ACL-2025 / mme_all.sh
Wendy-Fly's picture
Upload mme_all.sh with huggingface_hub
51b2cb5 verified
#!/bin/bash
python -m llava.eval.model_vqa_loader \
--model-path checkpoints/llava-v1.5-7b-task-llava_image_tune_logits_NImg_Gas_5P_0203 \
--question-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/llava_mme.jsonl \
--image-folder /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/MME_Benchmark_release_version \
--answers-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/answers/llava_image_tune_logits_NImg_Gas_5P_0203.jsonl \
--temperature 0 \
--conv-mode vicuna_v1
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME
python convert_answer_to_mme.py --experiment llava_image_tune_logits_NImg_Gas_5P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/eval_tool
python calculation.py --results_dir answers/llava_image_tune_logits_NImg_Gas_5P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/NIPS_2025/LLaVA
#!/bin/bash
python -m llava.eval.model_vqa_loader \
--model-path checkpoints/llava-v1.5-7b-task-llava_image_tune_logits_NImg_Gas_10P_0203 \
--question-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/llava_mme.jsonl \
--image-folder /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/MME_Benchmark_release_version \
--answers-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/answers/llava_image_tune_logits_NImg_Gas_10P_0203.jsonl \
--temperature 0 \
--conv-mode vicuna_v1
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME
python convert_answer_to_mme.py --experiment llava_image_tune_logits_NImg_Gas_10P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/eval_tool
python calculation.py --results_dir answers/llava_image_tune_logits_NImg_Gas_10P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/NIPS_2025/LLaVA
#!/bin/bash
python -m llava.eval.model_vqa_loader \
--model-path checkpoints/llava-v1.5-7b-task-llava_image_tune_logits_NImg_Gas_20P_0203 \
--question-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/llava_mme.jsonl \
--image-folder /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/MME_Benchmark_release_version \
--answers-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/answers/llava_image_tune_logits_NImg_Gas_20P_0203.jsonl \
--temperature 0 \
--conv-mode vicuna_v1
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME
python convert_answer_to_mme.py --experiment llava_image_tune_logits_NImg_Gas_20P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/eval_tool
python calculation.py --results_dir answers/llava_image_tune_logits_NImg_Gas_20P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/NIPS_2025/LLaVA
#!/bin/bash
python -m llava.eval.model_vqa_loader \
--model-path checkpoints/llava-v1.5-7b-task-llava_image_tune_logits_NImg_Gas_40P_0203 \
--question-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/llava_mme.jsonl \
--image-folder /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/MME_Benchmark_release_version \
--answers-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/answers/llava_image_tune_logits_NImg_Gas_40P_0203.jsonl \
--temperature 0 \
--conv-mode vicuna_v1
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME
python convert_answer_to_mme.py --experiment llava_image_tune_logits_NImg_Gas_40P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/eval_tool
python calculation.py --results_dir answers/llava_image_tune_logits_NImg_Gas_40P_0203
##################################################################################################################
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/NIPS_2025/LLaVA
#!/bin/bash
python -m llava.eval.model_vqa_loader \
--model-path checkpoints/llava-v1.5-7b-task-llava_image_tune_logits_NImg_Rand_5P_0203 \
--question-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/llava_mme.jsonl \
--image-folder /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/MME_Benchmark_release_version \
--answers-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/answers/llava_image_tune_logits_NImg_Rand_5P_0203.jsonl \
--temperature 0 \
--conv-mode vicuna_v1
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME
python convert_answer_to_mme.py --experiment llava_image_tune_logits_NImg_Rand_5P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/eval_tool
python calculation.py --results_dir answers/llava_image_tune_logits_NImg_Rand_5P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/NIPS_2025/LLaVA
#!/bin/bash
python -m llava.eval.model_vqa_loader \
--model-path checkpoints/llava-v1.5-7b-task-llava_image_tune_logits_NImg_Rand_10P_0203 \
--question-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/llava_mme.jsonl \
--image-folder /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/MME_Benchmark_release_version \
--answers-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/answers/llava_image_tune_logits_NImg_Rand_10P_0203.jsonl \
--temperature 0 \
--conv-mode vicuna_v1
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME
python convert_answer_to_mme.py --experiment llava_image_tune_logits_NImg_Rand_10P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/eval_tool
python calculation.py --results_dir answers/llava_image_tune_logits_NImg_Rand_10P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/NIPS_2025/LLaVA
