GOT-OCR 离线图像识别技术易语言源码

虚vs伪 · 发表于 2024-12-26 16:51:24

本帖最后由虚vs伪于 2024-12-26 16:52 编辑

好不容易下载解压运行了，结果报错。

Loading language config...
Loading config......
正在导入库......
正在加载模型......
模型加载完成，正在启动 Webui......
* Serving Flask app 'myhttp'
* Debug mode: off
WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
* Running on all addresses (0.0.0.0)
* Running on http://127.0.0.1:5000
* Running on http://192.168.9.101:5000
Press CTRL+C to quit
test
uploads/ocr.png
The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.
The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
The `seen_tokens` attribute is deprecated and will be removed in v4.41. Use the `cache_position` model input instead.
F:\GOT-OCR\python\lib\site-packages\transformers\models\qwen2\modeling_qwen2.py:580: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:555.)
attn_output = torch.nn.functional.scaled_dot_product_attention(
127.0.0.1 - - [26/Dec/2024 15:49:01] "POST /ocr HTTP/1.1" 200 -