update

.gitattributes

@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.t7 filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,4 @@
+*.DS_store
+*.pyc
+flagged
+*.png

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8 (pointcloud-c)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/pointcloud-c.iml" filepath="$PROJECT_DIR$/.idea/pointcloud-c.iml" />
+    </modules>
+  </component>
+</project>

.idea/pointcloud-c.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.8 (pointcloud-c)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

DGCNN.py

@@ -0,0 +1,121 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+@Author: Yue Wang
+@Contact: yuewangx@mit.edu
+@File: model.py
+@Time: 2018/10/13 6:35 PM
+"""
+
+import os
+import sys
+import copy
+import math
+import numpy as np
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+def knn(x, k):
+    inner = -2 * torch.matmul(x.transpose(2, 1), x)
+    xx = torch.sum(x ** 2, dim=1, keepdim=True)
+    pairwise_distance = -xx - inner - xx.transpose(2, 1)
+
+    idx = pairwise_distance.topk(k=k, dim=-1)[1]  # (batch_size, num_points, k)
+    return idx
+
+
+def get_graph_feature(x, k=20, idx=None):
+    batch_size = x.size(0)
+    num_points = x.size(2)
+    x = x.view(batch_size, -1, num_points)
+    if idx is None:
+        idx = knn(x, k=k)  # (batch_size, num_points, k)
+    device = torch.device('cpu')
+
+    idx_base = torch.arange(0, batch_size, device=device).view(-1, 1, 1) * num_points
+
+    idx = idx + idx_base
+
+    idx = idx.view(-1)
+
+    _, num_dims, _ = x.size()
+
+    x = x.transpose(2,
+                    1).contiguous()  # (batch_size, num_points, num_dims)  -> (batch_size*num_points, num_dims) #   batch_size * num_points * k + range(0, batch_size*num_points)
+    feature = x.view(batch_size * num_points, -1)[idx, :]
+    feature = feature.view(batch_size, num_points, k, num_dims)
+    x = x.view(batch_size, num_points, 1, num_dims).repeat(1, 1, k, 1)
+
+    feature = torch.cat((feature - x, x), dim=3).permute(0, 3, 1, 2).contiguous()
+
+    return feature
+
+class DGCNN(nn.Module):
+    def __init__(self, output_channels=40):
+        super(DGCNN, self).__init__()
+        self.k = 20
+        emb_dims = 1024
+        dropout = 0.5
+
+        self.bn1 = nn.BatchNorm2d(64)
+        self.bn2 = nn.BatchNorm2d(64)
+        self.bn3 = nn.BatchNorm2d(128)
+        self.bn4 = nn.BatchNorm2d(256)
+        self.bn5 = nn.BatchNorm1d(emb_dims)
+
+        self.conv1 = nn.Sequential(nn.Conv2d(6, 64, kernel_size=1, bias=False),
+                                   self.bn1,
+                                   nn.LeakyReLU(negative_slope=0.2))
+        self.conv2 = nn.Sequential(nn.Conv2d(64 * 2, 64, kernel_size=1, bias=False),
+                                   self.bn2,
+                                   nn.LeakyReLU(negative_slope=0.2))
+        self.conv3 = nn.Sequential(nn.Conv2d(64 * 2, 128, kernel_size=1, bias=False),
+                                   self.bn3,
+                                   nn.LeakyReLU(negative_slope=0.2))
+        self.conv4 = nn.Sequential(nn.Conv2d(128 * 2, 256, kernel_size=1, bias=False),
+                                   self.bn4,
+                                   nn.LeakyReLU(negative_slope=0.2))
+        self.conv5 = nn.Sequential(nn.Conv1d(512, emb_dims, kernel_size=1, bias=False),
+                                   self.bn5,
+                                   nn.LeakyReLU(negative_slope=0.2))
+        self.linear1 = nn.Linear(emb_dims * 2, 512, bias=False)
+        self.bn6 = nn.BatchNorm1d(512)
+        self.dp1 = nn.Dropout(p=dropout)
+        self.linear2 = nn.Linear(512, 256)
+        self.bn7 = nn.BatchNorm1d(256)
+        self.dp2 = nn.Dropout(p=dropout)
+        self.linear3 = nn.Linear(256, output_channels)
+
+    def forward(self, x):
+        batch_size = x.size(0)
+        x = get_graph_feature(x, k=self.k)
+        x = self.conv1(x)
+        x1 = x.max(dim=-1, keepdim=False)[0]
+
+        x = get_graph_feature(x1, k=self.k)
+        x = self.conv2(x)
+        x2 = x.max(dim=-1, keepdim=False)[0]
+
+        x = get_graph_feature(x2, k=self.k)
+        x = self.conv3(x)
+        x3 = x.max(dim=-1, keepdim=False)[0]
+
+        x = get_graph_feature(x3, k=self.k)
+        x = self.conv4(x)
+        x4 = x.max(dim=-1, keepdim=False)[0]
+
+        x = torch.cat((x1, x2, x3, x4), dim=1)
+
+        x = self.conv5(x)
+        x1 = F.adaptive_max_pool1d(x, 1).view(batch_size, -1)
+        x2 = F.adaptive_avg_pool1d(x, 1).view(batch_size, -1)
+        x = torch.cat((x1, x2), 1)
+
+        x = F.leaky_relu(self.bn6(self.linear1(x)), negative_slope=0.2)
+        x = self.dp1(x)
+        x = F.leaky_relu(self.bn7(self.linear2(x)), negative_slope=0.2)
+        x = self.dp2(x)
+        x = self.linear3(x)
+        return x

