lmms_eval/tasks/llava-bench-coco/utils.py [148:198]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    category_review_dict = {"question": question, "ans1": ans1, "ans2": ans2, "context": context, "category": category, "review": review, "scores": scores, "eval_model": model_name, "content": content}

    non_category_review_dict = deepcopy(category_review_dict)
    non_category_review_dict["scores"] = [-999, -999]

    data_dict = {}
    for m in LLAVA_W_METRICS:
        if m == metric:
            data_dict[m] = category_review_dict
        else:
            data_dict[m] = non_category_review_dict
    data_dict["gpt_eval_llava_all"] = category_review_dict

    # return {"gpt_eval_llava_all": review_dict}
    return data_dict


def llava_conv_aggregation(results):
    return llava_aggregation(results, "conv")


def llava_complex_aggregation(results):
    return llava_aggregation(results, "complex")


def llava_detail_aggregation(results):
    return llava_aggregation(results, "detail")


def llava_all_aggregation(results):
    return llava_aggregation(results, "all")


def llava_aggregation(results, category):
    try:
        scores = []
        for result in results:
            if -999 in result["scores"]:
                continue
            scores.append(result["scores"])

        stats = np.asarray(scores).mean(0).tolist()
        stats = [round(x, 3) for x in stats]
        # gpt4_score_percentage = stats[0] * 10
        # model_score_percentage = stats[1] * 10
        # eval_logger.info(f"Category: {category}")
        # eval_logger.info(f"GPT4 Score: {gpt4_score_percentage:.1f}%")
        # eval_logger.info(f"Model Score: {model_score_percentage:.1f}%")
        # eval_logger.info("=========================")
        return round(stats[1] / stats[0] * 100, 1)
    except Exception as e:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



lmms_eval/tasks/llava-in-the-wild/utils.py [145:195]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    category_review_dict = {"question": question, "ans1": ans1, "ans2": ans2, "context": context, "category": category, "review": review, "scores": scores, "eval_model": model_name, "content": content}

    non_category_review_dict = deepcopy(category_review_dict)
    non_category_review_dict["scores"] = [-999, -999]

    data_dict = {}
    for m in LLAVA_W_METRICS:
        if m == metric:
            data_dict[m] = category_review_dict
        else:
            data_dict[m] = non_category_review_dict
    data_dict["gpt_eval_llava_all"] = category_review_dict

    # return {"gpt_eval_llava_all": review_dict}
    return data_dict


def llava_conv_aggregation(results):
    return llava_aggregation(results, "conv")


def llava_complex_aggregation(results):
    return llava_aggregation(results, "complex")


def llava_detail_aggregation(results):
    return llava_aggregation(results, "detail")


def llava_all_aggregation(results):
    return llava_aggregation(results, "all")


def llava_aggregation(results, category):
    try:
        scores = []
        for result in results:
            if -999 in result["scores"]:
                continue
            scores.append(result["scores"])

        stats = np.asarray(scores).mean(0).tolist()
        stats = [round(x, 3) for x in stats]
        # gpt4_score_percentage = stats[0] * 10
        # model_score_percentage = stats[1] * 10
        # eval_logger.info(f"Category: {category}")
        # eval_logger.info(f"GPT4 Score: {gpt4_score_percentage:.1f}%")
        # eval_logger.info(f"Model Score: {model_score_percentage:.1f}%")
        # eval_logger.info("=========================")
        return round(stats[1] / stats[0] * 100, 1)
    except Exception as e:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -