added type detection pipeline

main_pipeline.py

@@ -0,0 +1,94 @@
+from pathlib import Path
+
+import torch
+from torch_geometric.data import Data
+from tqdm import tqdm
+
+import polyscope as ps
+import numpy as np
+
+from torch.utils.data import DataLoader
+
+# Dataset and Dataloaders
+# =============================================================================
+
+# Transforms
+from ml_lib.point_toolset.point_io import BatchToData
+from ml_lib.utils.model_io import SavedLightningModels
+
+
+# Datasets
+from datasets.full_pointclouds import FullCloudsDataset
+from utils.pointcloud import read_pointcloud, normalize_pointcloud, cluster_cubes, append_onehotencoded_type, \
+    label2color, polytopes_to_planes
+from utils.project_config import GlobalVar, ThisConfig
+
+
+def prepare_dataloader(config_obj):
+    dataset = FullCloudsDataset(config_obj.data.root, split=GlobalVar.data_split.test,
+                                setting=GlobalVar.settings[config_obj.model.type])
+    # noinspection PyTypeChecker
+    return DataLoader(dataset, batch_size=config_obj.train.batch_size,
+                      num_workers=config_obj.data.worker, shuffle=False)
+
+
+def restore_logger_and_model(log_dir):
+    model = SavedLightningModels.load_checkpoint(models_root_path=log_dir, n=-1)
+    model = model.restore()
+    if torch.cuda.is_available():
+        model.cuda()
+    else:
+        model.cpu()
+    return model
+
+def predict_prim_type(input_pc, model):
+
+    input_data = (
+        torch.tensor(np.array([input_pc[:, 3:6]], np.float)),
+        torch.tensor(input_pc[:, 0:3]),
+        np.zeros(input_pc.shape[0])
+    )
+
+    batch_to_data = BatchToData()
+
+    data = batch_to_data(input_data[0], input_data[1], input_data[2])
+    y = loaded_model(data.to(device='cuda' if torch.cuda.is_available() else 'cpu'))
+    y_primary = torch.argmax(y.main_out, dim=-1).squeeze().cpu().numpy()
+
+    return np.concatenate((input_pc, y_primary.reshape(-1,1)), axis=1)
+
+if __name__ == '__main__':
+
+    input_pc_path = 'data/pc/pc.txt'
+
+    model_path = Path('trained_models/version_1')
+    config_filename = 'config.ini'
+    config = ThisConfig()
+    config.read_file((Path(model_path) / config_filename).open('r'))
+    loaded_model = restore_logger_and_model(model_path)
+    loaded_model.eval()
+
+    input_pc = read_pointcloud(input_pc_path, ' ', False)
+
+    input_pc = normalize_pointcloud(input_pc)
+
+    grid_clusters = cluster_cubes(input_pc, [1,1,1], 2048)
+
+    ps.init()
+
+    for i,grid_cluster_pc in enumerate(grid_clusters):
+
+        print("Cluster pointcloud size: {}".format(grid_cluster_pc.shape[0]))
+
+        pc_with_prim_type = predict_prim_type(grid_cluster_pc, loaded_model)
+
+        #pc_with_prim_type = polytopes_to_planes(pc_with_prim_type)
+
+        pc_with_prim_type = append_onehotencoded_type(pc_with_prim_type)
+
+        pc = ps.register_point_cloud("points_" + str(i), pc_with_prim_type[:, :3], radius=0.01)
+        pc.add_color_quantity("prim types", label2color(pc_with_prim_type[:, 6].astype(np.int64)), True)
+
+    ps.show()
+
+    print('Done')

requirements.txt

@@ -0,0 +1,91 @@
+absl-py==0.9.0
+attrs==19.3.0
+bravado==10.6.2
+bravado-core==5.17.0
+cachetools==4.1.0
+certifi==2020.4.5.2
+chardet==3.0.4
+click==7.1.2
+combo==0.1.0
+cycler==0.10.0
+decorator==4.4.2
+future==0.18.2
+gitdb==4.0.5
+GitPython==3.1.3
+google-auth==1.16.1
+google-auth-oauthlib==0.4.1
+googledrivedownloader==0.4
+grpcio==1.29.0
+h5py==2.10.0
+idna==2.9
+imageio==2.8.0
+importlib-metadata==1.6.1
+isodate==0.6.0
