I met an error:ValueError: operands could not be broadcast together with shapes (480,672) (1,1,3)

[libbo1006]

When I run "python test.py ctdet --exp_id coco_dla --keep_res --load_model ../models/ctdet_coco_dla_2x.pth", there is an error :
coco_dla |#### | [653/5000]|Tot: 0:00:59 |ETA: 0:06:07 |tot 0.046s (0.053s) |load 0.000s (0.000s) |pre 0.000s (0.001s) |net 0.040s (0.046s) |dec 0.003s (0.003s) |post 0.003s (0.003s) |merge 0.000s (0.000s) [[ 96 133 171 ... 206 207 217]
[ 89 120 131 ... 212 216 212]
[ 92 130 155 ... 208 219 208]
...
[126 122 129 ... 90 96 97]
[117 120 124 ... 100 93 91]
[101 107 109 ... 120 108 117]]
Traceback (most recent call last):
File "test.py", line 127, in
prefetch_test(opt)
File "test.py", line 70, in prefetch_test
for ind, (img_id, pre_processed_images) in enumerate(data_loader):
File "c:\programdata\anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 345, in next
data = self._next_data()
File "c:\programdata\anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 385, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "c:\programdata\anaconda3\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "c:\programdata\anaconda3\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "test.py", line 42, in getitem
images[scale], meta[scale] = self.pre_process_func(image, scale)
File "E:\CenterNet-windows-master\CenterNet-windows-master\src\lib\detectors\base_detector.py", line 57, in pre_process
inp_image = ((inp_image / 255. - self.mean) / self.std).astype(np.float32)
ValueError: operands could not be broadcast together with shapes (480,672) (1,1,3)

I used pytorch 1.4.0 torchvision 0.5.0 python 3.7.4