learning3d 0.1.0__py3-none-any.whl → 0.2.1__py3-none-any.whl

{learning3d/data_utils → data_utils}/dataloaders.py

@@ -16,8 +16,9 @@ from scipy.spatial.distance import minkowski
 from scipy.spatial import cKDTree
 from torch.utils.data import Dataset
 
-def download_modelnet40(root_dir):
-	DATA_DIR = os.path.join(root_dir, 'data')
+def download_modelnet40():
+	BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+	DATA_DIR = os.path.join(BASE_DIR, os.pardir, 'data')
 	if not os.path.exists(DATA_DIR):
 		os.mkdir(DATA_DIR)
 	if not os.path.exists(os.path.join(DATA_DIR, 'modelnet40_ply_hdf5_2048')):
@@ -27,10 +28,11 @@ def download_modelnet40(root_dir):
 		os.system('mv %s %s' % (zipfile[:-4], DATA_DIR))
 		os.system('rm %s' % (zipfile))
 
-def load_data(root_dir, train, use_normals):
+def load_data(train, use_normals):
 	if train: partition = 'train'
 	else: partition = 'test'
-	DATA_DIR = os.path.join(root_dir, 'data')
+	BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+	DATA_DIR = os.path.join(BASE_DIR, os.pardir, 'data')
 	all_data = []
 	all_label = []
 	for h5_name in glob.glob(os.path.join(DATA_DIR, 'modelnet40_ply_hdf5_2048', 'ply_data_%s*.h5' % partition)):
@@ -184,15 +186,13 @@ class ModelNet40Data(Dataset):
 		self,
 		train=True,
 		num_points=1024,
-		download=False,
-		root_dir='./',
+		download=True,
 		randomize_data=False,
 		use_normals=False
 	):
 		super(ModelNet40Data, self).__init__()
-		self.root_dir = root_dir
-		if download: download_modelnet40(root_dir=root_dir)
-		self.data, self.labels = load_data(root_dir, train, use_normals)
+		if download: download_modelnet40()
+		self.data, self.labels = load_data(train, use_normals)
 		if not train: self.shapes = self.read_classes_ModelNet40()
 		self.num_points = num_points
 		self.randomize_data = randomize_data
@@ -218,7 +218,8 @@ class ModelNet40Data(Dataset):
 		return self.shapes[label]
 
 	def read_classes_ModelNet40(self):
-		DATA_DIR = os.path.join(self.root_dir, 'data')
+		BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+		DATA_DIR = os.path.join(BASE_DIR, os.pardir, 'data')
 		file = open(os.path.join(DATA_DIR, 'modelnet40_ply_hdf5_2048', 'shape_names.txt'), 'r')
 		shape_names = file.read()
 		shape_names = np.array(shape_names.split('\n')[:-1])
@@ -226,7 +227,7 @@ class ModelNet40Data(Dataset):
 
 
 class ClassificationData(Dataset):
-	def __init__(self, data_class):
+	def __init__(self, data_class=ModelNet40Data()):
 		super(ClassificationData, self).__init__()
 		self.set_class(data_class)
 
@@ -247,7 +248,7 @@ class ClassificationData(Dataset):
 
 
 class RegistrationData(Dataset):
-	def __init__(self, algorithm, data_class, partial_source=False, partial_template=False, noise=False, additional_params={}):
+	def __init__(self, algorithm, data_class=ModelNet40Data(), partial_source=False, partial_template=False, noise=False, additional_params={}):
 		super(RegistrationData, self).__init__()
 		available_algorithms = ['PCRNet', 'PointNetLK', 'DCP', 'PRNet', 'iPCRNet', 'RPMNet', 'DeepGMR']
 		if algorithm in available_algorithms: self.algorithm = algorithm
@@ -361,9 +362,10 @@ class FlowData(Dataset):
 
