steffen/Labeling-Primitives-With-Point2Net
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

small changes

Browse Source
This commit is contained in:
Markus Friedrich 2019-09-19 18:19:38 +02:00
parent 46334b8456
commit 76870a7bf8
2 changed files with 27 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
pointcloud.py
View File

@ -68,7 +68,7 @@ def read_pointcloud(path, delimiter=' ', hasHeader=True):
if hasHeader: if hasHeader:
# Get rid of the Header # Get rid of the Header
_ = f.readline() _ = f.readline()
# This itrates over all lines, splits them anc converts values to floats. Will fail on wrong values. # 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 != ''] pc = [[float(x) for x in line.rstrip().split(delimiter)] for line in f if line != '']
return np.asarray(pc) return np.asarray(pc)
@ -215,7 +215,8 @@ def write_clusters(path, clusters, type_column=6):
return t return t
types = np.array([type_mapping(t) for t in types]) types = np.array([type_mapping(t) for t in types])
print("Types: ", 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, types.reshape(1, types.shape[0]),delimiter=';', header='', comments='', fmt='%i')
np.savetxt(file, cluster[:, :6], header=str(len(cluster)) + ' ' + str(6), comments='') np.savetxt(file, cluster[:, :6], header=str(len(cluster)) + ' ' + str(6), comments='')

33
predict/predict.py
View File

@ -63,7 +63,7 @@ sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/../') # add proj
parser = argparse.ArgumentParser() parser = argparse.ArgumentParser()
parser.add_argument('--npoints', type=int, default=2048, help='resample points number') parser.add_argument('--npoints', type=int, default=2048, help='resample points number')
parser.add_argument('--model', type=str, default='./checkpoint/seg_model_custom_131.pth', help='model path') parser.add_argument('--model', type=str, default='./checkpoint/seg_model_custom_0.pth', help='model path')
parser.add_argument('--sample_idx', type=int, default=0, help='select a sample to segment and view result') parser.add_argument('--sample_idx', type=int, default=0, help='select a sample to segment and view result')
parser.add_argument('--headers', type=strtobool, default=True, help='if raw files come with headers') parser.add_argument('--headers', type=strtobool, default=True, help='if raw files come with headers')
parser.add_argument('--with_normals', type=strtobool, default=True, help='if training will include normals') parser.add_argument('--with_normals', type=strtobool, default=True, help='if training will include normals')
@ -84,7 +84,19 @@ if __name__ == '__main__':
print('Create data set ..') print('Create data set ..')
dataset_folder = './data/raw/predict/' dataset_folder = './data/raw/predict/'
pointcloud_file = './pointclouds/m3.xyz'
# pointcloud_file = './pointclouds/0_0.xyz'
# pointcloud_file = 'C:/Projekte/csg-fitter/csg-fitter/models/0/0.xyz'
param_set = {"test1": {"cells": 2, "eps": 0.15, "min_samples": 100}}
file = "test1"
used_params = param_set[file]
pointcloud_file = 'C:/Projekte/visigrapp2020/data/' + file + '/pc.txt'
# Load and pre-process point cloud # Load and pre-process point cloud
pcloud = pc.read_pointcloud(pointcloud_file) pcloud = pc.read_pointcloud(pointcloud_file)
@ -93,7 +105,8 @@ if __name__ == '__main__':
#pc_clusters = pc.hierarchical_clustering(pcloud, selected_indices_0=[0, 1, 2, 3, 4, 5], #pc_clusters = pc.hierarchical_clustering(pcloud, selected_indices_0=[0, 1, 2, 3, 4, 5],
# selected_indices_1=[0, 1, 2, 3, 4, 5], eps=0.7, min_samples=5) # selected_indices_1=[0, 1, 2, 3, 4, 5], eps=0.7, min_samples=5)
pc_clusters = pc.cluster_cubes(pcloud, [4, 4, 4]) n_cells = used_params["cells"]
pc_clusters = pc.cluster_cubes(pcloud, [n_cells, n_cells, n_cells])
print("Pre-Processing: Clustering") print("Pre-Processing: Clustering")
pc.draw_clusters(pc_clusters) pc.draw_clusters(pc_clusters)
@ -196,12 +209,12 @@ if __name__ == '__main__':
# Clustering that results in per-primitive type clusters # Clustering that results in per-primitive type clusters
# ------------------------------------------------------------------------------------------------------------------ # ------------------------------------------------------------------------------------------------------------------
# labeled_dataset = np.loadtxt('labeled_dataset.txt') #labeled_dataset = np.loadtxt('labeled_dataset.txt')
pc.draw_sample_data(labeled_dataset) pc.draw_sample_data(labeled_dataset)
# Try to get rid of outliers. # Try to get rid of outliers.
labeled_dataset,outliers = pc.split_outliers(labeled_dataset, columns=[0,1,2,3,4,5]) # labeled_dataset,outliers = pc.split_outliers(labeled_dataset, columns=[0,1,2,3,4,5])
pc.draw_sample_data(outliers, False) # pc.draw_sample_data(outliers, False)
print("Final clustering..") print("Final clustering..")
@ -211,9 +224,9 @@ if __name__ == '__main__':
total_clusters = [] total_clusters = []
clusters = pc.cluster_dbscan(labeled_dataset, [0,1,2,3,4,5], eps=0.1, min_samples=100) clusters = pc.cluster_dbscan(labeled_dataset, [0,1,2,3,4,5], eps=used_params["eps"], min_samples=used_params["min_samples"])
print("Pre-clustering done. Clusters: ", len(clusters)) print("Pre-clustering done. Clusters: ", len(clusters))
pc.draw_clusters(clusters) #pc.draw_clusters(clusters)
for cluster in clusters: for cluster in clusters:
#cluster = pc.normalize_pointcloud(cluster) #cluster = pc.normalize_pointcloud(cluster)
@ -225,11 +238,11 @@ if __name__ == '__main__':
print("No need for 2nd level clustering since there is only a single primitive type in the cluster.") print("No need for 2nd level clustering since there is only a single primitive type in the cluster.")
total_clusters.append(cluster) total_clusters.append(cluster)
else: else:
sub_clusters = pc.cluster_dbscan(cluster, [0,1,2,7,8,9,10], eps=0.1, min_samples=100) sub_clusters = pc.cluster_dbscan(cluster, [0,1,2,7,8,9,10], eps=used_params["eps"], min_samples=used_params["min_samples"])
print("Sub clusters: ", len(sub_clusters)) print("Sub clusters: ", len(sub_clusters))
total_clusters.extend(sub_clusters) total_clusters.extend(sub_clusters)
result_clusters = list(filter(lambda c: c.shape[0] > 100, total_clusters)) result_clusters = list(filter(lambda c: c.shape[0] > used_params["min_samples"], total_clusters))
for cluster in result_clusters: for cluster in result_clusters:
print("Cluster: ", cluster.shape[0]) print("Cluster: ", cluster.shape[0])