search

VikParuchuri / surya

OCR, layout analysis, reading order, line detection in 90+ languages
https://www.datalab.to
GNU General Public License v3.0
9.05k stars 565 forks source link

Unable to perform multi-image inference #134

Open qrsssh opened 3 weeks ago

qrsssh commented 3 weeks ago

@VikParuchuri read order model Unable to perform multi-batch inference, error message when reasoning on multiple images code: model = load_model(device="cpu", dtype=torch.float32)

processor = load_processor()

ii = Image.open(IMAGE_PATH)

jj = ii.copy() kk = ii.copy() inputs = [ii, jj, kk] bb = [bboxes, list(bboxes), list(bboxes)]

order_predictions = batch_ordering(inputs, bb, model, processor, batch_size=4)

error:

Loaded reading order model vikp/surya_order on device cpu with dtype torch.float32 xxx vikp/surya_order Traceback (most recent call last): File "D:\code\pycharm\OCR_LAYOUT - \sb.py", line 147, in order_predictions = batch_ordering(inputs, bb, model, processor, batch_size=4) File "D:\code\pycharm\OCR_LAYOUT - \surya\ordering.py", line 70, in batch_ordering return_dict = model( File "C:\Users\AppData\Roaming\Python\Python39\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "C:\Users\AppData\Roaming\Python\Python39\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl return forward_call(*args, *kwargs) File "D:\code\pycharm\OCR_LAYOUT - \surya\model\ordering\encoderdecoder.py", line 64, in forward decoder_outputs = self.decoder( File "C:\Users\AppData\Roaming\Python\Python39\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl return self._call_impl(args, kwargs) File "C:\Users\AppData\Roaming\Python\Python39\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl return forward_call(*args, kwargs) File "D:\code\pycharm\OCR_LAYOUT - \surya\model\ordering\decoder.py", line 526, in forward outputs = self.model.decoder( File "C:\Users\AppData\Roaming\Python\Python39\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "C:\Users\AppData\Roaming\Python\Python39\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl return forward_call(args, kwargs) File "D:\code\pycharm\OCR_LAYOUT - \surya\model\ordering\decoder.py", line 342, in forward inputs_embeds = self.embed_tokens(input_boxes, input_boxes_counts, past_key_values_length) self.embed_scale File "C:\Users\AppData\Roaming\Python\Python39\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl return self._call_impl(args, kwargs) File "C:\Users\AppData\Roaming\Python\Python39\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl return forward_call(*args, *kwargs) File "D:\code\pycharm\OCR_LAYOUT - \surya\model\ordering\decoder.py", line 261, in forward coord_embeds = self.x1_embed(x1) + self.y1_embed(y1) + self.x2_embed(x2) + self.y2_embed(y2) File "C:\Users\AppData\Roaming\Python\Python39\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl return self._call_impl(args, kwargs) File "C:\Users\AppData\Roaming\Python\Python39\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "C:\Users\AppData\Roaming\Python\Python39\site-packages\torch\nn\modules\sparse.py", line 162, in forward return F.embedding( File "C:\Users\AppData\Roaming\Python\Python39\site-packages\torch\nn\functional.py", line 2233, in embedding return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse) IndexError: index out of range in self

Process finished with exit code 1

qrsssh commented 2 weeks ago

sorry my code reason, close this issue