Gary3410

Thanks! As for DOTA dataset, you chose the pictures with movable objects such as cars and planes, Does the AP only contain movable objects categories?

Hello! Thank you for your interest in this work. This error looks like a Detic environment config issue, you can refer to [this](https://github.com/facebookresearch/Detic/blob/main/docs/INSTALL.md) to install it. Meanwhile, this [issue](https://github.com/facebookresearch/Detic/issues/65) may...

Hi, thanks for your interest in this work. After you have completed the Detic installation, you need to move the necessary files from the ``Detic`` directory such as ``config`` to...

Hi, thank you for your interest in this work! Our current TaPA can only generate high-level planning and cannot be executed directly in the simulator. So the results in Table...

This problem might be caused by a lack of CPU memory, cover weights require at least 26GB of memory. Here you can find more detailed explanations and solutions [issues#224](https://github.com/Lightning-AI/lit-llama/issues/244). Also,...

Hello, getting images from ai2thor is easy, after initializing the scene, the following code is executed to get the RGB image, depth image, and instance segmentation masks. https://github.com/Gary3410/TaPA/blob/f430e807aced2156acd2da480ececbe684f1c776/create_dataset/create_partial_vision_dataset.py#L195-L200 Hope this...

Well, this may seem like a problem with the environment initiation, try starting it with the following code: https://github.com/Gary3410/TaPA/blob/f430e807aced2156acd2da480ececbe684f1c776/create_dataset/create_partial_vision_dataset.py#L5-L6 https://github.com/Gary3410/TaPA/blob/f430e807aced2156acd2da480ececbe684f1c776/create_dataset/create_partial_vision_dataset.py#L38-L58 If the above code does not work, you can get...

I'm sorry for not getting back to you sooner. This might be due to a problem with the lit-llama version, you can try to finetune the model on the latest...