.normalize is not None: - add_channel=3 if self.use_xyz else 0 - self.affine_alpha = nn.Parameter(torch.ones([1,1,1,channel + add_channel])) - self.affine_beta = nn.Parameter(torch.zeros([1, 1, 1, channel + add_channel])) - - def forward(self, xyz, points): - B, N, C = xyz.shape - S = self.groups - xyz = xyz.contiguous() # xyz [btach, points, xyz] - - # fps_idx = torch.multinomial(torch.linspace(0, N - 1, steps=N).repeat(B, 1).to(xyz.device), num_samples=self.groups, replacement=False).long() - # fps_idx = farthest_point_sample(xyz, self.groups).long() - fps_idx = pointnet2_utils.furthest_point_sample(xyz, self.groups).long() # [B, npoint] - new_xyz = index_points(xyz, fps_idx) # [B, npoint, 3] - new_points = index_points(points, fps_idx) # [B, npoint, d] - - idx = knn_point(self.kneighbors, xyz, new_xyz) - # idx = query_ball_point(radius, nsample, xyz, new_xyz) - grouped_xyz = index_points(xyz, idx) # [B, npoint, k, 3] - grouped_points = index_points(points, idx) # [B, npoint, k, d] - if self.use_xyz: - grouped_points = torch.cat([grouped_points, grouped_xyz],dim=-1) # [B, npoint, k, d+3] - if self.normalize is not None: - if self.normalize =="center": - std, mean = torch.std_mean(grouped_points, dim=2, keepdim=True) - if self.normalize =="anchor": - mean = torch.cat([new_points, new_xyz],dim=-1) if self.use_xyz else new_points - mean = mean.unsqueeze(dim=-2) # [B, npoint, 1, d+3] - std = torch.std(grouped_points-mean) - grouped_points = (grouped_points-mean)/(std + 1e-5) - grouped_points = self.affine_alpha*grouped_points + self.affine_beta - - new_points = torch.cat([grouped_points, new_points.view(B, S, 1, -1).repeat(1, 1, self.kneighbors, 1)], dim=-1) - return new_xyz, new_points - - -class ConvBNReLU1D(nn.Module): - def __init__(self, in_channels, out_channels, kernel_size=1, bias=True, activation='relu'): - super(ConvBNReLU1D, self).__init__() - self.act = get_activation(activation) - self.net = nn.Sequential( - nn.Conv1d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, bias=bias), - nn.BatchNorm1d(out_channels), - self.act - ) - - def forward(self, x): - return self.net(x) - - -class ConvBNReLURes1D(nn.Module): - def __init__(self, channel, kernel_size=1, groups=1, res_expansion=1.0, bias=True, activation='relu'): - super(ConvBNReLURes1D, self).__init__() - self.act = get_activation(activation) - self.net1 = nn.Sequential( - nn.Conv1d(in_channels=channel, out_channels=int(channel * res_expansion), - kernel_size=kernel_size, groups=groups, bias=bias), - nn.BatchNorm1d(int(channel * res_expansion)), - self.act - ) - self.net2 = nn.Sequential( - nn.Conv1d(in_channels=int(channel * res_expansion), out_channels=channel, - kernel_size=kernel_size, groups=groups, bias=bias), - nn.BatchNorm1d(channel) - ) - - def forward(self, x): - return self.act(self.net2(self.net1(x)) + x) - - -class PreExtraction(nn.Module): - def __init__(self, channels, out_channels, blocks=1, groups=1, res_expansion=1, bias=True, - activation='relu', use_xyz=True): - """ - input: [b,g,k,d]: output:[b,d,g] - :param channels: - :param blocks: - """ - super(PreExtraction, self).__init__() - in_channels = 3+2*channels if use_xyz else 2*channels - self.transfer = ConvBNReLU1D(in_channels, out_channels, bias=bias, activation=activation) - operation = [] - for _ in range(blocks): - operation.append( - ConvBNReLURes1D(out_channels, groups=groups, res_expansion=res_expansion, - bias=bias, activation=activation) - ) - self.operation = nn.Sequential(*operation) - - def forward(self, x): - b, n, s, d = x.size() # torch.Size([32, 512, 32, 6]) - x = x.permute(0, 1, 3, 2) - x = x.reshape(-1, d, s) - x = self.transfer(x) - batch_size, _, _ = x.size() - x = self.operation(x) # [b, d, k] - x = F.adaptive_max_pool1d(x, 1).view(batch_size, -1) - x = x.reshape(b, n, -1).permute(0, 2, 1) - return x - - -class PosExtraction(nn.Module): - def __init__(self, channels, blocks=1, groups=1, res_expansion=1, bias=True, activation='relu'): - """ - input[b,d,g]; output[b,d,g] - :param channels: - :param blocks: - """ - super(PosExtraction, self).__init__() - operation = [] - for _ in range(blocks): - operation.append( - ConvBNReLURes1D(channels, groups=groups, res_expansion=res_expansion, bias=bias, activation=activation) - ) - self.operation = nn.Sequential(*operation) - - def forward(self, x): # [b, d, g] - return self.operation(x) - - -class modelelite3(nn.Module): - def __init__(self, points=1024, class_num=40, embed_dim=64, groups=1, res_expansion=1.0, - activation="relu", bias=True, use_xyz=True, normalize="center", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs): - super(modelelite3, self).__init__() - self.stages = len(pre_blocks) - self.class_num = class_num - self.points = points - self.embedding = ConvBNReLU1D(3, embed_dim, bias=bias, activation=activation) - assert len(pre_blocks) == len(k_neighbors) == len(reducers) == len(pos_blocks) == len(dim_expansion), \ - "Please check stage number consistent for pre_blocks, pos_blocks k_neighbors, reducers." - self.local_grouper_list = nn.ModuleList() - self.pre_blocks_list = nn.ModuleList() - self.pos_blocks_list = nn.ModuleList() - last_channel = embed_dim - anchor_points = self.points - for i in range(len(pre_blocks)): - out_channel = last_channel * dim_expansion[i] - pre_block_num = pre_blocks[i] - pos_block_num = pos_blocks[i] - kneighbor = k_neighbors[i] - reduce = reducers[i] - anchor_points = anchor_points // reduce - # append local_grouper_list - local_grouper = LocalGrouper(last_channel, anchor_points, kneighbor, use_xyz, normalize) # [b,g,k,d] - self.local_grouper_list.append(local_grouper) - # append pre_block_list - pre_block_module = PreExtraction(last_channel, out_channel, pre_block_num, groups=groups, - res_expansion=res_expansion, - bias=bias, activation=activation, use_xyz=use_xyz) - self.pre_blocks_list.append(pre_block_module) - # append pos_block_list - pos_block_module = PosExtraction(out_channel, pos_block_num, groups=groups, - res_expansion=res_expansion, bias=bias, activation=activation) - self.pos_blocks_list.append(pos_block_module) - - last_channel = out_channel - - self.act = get_activation(activation) - self.classifier = nn.Sequential( - nn.Linear(last_channel, 512), - nn.BatchNorm1d(512), - self.act, - nn.Dropout(0.5), - nn.Linear(512, 256), - nn.BatchNorm1d(256), - self.act, - nn.Dropout(0.5), - nn.Linear(256, self.class_num) - ) - - def forward(self, x): - xyz = x.permute(0, 2, 1) - batch_size, _, _ = x.size() - x = self.embedding(x) # B,D,N - for i in range(self.stages): - # Give xyz[b, p, 3] and fea[b, p, d], return new_xyz[b, g, 3] and new_fea[b, g, k, d] - xyz, x = self.local_grouper_list[i](xyz, x.permute(0, 2, 1)) # [b,g,3] [b,g,k,d] - x = self.pre_blocks_list[i](x) # [b,d,g] - x = self.pos_blocks_list[i](x) # [b,d,g] - - x = F.adaptive_max_pool1d(x, 1).squeeze(dim=-1) - x = self.classifier(x) - return x - - - -def modelelite3A1(num_classes=40, **kwargs) -> modelelite3: # 3.48M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3B1(num_classes=40, **kwargs) -> modelelite3: # 2.78M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.0625, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3C1(num_classes=40, **kwargs) -> modelelite3: # 4.87M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3D1(num_classes=40, **kwargs) -> modelelite3: # 2.26M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=8, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3E1(num_classes=40, **kwargs) -> modelelite3: # 2.43M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3F1(num_classes=40, **kwargs) -> modelelite3: # 0.85M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3G1(num_classes=40, **kwargs) -> modelelite3: # 0.85M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3H1(num_classes=40, **kwargs) -> modelelite3: # 3.56M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=1, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3I1(num_classes=40, **kwargs) -> modelelite3: # 0.90M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 3, 3, 3], pos_blocks=[3, 3, 3, 3], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3J1(num_classes=40, **kwargs) -> modelelite3: # 0.93M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 4, 6, 3], pos_blocks=[3, 4, 6, 3], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3K1(num_classes=40, **kwargs) -> modelelite3: # 0.93M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=8, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 4, 6, 3], pos_blocks=[3, 4, 6, 3], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3L1(num_classes=40, **kwargs) -> modelelite3: # 0.95M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=8, res_expansion=0.25, - activation="relu", bias=True, use_xyz=True, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 4, 6, 3], pos_blocks=[3, 4, 6, 3], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -########version 2: 64 neighbors with 0.5 drop ratio ########### -def modelelite3A2(num_classes=40, **kwargs) -> modelelite3: # 3.48M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3B2(num_classes=40, **kwargs) -> modelelite3: # 2.78M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.0625, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3C2(num_classes=40, **kwargs) -> modelelite3: # 4.87M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3D2(num_classes=40, **kwargs) -> modelelite3: # 2.26M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=8, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3E2(num_classes=40, **kwargs) -> modelelite3: # 2.43M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3F2(num_classes=40, **kwargs) -> modelelite3: # 0.85M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3G2(num_classes=40, **kwargs) -> modelelite3: # 0.85M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3H2(num_classes=40, **kwargs) -> modelelite3: # 3.56M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=1, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3I2(num_classes=40, **kwargs) -> modelelite3: # 0.90M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 3, 3, 3], pos_blocks=[3, 3, 3, 3], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3J2(num_classes=40, **kwargs) -> modelelite3: # 0.93M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 4, 6, 3], pos_blocks=[3, 4, 6, 3], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3K2(num_classes=40, **kwargs) -> modelelite3: # 0.93M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=8, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 4, 6, 3], pos_blocks=[3, 4, 6, 3], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3L2(num_classes=40, **kwargs) -> modelelite3: # 0.95M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=8, res_expansion=0.25, - activation="relu", bias=True, use_xyz=True, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 4, 6, 3], pos_blocks=[3, 4, 6, 3], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - - - -def modelelite3X1(num_classes=40, **kwargs) -> modelelite3: # 1.11M 1m47s/16s - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X2(num_classes=40, **kwargs) -> modelelite3: # 0.94M 121/18s - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=2, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X3(num_classes=40, **kwargs) -> modelelite3: # 0.94 87/14s - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 1], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X4(num_classes=40, **kwargs) -> modelelite3: # 2.77 107s/17s - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 1], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X5(num_classes=40, **kwargs) -> modelelite3: # 1.59 - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 1], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 1], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X6(num_classes=40, **kwargs) -> modelelite3: # 1.44 - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=4, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 1], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 1], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X7(num_classes=40, **kwargs) -> modelelite3: # 1.11M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24,24,24,24], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X8(num_classes=40, **kwargs) -> modelelite3: # 0.95M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[1, 1, 2, 1], pos_blocks=[1, 1, 1, 1], - k_neighbors=[24,24,24,24], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X9(num_classes=40, **kwargs) -> modelelite3: # 1.59M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 1], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 1], - k_neighbors=[24,24,24,24], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X10(num_classes=40, **kwargs) -> modelelite3: # 0.72M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 1], pre_blocks=[1, 1, 2, 1], pos_blocks=[1, 1, 2, 1], - k_neighbors=[24,24,24,24], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X11(num_classes=40, **kwargs) -> modelelite3: # 0.98M 79/13s - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[1, 2, 2, 2], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 0], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X12(num_classes=40, **kwargs) -> modelelite3: # 0.98M 78/13s - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[1, 2, 2, 2], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 0], - k_neighbors=[24,24,24,24], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X13(num_classes=40, **kwargs) -> modelelite3: # 0.94M 90/15s - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[1, 2, 2, 2], pre_blocks=[1, 2, 2, 2], pos_blocks=[1, 1, 0, 0], - k_neighbors=[24,24,24,24], reducers=[2, 2, 2, 2], **kwargs) - -if __name__ == '__main__': - # data = torch.rand(2, 128, 10) - # model = ConvBNReLURes1D(128, groups=2, activation='relu') - # out = model(data) - # print(out.shape) - # - # batch, groups, neighbors, dim = 2, 512, 32, 16 - # x = torch.rand(batch, groups, neighbors, dim) - # pre_extractor = PreExtraction(dim, 3) - # out = pre_extractor(x) - # print(out.shape) - # - # x = torch.rand(batch, dim, groups) - # pos_extractor = PosExtraction(dim, 3) - # out = pos_extractor(x) - # print(out.shape) - - data = torch.rand(2, 3, 1024) - - print("===> testing modelN ...") - model = modelelite3A1() - out = model(data) - print(out.shape) diff --git a/classification_ModelNet40/models/model31.py b/classification_ModelNet40/models/pointmlp.py similarity index 67% rename from classification_ModelNet40/models/model31.py rename to classification_ModelNet40/models/pointmlp.py index 53ff872..c6dce17 100644 --- a/classification_ModelNet40/models/model31.py +++ b/classification_ModelNet40/models/pointmlp.py @@ -1,18 +1,4 @@ -""" -Based on model30, change the grouper operation by normalization. -Based on model28, only change configurations, mainly the reducer. -Based on model27, change to x-a, reorgnized structure -Based on model25, simple LocalGrouper (not x-a), reorgnized structure -Based on model24, using ReLU to replace GELU -Based on model22, remove attention -Bsed on model21, change FPS to random sampling. -Exactly based on Model10, but ReLU to GeLU -Based on Model8, add dropout and max, avg combine. -Based on Local model, add residual connections. -The extraction is doubled for depth. -Learning Point Cloud with Progressively Local representation. -[B,3,N] - {[B,G,K,d]-[B,G,d]} - {[B,G',K,d]-[B,G',d]} -cls -""" + import torch import torch.nn as nn import torch.nn.functional as F @@ -291,12 +277,12 @@ class PosExtraction(nn.Module): return self.operation(x) -class model31(nn.Module): +class Model(nn.Module): def __init__(self, points=1024, class_num=40, embed_dim=64, groups=1, res_expansion=1.0, activation="relu", bias=True, use_xyz=True, normalize="center", dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs): - super(model31, self).__init__() + super(Model, self).__init__() self.stages = len(pre_blocks) self.class_num = class_num self.points = points @@ -359,130 +345,24 @@ class model31(nn.Module): -def model31A(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) -def model31B(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, - activation="relu", bias=False, use_xyz=False, normalize="center", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def model31C(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, +def pointMLP(num_classes=40, **kwargs) -> Model: + return Model(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, activation="relu", bias=False, use_xyz=False, normalize="anchor", dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) -def model31D(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, + +def pointMLPElite(num_classes=40, **kwargs) -> Model: + return Model(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=0.25, activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - - -def model31E(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=1.0, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def model31F(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def model31G(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=16, res_expansion=2.0, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - -def model31H(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=128, groups=1, res_expansion=1, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2], pre_blocks=[4, 4], pos_blocks=[4, 4], - k_neighbors=[32, 32], reducers=[4, 4], **kwargs) - -def model31I(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=128, groups=1, res_expansion=1, - activation="gelu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2], pre_blocks=[4, 4], pos_blocks=[4, 4], - k_neighbors=[32, 32], reducers=[4, 4], **kwargs) - -def