Skip to content

Validation Accuracy different from paper #20

@soonchangAI

Description

@soonchangAI

Hi, the validation accuracy I calculated for the fine-tuned models are different from the paper.
Command:

python -m torch.distributed.launch --nproc_per_node 2  tools/run.py --tasks vqa --datasets m4c_textvqa --model m4c_split \
--config $config \
--save_dir $folder \
--run_type val \
--resume_file $finetuned_model \
training_parameters.distributed True 

I observed changing the batch size results in different values.

Val accuracy for batch size = 32 Val acc for batch size = 128 In paper
TextVQA TAP (base) 49.87 49.53 49.91
TextVQA TAP (additional data) 54.31 54.13 54.71

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions