I am trying to train my point cloud data on PointCNN so I need to convert my dataset to hdf5 as used in PointCNN. PointCNN used the modelnet40_ply_hdf5_2048 dataset. I have tried converting my custom dataset but I am having issues with the label.
I tried this to get the label/shape_names
shape_ids = {}
shape_ids = [line.rstrip() for line in open(os.path.join(PATH, 'filelist1.txt'))]
shape_names = ['_'.join(x.split('_')[0:-1]) for x in shape_ids]
datapath = [(shape_names[i], os.path.join(PATH, shape_names[i], shape_ids[i])) for i
in range(len(shape_ids))]
Convert to h5py file
import numpy as np
from tqdm import tqdm
import h5py
filenames = [line.rstrip() for line in open(os.path.join(PATH))]
f = h5py.File("filename", 'w')
data = np.zeros((len(filenames), 1024, 3))
for i in range(0, len(datapath)):
fn = datapath[i]
cls = classes[datapath[i][0]]
label = np.array([cls]).astype(np.int32)
csvreader = np.genfromtxt("data1/" + filenames[i] + ".csv", delimiter=",").astype(np.float32)
for j in range(0,1024):
data[i,j] = [csvreader[j][0], csvreader[j][1], csvreader[j][2]]
label
dset1 = f.create_dataset("data", data=data, compression="gzip", compression_opts=4)
dset2 = f.create_dataset("label", data=label, compression="gzip", compression_opts=1)
f.close()
It did convert successfully but when I tried to train on PointCNN
PointCNN training
------Building model-------
------Successfully Built model-------
Traceback (most recent call last):
File "train_pytorch.py", line 174, in <module>
current_data, current_label, _ = provider.shuffle_data(current_data, np.squeeze(current_label))
File "provider.py", line 28, in shuffle_data
idx = np.arange(len(labels))
TypeError: len() of unsized object