Zhihao Liang

Mask heads and COCO_dataset_api

7

I've convert the coco_dataset into voc_type, but i meet some trouble during training. Can you complete the model with mask heads and the metadataset api for coco_dataset, if you can...

Thanks for your amazing code! I visualized some gt poses by projecting the sampled points from the meshes on the images. I found some cases as follows: > `0048/000001` such...

Recommend: replace 'sklearn.neighbors.NearestNeighbors' with 'scipy.spatial.cKDTree' to accerlate

1

```python from sklearn.neighbors import NearestNeighbors nn = NearestNeighbors(n_neighbors=k_nn+1, algorithm='kd_tree').fit(xyz) distances, neighbors = nn.kneighbors(xyz) neighbors = neighbors[:, 1:] distances = distances[:, 1:] ``` can be replace with: ```python from scipy.spatial import...

The difference of RGB output between c++ and python processing in SensReader part

1

I've run both `c++` and `python` toolkits in `SensReader`. I found the RGB output results of them are different. And I found the storage of c++'s RGB outputs is larger...

Generate 0 positive grasp in my own dataset

1

Hi, I build my own dataset following your **Network trainig** partial. My data storage format is as follow: ``` └─ roor ├─ objects.txt ├─ input │ ├─ example_gt.pcd │ ├─...

Training about COCO

1

I've converted the coco_dataset into the voc style, the flag txt in ImageSets for each class and rewrite the label and label_1c for coco which generates labels' txt. I think...