model31J(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=128, groups=1, res_expansion=1, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2], pre_blocks=[4, 4], pos_blocks=[4, 4], - k_neighbors=[24, 24], reducers=[4, 4], **kwargs) - -def model31K(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=384, groups=1, res_expansion=1, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[1, 1], pre_blocks=[4, 4], pos_blocks=[4, 4], - k_neighbors=[32, 32], reducers=[4, 4], **kwargs) - -def model31L(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=128, groups=1, res_expansion=1, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2], pre_blocks=[3, 3, 3], pos_blocks=[3, 3, 3], - k_neighbors=[24, 24, 24], reducers=[4, 4, 2], **kwargs) - -def model31M(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=128, groups=1, res_expansion=1, - activation="leakyrelu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2], pre_blocks=[4, 4], pos_blocks=[4, 4], - k_neighbors=[32, 32], reducers=[4, 4], **kwargs) - -def model31N(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=1.0, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[4, 8, 4, 2], pos_blocks=[4, 8, 4, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - + dim_expansion=[2, 2, 2, 1], pre_blocks=[1, 1, 2, 1], pos_blocks=[1, 1, 2, 1], + k_neighbors=[24,24,24,24], reducers=[2, 2, 2, 2], **kwargs) if __name__ == '__main__': - # data = torch.rand(2, 128, 10) - # model = ConvBNReLURes1D(128, groups=2, activation='relu') - # out = model(data) - # print(out.shape) - # - # batch, groups, neighbors, dim = 2, 512, 32, 16 - # x = torch.rand(batch, groups, neighbors, dim) - # pre_extractor = PreExtraction(dim, 3) - # out = pre_extractor(x) - # print(out.shape) - # - # x = torch.rand(batch, dim, groups) - # pos_extractor = PosExtraction(dim, 3) - # out = pos_extractor(x) - # print(out.shape) - data = torch.rand(2, 3, 1024) - - print("===> testing modelK ...") - model = model31K() + print("===> testing pointMLP ...") + model = pointMLP() out = model(data) print(out.shape) - print("===> testing modelL ...") - model = model31L() - out = model(data) - print(out.shape) - - print("===> testing modelM ...") - model = model31M() - out = model(data) - print(out.shape) - - print("===> testing modelN ...") - model = model31N() - out = model(data) - print(out.shape) diff --git a/classification_ScanObjectNN/models/__init__.py b/classification_ScanObjectNN/models/__init__.py index e24d217..b8815da 100644 --- a/classification_ScanObjectNN/models/__init__.py +++ b/classification_ScanObjectNN/models/__init__.py @@ -1,31 +1,3 @@ from __future__ import absolute_import -from .pointnet import PointNet -from .model21 import model21H -from .model1 import model1A, model1B, model1C, model1D, model1E, model1F -from .model2 import model2A1,model2A2, model2A3, model2A4, model2A5, model2A6, \ - model2A7, model2A8, model2A9, model2A10, model2A11, model2A12 -from .model3 import model3A1, model3A2, model3A3, model3A4, model3A5, model3A6, \ - model3A7, model3A8, model3A9, model3A10, model3A11, model3A12 -from .model4 import model4A1, model4A2, model4A3, model4A4, model4A5, model4A6, model4A7, model4A8 -from .model22 import model22H -from .model23 import model23H -from .model24 import model24H -from .model25 import model25A, model25B, model25C, model25D, model25E, model25F, model25G, model25H, model25I, \ - model25J, model25H1, model25H2, model25H3,model25H4, model25H5, model25H6, model25H7, model25H8 -from .model26 import model26H, model26G -from .model27 import model27A, model27B, model27C, model27D, model27E, model27F, model27G, model27H, model27I, model27J -from .model28 import model28A, model28B, model28C, model28D, model28E, model28F, model28G, model28H, model28I, model28J -from .model29 import model29A, model29B, model29C, model29D, model29E, model29F, model29G, model29H, model29I, model29J -from .model30 import model30A, model30B, model30C, model30D, model30E, model30F, model30G, model30H, model30I, model30J -from .model31 import model31A, model31B, model31C, model31D, model31E, model31F, model31G, \ - model31Ablation1111, model31Ablation1111NOnorm, model31Ablation3333, model31Ablation3333NOnorm, \ - model31AblationNopre, model31AblationNopos, model31Ablation2222NOnorm -from .model32 import model32A, model32B, model32C, model32D - -from .modelelite3 import modelelite3A1, modelelite3A2, modelelite3B1, modelelite3B2, modelelite3C1, modelelite3C2, \ - modelelite3D1, modelelite3D2, modelelite3E1, modelelite3E2, modelelite3F1, modelelite3F2, modelelite3G1, \ - modelelite3G2, modelelite3H1, modelelite3H2, modelelite3I1, modelelite3I2, modelelite3J1, modelelite3J2, \ - modelelite3K1, modelelite3K2, modelelite3L1, modelelite3L2, modelelite3M1, modelelite3M2, \ - modelelite3X1, modelelite3X2, modelelite3X3, modelelite3X4, modelelite3X5, modelelite3X6, modelelite3X7, \ - modelelite3X8, modelelite3X9, modelelite3X10, modelelite3X11, modelelite3X12, modelelite3X13 +from .pointmlp import pointMLP, pointMLPElite diff --git a/classification_ScanObjectNN/models/modelelite3.py b/classification_ScanObjectNN/models/modelelite3.py deleted file mode 100644 index e8a54b9..0000000 --- a/classification_ScanObjectNN/models/modelelite3.py +++ /dev/null @@ -1,639 +0,0 @@ -""" -Based on model31, different configures for elite version. -Based on model30, change the grouper operation by normalization. -Based on model28, only change configurations, mainly the reducer. -Based on model27, change to x-a, reorgnized structure -Based on model25, simple LocalGrouper (not x-a), reorgnized structure -Based on model24, using ReLU to replace GELU -Based on model22, remove attention -Bsed on model21, change FPS to random sampling. -Exactly based on Model10, but ReLU to GeLU -Based on Model8, add dropout and max, avg combine. -Based on Local model, add residual connections. -The extraction is doubled for depth. -Learning Point Cloud with Progressively Local