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

Please run accumulate() first

Error message

Please run accumulate() first

What it means

COCO's summarize() requires evaluation results accumulated by accumulate() first; the internal self.eval is None until then. Calling summarize() before accumulate() raises a generic Exception telling the user the required prior step was skipped.

Source

Thrown at pytorch_object_detection/train_coco_dataset/validation.py:89

    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 main(parser_data):
    device = torch.device(parser_data.device if torch.cuda.is_available() else "cpu")
    print("Using {} device training.".format(device.type))

    data_transform = {
        "val": transforms.Compose([transforms.ToTensor()])
    }

    # read class_indict
    label_json_path = './coco91_indices.json'
    assert os.path.exists(label_json_path), "json file {} dose not exist.".format(label_json_path)
    with open(label_json_path, 'r') as f:
        category_index = json.load(f)

View on GitHub (pinned to 1ec3fe6f37)

Solutions

1. Call evaluator.accumulate() before summarize()
2. Ensure evaluate() ran and predictions were loaded (evaluator.update() calls) before accumulate
3. If summarizing multiple times, reuse the same evaluator after a single accumulate

Example fix

// before
coco_evaluator = COCOeval(coco, iouType='bbox')
coco_evaluator.evaluate()
stats, print_info = summarize(coco_evaluator)
// after
coco_evaluator = COCOeval(coco, iouType='bbox')
coco_evaluator.evaluate()
coco_evaluator.accumulate()
stats, print_info = summarize(coco_evaluator)

def safe_summarize(evaluator):
    if getattr(evaluator, 'eval', None) is None:
        evaluator.accumulate()
    return evaluator.summarize()

try:
    stats, print_info = summarize(coco_evaluator)
except Exception as e:
    if 'Please run accumulate() first' in str(e):
        coco_evaluator.accumulate()
        stats, print_info = summarize(coco_evaluator)
    else:
        raise

When it happens

Trigger: Calling coco_evaluator.summarize() immediately after constructing a COCOeval object, without first calling accumulate().

Common situations: Custom evaluation scripts that build COCOeval but forget the accumulate() step; reordering calls after refactoring; catching only some stats and calling summarize twice on a fresh evaluator.

Related errors

• expected stages_repeats as list of 3 positive ints
• expected stages_out_channels as list of 5 positive ints
• image: {} isn't RGB mode.
• not find GPU device for training.
• dataset have {} classes, but input {}

AI-assisted analysis of WZMIAOMIAO/deep-learning-for-image-processing@1ec3fe6f37 (2026-08-30). Data as JSON: /api/errors/f92c473cc70287a9. Report an issue: GitHub.