 
 class SceneflowDataset(Dataset):
-	def __init__(self, root_dir, npoints=1024, root='', partition='train'):
+	def __init__(self, npoints=1024, root='', partition='train'):
 		if root == '':
-			DATA_DIR = os.path.join(root_dir, 'data')
+			BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+			DATA_DIR = os.path.join(BASE_DIR, os.pardir, 'data')
 			root = os.path.join(DATA_DIR, 'data_processed_maxcut_35_20k_2k_8192')
 			if not os.path.exists(root): 
 				print("To download dataset, click here: https://drive.google.com/file/d/1CMaxdt-Tg1Wct8v8eGNwuT7qRSIyJPY-/view")

examples/test_curvenet.py

@@ -0,0 +1,118 @@
+import open3d as o3d
+import argparse
+import os
+import sys
+import logging
+import numpy
+import numpy as np
+import torch
+import torch.utils.data
+import torchvision
+from torch.utils.data import DataLoader
+from tensorboardX import SummaryWriter
+from tqdm import tqdm
+
+# Only if the files are in example folder.
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+if BASE_DIR[-8:] == 'examples':
+	sys.path.append(os.path.join(BASE_DIR, os.pardir))
+	os.chdir(os.path.join(BASE_DIR, os.pardir))
+	
+from learning3d.models import CurveNet
+from learning3d.data_utils import ClassificationData, ModelNet40Data
+
+def display_open3d(template):
+	template_ = o3d.geometry.PointCloud()
+	template_.points = o3d.utility.Vector3dVector(template)
+	# template_.paint_uniform_color([1, 0, 0])
+	o3d.visualization.draw_geometries([template_])
+
+def test_one_epoch(device, model, test_loader, testset):
+	model.eval()
+	test_loss = 0.0
+	pred  = 0.0
+	count = 0
+	for i, data in enumerate(tqdm(test_loader)):
+		points, target = data
+		target = target[:,0]
+
+		points = points.to(device)
+		target = target.to(device)
+
+		output = model(points)
+		loss_val = torch.nn.functional.nll_loss(
+			torch.nn.functional.log_softmax(output, dim=1), target, size_average=False)
+		print("Ground Truth Label: ", testset.get_shape(target[0].item()))
+		print("Predicted Label:    ", testset.get_shape(torch.argmax(output[0]).item()))
+		display_open3d(points.detach().cpu().numpy()[0])
+
+		test_loss += loss_val.item()
+		count += output.size(0)
+
+		_, pred1 = output.max(dim=1)
+		ag = (pred1 == target)
+		am = ag.sum()
+		pred += am.item()
+
+	test_loss = float(test_loss)/count
+	accuracy = float(pred)/count
+	return test_loss, accuracy
+
+def test(args, model, test_loader, testset):
+	test_loss, test_accuracy = test_one_epoch(args.device, model, test_loader, testset)
+	print("Accuracy: ", test_accuracy*100)
+
+def options():
+	parser = argparse.ArgumentParser(description='Point Cloud Registration')
+	parser.add_argument('--dataset_path', type=str, default='ModelNet40',
+						metavar='PATH', help='path to the input dataset') # like '/path/to/ModelNet40'
+	parser.add_argument('--eval', type=bool, default=False, help='Train or Evaluate the network.')
+
+	# settings for input data
+	parser.add_argument('--dataset_type', default='modelnet', choices=['modelnet', 'shapenet2'],
+						metavar='DATASET', help='dataset type (default: modelnet)')
+	parser.add_argument('--num_points', default=1024, type=int,
+						metavar='N', help='points in point-cloud (default: 1024)')
+
+	# settings for CurveNet
+	parser.add_argument('-j', '--workers', default=4, type=int,
+						metavar='N', help='number of data loading workers (default: 4)')
+	parser.add_argument('-b', '--batch_size', default=32, type=int,
+						metavar='N', help='mini-batch size (default: 32)')
+	parser.add_argument('--num_classes', default=40, type=int,
+						metavar='K', help='number of classes to be predicted')
+
+	# settings for on training
+	parser.add_argument('--pretrained', default='learning3d/pretrained/exp_curvenet/models/model.t7', type=str,
+						metavar='PATH', help='path to pretrained model file (default: null (no-use))')
+	parser.add_argument('--device', default='cuda:0', type=str,
+						metavar='DEVICE', help='use CUDA if available')
+
+	args = parser.parse_args()
+	return args
+
+def main():
+	args = options()
+	args.dataset_path = os.path.join(os.getcwd(), os.pardir, os.pardir, 'ModelNet40', 'ModelNet40')
+	
+	testset = ClassificationData(ModelNet40Data(train=False))
+	test_loader = DataLoader(testset, batch_size=args.batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
+
+	if not torch.cuda.is_available():
+		args.device = 'cpu'
+	args.device = torch.device(args.device)
+
+	# Create PointNet Model.
+	model = CurveNet(num_classes=args.num_classes, k=20)
+
+	if args.pretrained:
+		assert os.path.isfile(args.pretrained)
+		weights = torch.load(args.pretrained, map_location='cpu')
+		weights = {k[7:]: v for k, v in weights.items()}
+		model.load_state_dict(weights)
+	model.to(args.device)
+
+	test(args, model, test_loader, testset)
+
+if __name__ == '__main__':
+	main()