representation. -[B,3,N] - {[B,G,K,d]-[B,G,d]} - {[B,G',K,d]-[B,G',d]} -cls -""" -import torch -import torch.nn as nn -import torch.nn.functional as F -# from torch import einsum -# from einops import rearrange, repeat -from einops.layers.torch import Rearrange - - -from pointnet2_ops import pointnet2_utils - - -def get_activation(activation): - if activation.lower() == 'gelu': - return nn.GELU() - elif activation.lower() == 'rrelu': - return nn.RReLU(inplace=True) - elif activation.lower() == 'selu': - return nn.SELU(inplace=True) - elif activation.lower() == 'silu': - return nn.SiLU(inplace=True) - elif activation.lower() == 'hardswish': - return nn.Hardswish(inplace=True) - elif activation.lower() == 'leakyrelu': - return nn.LeakyReLU(inplace=True) - else: - return nn.ReLU(inplace=True) - - -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) - distance = torch.min(distance, dist) - 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 knn_point(nsample, xyz, new_xyz): - """ - Input: - nsample: max sample number in local region - xyz: all points, [B, N, C] - new_xyz: query points, [B, S, C] - Return: - group_idx: grouped points index, [B, S, nsample] - """ - sqrdists = square_distance(new_xyz, xyz) - _, group_idx = torch.topk(sqrdists, nsample, dim=-1, largest=False, sorted=False) - return group_idx - - -class LocalGrouper(nn.Module): - def __init__(self, channel, groups, kneighbors, use_xyz=True, normalize="center", **kwargs): - """ - Give xyz[b,p,3] and fea[b,p,d], return new_xyz[b,g,3] and new_fea[b,g,k,d] - :param groups: groups number - :param kneighbors: k-nerighbors - :param kwargs: others - """ - super(LocalGrouper, self).__init__() - self.groups = groups - self.kneighbors = kneighbors - self.use_xyz = use_xyz - if normalize is not None: - self.normalize = normalize.lower() - else: - self.normalize = None - if self.normalize not in ["center", "anchor"]: - print(f"Unrecognized normalize parameter (self.normalize), set to None. Should be one of [center, anchor].") - self.normalize = None - if self.normalize is not None: - add_channel=3 if self.use_xyz else 0 - self.affine_alpha = nn.Parameter(torch.ones([1,1,1,channel + add_channel])) - self.affine_beta = nn.Parameter(torch.zeros([1, 1, 1, channel + add_channel])) - - def forward(self, xyz, points): - B, N, C = xyz.shape - S = self.groups - xyz = xyz.contiguous() # xyz [btach, points, xyz] - - # fps_idx = torch.multinomial(torch.linspace(0, N - 1, steps=N).repeat(B, 1).to(xyz.device), num_samples=self.groups, replacement=False).long() - # fps_idx = farthest_point_sample(xyz, self.groups).long() - fps_idx = pointnet2_utils.furthest_point_sample(xyz, self.groups).long() # [B, npoint] - new_xyz = index_points(xyz, fps_idx) # [B, npoint, 3] - new_points = index_points(points, fps_idx) # [B, npoint, d] - - idx = knn_point(self.kneighbors, xyz, new_xyz) - # idx = query_ball_point(radius, nsample, xyz, new_xyz) - grouped_xyz = index_points(xyz, idx) # [B, npoint, k, 3] - grouped_points = index_points(points, idx) # [B, npoint, k, d] - if self.use_xyz: - grouped_points = torch.cat([grouped_points, grouped_xyz],dim=-1) # [B, npoint, k, d+3] - if self.normalize is not None: - if self.normalize =="center": - std, mean = torch.std_mean(grouped_points, dim=2, keepdim=True) - if self.normalize =="anchor": - mean = torch.cat([new_points, new_xyz],dim=-1) if self.use_xyz else new_points - mean = mean.unsqueeze(dim=-2) # [B, npoint, 1, d+3] - std = torch.std(grouped_points-mean) - grouped_points = (grouped_points-mean)/(std + 1e-5) - grouped_points = self.affine_alpha*grouped_points + self.affine_beta - - new_points = torch.cat([grouped_points, new_points.view(B, S, 1, -1).repeat(1, 1, self.kneighbors, 1)], dim=-1) - return new_xyz, new_points - - -class ConvBNReLU1D(nn.Module): - def __init__(self, in_channels, out_channels, kernel_size=1, bias=True, activation='relu'): - super(ConvBNReLU1D, self).__init__() - self.act = get_activation(activation) - self.net = nn.Sequential( - nn.Conv1d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, bias=bias), - nn.BatchNorm1d(out_channels), - self.act - ) - - def forward(self, x): - return self.net(x) - - -class ConvBNReLURes1D(nn.Module): - def __init__(self, channel, kernel_size=1, groups=1, res_expansion=1.0, bias=True, activation='relu'): - super(ConvBNReLURes1D, self).__init__() - self.act = get_activation(activation) - self.net1 = nn.Sequential( - nn.Conv1d(in_channels=channel, out_channels=int(channel * res_expansion), - kernel_size=kernel_size, groups=groups, bias=bias), - nn.BatchNorm1d(int(channel * res_expansion)), - self.act - ) - self.net2 = nn.Sequential( - nn.Conv1d(in_channels=int(channel * res_expansion), out_channels=channel, - kernel_size=kernel_size, groups=groups, bias=bias), - nn.BatchNorm1d(channel) - ) - - def forward(self, x): - return self.act(self.net2(self.net1(x)) + x) - - -class PreExtraction(nn.Module): - def __init__(self, channels, out_channels, blocks=1, groups=1, res_expansion=1, bias=True, - activation='relu', use_xyz=True): - """ - input: [b,g,k,d]: output:[b,d,g] - :param channels: - :param blocks: - """ - super(PreExtraction, self).__init__() - in_channels = 3+2*channels if use_xyz else 2*channels - self.transfer = ConvBNReLU1D(in_channels, out_channels, bias=bias, activation=activation) - operation = [] - for _ in range(blocks): - operation.append( - ConvBNReLURes1D(out_channels, groups=groups, res_expansion=res_expansion, - bias=bias, activation=activation) - ) - self.operation = nn.Sequential(*operation) - - def forward(self, x): - b, n, s, d = x.size() # torch.Size([32, 512, 32, 6]) - x = x.permute(0, 1, 3, 2) - x = x.reshape(-1, d, s) - x = self.transfer(x) - batch_size, _, _ = x.size() - x = self.operation(x) # [b, d, k] - x = F.adaptive_max_pool1d(x, 1).view(batch_size, -1) - x = x.reshape(b, n, -1).permute(0, 2, 1) - return x - - -class PosExtraction(nn.Module): - def __init__(self, channels, blocks=1, groups=1, res_expansion=1, bias=True, activation='relu'): - """ - input[b,d,g]; output[b,d,g] - :param channels: - :param blocks: - """ - super(PosExtraction, self).