GDANet_WOLFMix.t7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef1f05156c6ace4f72e9e70ac373dd7f5d8ece8fe2af15a1099c56b8e13431dd
+size 3796397

GDANet_cls.py

@@ -0,0 +1,113 @@
+import torch.nn as nn
+import torch
+import torch.nn.functional as F
+from util.GDANet_util import local_operator, GDM, SGCAM
+
+
+class GDANET(nn.Module):
+    def __init__(self):
+        super(GDANET, self).__init__()
+
+        self.bn1 = nn.BatchNorm2d(64, momentum=0.1)
+        self.bn11 = nn.BatchNorm2d(64, momentum=0.1)
+        self.bn12 = nn.BatchNorm1d(64, momentum=0.1)
+
+        self.bn2 = nn.BatchNorm2d(64, momentum=0.1)
+        self.bn21 = nn.BatchNorm2d(64, momentum=0.1)
+        self.bn22 = nn.BatchNorm1d(64, momentum=0.1)
+
+        self.bn3 = nn.BatchNorm2d(128, momentum=0.1)
+        self.bn31 = nn.BatchNorm2d(128, momentum=0.1)
+        self.bn32 = nn.BatchNorm1d(128, momentum=0.1)
+
+        self.bn4 = nn.BatchNorm1d(512, momentum=0.1)
+
+        self.conv1 = nn.Sequential(nn.Conv2d(6, 64, kernel_size=1, bias=True),
+                                   self.bn1)
+        self.conv11 = nn.Sequential(nn.Conv2d(64, 64, kernel_size=1, bias=True),
+                                    self.bn11)
+        self.conv12 = nn.Sequential(nn.Conv1d(64 * 2, 64, kernel_size=1, bias=True),
+                                    self.bn12)
+
+        self.conv2 = nn.Sequential(nn.Conv2d(67 * 2, 64, kernel_size=1, bias=True),
+                                   self.bn2)
+        self.conv21 = nn.Sequential(nn.Conv2d(64, 64, kernel_size=1, bias=True),
+                                    self.bn21)
+        self.conv22 = nn.Sequential(nn.Conv1d(64 * 2, 64, kernel_size=1, bias=True),
+                                    self.bn22)
+
+        self.conv3 = nn.Sequential(nn.Conv2d(131 * 2, 128, kernel_size=1, bias=True),
+                                   self.bn3)
+        self.conv31 = nn.Sequential(nn.Conv2d(128, 128, kernel_size=1, bias=True),
+                                    self.bn31)
+        self.conv32 = nn.Sequential(nn.Conv1d(128, 128, kernel_size=1, bias=True),
+                                    self.bn32)
+
+        self.conv4 = nn.Sequential(nn.Conv1d(256, 512, kernel_size=1, bias=True),
+                                   self.bn4)
+
+        self.SGCAM_1s = SGCAM(64)
+        self.SGCAM_1g = SGCAM(64)
+        self.SGCAM_2s = SGCAM(64)
+        self.SGCAM_2g = SGCAM(64)
+
+        self.linear1 = nn.Linear(1024, 512, bias=True)
+        self.bn6 = nn.BatchNorm1d(512)
+        self.dp1 = nn.Dropout(p=0.4)
+        self.linear2 = nn.Linear(512, 256, bias=True)
+        self.bn7 = nn.BatchNorm1d(256)
+        self.dp2 = nn.Dropout(p=0.4)
+        self.linear3 = nn.Linear(256, 40, bias=True)
+
+    def forward(self, x):
+        B, C, N = x.size()
+        ###############
+        """block 1"""
+        # Local operator:
+        x1 = local_operator(x, k=30)
+        x1 = F.relu(self.conv1(x1))
+        x1 = F.relu(self.conv11(x1))
+        x1 = x1.max(dim=-1, keepdim=False)[0]
+
+        # Geometry-Disentangle Module:
+        x1s, x1g = GDM(x1, M=256)
+
+        # Sharp-Gentle Complementary Attention Module:
+        y1s = self.SGCAM_1s(x1, x1s.transpose(2, 1))
+        y1g = self.SGCAM_1g(x1, x1g.transpose(2, 1))
+        z1 = torch.cat([y1s, y1g], 1)
+        z1 = F.relu(self.conv12(z1))
+        ###############
+        """block 2"""
+        x1t = torch.cat((x, z1), dim=1)
+        x2 = local_operator(x1t, k=30)
+        x2 = F.relu(self.conv2(x2))
+        x2 = F.relu(self.conv21(x2))
+        x2 = x2.max(dim=-1, keepdim=False)[0]
+
+        x2s, x2g = GDM(x2, M=256)
+
+        y2s = self.SGCAM_2s(x2, x2s.transpose(2, 1))
+        y2g = self.SGCAM_2g(x2, x2g.transpose(2, 1))
+        z2 = torch.cat([y2s, y2g], 1)
+        z2 = F.relu(self.conv22(z2))
+        ###############
+        x2t = torch.cat((x1t, z2), dim=1)
+        x3 = local_operator(x2t, k=30)
+        x3 = F.relu(self.conv3(x3))
+        x3 = F.relu(self.conv31(x3))
+        x3 = x3.max(dim=-1, keepdim=False)[0]
+        z3 = F.relu(self.conv32(x3))
+        ###############
+        x = torch.cat((z1, z2, z3), dim=1)
+        x = F.relu(self.conv4(x))
+        x11 = F.adaptive_max_pool1d(x, 1).view(B, -1)
+        x22 = F.adaptive_avg_pool1d(x, 1).view(B, -1)
+        x = torch.cat((x11, x22), 1)
+
+        x = F.relu(self.bn6(self.linear1(x)))
+        x = self.dp1(x)
+        x = F.relu(self.bn7(self.linear2(x)))
+        x = self.dp2(x)
+        x = self.linear3(x)
+        return x

