WZMIAOMIAO/deep-learning-for-image-processing · error · Exception

Please run accumulate() first

Error message

Please run accumulate() first

What it means

The COCO-style evaluator's summarize computes per-area/per-maxDets stats from self.eval, which is only populated after accumulate() runs. Calling summarize (or save_info, which calls summarize) before accumulate leaves self.eval None/empty and raises Exception('Please run accumulate() first').

Source

Thrown at pytorch_object_detection/mask_rcnn/validation.py:88

    stats, print_list = [0] * 12, [""] * 12
    stats[0], print_list[0] = _summarize(1)
    stats[1], print_list[1] = _summarize(1, iouThr=.5, maxDets=self.params.maxDets[2])
    stats[2], print_list[2] = _summarize(1, iouThr=.75, maxDets=self.params.maxDets[2])
    stats[3], print_list[3] = _summarize(1, areaRng='small', maxDets=self.params.maxDets[2])
    stats[4], print_list[4] = _summarize(1, areaRng='medium', maxDets=self.params.maxDets[2])
    stats[5], print_list[5] = _summarize(1, areaRng='large', maxDets=self.params.maxDets[2])
    stats[6], print_list[6] = _summarize(0, maxDets=self.params.maxDets[0])
    stats[7], print_list[7] = _summarize(0, maxDets=self.params.maxDets[1])
    stats[8], print_list[8] = _summarize(0, maxDets=self.params.maxDets[2])
    stats[9], print_list[9] = _summarize(0, areaRng='small', maxDets=self.params.maxDets[2])
    stats[10], print_list[10] = _summarize(0, areaRng='medium', maxDets=self.params.maxDets[2])
    stats[11], print_list[11] = _summarize(0, areaRng='large', maxDets=self.params.maxDets[2])

    print_info = "\n".join(print_list)

    if not self.eval:
        raise Exception('Please run accumulate() first')

    return stats, print_info


def save_info(coco_evaluator,
              category_index: dict,
              save_name: str = "record_mAP.txt"):
    iou_type = coco_evaluator.params.iouType
    print(f"IoU metric: {iou_type}")
    # calculate COCO info for all classes
    coco_stats, print_coco = summarize(coco_evaluator)

    # calculate voc info for every classes(IoU=0.5)
    classes = [v for v in category_index.values() if v != "N/A"]
    voc_map_info_list = []
    for i in range(len(classes)):
        stats, _ = summarize(coco_evaluator, catId=i)
        voc_map_info_list.append(" {:15}: {}".format(classes[i], stats[1]))

View on GitHub (pinned to 1ec3fe6f37)

Solutions

1. Call evaluator.accumulate() before evaluator.summarize()
2. Ensure the full sequence: evaluator.synchronize_results() (or gather) -> accumulate() -> summarize() -> save_info(...)
3. Guard calls: only summarize if getattr(evaluator, 'eval', None) is not None

Example fix

// before
save_info(coco_evaluator, category_index)
// after
coco_evaluator.accumulate()
save_info(coco_evaluator, category_index)

coco_evaluator.synchronize_results() if hasattr(coco_evaluator, 'synchronize_results') else None
coco_evaluator.accumulate()
assert getattr(coco_evaluator, 'eval', None) is not None, 'accumulate produced no eval'
stats = coco_evaluator.summarize()

def can_summarize(ev):
    return getattr(ev, 'eval', None) is not None

try:
    save_info(coco_evaluator, category_index)
except Exception as e:
    if 'accumulate()' in str(e):
        coco_evaluator.accumulate()
        save_info(coco_evaluator, category_index)
    else:
        raise

When it happens

Trigger: Calling evaluator.summarize() immediately after update() without evaluator.accumulate(); calling save_info(coco_evaluator, ...) before accumulating; distributed runs where one process skipped synchronize/accumulate.

Common situations: Custom validation loops reordered incorrectly; early-exit during epoch validation; forgetting accumulate in multi-GPU evaluation after merging results.

Related errors

• Unknown iou type {}
• not support iou_type: {self.iou_type}
• not support iou_type: {self.iou_type}
• Please run accumulate() first
• Please run accumulate() first

AI-assisted analysis of WZMIAOMIAO/deep-learning-for-image-processing@1ec3fe6f37 (2026-08-30). Data as JSON: /api/errors/05349bc6a3338ccd. Report an issue: GitHub.