#!/bin/bash
python -m llava.eval.model_vqa_loader \
--model-path checkpoints/llava-v1.5-7b-task-llava_image_tune_logits_NImg_Rand_20P_0203 \
--question-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/llava_mme.jsonl \
--image-folder /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/MME_Benchmark_release_version \
--answers-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/answers/llava_image_tune_logits_NImg_Rand_20P_0203.jsonl \
--temperature 0 \
--conv-mode vicuna_v1
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME
python convert_answer_to_mme.py --experiment llava_image_tune_logits_NImg_Rand_20P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/eval_tool
python calculation.py --results_dir answers/llava_image_tune_logits_NImg_Rand_20P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/NIPS_2025/LLaVA
#!/bin/bash
python -m llava.eval.model_vqa_loader \
--model-path checkpoints/llava-v1.5-7b-task-llava_image_tune_logits_NImg_Rand_40P_0203 \
--question-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/llava_mme.jsonl \
--image-folder /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/MME_Benchmark_release_version \
--answers-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/answers/llava_image_tune_logits_NImg_Rand_40P_0203.jsonl \
--temperature 0 \
--conv-mode vicuna_v1
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME
python convert_answer_to_mme.py --experiment llava_image_tune_logits_NImg_Rand_40P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/eval_tool
python calculation.py --results_dir answers/llava_image_tune_logits_NImg_Rand_40P_0203
############################################################################################################################
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/NIPS_2025/LLaVA
#!/bin/bash
python -m llava.eval.model_vqa_loader \
--model-path checkpoints/llava-v1.5-7b-task-llava_image_tune_logits_NImg_High_5P_0203 \
--question-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/llava_mme.jsonl \
--image-folder /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/MME_Benchmark_release_version \
--answers-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/answers/llava_image_tune_logits_NImg_High_5P_0203.jsonl \
--temperature 0 \
--conv-mode vicuna_v1
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME
python convert_answer_to_mme.py --experiment llava_image_tune_logits_NImg_High_5P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/eval_tool
python calculation.py --results_dir answers/llava_image_tune_logits_NImg_High_5P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/NIPS_2025/LLaVA
#!/bin/bash
python -m llava.eval.model_vqa_loader \
--model-path checkpoints/llava-v1.5-7b-task-llava_image_tune_logits_NImg_High_10P_0203 \
--question-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/llava_mme.jsonl \
--image-folder /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/MME_Benchmark_release_version \
--answers-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/answers/llava_image_tune_logits_NImg_High_10P_0203.jsonl \
--temperature 0 \
--conv-mode vicuna_v1
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME
python convert_answer_to_mme.py --experiment llava_image_tune_logits_NImg_High_10P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/eval_tool
python calculation.py --results_dir answers/llava_image_tune_logits_NImg_High_10P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/NIPS_2025/LLaVA
#!/bin/bash
python -m llava.eval.model_vqa_loader \
--model-path checkpoints/llava-v1.5-7b-task-llava_image_tune_logits_NImg_High_20P_0203 \
--question-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/llava_mme.jsonl \
--image-folder /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/MME_Benchmark_release_version \
--answers-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/answers/llava_image_tune_logits_NImg_High_20P_0203.jsonl \
--temperature 0 \
--conv-mode vicuna_v1
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME
python convert_answer_to_mme.py --experiment llava_image_tune_logits_NImg_High_20P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/eval_tool
python calculation.py --results_dir answers/llava_image_tune_logits_NImg_High_20P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/NIPS_2025/LLaVA
#!/bin/bash
python -m llava.eval.model_vqa_loader \
--model-path checkpoints/llava-v1.5-7b-task-llava_image_tune_logits_NImg_High_40P_0203 \
--question-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/llava_mme.jsonl \
--image-folder /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/MME_Benchmark_release_version \
--answers-file /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/answers/llava_image_tune_logits_NImg_High_40P_0203.jsonl \
--temperature 0 \
--conv-mode vicuna_v1
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME
python convert_answer_to_mme.py --experiment llava_image_tune_logits_NImg_High_40P_0203
cd /inspire/hdd/ws-ba572160-47f8-4ca1-984e-d6bcdeb95dbb/a100-maybe/albus/DataSet/LLaVA-VQA-Eval/MME/eval_tool
python calculation.py --results_dir answers/llava_image_tune_logits_NImg_High_40P_0203