{learning3d/examples → examples}/test_dcp.py

@@ -88,8 +88,6 @@ def options():
 						metavar='DATASET', help='dataset type (default: modelnet)')
 	parser.add_argument('--num_points', default=1024, type=int,
 						metavar='N', help='points in point-cloud (default: 1024)')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for PointNet
 	parser.add_argument('--pointnet', default='tune', type=str, choices=['fixed', 'tune'],
@@ -116,8 +114,8 @@ def main():
 	args = options()
 	torch.backends.cudnn.deterministic = True
 	
-	trainset = RegistrationData('DCP', ModelNet40Data(train=True, root_dir=args.root_dir))
-	testset = RegistrationData('DCP', ModelNet40Data(train=False, root_dir=args.root_dir))
+	trainset = RegistrationData('DCP', ModelNet40Data(train=True))
+	testset = RegistrationData('DCP', ModelNet40Data(train=False))
 	train_loader = DataLoader(trainset, batch_size=args.batch_size, shuffle=True, drop_last=True, num_workers=args.workers)
 	test_loader = DataLoader(testset, batch_size=args.batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
 
@@ -132,7 +130,7 @@ def main():
 
 	if args.pretrained:
 		assert os.path.isfile(args.pretrained)
-		model.load_state_dict(torch.load(args.pretrained), strict=False)
+		model.load_state_dict(torch.load(args.pretrained, map_location='cpu'), strict=False)
 	model.to(args.device)
 
 	test(args, model, test_loader)

{learning3d/examples → examples}/test_deepgmr.py

@@ -103,8 +103,6 @@ def options():
 						metavar='K', help='No of nearest neighbors to be estimated.')
 	parser.add_argument('--use_rri', default=True, type=bool,
 						help='Find nearest neighbors to estimate features from PointNet.')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for on training
 	parser.add_argument('-j', '--workers', default=4, type=int,
@@ -123,8 +121,8 @@ def main():
 	args = options()
 	torch.backends.cudnn.deterministic = True
 	
-	trainset = RegistrationData('DeepGMR', ModelNet40Data(train=True, root_dir=args.root_dir))
-	testset = RegistrationData('DeepGMR', ModelNet40Data(train=False, root_dir=args.root_dir))
+	trainset = RegistrationData('DeepGMR', ModelNet40Data(train=True))
+	testset = RegistrationData('DeepGMR', ModelNet40Data(train=False))
 	train_loader = DataLoader(trainset, batch_size=args.batch_size, shuffle=True, drop_last=True, num_workers=args.workers)
 	test_loader = DataLoader(testset, batch_size=args.batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
 
@@ -137,7 +135,7 @@ def main():
 
 	if args.pretrained:
 		assert os.path.isfile(args.pretrained)
-		model.load_state_dict(torch.load(args.pretrained), strict=False)
+		model.load_state_dict(torch.load(args.pretrained, map_location='cpu'), strict=False)
 	model.to(args.device)
 
 	test(args, model, test_loader)