+joblib==0.15.1
+jsonpointer==2.0
+jsonref==0.2
+jsonschema==3.2.0
+kiwisolver==1.2.0
+llvmlite==0.32.1
+Markdown==3.2.2
+matplotlib==3.2.1
+monotonic==1.5
+msgpack==1.0.0
+msgpack-python==0.5.6
+natsort==7.0.1
+neptune-client==0.4.109
+networkx==2.4
+numba==0.49.1
+numpy==1.18.5
+oauthlib==3.1.0
+pandas==1.0.4
+Pillow==7.1.2
+plyfile==0.7.2
+polyscope==0.1.2
+protobuf==3.12.2
+py3nvml==0.2.6
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+PyJWT==1.7.1
+pyod==0.8.0
+pyparsing==2.4.7
+pyrsistent==0.16.0
+python-dateutil==2.8.1
+pytorch-lightning==0.7.6
+pytz==2020.1
+PyWavelets==1.1.1
+PyYAML==5.3.1
+rdflib==5.0.0
+requests==2.23.0
+requests-oauthlib==1.3.0
+rfc3987==1.3.8
+rsa==4.0
+scikit-image==0.17.2
+scikit-learn==0.23.1
+scipy==1.4.1
+simplejson==3.17.0
+six==1.15.0
+smmap==3.0.4
+strict-rfc3339==0.7
+suod==0.0.4
+swagger-spec-validator==2.7.0
+tensorboard==2.2.2
+tensorboard-plugin-wit==1.6.0.post3
+test-tube==0.7.5
+threadpoolctl==2.1.0
+tifffile==2020.6.3
+torch==1.4.0+cpu
+torch-cluster==1.5.4
+torch-geometric==1.4.3
+torch-scatter==2.0.4
+torch-sparse==0.6.1
+torchcontrib==0.0.2
+torchvision==0.5.0
+tqdm==4.45.0
+typing-extensions==3.7.4.2
+urllib3==1.25.9
+webcolors==1.11.1
+websocket-client==0.57.0
+Werkzeug==1.0.1
+xmltodict==0.12.0
+zipp==3.1.0

utils/pointcloud.py

@@ -0,0 +1,282 @@
+import numpy as np
+from sklearn.cluster import DBSCAN
+
+from pyod.models.knn import KNN
+from pyod.models.sod import SOD
+from pyod.models.abod import ABOD
+from pyod.models.sos import SOS
+from pyod.models.pca import PCA
+from pyod.models.ocsvm import OCSVM
+from pyod.models.mcd import MCD
+from pyod.models.lof import LOF
+from pyod.models.cof import COF
+from pyod.models.cblof import CBLOF
+from pyod.models.loci import LOCI
+from pyod.models.hbos import HBOS
+from pyod.models.lscp import LSCP
+from pyod.models.feature_bagging import FeatureBagging
+
+from utils.project_config import Classes
+
+
+def polytopes_to_planes(pc):
+    pc[(pc[:, 6] == float(Classes.Box)) | (pc[:, 6] == float(Classes.Polytope)), 6] = float(Classes.Plane);
+    return pc
+
+
+def mini_color_table(index, norm=True):
+    colors = [
+        [0.,0.,0.],
+        [0.5000, 0.5400, 0.5300], [0.8900, 0.1500, 0.2100], [0.6400, 0.5800, 0.5000],
+        [1.0000, 0.3800, 0.0100], [1.0000, 0.6600, 0.1400], [0.4980, 1.0000, 0.0000],
+        [0.4980, 1.0000, 0.8314], [0.9412, 0.9725, 1.0000], [0.5412, 0.1686, 0.8863],
+        [0.5765, 0.4392, 0.8588], [0.3600, 0.1400, 0.4300], [0.5600, 0.3700, 0.6000],
+    ]
+
+    color = colors[index % len(colors)]
+
+    if not norm:
+        color[0] *= 255
+        color[1] *= 255
+        color[2] *= 255
+
+    return color
+
+
+def cluster2Color(cluster, cluster_idx):
+    colors = np.zeros(shape=(len(cluster), 3))
+    point_idx = 0
+    for point in cluster:
+        colors[point_idx, :] = mini_color_table(cluster_idx)
+        point_idx += 1
+
+    return colors
+
+
+def label2color(labels):
+    '''
+    labels: np.ndarray with shape (n, )
+    colors(return): np.ndarray with shape (n, 3)
+    '''
+    num = labels.shape[0]
+    colors = np.zeros((num, 3))
+
+    minl, maxl = np.min(labels), np.max(labels)
+    for l in range(minl, maxl + 1):
+        colors[labels == l, :] = mini_color_table(l)
+
+    return colors
+
+
+def read_pointcloud(path, delimiter=' ', hasHeader=True):
+    with open(path, 'r') as f:
+        if hasHeader:
+            # Get rid of the Header
+            _ = f.readline()
+        # This iterates over all lines, splits them and converts values to floats. Will fail on wrong values.
