Jiahui Zhu

What do you see as the limitations of your work？

 the knife blade is not match the goal image

I found the similar using DINO to find correspond feature in this repo. but he need the goal image's depth to find the transformation. When we use the goal image...

哥，你知道怎么test了吗？就是输入图片和文本给模型，模型就知道怎么输出动作

@Cubism-star

how can you access the dataset? i meet my problem is ``` Traceback (most recent call last): File "E:\Robot_learning\language-table-main\language_table\examples\dataset_example.py", line 57, in app.run(main) File "C:\Users\zhujiahui\anaconda3\envs\lava\lib\site-packages\absl\app.py", line 308, in run _run_main(main,...

because CLIP only can use RGB?