{learning3d/examples → examples}/test_masknet.py

@@ -117,8 +117,6 @@ def options():
 						help='Add noise in source point clouds.')
 	parser.add_argument('--outliers', default=False, type=bool,
 						help='Add outliers to template point cloud.')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for on testing
 	parser.add_argument('-j', '--workers', default=1, type=int,
@@ -139,7 +137,7 @@ def main():
 	args = options()
 	torch.backends.cudnn.deterministic = True
 
-	testset = RegistrationData('PointNetLK', ModelNet40Data(train=False, num_points=args.num_points, root_dir=args.root_dir),
+	testset = RegistrationData('PointNetLK', ModelNet40Data(train=False, num_points=args.num_points),
 									partial_source=args.partial_source, noise=args.noise,
 									additional_params={'use_masknet': True})
 	test_loader = DataLoader(testset, batch_size=args.test_batch_size, shuffle=False, drop_last=False, num_workers=args.workers)

{learning3d/examples → examples}/test_masknet2.py

@@ -120,8 +120,6 @@ def options():
 						help='Add noise in source point clouds.')
 	parser.add_argument('--outliers', default=False, type=bool,
 						help='Add outliers to template point cloud.')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for on testing
 	parser.add_argument('-j', '--workers', default=1, type=int,
@@ -142,7 +140,7 @@ def main():
 	args = options()
 	torch.backends.cudnn.deterministic = True
 
-	testset = RegistrationData('PointNetLK', ModelNet40Data(train=False, num_points=args.num_points, root_dir=args.root_dir),
+	testset = RegistrationData('PointNetLK', ModelNet40Data(train=False, num_points=args.num_points),
 									partial_template=args.partial_template, partial_source=args.partial_source, 
 									noise=args.noise, additional_params={'use_masknet': True, 'partial_point_cloud_method': 'planar_crop'})
 	test_loader = DataLoader(testset, batch_size=args.test_batch_size, shuffle=False, drop_last=False, num_workers=args.workers)

{learning3d/examples → examples}/test_pcn.py

@@ -70,8 +70,6 @@ def options():
 						metavar='DATASET', help='dataset type (default: modelnet)')
 	parser.add_argument('--num_points', default=1024, type=int,
 						metavar='N', help='points in point-cloud (default: 1024)')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for PCN
 	parser.add_argument('--emb_dims', default=1024, type=int,
@@ -97,8 +95,8 @@ def main():
 	args = options()
 	args.dataset_path = os.path.join(os.getcwd(), os.pardir, os.pardir, 'ModelNet40', 'ModelNet40')
 
-	trainset = ClassificationData(ModelNet40Data(train=True, root_dir=args.root_dir))
-	testset = ClassificationData(ModelNet40Data(train=False, root_dir=args.root_dir))
+	trainset = ClassificationData(ModelNet40Data(train=True))
+	testset = ClassificationData(ModelNet40Data(train=False))
 	train_loader = DataLoader(trainset, batch_size=args.batch_size, shuffle=True, drop_last=True, num_workers=args.workers)
 	test_loader = DataLoader(testset, batch_size=args.batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
 

{learning3d/examples → examples}/test_pcrnet.py

@@ -74,8 +74,6 @@ def options():
 						metavar='DATASET', help='dataset type (default: modelnet)')
 	parser.add_argument('--num_points', default=1024, type=int,
 						metavar='N', help='points in point-cloud (default: 1024)')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for PointNet
 	parser.add_argument('--emb_dims', default=1024, type=int,
@@ -99,7 +97,7 @@ def options():
 def main():
 	args = options()
 
-	testset = RegistrationData('PCRNet', ModelNet40Data(train=False, root_dir=args.root_dir))
+	testset = RegistrationData('PCRNet', ModelNet40Data(train=False))
 	test_loader = DataLoader(testset, batch_size=args.batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
 
 	if not torch.cuda.is_available():