__init__() - operation = [] - for _ in range(blocks): - operation.append( - ConvBNReLURes1D(channels, groups=groups, res_expansion=res_expansion, bias=bias, activation=activation) - ) - self.operation = nn.Sequential(*operation) - - def forward(self, x): # [b, d, g] - return self.operation(x) - - -class modelelite3(nn.Module): - def __init__(self, points=1024, class_num=40, embed_dim=64, groups=1, res_expansion=1.0, - activation="relu", bias=True, use_xyz=True, normalize="center", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs): - super(modelelite3, self).__init__() - self.stages = len(pre_blocks) - self.class_num = class_num - self.points = points - self.embedding = ConvBNReLU1D(3, embed_dim, bias=bias, activation=activation) - assert len(pre_blocks) == len(k_neighbors) == len(reducers) == len(pos_blocks) == len(dim_expansion), \ - "Please check stage number consistent for pre_blocks, pos_blocks k_neighbors, reducers." - self.local_grouper_list = nn.ModuleList() - self.pre_blocks_list = nn.ModuleList() - self.pos_blocks_list = nn.ModuleList() - last_channel = embed_dim - anchor_points = self.points - for i in range(len(pre_blocks)): - out_channel = last_channel * dim_expansion[i] - pre_block_num = pre_blocks[i] - pos_block_num = pos_blocks[i] - kneighbor = k_neighbors[i] - reduce = reducers[i] - anchor_points = anchor_points // reduce - # append local_grouper_list - local_grouper = LocalGrouper(last_channel, anchor_points, kneighbor, use_xyz, normalize) # [b,g,k,d] - self.local_grouper_list.append(local_grouper) - # append pre_block_list - pre_block_module = PreExtraction(last_channel, out_channel, pre_block_num, groups=groups, - res_expansion=res_expansion, - bias=bias, activation=activation, use_xyz=use_xyz) - self.pre_blocks_list.append(pre_block_module) - # append pos_block_list - pos_block_module = PosExtraction(out_channel, pos_block_num, groups=groups, - res_expansion=res_expansion, bias=bias, activation=activation) - self.pos_blocks_list.append(pos_block_module) - - last_channel = out_channel - - self.act = get_activation(activation) - self.classifier = nn.Sequential( - nn.Linear(last_channel, 512), - nn.BatchNorm1d(512), - self.act, - nn.Dropout(0.5), - nn.Linear(512, 256), - nn.BatchNorm1d(256), - self.act, - nn.Dropout(0.5), - nn.Linear(256, self.class_num) - ) - - def forward(self, x): - xyz = x.permute(0, 2, 1) - batch_size, _, _ = x.size() - x = self.embedding(x) # B,D,N - for i in range(self.stages): - # Give xyz[b, p, 3] and fea[b, p, d], return new_xyz[b, g, 3] and new_fea[b, g, k, d] - xyz, x = self.local_grouper_list[i](xyz, x.permute(0, 2, 1)) # [b,g,3] [b,g,k,d] - x = self.pre_blocks_list[i](x) # [b,d,g] - x = self.pos_blocks_list[i](x) # [b,d,g] - - x = F.adaptive_max_pool1d(x, 1).squeeze(dim=-1) - x = self.classifier(x) - return x - - - -def modelelite3A1(num_classes=40, **kwargs) -> modelelite3: # 3.48M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3B1(num_classes=40, **kwargs) -> modelelite3: # 2.78M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.0625, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3C1(num_classes=40, **kwargs) -> modelelite3: # 4.87M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3D1(num_classes=40, **kwargs) -> modelelite3: # 2.26M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=8, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3E1(num_classes=40, **kwargs) -> modelelite3: # 2.43M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3F1(num_classes=40, **kwargs) -> modelelite3: # 0.85M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3G1(num_classes=40, **kwargs) -> modelelite3: # 0.85M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3H1(num_classes=40, **kwargs) -> modelelite3: # 3.56M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=1, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3I1(num_classes=40, **kwargs) -> modelelite3: # 0.90M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 3, 3, 3], pos_blocks=[3, 3, 3, 3], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3J1(num_classes=40, **kwargs) -> modelelite3: # 0.93M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 4, 6, 3], pos_blocks=[3, 4, 6, 3], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3K1(num_classes=40, **kwargs) -> modelelite3: # 0.93M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=8, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 4, 6, 3], pos_blocks=[3, 4, 6, 3], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3L1(num_classes=40, **kwargs) -> modelelite3: # 0.95M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=8, res_expansion=0.25, - activation="relu", bias=True, use_xyz=True, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 4, 6, 3], pos_blocks=[3, 4, 6, 3], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3M1(num_classes=40, **kwargs) -> modelelite3: # 0.94M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2], pre_blocks=[4, 4, 4], pos_blocks=[4, 4, 4], - k_neighbors=[24, 24, 24], reducers=[2, 2, 2], **kwargs) - - - -########version 2: 64 neighbors with 0.5 drop ratio ########### -def modelelite3A2(num_classes=40, **kwargs) -> modelelite3: # 3.48M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3B2(num_classes=40, **kwargs) -> modelelite3: # 2.78M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.0625, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3C2(num_classes=40, **kwargs) -> modelelite3: # 4.87M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3D2(num_classes=40, **kwargs) -> modelelite3: # 2.26M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=8, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3E2(num_classes=40, **kwargs) -> modelelite3: # 2.43M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3F2(num_classes=40, **kwargs) -> modelelite3: # 0.85M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3G2(num_classes=40, **kwargs) -> modelelite3: # 0.85M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3H2(num_classes=40, **kwargs) -> modelelite3: # 3.56M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=1, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3I2(num_classes=40, **kwargs) -> modelelite3: # 0.90M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 3, 3, 3], pos_blocks=[3, 3, 3, 3], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3J2(num_classes=40, **kwargs) -> modelelite3: # 0.93M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 4, 6, 3], pos_blocks=[3, 4, 6, 3], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3K2(num_classes=40, **kwargs) -> modelelite3: # 0.93M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=8, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 4, 6, 3], pos_blocks=[3, 4, 6, 3], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3L2(num_classes=40, **kwargs) -> modelelite3: # 0.95M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=8, res_expansion=0.25, - activation="relu", bias=True, use_xyz=True, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 4, 6, 3], pos_blocks=[3, 4, 6, 3], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def modelelite3M2(num_classes=40, **kwargs) -> modelelite3: # 0.94M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=4, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2], pre_blocks=[4, 4, 4], pos_blocks=[4, 4, 4], - k_neighbors=[32, 32, 32], reducers=[2, 2, 2], **kwargs) - - - -def modelelite3X1(num_classes=40, **kwargs) -> modelelite3: # 1.11M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X2(num_classes=40, **kwargs) -> modelelite3: # 0.94M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=2, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X3(num_classes=40, **kwargs) -> modelelite3: # 0.94 - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 1], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X4(num_classes=40, **kwargs) -> modelelite3: # 2.77 - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 1], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X5(num_classes=40, **kwargs) -> modelelite3: # 1.59 - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 1], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 1], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X6(num_classes=40, **kwargs) -> modelelite3: # 1.44 - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=4, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 1], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 1], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X7(num_classes=40, **kwargs) -> modelelite3: # 1.11M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24,24,24,24], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X8(num_classes=40, **kwargs) -> modelelite3: # 0.95M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[1, 1, 2, 1], pos_blocks=[1, 1, 1, 1], - k_neighbors=[24,24,24,24], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X9(num_classes=40, **kwargs) -> modelelite3: # 1.59M - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 1], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 1], - k_neighbors=[24,24,24,24], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X10(num_classes=40, **kwargs) -> modelelite3: # 0.72M - return modelelite3(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 1], pre_blocks=[1, 1, 2, 1], pos_blocks=[1, 1, 2, 1], - k_neighbors=[24,24,24,24], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X11(num_classes=40, **kwargs) -> modelelite3: # 0.98M 79/13s - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[1, 2, 2, 2], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 0], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X12(num_classes=40, **kwargs) -> modelelite3: # 0.98M 78/13s - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.25, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[1, 2, 2, 2], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 0], - k_neighbors=[24,24,24,24], reducers=[2, 2, 2, 2], **kwargs) - -def modelelite3X13(num_classes=40, **kwargs) -> modelelite3: # 0.94M 90/15s - return modelelite3(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[1, 2, 2, 2], pre_blocks=[1, 2, 2, 2], pos_blocks=[1, 1, 0, 0], - k_neighbors=[24,24,24,24], reducers=[2, 2, 2, 2], **kwargs) - - - -if __name__ == '__main__': - # data = torch.rand(2, 128, 10) - # model = ConvBNReLURes1D(128, groups=2, activation='relu') - # out = model(data) - # print(out.shape) - # - # batch, groups, neighbors, dim = 2, 512, 32, 16 - # x = torch.rand(batch, groups, neighbors, dim) - # pre_extractor = PreExtraction(dim, 3) - # out = pre_extractor(x) - # print(out.shape) - # - # x = torch.rand(batch, dim, groups) - # pos_extractor = PosExtraction(dim, 3) - # out = pos_extractor(x) - # print(out.shape) - - data = torch.rand(2, 3, 1024) - - print("===> testing modelN ...") - model = modelelite3A1() - out = model(data) - print(out.shape) diff --git a/classification_ScanObjectNN/models/model31.py b/classification_ScanObjectNN/models/pointmlp.py similarity index 63% rename from classification_ScanObjectNN/models/model31.py rename to classification_ScanObjectNN/models/pointmlp.py index d6984b9..c6dce17 100644 --- a/classification_ScanObjectNN/models/model31.py +++ b/classification_ScanObjectNN/models/pointmlp.py @@ -1,18 +1,4 @@ -""" -Based on model30, change the grouper operation by normalization. -Based on model28, only change configurations, mainly the reducer. -Based on model27, change to x-a, reorgnized structure -Based on model25, simple LocalGrouper (not x-a), reorgnized structure -Based on model24, using ReLU to replace GELU -Based on model22, remove attention -Bsed on model21, change FPS to random sampling. -Exactly based on Model10, but ReLU to GeLU -Based on Model8, add dropout and max, avg combine. -Based on Local model, add residual connections. -The extraction is doubled for depth. -Learning Point Cloud with Progressively Local representation. -[B,3,N] - {[B,G,K,d]-[B,G,d]} - {[B,G',K,d]-[B,G',d]} -cls -""" + import torch import torch.nn as nn import torch.nn.functional as F @@ -291,12 +277,12 @@ class PosExtraction(nn.Module): return self.operation(x) -class model31(nn.Module): +class Model(nn.Module): def __init__(self, points=1024, class_num=40, embed_dim=64, groups=1, res_expansion=1.0, activation="relu", bias=True, use_xyz=True, normalize="center", dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs): - super(model31, self).