Eval Error

[tm1412]

Hello, during the evaluation on my dataset, it encounters this error. It stops and reports an error after processing a few images, and it only continues when I remove those images. This process repeats itself. Can you help me with this?

Traceback (most recent call last):
File "eval_mixNet.py", line 259, in
main(vis_dir)
File "eval_mixNet.py", line 231, in main
inference(model, test_loader, output_dir)
File "eval_mixNet.py", line 65, in inference
for i, (image, meta) in enumerate(test_loader):
File "D:\anaconda\envs\mixnet\lib\site-packages\torch\utils\data\dataloader.py", line 633, in next
data = self._next_data()
File "D:\anaconda\envs\mixnet\lib\site-packages\torch\utils\data\dataloader.py", line 677, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "D:\anaconda\envs\mixnet\lib\site-packages\torch\utils\data_utils\fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "D:\anaconda\envs\mixnet\lib\site-packages\torch\utils\data_utils\fetch.py", line 51, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "D:\OCR_AICS\MixNet\dataset\Total_Text.py", line 134, in getitem
data = self.load_img_gt(item)
File "D:\OCR_AICS\MixNet\dataset\Total_Text.py", line 108, in load_img_gt
polygons = self.parse_mat(annotation_path)
File "D:\OCR_AICS\MixNet\dataset\Total_Text.py", line 61, in parse_mat
pts = np.stack([x, y]).T.astype(np.int32)
File "<array_function internals>", line 200, in stack
File "D:\anaconda\envs\mixnet\lib\site-packages\numpy\core\shape_base.py", line 464, in stack
raise ValueError('all input arrays must have the same shape')
ValueError: all input arrays must have the same shape

[D641593]

Hello, there seems to be an error while reading the annotation.
Maybe the annonation of these images doesn't match the format.
I guess it could start by checking the annotations for these images or try removing the part of the code that reads the annotations.