{learning3d/examples → examples}/test_pnlk.py

@@ -74,8 +74,6 @@ def options():
 						metavar='DATASET', help='dataset type (default: modelnet)')
 	parser.add_argument('--num_points', default=1024, type=int,
 						metavar='N', help='points in point-cloud (default: 1024)')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for PointNet
 	parser.add_argument('--emb_dims', default=1024, type=int,
@@ -100,7 +98,7 @@ def options():
 def main():
 	args = options()
 
-	testset = RegistrationData('PointNetLK', ModelNet40Data(train=False, root_dir=args.root_dir))
+	testset = RegistrationData('PointNetLK', ModelNet40Data(train=False))
 	test_loader = DataLoader(testset, batch_size=8, shuffle=False, drop_last=False, num_workers=args.workers)
 
 	if not torch.cuda.is_available():

{learning3d/examples → examples}/test_pointconv.py

@@ -73,8 +73,6 @@ def options():
 						metavar='DATASET', help='dataset type (default: modelnet)')
 	parser.add_argument('--num_points', default=1024, type=int,
 						metavar='N', help='points in point-cloud (default: 1024)')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for PointNet
 	parser.add_argument('--pointnet', default='tune', type=str, choices=['fixed', 'tune'],
@@ -101,7 +99,7 @@ def main():
 	args = options()
 	args.dataset_path = os.path.join(os.getcwd(), os.pardir, os.pardir, 'ModelNet40', 'ModelNet40')
 	
-	testset = ClassificationData(ModelNet40Data(train=False, root_dir=args.root_dir))
+	testset = ClassificationData(ModelNet40Data(train=False))
 	test_loader = DataLoader(testset, batch_size=args.batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
 
 	if not torch.cuda.is_available():

{learning3d/examples → examples}/test_pointnet.py

@@ -73,8 +73,6 @@ def options():
 						metavar='DATASET', help='dataset type (default: modelnet)')
 	parser.add_argument('--num_points', default=1024, type=int,
 						metavar='N', help='points in point-cloud (default: 1024)')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for PointNet
 	parser.add_argument('--pointnet', default='tune', type=str, choices=['fixed', 'tune'],
@@ -101,7 +99,7 @@ def main():
 	args = options()
 	args.dataset_path = os.path.join(os.getcwd(), os.pardir, os.pardir, 'ModelNet40', 'ModelNet40')
 	
-	testset = ClassificationData(ModelNet40Data(train=False, root_dir=args.root_dir))
+	testset = ClassificationData(ModelNet40Data(train=False))
 	test_loader = DataLoader(testset, batch_size=args.batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
 
 	if not torch.cuda.is_available():

{learning3d/examples → examples}/test_prnet.py

@@ -79,8 +79,6 @@ def options():
 	# settings for input data
 	parser.add_argument('--dataset_type', default='modelnet', choices=['modelnet', 'shapenet2'],
 						metavar='DATASET', help='dataset type (default: modelnet)')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for PointNet
 	parser.add_argument('--emb_dims', default=512, type=int,
@@ -104,8 +102,8 @@ def main():
 	args = options()
 	torch.backends.cudnn.deterministic = True
 	
-	trainset = RegistrationData('PRNet', ModelNet40Data(train=True, root_dir=args.root_dir), partial_source=True, partial_template=True)
-	testset = RegistrationData('PRNet', ModelNet40Data(train=False, root_dir=args.root_dir), partial_source=True, partial_template=True)
+	trainset = RegistrationData('PRNet', ModelNet40Data(train=True), partial_source=True, partial_template=True)
+	testset = RegistrationData('PRNet', ModelNet40Data(train=False), partial_source=True, partial_template=True)
 	train_loader = DataLoader(trainset, batch_size=args.batch_size, shuffle=True, drop_last=True, num_workers=args.workers)
 	test_loader = DataLoader(testset, batch_size=args.batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
 