app.py

@@ -0,0 +1,119 @@
+import gradio as gr
+import mathutils
+import math
+import numpy as np
+import matplotlib.pyplot as plt
+import matplotlib
+import matplotlib.cm as cmx
+import os.path as osp
+import h5py
+import random
+import torch
+import torch.nn as nn
+
+from GDANet_cls import GDANET
+from DGCNN import DGCNN
+
+with open('shape_names.txt') as f:
+    CLASS_NAME = f.read().splitlines()
+
+model_gda = GDANET()
+model_gda = nn.DataParallel(model_gda)
+model_gda.load_state_dict(torch.load('./GDANet_WOLFMix.t7', map_location=torch.device('cpu')))
+model_gda.eval()
+
+model_dgcnn = DGCNN()
+model_dgcnn = nn.DataParallel(model_dgcnn)
+model_dgcnn.load_state_dict(torch.load('./dgcnn.t7', map_location=torch.device('cpu')))
+model_dgcnn.eval()
+
+def pyplot_draw_point_cloud(points, corruption):
+    rot1 = mathutils.Euler([-math.pi / 2, 0, 0]).to_matrix().to_3x3()
+    rot2 = mathutils.Euler([0, 0, math.pi]).to_matrix().to_3x3()
+    points = np.dot(points, rot1)
+    points = np.dot(points, rot2)
+    x, y, z = points[:, 0], points[:, 1], points[:, 2]
+    colorsMap = 'winter'
+    cs = y
+    cm = plt.get_cmap(colorsMap)
+    cNorm = matplotlib.colors.Normalize(vmin=-1, vmax=1)
+    scalarMap = cmx.ScalarMappable(norm=cNorm, cmap=cm)
+    fig = plt.figure(figsize=(5, 5))
+    ax = fig.add_subplot(111, projection='3d')
+    ax.scatter(x, y, z, c=scalarMap.to_rgba(cs))
+    scalarMap.set_array(cs)
+    ax.set_xlim(-1, 1)
+    ax.set_ylim(-1, 1)
+    ax.set_zlim(-1, 1)
+    plt.axis('off')
+    plt.title(corruption, fontsize=30)
+    plt.tight_layout()
+    plt.savefig('visualization.png', bbox_inches='tight', dpi=200)
+    plt.close()
+
+
+
+def load_dataset(corruption_idx, severity):
+    corruptions = [
+        'clean',
+        'scale',
+        'jitter',
+        'rotate',
+        'dropout_global',
+        'dropout_local',
+        'add_global',
+        'add_local',
+    ]
+    corruption_type = corruptions[corruption_idx]
+    if corruption_type == 'clean':
+        f = h5py.File(osp.join('modelnet_c', corruption_type + '.h5'))
+    else:
+        f = h5py.File(osp.join('modelnet_c', corruption_type + '_{}'.format(severity-1) + '.h5'))
+    data = f['data'][:].astype('float32')
+    label = f['label'][:].astype('int64')
+    f.close()
+    return data, label
+
+def recognize_pcd(model, pcd):
+    pcd = torch.tensor(pcd).unsqueeze(0)
+    pcd = pcd.permute(0, 2, 1)
+    output = model(pcd)
+    prediction = output.softmax(-1).flatten()
+    _, top5_idx = torch.topk(prediction, 5)
+    return {CLASS_NAME[i]: float(prediction[i]) for i in top5_idx.tolist()}
+
+def run(seed, corruption_idx, severity):
+    data, label = load_dataset(corruption_idx, severity)
+    sample_indx = int(seed)
+    pcd, cls = data[sample_indx], label[sample_indx]