__init__() + super(Model, self).__init__() self.stages = len(pre_blocks) self.class_num = class_num self.points = points @@ -359,172 +345,24 @@ class model31(nn.Module): -def model31A(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) -def model31B(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, - activation="relu", bias=False, use_xyz=False, normalize="center", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def model31C(num_classes=40, **kwargs) -> model31: # 85.219, 85.67, 85.115 , 85.566 - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, +def pointMLP(num_classes=40, **kwargs) -> Model: + return Model(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, activation="relu", bias=False, use_xyz=False, normalize="anchor", dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) -def model31D(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, + +def pointMLPElite(num_classes=40, **kwargs) -> Model: + return Model(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=0.25, activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[20, 20, 20, 20], reducers=[2, 2, 2, 2], **kwargs) - - -def model31E(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=32, groups=1, res_expansion=1.0, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def model31F(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=0.125, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -def model31G(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=16, res_expansion=2.0, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[32, 32, 32, 32], reducers=[2, 2, 2, 2], **kwargs) - - -""" -for ablation study -""" - -def model31Ablation1111(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 1], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - -def model31Ablation1111NOnorm(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, - activation="relu", bias=False, use_xyz=False, normalize=None, - dim_expansion=[2, 2, 2, 2], pre_blocks=[1, 1, 1, 1], pos_blocks=[1, 1, 1, 1], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - -def model31Ablation3333(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 3, 3, 3], pos_blocks=[3, 3, 3, 3], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - -def model31Ablation3333NOnorm(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, - activation="relu", bias=False, use_xyz=False, normalize=None, - dim_expansion=[2, 2, 2, 2], pre_blocks=[3, 3, 3, 3], pos_blocks=[3, 3, 3, 3], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - -def model31Ablation2222NOnorm(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, - activation="relu", bias=False, use_xyz=False, normalize=None, - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - - -def model31AblationNopre(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[0, 0, 0, 0], pos_blocks=[2, 2, 2, 2], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - -def model31AblationNopos(num_classes=40, **kwargs) -> model31: - return model31(points=1024, class_num=num_classes, embed_dim=64, groups=1, res_expansion=1.0, - activation="relu", bias=False, use_xyz=False, normalize="anchor", - dim_expansion=[2, 2, 2, 2], pre_blocks=[2, 2, 2, 2], pos_blocks=[0, 0, 0, 0], - k_neighbors=[24, 24, 24, 24], reducers=[2, 2, 2, 2], **kwargs) - + dim_expansion=[2, 2, 2, 1], pre_blocks=[1, 1, 2, 1], pos_blocks=[1, 1, 2, 1], + k_neighbors=[24,24,24,24], reducers=[2, 2, 2, 2], **kwargs) if __name__ == '__main__': - # data = torch.rand(2, 128, 10) - # model = ConvBNReLURes1D(128, groups=2, activation='relu') - # out = model(data) - # print(out.shape) - # - # batch, groups, neighbors, dim = 2, 512, 32, 16 - # x = torch.rand(batch, groups, neighbors, dim) - # pre_extractor = PreExtraction(dim, 3) - # out = pre_extractor(x) - # print(out.shape) - # - # x = torch.rand(batch, dim, groups) - # pos_extractor = PosExtraction(dim, 3) - # out = pos_extractor(x) - # print(out.shape) - data = torch.rand(2, 3, 1024) - print("===> testing model ...") - model = model31() - out = model(data) - print(out.shape) - - print("===> testing modelA ...") - model = model31A() - out = model(data) - print(out.shape) - - print("===> testing modelB ...") - model = model31B() - out = model(data) - print(out.shape) - - print("===> testing modelC ...") - model = model31C() - out = model(data) - print(out.shape) - - print("===> testing modelD ...") - model = model31D() - out = model(data) - print(out.shape) - - - print("===> testing model31Ablation1111 ...") - model = model31Ablation1111() - out = model(data) - print(out.shape) - - print("===> testing model31Ablation1111NOnorm ...") - model = model31Ablation1111NOnorm() - out = model(data) - print(out.shape) - - print("===> testing model31Ablation3333 ...") - model = model31Ablation3333() - out = model(data) - print(out.shape) - - print("===> testing model31Ablation3333NOnorm ...") - model = model31Ablation3333NOnorm() - out = model(data) - print(out.shape) - - print("===> testing model31AblationNopre ...") - model = model31AblationNopre() - out = model(data) - print(out.shape) - - print("===> testing model31AblationNopos ...") - model = model31AblationNopos() + print("===> testing pointMLP ...") + model = pointMLP() out = model(data) print(out.shape)