Zongbao Feng comments

Results 8 comments of


                                            Zongbao Feng

Low performance in multiclass detection

so good result to hard to get it

patchUbuntu.sh error: ‘msg.msg_id’ may be used uninitialized in this function [-Werror=maybe-uninitialized]

I apply patch like below , and then build successed ```diff --- a/kernel/nvidia/drivers/net/ethernet/nvidia/pcie/tegra_vnet.c +++ b/kernel/nvidia/drivers/net/ethernet/nvidia/pcie/tegra_vnet.c @@ -967,6 +967,7 @@ static void process_ctrl_msg(struct work_struct *work) struct ep_ring_buf *ep_mem = &tvnet->ep_mem; struct...

这个不支持多说和文章搜索吗？

这个可以有。

Add PyTorch1.2+ support

USEFULL

Conda stuck at "Executing transaction"

same situation on Ubuntu 18.04 plarform .

Problems about the pretrained model

Therefore, apart from waiting for your classification weight parameters, are there any other feasible methods?

[Question] Why I can get semantic or instance image for shape cube, but not for franka pandar arm?

Thanks for your reply so much. my scene config is here : ```python class MyCabinetSceneCfg(ObjectTableSceneCfg): def __post_init__(self): # Set franka as robot print(f"FRANKA_PANDA_HIGH_PD_CFG {FRANKA_PANDA_HIGH_PD_CFG}") self.robot = FRANKA_PANDA_HIGH_PD_CFG.replace(prim_path="{ENV_REGEX_NS}/Robot", semantic_tags=[("class", "franka")],) #...

[Question] Why I can get semantic or instance image for shape cube, but not for franka pandar arm?

thks for your solution. it'ok . all class extend `SpawnerCfg` should have this field. ![camera_semantic_id_fast_0_50](https://github.com/user-attachments/assets/722c41a6-88d2-4808-9b6d-328d85e67618)