import torch.nn.functional as F
# Hyper parameters
# path to shapenet
datapath = './shapenetcore_partanno_segmentation_benchmark_v0/'
# resample to some points
num_points = 2500
# how many inputs you load to NN at the same time
batchsize = 32
# how many epoch to iterate
epochsize = 250
# workers
workers = 6
# load shapenet datasets
dataset = ShapeNetDataset(datapath, classification=True, npoints=num_points)
testset = ShapeNetDataset(datapath, classification=True, npoints=num_points)
dataloader = torch.utils.data.DataLoader(dataset,
batchsize,
shuffle=True,
num_workers=workers)
testdataloader = torch.utils.data.DataLoader(testset,
batchsize,
shuffle=True,
num_workers=workers)
num_classes = len(dataset.classes)
print(num_classes)
# classifier initialization
parser.add_argument("--sample_size")
return parser
if __name__ == "__main__":
args = get_parser().parse_args()
logger = setup_logger(name="demo")
logger.info("Arguments: " + str(args))
cfg.CHECKPOINT = args.checkpoint
data_dir = args.data_dir
synset_id = args.synset_id
output_dir = args.output_dir
dataset = ShapeNetDataset(cfg, data_dir)
synset_ids = dataset.synset_ids
first_idx = synset_ids.index(synset_id)
model_num = int(synset_ids.count(synset_id) / 24)
sample_size = int(args.sample_size)
torch.manual_seed(0)
idx_list = torch.randint(0, model_num, size=(sample_size, ))
idx_list += first_idx
all_iou = []
for idx in idx_list:
item = dataset[
idx] # img, verts, faces, points, normals, voxels, P, _imgs, render_RTs, RT, sid, mid, iid
img = item[0].squeeze()
imgs = item[7]
default='Chair',
help="class_choice")
parser.add_argument('--feature_transform',
action='store_true',
help="use feature transform")
opt = parser.parse_args()
print(opt)
opt.manualSeed = random.randint(1, 10000) # fix seed
print("Random Seed: ", opt.manualSeed)
random.seed(opt.manualSeed)
torch.manual_seed(opt.manualSeed)
dataset = ShapeNetDataset(root=opt.dataset,
classification=False,
class_choice=[opt.class_choice])
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=opt.batchSize,
shuffle=True,
num_workers=int(opt.workers))
test_dataset = ShapeNetDataset(root=opt.dataset,
classification=False,
class_choice=[opt.class_choice],
split='test',
data_augmentation=False)
testdataloader = torch.utils.data.DataLoader(test_dataset,
batch_size=opt.batchSize,
shuffle=True,
num_workers=int(opt.workers))
from dataset import ShapeNetDataset
from model import PointNetCls
import torch.nn.functional as F
parser = argparse.ArgumentParser()
parser.add_argument('--model', type=str, default='', help='model path')
parser.add_argument('--num_points',
type=int,
default=2500,
help='input batch size')
dataset_root = '../shapenet'
opt = parser.parse_args()
print(opt)
test_dataset = ShapeNetDataset(root=dataset_root,
classification=True,
split='test',
npoints=opt.num_points)
train_dataset = ShapeNetDataset(root=dataset_root,
classification=True,
npoints=opt.num_points)
test_dataloader = torch.utils.data.DataLoader(test_dataset,
batch_size=32,
shuffle=True,
num_workers=8)
train_dataloader = torch.utils.data.DataLoader(train_dataset,
batch_size=32,
shuffle=True,
num_workers=8)
action='store_true',
help="use feature transform")
opt = parser.parse_args()
print(opt)
blue = lambda x: '\033[94m' + x + '\033[0m'
opt.manualSeed = random.randint(1, 10000) # fix seed
print("Random Seed: ", opt.manualSeed)
random.seed(opt.manualSeed)
torch.manual_seed(opt.manualSeed)
if opt.dataset_type == 'shapenet':
dataset = ShapeNetDataset(root=opt.dataset,
classification=True,
npoints=opt.num_points)
test_dataset = ShapeNetDataset(root=opt.dataset,
classification=True,
split='test',
npoints=opt.num_points,
data_augmentation=False)
elif opt.dataset_type == 'modelnet40':
dataset = ModelNetDataset(root=opt.dataset,
npoints=opt.num_points,
split='trainval')
test_dataset = ModelNetDataset(root=opt.dataset,
split='test',
npoints=opt.num_points,
clr = (clr - clr.min()) / (clr.max() - clr.min()) # normalization
sct = ax.scatter(
pts[:, 0],
pts[:, 1],
pts[:, 2],
c=clr,
zdir='y',
s=sz,
cmap=cmap,
# depthshade=False,
edgecolors=(0.5, 0.5, 0.5))
ax.set_axis_off()
ax.set_facecolor("white")
return ax, sct
if __name__ == '__main__':
dataroot = "data/shapenetcore_partanno_segmentation_benchmark_v0"
dataset = ShapeNetDataset(
root=dataroot,
class_choice='Airplane',
split='train',
classification=True,
num_points=2048,
)
ax, sct = draw_pts(dataset[random.randint(0, 100)][0],
clr=None,
cmap='CMRmap')
ax.figure.show()
parser.add_argument('--dataset', type=str, required=True, help="dataset path")
parser.add_argument('--feature_transform', action='store_true', help="use feature transform")
opt = parser.parse_args()
print(opt)
blue = lambda x: '\033[94m' + x + '\033[0m'
opt.manualSeed = random.randint(1, 10000) # fix seed
print("Random Seed: ", opt.manualSeed)
random.seed(opt.manualSeed)
torch.manual_seed(opt.manualSeed)
dataset = ShapeNetDataset(
root=opt.dataset,
classification=True,
npoints=opt.num_points)
dataloader = torch.utils.data.DataLoader(
dataset,
batch_size=opt.batchSize,
shuffle=True,
num_workers=int(opt.workers))
print(len(dataset))
num_classes = len(dataset.classes)
print('classes', num_classes)
try:
os.makedirs(opt.outf)
except OSError: