bigbrother001

Hello, thanks for your great work. Anyway, I can't understand the content in the \src\test\data\test_reference.json, especially the scores, what they means and how do you get them?

Where is the TF-IDF from for the CIDEr?

1

I want to ask that where do the TD-IDF of a word comes from? I guess maybe it is calculated in another dataset.

and how to find it? thanks

May I ask what is the use of pycocoevalcap/spice/cache/data.mdb? It's just too large, can I delete it or how to make it smaller?

package versions have conflicting dependencies.

1

Thanks for great work! when I try to install the environment by `pip install -r requirements.txt` It will tell me that package versions have conflicting dependencies. For example, > The...

Thanks for great work! Based on my experience with using minigpt4, it tends to generate long and detailed caption for given image. But the cases in figure 3 in the...

When I open the `https://huggingface.co/spaces/FoundationVision/LlamaGen`, It is showed as follow: runtime error Traceback (most recent call last): File "/home/user/app/app.py", line 171, in t5_model, vq_model, gpt_model, image_size = load_model(args) File "/home/user/app/app.py",...

Wow, it looks like that you have done a lot of research in Image caption evaluation. While, I come here for composite dataset, would you like tell me how to...

Thanks for great work! I find that this paper is accepted by NLP4Eval and I am very interested in this Conference, could you tell me how to find more information,...