@@ -119,7 +117,7 @@ def main():
 
 	if args.pretrained:
 		assert os.path.isfile(args.pretrained)
-		model.load_state_dict(torch.load(args.pretrained), strict=False)
+		model.load_state_dict(torch.load(args.pretrained, map_location='cpu'), strict=False)
 	model.to(args.device)
 
 	test(args, model, test_loader)

{learning3d/examples → examples}/test_rpmnet.py

@@ -74,8 +74,6 @@ def options():
 						metavar='DATASET', help='dataset type (default: modelnet)')
 	parser.add_argument('--num_points', default=1024, type=int,
 						metavar='N', help='points in point-cloud (default: 1024)')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for PointNet
 	parser.add_argument('--emb_dims', default=1024, type=int,
@@ -100,7 +98,7 @@ def options():
 def main():
 	args = options()
 
-	testset = RegistrationData('RPMNet', ModelNet40Data(train=False, num_points=args.num_points, use_normals=True, root_dir=args.root_dir), partial_source=True, partial_template=False)
+	testset = RegistrationData('RPMNet', ModelNet40Data(train=False, num_points=args.num_points, use_normals=True), partial_source=True, partial_template=False)
 	test_loader = DataLoader(testset, batch_size=1, shuffle=False, drop_last=False, num_workers=args.workers)
 
 	if not torch.cuda.is_available():

{learning3d/examples → examples}/train_PointNetLK.py

@@ -147,8 +147,6 @@ def options():
 						metavar='DATASET', help='dataset type (default: modelnet)')
 	parser.add_argument('--num_points', default=1024, type=int,
 						metavar='N', help='points in point-cloud (default: 1024)')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for PointNet
 	parser.add_argument('--fine_tune_pointnet', default='tune', type=str, choices=['fixed', 'tune'],
@@ -197,8 +195,8 @@ def main():
 	textio.cprint(str(args))
 
 	
-	trainset = RegistrationData('PointNetLK', ModelNet40Data(train=True, root_dir=args.root_dir))
-	testset = RegistrationData('PointNetLK', ModelNet40Data(train=False, root_dir=args.root_dir))
+	trainset = RegistrationData('PointNetLK', ModelNet40Data(train=True))
+	testset = RegistrationData('PointNetLK', ModelNet40Data(train=False))
 	train_loader = DataLoader(trainset, batch_size=args.batch_size, shuffle=True, drop_last=True, num_workers=args.workers)
 	test_loader = DataLoader(testset, batch_size=8, shuffle=False, drop_last=False, num_workers=args.workers)
 

{learning3d/examples → examples}/train_dcp.py

@@ -168,8 +168,6 @@ def options():
 						metavar='DATASET', help='dataset type (default: modelnet)')
 	parser.add_argument('--num_points', default=1024, type=int,
 						metavar='N', help='points in point-cloud (default: 1024)')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for PointNet
 	parser.add_argument('--pointnet', default='tune', type=str, choices=['fixed', 'tune'],
@@ -216,8 +214,8 @@ def main():
 	textio.cprint(str(args))
 
 	
-	trainset = RegistrationData('DCP', ModelNet40Data(train=True, root_dir=args.root_dir))
-	testset = RegistrationData('DCP', ModelNet40Data(train=False, root_dir=args.root_dir))
+	trainset = RegistrationData('DCP', ModelNet40Data(train=True))
+	testset = RegistrationData('DCP', ModelNet40Data(train=False))
 	train_loader = DataLoader(trainset, batch_size=args.batch_size, shuffle=True, drop_last=True, num_workers=args.workers)
 	test_loader = DataLoader(testset, batch_size=args.batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
 

{learning3d/examples → examples}/train_deepgmr.py

@@ -165,8 +165,6 @@ def options():
 						metavar='DATASET', help='dataset type (default: modelnet)')
 	parser.add_argument('--num_points', default=1024, type=int,
 						metavar='N', help='points in point-cloud (default: 1024)')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	parser.add_argument('--nearest_neighbors', default=20, type=int,
 						metavar='K', help='No of nearest neighbors to be estimated.')
@@ -213,8 +211,8 @@ def main():
 	textio = IOStream('checkpoints/' + args.exp_name + '/run.log')
 	textio.cprint(str(args))
 	
