AdvancedLiterateMachinery
AdvancedLiterateMachinery copied to clipboard
A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.
DocXChain OCR 识别较慢,CPU 占用率过高,但是 GPU 占用率确不高,请问是什么原因导致的?
lore-tsr训练时输出的这些参数都代表什么意义,哪位大佬可以帮忙解释下啊 
Loss is nan, stopping training {'pt_loss': tensor(nan, device='cuda:0', grad_fn=), 'poly_loss': tensor(nan, device='cuda:0', grad_fn=), 'rec_loss': tensor(3.2648, device='cuda:0', grad_fn=)}
请问下,cv_resnet18_ocr-detection-line-level_damo,这么小的模型为啥开销这么大,是有什么config参数没改吗? 除了ocr-detection, 其他模块模型开销都在1s以内 我的环境是:cuda11.8, cudnn8.6.0, tensorflow2.11.0
# TypeError in create_grid_input.py: Mismatch in save_pkl_file arguments ## Issue Summary A TypeError is occurring in the `create_grid_input.py` script due to a mismatch between the number of arguments in the...
# TypeError in create_grid_input.py ## Description of the Issue When running the script, the following error occurs: ``` File "/Users/i_manav.gupta/VGT_V4/VGT/object_detection/create_grid_input.py", line 215, in save_pkl_file(grid, args.output, f"page_{page}", page, args.model) TypeError: save_pkl_file()...
Running the VGT inference script fails because the model file at https://layoutlm.blob.core.windows.net/dit/dit-pts/dit-base-224-p16-500k-62d53a.pth cannot be publicly accessed due to an HTTP 409 error.
Does anyone train LevOCR with long sentences ? NAR or Iterative Transformer is quite bad when they recognize long sequences, I want to know LevOCR can recognize long sentences like...
Please let me know the training hardware setting(GPU) for Omniparser How long does it take to pretrain the model?