JingyeChen

关于注意力机制初始状态的问题

1

请问一下~在代码里面我看到您的注意力模型初始状态是全0 hidden = Variable(torch.zeros(nB,hidden_size).type_as(feats.data)) (asrn_res.py 106行) 注意力模型作为一个解码器，那么初始状态是不是应该设定为编码器的末状态呢 （不过我用全0初始状态跑代码，效果也挺棒的233）

Does anybody know what is the text prompt for IIIT5K? Thanks!

Thanks for your excellent works! I wonder that will the breast biospy dataset used in your paper be publicly available? I am looking forward to your reply :D

Hello! Thanks for your excellent work and your effort on sharing this code 👍 . Here I have some questions when trying to re-implement it: 1) According to the paper,...

Add new paper "textdiffuser: diffusion models as text painters"

1

Hello authors! Many thanks for your excellent survey! Would you consider to add the paper "textdiffuser: diffusion models as text painters" (https://arxiv.org/abs/2305.10855) to this page? This paper tries to leverage...

Hi, thanks for your excellent work! May I ask during the test stage, can I input multiple images simultaneously for processing? It will be faster compared with single image inference....

Has anyone encountered the pyarrow.lib.ArrowTypeError when downloading?

35

File "/mnt/disk/Panda-70M/dataset_dataloading/video2dataset/video2dataset/data_writer.py", line 44, in flush df = pa.Table.from_pydict(self.buffer, self.schema) File "pyarrow/table.pxi", line 1813, in pyarrow.lib._Tabular.from_pydict File "pyarrow/table.pxi", line 5356, in pyarrow.lib._from_pydict File "pyarrow/array.pxi", line 374, in pyarrow.lib.asarray File "pyarrow/array.pxi",...

Thanks for your excellent work and it indeed inspired me a lot! I am wondering is it possible to generate completed images in RGBA format for easier segmentation?