-	trainset = RegistrationData('DeepGMR', ModelNet40Data(train=True, root_dir=args.root_dir), additional_params={'nearest_neighbors': args.nearest_neighbors})
-	testset = RegistrationData('DeepGMR', ModelNet40Data(train=False, root_dir=args.root_dir), additional_params={'nearest_neighbors': args.nearest_neighbors})
+	trainset = RegistrationData('DeepGMR', ModelNet40Data(train=True), additional_params={'nearest_neighbors': args.nearest_neighbors})
+	testset = RegistrationData('DeepGMR', ModelNet40Data(train=False), additional_params={'nearest_neighbors': args.nearest_neighbors})
 	train_loader = DataLoader(trainset, batch_size=args.batch_size, shuffle=True, drop_last=True, num_workers=args.workers)
 	test_loader = DataLoader(testset, batch_size=args.batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
 

{learning3d/examples → examples}/train_masknet.py

@@ -160,8 +160,6 @@ def options():
 						help='Add noise in source point clouds.')
 	parser.add_argument('--outliers', default=False, type=bool,
 						help='Add outliers to template point cloud.')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for on training
 	parser.add_argument('--seed', type=int, default=1234)
@@ -204,10 +202,10 @@ def main():
 	textio = IOStream('checkpoints/' + args.exp_name + '/run.log')
 	textio.cprint(str(args))
 
-	trainset = RegistrationData(ModelNet40Data(train=True, num_points=args.num_points, unseen=args.unseen, root_dir=args.root_dir),
+	trainset = RegistrationData(ModelNet40Data(train=True, num_points=args.num_points, unseen=args.unseen),
 								partial_source=args.partial_source, noise=args.noise, outliers=args.outliers, 
 								additional_params={'use_masknet': True})
-	testset = RegistrationData(ModelNet40Data(train=False, num_points=args.num_points, unseen=args.unseen, root_dir=args.root_dir),
+	testset = RegistrationData(ModelNet40Data(train=False, num_points=args.num_points, unseen=args.unseen),
 								partial_source=args.partial_source, noise=args.noise, outliers=args.outliers,
 								additional_params={'use_masknet': True})
 	train_loader = DataLoader(trainset, batch_size=args.batch_size, shuffle=True, drop_last=True, num_workers=args.workers)

{learning3d/examples → examples}/train_pcn.py

@@ -138,8 +138,6 @@ def options():
 						metavar='DATASET', help='dataset type (default: modelnet)')
 	parser.add_argument('--num_points', default=1024, type=int,
 						metavar='N', help='points in point-cloud (default: 1024)')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for PCN
 	parser.add_argument('--emb_dims', default=1024, type=int,
@@ -185,8 +183,8 @@ def main():
 	textio.cprint(str(args))
 
 	
-	trainset = ClassificationData(ModelNet40Data(train=True, root_dir=args.root_dir))
-	testset = ClassificationData(ModelNet40Data(train=False, root_dir=args.root_dir))
+	trainset = ClassificationData(ModelNet40Data(train=True))
+	testset = ClassificationData(ModelNet40Data(train=False))
 	train_loader = DataLoader(trainset, batch_size=args.batch_size, shuffle=True, drop_last=True, num_workers=args.workers)
 	test_loader = DataLoader(testset, batch_size=args.batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
 

{learning3d/examples → examples}/train_pcrnet.py

@@ -147,8 +147,6 @@ def options():
 						metavar='DATASET', help='dataset type (default: modelnet)')
 	parser.add_argument('--num_points', default=1024, type=int,
 						metavar='N', help='points in point-cloud (default: 1024)')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for PointNet
 	parser.add_argument('--pointnet', default='tune', type=str, choices=['fixed', 'tune'],
@@ -195,8 +193,8 @@ def main():
 	textio.cprint(str(args))
 
