Linhui Xiao

[email protected], thanks a lot!

I successfully reproduced by following the author's description. maybe your numpy version not match or some environment problem.

Is there a script to generate image captions like Figure 5 in the paper

I have solved this bug: this is a bug, please fix the code in models/beam_search.py line 118: ``` # selected_beam = selected_idx / candidate_logprob.shape[-1] selected_beam = torch.div(selected_idx, candidate_logprob.shape[-1], rounding_mode="floor") ```

I have solve this bug，this is because m2 coco dataset use java core，its need install some software as follows： ``` sudo apt update sudo apt install default-jdk sudo apt install...

I have solved this issue: this is a bug, please fix the code in models/beam_search.py line 118: # selected_beam = selected_idx / candidate_logprob.shape[-1] selected_beam = torch.div(selected_idx, candidate_logprob.shape[-1], rounding_mode="floor")

Thank you very much. Due to area internet access limitations, the Bert_base_cased model can‘t be loaded from the internet automatically, this code solves my problem that loading the Bert model...

**env ：** Name Version Build Channel _libgcc_mutex 0.1 conda_forge https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge _openmp_mutex 4.5 2_gnu https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge bzip2 1.0.8 h7f98852_4 https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge ca-certificates 2022.12.7 ha878542_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge certifi 2022.12.7 pypi_0 pypi charset-normalizer 2.1.1 pypi_0 pypi...

@wenhui0924 Thank you for taking time out of your busy schedule to answer our questions. May I ask whether the giant model you mentioned will be open sourced?

@wenhui0924 Can you release the pre-trained gaint model? After all, the performance in the Beit-3 paper is very strong, which is based on the gaint model, while the worse base...