+        pc = [[float(x) for x in line.rstrip().split(delimiter)] for line in f if line != '']
+
+    return np.asarray(pc)[:, :6]
+
+
+def write_pointcloud(file, pc, numCols=6):
+    np.savetxt(file, pc[:, :numCols], header=str(len(pc)) + ' ' + str(numCols), comments='')
+
+
+def farthest_point_sampling(pts, K):
+    if pts.shape[0] < K:
+        return pts
+
+    def calc_distances(p0, points):
+        return ((p0[:3] - points[:, :3]) ** 2).sum(axis=1)
+
+    farthest_pts = np.zeros((K, pts.shape[1]))
+    farthest_pts[0] = pts[np.random.randint(len(pts))]
+    distances = calc_distances(farthest_pts[0], pts)
+    for i in range(1, K):
+        farthest_pts[i] = pts[np.argmax(distances)]
+        distances = np.minimum(distances, calc_distances(farthest_pts[i], pts))
+
+    return farthest_pts
+
+
+def cluster_per_column(pc, column):
+    clusters = []
+    for i in range(0, int(np.max(pc[:, column]))):
+        cluster_pc = pc[pc[:, column] == i, :]
+        clusters.append(cluster_pc)
+
+    return clusters
+
+
+def cluster_cubes(data, cluster_dims, max_points_per_cluster=-1, min_points_per_cluster=-1):
+    if cluster_dims[0] is 1 and cluster_dims[1] is 1 and cluster_dims[2] is 1:
+        print("no need to cluster.")
+        return [farthest_point_sampling(data, max_points_per_cluster)]
+
+    max = data[:, :3].max(axis=0)
+    max += max * 0.01
+
+    min = data[:, :3].min(axis=0)
+    min -= min * 0.01
+
+    size = (max - min)
+
+    clusters = {}
+
+    cluster_size = size / np.array(cluster_dims, dtype=np.float32)
+
+    print('Min: ' + str(min) + ' Max: ' + str(max))
+    print('Cluster Size: ' + str(cluster_size))
+
+    for row in data:
+        # print('Row: ' + str(row))
+
+        cluster_pos = ((row[:3] - min) / cluster_size).astype(int)
+        cluster_idx = cluster_dims[0] * cluster_dims[2] * cluster_pos[1] + cluster_dims[0] * cluster_pos[2] + \
+                      cluster_pos[0]
+        clusters.setdefault(cluster_idx, []).append(row)
+
+        # Apply farthest point sampling to each cluster
+    final_clusters = []
+    for key, cluster in clusters.items():
+        c = np.vstack(cluster)
+        if c.shape[0] < min_points_per_cluster and -1 is not min_points_per_cluster:
+            continue
+
+        if max_points_per_cluster is not -1:
+            final_clusters.append(farthest_point_sampling(c, max_points_per_cluster))
+        else:
+            final_clusters.append(c)
+
+    return final_clusters
+
+
+def cluster_dbscan(data, selected_indices, eps, min_samples=5, metric='euclidean', algo='auto'):
+    # print('Clustering. Min Samples: ' + str(min_samples) + ' EPS: ' + str(eps) + "Selected Indices: " + str(selected_indices))
+
+    # 0,1,2 :   pos
+    # 3,4,5 :   normal
+    # 6:        type index
+    # 7,8,9,10: type index one hot encoded
+    # 11,12:    normal as angles
+
+    db_res = DBSCAN(eps=eps, metric=metric, n_jobs=-1, min_samples=min_samples, algorithm=algo).fit(
+        data[:, selected_indices])
+
+    labels = db_res.labels_
+    n_clusters = len(set(labels)) - (1 if -1 in labels else 0)
+    n_noise = list(labels).count(-1)
+    # print("Noise: " + str(n_noise) + " Clusters: " + str(n_clusters))
+
+    clusters = {}
+    for idx, l in enumerate(labels):