+    pyplot_draw_point_cloud(pcd, CLASS_NAME[cls[0]])
+    output = 'visualization.png'
+    return output, recognize_pcd(model_dgcnn, pcd), recognize_pcd(model_gda, pcd)
+
+if __name__ == '__main__':
+    iface = gr.Interface(
+        fn=run,
+        inputs=[
+            gr.components.Number(label='Sample Seed', precision=0),
+            gr.components.Radio(
+                ['Clean', 'Scale', 'Jitter', 'Rotate', 'Drop Global', 'Drop Local', 'Add Global', 'Add Local'],
+                value='Clean', type="index", label='Corruption Type'),
+            gr.components.Slider(1, 5, step=1, label='Corruption severity'),
+        ],
+        outputs=[
+            gr.components.Image(type="file", label="Visualization"),
+            gr.components.Label(num_top_classes=5, label="Baseline (DGCNN) Prediction"),
+            gr.components.Label(num_top_classes=5, label="Ours (GDANet+WolfMix) Prediction")
+        ],
+        live=False,
+        allow_flagging='never',
+        title="Benchmarking and Analyzing Point Cloud Classification under Corruptions [ICML 2022]",
+        description="Welcome to the demo of ModelNet-C! You can visualize various types of corrupted point clouds in ModelNet-C and see how our proposed techniques contribute to robust predicitions compared to baseline methods.",
+        examples=[
+            [0, 'Jitter', 5],
+            [999, 'Drop Local', 5],
+        ],
+        # css=".output-image, .image-preview {height: 500px !important}",
+        article="<p style='text-align: center'><a href='https://github.com/jiawei-ren/ModelNet-C' target='_blank'>ModelNet-C @ GitHub</a></p> "
+    )
+    iface.launch()

dgcnn.t7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f366f60ca9dacf42cff5b747ba86020f10a6480ab31bb8122a8a609152ce4baa
+size 7268024

downsample.py

@@ -0,0 +1,12 @@
+import glob
+import h5py
+
+for fpath in glob.glob('modelnet_c/*.h5'):
+    f = h5py.File(fpath)
+    data = f['data'][:].astype('float32')
+    label = f['label'][:].astype('int64')
+    f.close()
+    f = h5py.File(fpath, 'w')
+    f.create_dataset('data', data=data[:100])
+    f.create_dataset('label', data=label[:100])
+    f.close()

modelnet_c/add_global_0.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0588ab009c0d0b4f4f8598e2fd7a6df0df14937b30a42ecdfc6c2811e70d494e
+size 61267680

modelnet_c/add_global_1.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e18f34cf1e30b58758edfbe20f4e0db0a53e067bc87520e20ee8eb9fc85035d
+size 61860000

modelnet_c/add_global_2.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c01495ed18ede2c5d9bab1cfc29555b9153e862c827909295504f76909addef
+size 62452320

modelnet_c/add_global_3.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d5e4594ca8aeb84e10397e0189b45a594f47009a4669d4efe070ffe72d4c4c
+size 63044640

