Xin Kong

@JenningsL I could run the code using batch_size=4, though batch_size is 16 in official version. Thanks for your prompt reply!

@MarkMoHR Hi! I followed your suggestion! But I got an error while running the code `forward_test_single_image.py `. Could you help me figure this out? Thanks a lot!!! I got this...

Hi! Same error here. What's the solution? Waiting for help!!! Thanks! `Traceback (most recent call last): File "test.py", line 38, in TEST_DATASET = part_dataset.PartDataset(root=DATA_PATH, npoints=NUM_POINT, classification=False, class_choice=FLAGS.category, split='test') File "/home/kx/project/3D/pointnet2-master/part_seg/part_dataset.py",...

@Coastline2018 I have trained the pointnet2_sem_seg model and get trained models. I want to load the model and test it with scannet_test.pickle. Also want to visualize the ground truth data...

Similar bugs here. When I tried to export trimesh to .obj which contains Path3D obj, I got error: ``` mesh.visual.kind in ['vertex', 'face'] and AttributeError: 'Path3D' object has no attribute...

@ymxlzgy I successfully run the code by building ceres and pcl1.8 with eigen3.2.9. Hope it helps.

@BertaBescos I can run the code with openCV2 but not OpenCV3. I find the program not fluent either with MaskRCNN or not. Waiting for your reply. Thanks!

Hi! Thanks a lot for building this awesome functorch! I have the same issue. I'm using `fmodel, params, buffers = combine_state_for_ensemble(models)` to stack models and optimizing the params in a...

@zou3519 Hi, thanks for your quick reply. In my case, I'm training many tiny networks and need to use the up-to-date network's weights every a few steps. So I need...

Thanks a lot for the quick reply! Yeah, we can do batch training with vmap. I found we can set different learning rates for different layers' parameters easily by using...