Open MrCrazyCrab opened 4 years ago
@DylanWusee i notice that you want to do data augmentation, but the code
"#batch_data, batch_label, batch_smpw = get_batch_wdp(TRAIN_DATASET, train_idxs, start_idx, end_idx) batch_data, batch_label, batch_smpw = get_batch(TRAIN_DATASET, train_idxs, start_idx, end_idx) Augment batched point clouds by rotation aug_data = provider.rotate_point_cloud_z(batch_data) #aug_data = provider.rotate_point_cloud(batch_data)" means that you just rotate your data, so i am curious why you do it? is there any tricks for to train the model?
"#batch_data, batch_label, batch_smpw = get_batch_wdp(TRAIN_DATASET, train_idxs, start_idx, end_idx) batch_data, batch_label, batch_smpw = get_batch(TRAIN_DATASET, train_idxs, start_idx, end_idx)
aug_data = provider.rotate_point_cloud_z(batch_data) #aug_data = provider.rotate_point_cloud(batch_data)"
means that you just rotate your data, so i am curious why you do it? is there any tricks for to train the model?
@DylanWusee i notice that you want to do data augmentation, but the code