The operation is unstable, and when trying to calculate a metric within a data set, it frequently encounters errors and stops.

YujieLu10 / LLMScore

LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation

121 stars 8 forks source link

The operation is unstable, and when trying to calculate a metric within a data set, it frequently encounters errors and stops. #5

Open Enderfga opened 1 year ago

Enderfga commented 1 year ago

  File "LLMScore/llm_evaluator/evaluation_instruction.py", line 40, in generate_score_with_rationale
    overall, error_counting, overall_rationale, error_counting_rationale = response.split("\n")[:4]
ValueError: not enough values to unpack (expected 4, got 3)