search

hkust-vgd / scanobjectnn

Code for Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data, ICCV 2019
MIT License
237 stars 31 forks source link

Evaluate Synthetic Trained on Real #16

Closed sheshap closed 4 years ago

sheshap commented 4 years ago

How to create the test "modelnet/modelnet_test.h5" file ?

I got the following error: Traceback (most recent call last): File "evaluate_synthetic_trained_on_real.py", line 83, in TEST_DATA, TEST_LABELS = data_utils.load_h5(TEST_FILE) File "/raid1/inprogress/ssheshap/Other/ForAWS/scanobjectnn/pointnet2/../data_utils.py", line 250, in load_h5 f = h5py.File(h5_filename) File "/raid1/inprogress/ssheshap/software/anaconda3/lib/python3.7/site-packages/h5py/_hl/files.py", line 394, in init swmr=swmr) File "/raid1/inprogress/ssheshap/software/anaconda3/lib/python3.7/site-packages/h5py/_hl/files.py", line 195, in make_fid fid = h5f.create(name, h5f.ACC_EXCL, fapl=fapl, fcpl=fcpl) File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper File "h5py/h5f.pyx", line 105, in h5py.h5f.create OSError: Unable to create file (unable to open file: name = 'modelnet/modelnet_test.h5', errno = 2, error message = 'No such file or directory', flags = 15, o_flags = c2)

mikacuy commented 4 years ago

Hi,

You can create the following h5 file using the modelnet40 objects from https://shapenet.cs.stanford.edu/media/modelnet40_ply_hdf5_2048.zip

The object classses used for this experiment is described in the paper. Then this error should be resolved.

Best, Mika