The original training data file about visorgpt

[Sierkinhane]

Hi, sorry for the late relay cause I'm too busy these days. I would like to first share th preprocessed .txt file of COCO box at here and you can use the below script to process it to .pt file:

cd ./train
python3 preprocess.py --corpus_path train_box.txt \
                      --vocab_path models/google_uncased_en_coord_vocab.txt \
                      --dataset_path train_seq.pt --processes_num 8 \
                      --seq_length 1024 --tgt_seq_length 1024 --data_processor lm

I will try to provide the code for converting box/mask/keypoint annotations of .json to sequences .txt in the coming days. :)

[Sierkinhane]

Hello, I will clean the code and prepare the instruction in the coming days. Maybe a week.

[weineuro]

Great, looking forward to your update.

[michal-wojdylak-wttech]

Hi, thanks @Sierkinhane for show how to create pt file from txt :)

[Crd1140234468]

Hi, sorry for the late relay cause I'm too busy these days. I would like to first share th preprocessed .txt file of COCO box at here and you can use the below script to process it to .pt file:

cd ./train
python3 preprocess.py --corpus_path train_box.txt \
                      --vocab_path models/google_uncased_en_coord_vocab.txt \
                      --dataset_path train_seq.pt --processes_num 8 \
                      --seq_length 1024 --tgt_seq_length 1024 --data_processor lm

I will try to provide the code for converting box/mask/keypoint annotations of .json to sequences .txt in the coming days. :)

Hello, if I want to train Object Centric Bounding-Box, the content of corpus is similar to "box; object centric; large; 1; 0; great white shark; [xmin 95 ymin 66 xmax 510 ymax 310]", or "box ; object centric; large; 1; 0; [ great white shark xmin 95 ymin 66 xmax 510 ymax 310 ]?

[Sierkinhane]

Hi, the second prompt is for continuous generation or scene completion for multiple objects. If only one object is involved in an image, the first prompt is sufficient.

[Crd1140234468]

Hi, the second prompt is for continuous generation or scene completion for multiple objects. If only one object is involved in an image, the first prompt is sufficient.

Thank you, I really appreciate your reply

[VicZlq]

Hello! Thank you so much for your work! Do you have any plans to make keypoint annotations .txt file public recently?

[Sierkinhane]

Exactly. I'm quite busy these months, but I plan to update the repository with the complete files next month. The txt files of cocokeypoints and crowdpose are available at here and here.

[VicZlq]

Thank you very much for your reply! May I ask if they are both processed with preprocess.py for pre-processing? Also, the two links you provided both seem to be crowdpose.txt files：）

[Sierkinhane]

Hi, I have updated the link. You can merge these txt files into one file and process it using preprocess.py.

[VicZlq]

Thank you very much for your prompt reply! There's a question I'd like to ask. I see that in the keypoint data, there is “person, person; [ a ”as well as “[ person a...], [ person a...]"Two types, does this affect the effectiveness of the training? Because I see in the demo, the type of seq_prompt is in the format of [ person.

[Sierkinhane]

They are two kinds of prompts and will not affect the modeling a lot. Maybe you can refer to the paper for details.

[VicZlq]

Thank you very much, I re-read the paper again. However, I have now trained and saved the file "visorgpt_dagger_train_seq.bin-200000" (430M), how do I handle it as "visorgpt_dagger_train_seq.bin/200000/mp_rank_00_model_states. pt" such file type?

[Sierkinhane]

It seems that you didn't use the deepspeed strategy. You can try to set --load_model_path as the .bin file.

[VicZlq]

OK! Your suggestion is valid! Looking forward to your complete inference code and your subsequent exciting work :)

[Sierkinhane]

Great! Thank you.