 	
-	trainset = RegistrationData('PCRNet', ModelNet40Data(train=True, root_dir=args.root_dir))
-	testset = RegistrationData('PCRNet', ModelNet40Data(train=False, root_dir=args.root_dir))
+	trainset = RegistrationData('PCRNet', ModelNet40Data(train=True))
+	testset = RegistrationData('PCRNet', ModelNet40Data(train=False))
 	train_loader = DataLoader(trainset, batch_size=args.batch_size, shuffle=True, drop_last=True, num_workers=args.workers)
 	test_loader = DataLoader(testset, batch_size=args.batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
 

{learning3d/examples → examples}/train_pointconv.py

@@ -163,8 +163,6 @@ def options():
 						metavar='DATASET', help='dataset type (default: modelnet)')
 	parser.add_argument('--num_points', default=1024, type=int,
 						metavar='N', help='points in point-cloud (default: 1024)')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for PointNet
 	parser.add_argument('--pointnet', default='tune', type=str, choices=['fixed', 'tune'],
@@ -212,8 +210,8 @@ def main():
 	textio.cprint(str(args))
 
 	
-	trainset = ClassificationData(ModelNet40Data(train=True, root_dir=args.root_dir))
-	testset = ClassificationData(ModelNet40Data(train=False, root_dir=args.root_dir))
+	trainset = ClassificationData(ModelNet40Data(train=True))
+	testset = ClassificationData(ModelNet40Data(train=False))
 	train_loader = DataLoader(trainset, batch_size=args.batch_size, shuffle=True, drop_last=True, num_workers=args.workers)
 	test_loader = DataLoader(testset, batch_size=args.batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
 

{learning3d/examples → examples}/train_pointnet.py

@@ -163,8 +163,6 @@ def options():
 						metavar='DATASET', help='dataset type (default: modelnet)')
 	parser.add_argument('--num_points', default=1024, type=int,
 						metavar='N', help='points in point-cloud (default: 1024)')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for PointNet
 	parser.add_argument('--pointnet', default='tune', type=str, choices=['fixed', 'tune'],
@@ -212,8 +210,8 @@ def main():
 	textio.cprint(str(args))
 
 	
-	trainset = ClassificationData(ModelNet40Data(train=True, root_dir=args.root_dir))
-	testset = ClassificationData(ModelNet40Data(train=False, root_dir=args.root_dir))
+	trainset = ClassificationData(ModelNet40Data(train=True))
+	testset = ClassificationData(ModelNet40Data(train=False))
 	train_loader = DataLoader(trainset, batch_size=args.batch_size, shuffle=True, drop_last=True, num_workers=args.workers)
 	test_loader = DataLoader(testset, batch_size=args.batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
 

{learning3d/examples → examples}/train_prnet.py

@@ -157,8 +157,6 @@ def options():
 						metavar='K', help='dim. of the feature vector (default: 1024)')
 	parser.add_argument('--num_iterations', default=3, type=int,
 						help='Number of Iterations')
-	parser.add_argument('--root_dir', default='./', type=str, 
-					 	help='path of the data where modelnet files are downloaded.')
 
 	# settings for on training
 	parser.add_argument('--seed', type=int, default=1234)
@@ -197,8 +195,8 @@ def main():
 	textio.cprint(str(args))
 
 	
-	trainset = RegistrationData('PRNet', ModelNet40Data(train=True, root_dir=args.root_dir), partial_source=True, partial_template=True)
-	testset = RegistrationData('PRNet', ModelNet40Data(train=False, root_dir=args.root_dir), partial_source=True, partial_template=True)
+	trainset = RegistrationData('PRNet', ModelNet40Data(train=True), partial_source=True, partial_template=True)
+	testset = RegistrationData('PRNet', ModelNet40Data(train=False), partial_source=True, partial_template=True)
 	train_loader = DataLoader(trainset, batch_size=args.batch_size, shuffle=True, drop_last=True, num_workers=args.workers)
 	test_loader = DataLoader(testset, batch_size=args.batch_size, shuffle=False, drop_last=False, num_workers=args.workers)