CapDec

CapDec copied to clipboard

davenu

Error(s) in loading state_dict for ClipCaptionModel

1

Dear author, thank you for you wonderful job. There is an error occured when I load the pre-trained weights. Well, it has been solved.

sszbuu

modality_offset

1

Thank you for the great work, though I have a question about the modality_offset, did you use that during the noise injection training? If no, the only modulation to the...

Flaick

how to download / create single_caption_per_sample_val.json file

6

can anyone please help me how to generate single_caption_per_sample_val.json file as mentioned in embeddings_generator.py file as shown below **annotations_path = f'/home/gamir/DER-Roei/davidn/myprivate_coco/annotations/single_caption_per_sample_val.json'**

BoiAkay

About FlickrStyle10K

1

Thank you very much for the wonderful work. I have a question about the evaluation of Table 2 in this paper. [FlickrStyle10K](https://zhegan27.github.io/Papers/FlickrStyle_v0.9.zip) provides only stylized text (7000 captions) for the...

LiLiParty

About using the Sentcap dataset and setting parameters for train.py

5

Dear author, I would like to use this code on the Senticap dataset. May I ask for the parameter settings for train.py, such as the number of epochs, the backbone...

Rouchestand

about the performance of the Zerocap demonstrated in this paper

1

Thanks for your amazing work on the zero-shot captioning task. As shown in Table 1 of this paper, the zerocap's performance on COCO is as follows:  however, it seems...

wanboyang

about the parameters of train.py

1

Hello, thanks for sharing the wonderful code! Could you please tell me how to configure the parameters of the train.py file to obtain the effect of the published model, or...

tianguang2525

Different results at CiDER metric in paper

1

Hi there, firstly thanks for sharing wonderful project! Can you share the embedding model and parameter values ​​that produced the best performance in the CiDER metric in table1 and fig3?...

taewhankim

About the type of gpt2

1

Hi, Thanks for your amazing work! I have a question about the type of GPT2. You have mentioned that you use gpt2 large as your langauge model (In section A.1),...

zjr2000