ValueError: operands could not be broadcast together with shapes (152960,) (458880,)

[OkGuai]

I'm getting the following error when I try to infer from an image.

• NUM_GPUS=1
• JOB_NAME=painter_vit_large
• CKPT_FILE=painter_vit_large.pth
• PROMPT=ADE_train_00001098
• SIZE=448
• MODEL=painter_vit_large_patch16_input896x448_win_dec64_8glb_sl1
• CKPT_PATH=premodel/painter_vit_large.pth
• DST_DIR=models_inference/premodel/ade20k_semseg_inference_painter_vit_large.pth_ADE_train_00001098_size448
• python eval/ade20k_semantic/ADE20kSemSegEvaluatorCustom.py --pred_dir models_inference/premodel/ade20k_semseg_inference_painter_vit_large.pth_ADE_train_00001098_size448
  10
  10
  loading predictions
  processing
  0%| | 0/10 [00:00<?, ?it/s]
  Traceback (most recent call last):
  File "/mnt/workspace/Painter/Painter/eval/ade20k_semantic/ADE20kSemSegEvaluatorCustom.py", line 178, in
  evaluator.process(inputs, outputs)
  File "/mnt/workspace/Painter/Painter/eval/ade20k_semantic/ADE20kSemSegEvaluatorCustom.py", line 101, in process
  (self._num_classes + 1) * pred.reshape(-1) + gt.reshape(-1),
  ValueError: operands could not be broadcast together with shapes (152960,) (458880,)

[OkGuai]

Any help would be very much appreciated.