In what order should I reproduce the paper? about videogpt-plus HOT 6 OPEN

In the official example, the two benchmarks each have their own weights

VideoGPT-plus/MBZUAI/VideoGPT-plus_Phi3-mini-4k/mvbench
VideoGPT-plus/MBZUAI/VideoGPT-plus_Phi3-mini-4k/vcgbench

from videogpt-plus.

step1
pretrain_projector_image_encoder.sh
step2
pretrain_projector_video_encoder.sh
step3
finetune_dual_encoder.sh
step4
eval/vcgbench/inference/run_ddp_inference.sh
step5
eval/vcgbench/gpt_evaluation/vcgbench_evaluate.sh

So besides the above setp123. and step45, is there any other information or steps I missed?

from videogpt-plus.

from .dataset_config import *

DataConfig = {
    "PRETRAINING": [CC3M_595K, COCO_CAP, COCO_REG, COCO_REC],

    "FINETUNING": [CONV_VideoChatGPT, VCG_HUMAN, VCG_PLUS_112K, CAPTION_VIDEOCHAT, CLASSIFICATION_K710, CLASSIFICATION_SSV2, CONV_VideoChat1, REASONING_NExTQA, REASONING_CLEVRER_QA, REASONING_CLEVRER_MC, VQA_WEBVID_QA],

    "VCGBench_FINETUNING": [CONV_VideoChatGPT, VCG_HUMAN, VCG_PLUS_112K, CAPTION_VIDEOCHAT, CONV_VideoChat1, VQA_WEBVID_QA],
    "MVBench_FINETUNING": [CLASSIFICATION_K710, CLASSIFICATION_SSV2, CONV_VideoChatGPT, REASONING_NExTQA, REASONING_CLEVRER_QA, REASONING_CLEVRER_MC, VQA_WEBVID_QA],

}

from videogpt-plus.

I didn't use VCGBench_FINETUNING and MVBench_FINETUNING. Will there be any problems?

from videogpt-plus.

Hi @rixejzvdl649,

Thank you for your interest in our work and providing the detailed information about your question. The steps you mentioned to reproduce our results (pretraining + finetuning + evaluation) are correct.

However, please note that we finetune two models/variants of VideoGPT+. The first variant finetuned using VCGBench_FINETUNING is used to evaluate on VCGBench and VCGBench-Diverse, and the second variant finetuned on MVBench_FINETUNING is used to evaluate on MVBench.

I hope it will help. Please let me know if you have any questions.

from videogpt-plus.

@mmaaz60 hello, does stage1 and stage2 can parallel?

from videogpt-plus.