+        if l is -1:
+            continue
+        clusters.setdefault(str(l), []).append(data[idx, :])
+
+    npClusters = []
+    for cluster in clusters.values():
+        npClusters.append(np.array(cluster))
+
+    return npClusters
+
+
+def draw_clusters(clusters):
+    clouds = []
+
+    for cluster_idx, cluster in enumerate(clusters):
+        cloud = o3d.PointCloud()
+        cloud.points = o3d.Vector3dVector(cluster[:, :3])
+        cloud.colors = o3d.Vector3dVector(cluster2Color(cluster, cluster_idx))
+        clouds.append(cloud)
+
+    o3d.draw_geometries(clouds)
+
+
+def write_clusters(path, clusters, type_column=6):
+    file = open(path, "w")
+    file.write(str(len(clusters)) + "\n")
+
+    for cluster in clusters:
+        # print("Types: ", cluster[:, type_column])
+
+        types = np.unique(cluster[:, type_column], axis=0).astype(int)
+
+        def type_mapping(t):
+            if t == 0:
+                return 2
+            elif t == 1:
+                return 1
+            elif t == 3:
+                return 4
+            return t
+
+        types = np.array([type_mapping(t) for t in types])
+        print("Types: {}, Points: {}".format(types, cluster.shape[0]))
+        # draw_sample_data(cluster)
+
+        np.savetxt(file, types.reshape(1, types.shape[0]), delimiter=';', header='', comments='', fmt='%i')
+        np.savetxt(file, cluster[:, :6], header=str(len(cluster)) + ' ' + str(6), comments='')
+
+
+def draw_sample_data(sample_data, colored_normals=False):
+    cloud = o3d.PointCloud()
+    cloud.points = o3d.Vector3dVector(sample_data[:, :3])
+    cloud.colors = \
+        o3d.Vector3dVector(label2color(sample_data[:, 6].astype(int)) if not colored_normals else sample_data[:, 3:6])
+
+    o3d.draw_geometries([cloud])
+
+
+def normalize_pointcloud(pc, factor=1.0):
+    max = pc.max(axis=0)
+    min = pc.min(axis=0)
+
+    f = np.max([abs(max[0] - min[0]), abs(max[1] - min[1]), abs(max[2] - min[2])])
+
+    pc[:, 0:3] /= (f * factor)
+    pc[:, 3:6] /= (np.linalg.norm(pc[:, 3:6], ord=2, axis=1, keepdims=True))
+
+    return pc
+
+
+def hierarchical_clustering(data, selected_indices_0, selected_indices_1, eps, min_samples=5, metric='euclidean',
+                            algo='auto'):
+    total_clusters = []
+
+    clusters = cluster_dbscan(data, selected_indices_0, eps, min_samples, metric=metric, algo=algo)
+
+    for cluster in clusters:
+        # cluster = normalize_pointcloud(cluster)
+        sub_clusters = cluster_dbscan(cluster, selected_indices_1, eps, min_samples, metric=metric, algo=algo)
+        total_clusters.extend(sub_clusters)
+
+    return total_clusters
+
+
+def filter_clusters(clusters, filter):
+    filtered_clusters = []
+
+    for c in clusters:
+        if filter(c):
+            filtered_clusters.append(c)
+
+    return filtered_clusters
+
+
+def split_outliers(pc, columns):
+    clf = LOF()  # FeatureBagging() # detector_list=[LOF(), KNN()]
+    clf.fit(pc[:, columns])
+
+    # LOF, kNN
+
+    return pc[clf.labels_ == 0], pc[clf.labels_ == 1]
+
+
+def append_onehotencoded_type(data, factor=1.0):
+    types = data[:, 6].astype(int)
+    res = np.zeros((len(types), 8))
+    res[np.arange(len(types)), types] = factor
+
+    return np.column_stack((data, res))