modelnet_c/add_global_4.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:989951ee7a7056f70c03f671a61a7ac55ca3d2b78eeccfeb855fcc033b276797
+size 63636960

modelnet_c/add_local_0.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd0e3adfcc8c98136b33f0a712033340e594cfcd7dafa3f76e6a8f517a59a429
+size 33310176

modelnet_c/add_local_1.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43986bd483fdcc5f4a8779c31f3b45d45401b82d18443161872d0862106a0fa6
+size 36271776

modelnet_c/add_local_2.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69968a6f58f25687058eaaca1a67a6890396cac812529e9529b978054e94c36
+size 39233376

modelnet_c/add_local_3.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:029c794a19cffe80797950d2aac661fe2cc35b978d486e3684024a0bcf42c10c
+size 42194976

modelnet_c/add_local_4.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8597a0a95f358cacb9f5ad8c1d76b74179988b4037b277dff7c58cd95c8146
+size 45156576

modelnet_c/clean.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:203ec0037ebdee84f13df5abe12e3cf0e1047192832ff6149ac54b4deaf37931
+size 30348576

modelnet_c/dropout_global_0.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b7527cc2512fd83e074b3f814cb88253781b2331d9f3c79c54acc3a0f6e64e
+size 22766880

modelnet_c/dropout_global_1.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c769d0f5f3bd7f9a4bf261d23b567fe75861b54c83671f5c46fe7ea288c79c
+size 18976032

modelnet_c/dropout_global_2.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6fe9780aee5fb4995e81313a3341df7b6c23d710e2bb0cd1bc46c9cb6e6815
+size 15185184

modelnet_c/dropout_global_3.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d9c46fe1d02d779895135d42861c34988355893c4d81ba54586ebb7571b4cd
+size 11394336

modelnet_c/dropout_global_4.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0342a91f9e16e29751e90296171c593e1eb35da0ffe3579a6664bb18c2f28d9b
+size 7603488

modelnet_c/dropout_local_0.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8751d701b16e7f37065a1322c4008bff807db5b2f2ab5ce9254fa941a519742
+size 27386976

modelnet_c/dropout_local_1.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2441fae91bc29fba8953799e11f604ec5beeb20913380ca225e1b9a8fe3b500
+size 24425376

modelnet_c/dropout_local_2.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa9a2ba4146bc522d7731a495134babd19d8b212105530abbcd40256c7eaaed
+size 21463776

modelnet_c/dropout_local_3.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc6742314f168e7a53209e81ce4298485fb665578953e9f231eb80fc7dd9940
+size 18502176

modelnet_c/dropout_local_4.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc12bb058cb674274a0e01e79b3810cf693e85aaa0d8a21832a3f3108d8c69f
+size 15540576

modelnet_c/jitter_0.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36b0e5c417d801b2b12d9a97cb4a998eb3d639d3a9bc7a714ee70dbda25d2284
+size 60675360

modelnet_c/jitter_1.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b770e594a0c72fbd4b7394e02d2a6bf0490c44acb7474fc2e3837de0827c5d
+size 60675360

modelnet_c/jitter_2.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d95bbc72d191f632a368873552bcaa15068082f424f184485b997d4e1ba6f05
+size 60675360

modelnet_c/jitter_3.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed401170657a4326638787c71004960db5cc5bb03de56df64ef335d73c975032
+size 60675360

modelnet_c/jitter_4.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4547327b47fa368814145f8397bf87061a86281afbf253f85c0a6d1abbd8251b
+size 60675360

modelnet_c/rotate_0.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95246d8c9506578039c4ab8f0cb1b8794d3d32c533e906aea724a04de8c3a1c7
+size 60675360

modelnet_c/rotate_1.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70147de9808e5ed0cdcb0184a1ade44241497c3d69d74576e5dc1b333cfc87aa
+size 60675360

modelnet_c/rotate_2.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ae9db2079eb728eb2f8cdc7dfdcb7ff5456575a986c7e10777cbcd29fb4fbb
+size 60675360

modelnet_c/rotate_3.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c13ab0be340e82c63ef325619759c71aae63a622a1846c95f0697152c3e7b1c
+size 60675360

modelnet_c/rotate_4.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d70d56407cb9a02308a34806bb908a1bba8db2779881a7a1a49ba7005119fb
+size 60675360

modelnet_c/scale_0.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4bb6638a9330960261aadda500d34060ad00143322cc2a40f3b5dea55ad7a40
+size 30348576