main/version3.x/pipeline_usage/PaddleOCR-VL-NVIDIA-Blackwell #17440
Replies: 7 comments 1 reply
-
|
你好,请问PaddleOCR-vl生成的json文件,有自带的解析成word方法吗 |
Beta Was this translation helpful? Give feedback.
-
|
之前的版本通过PaddleX 高稳定性服务化部署方案基于 NVIDIA Triton Inference Server 打造,可以修改config_gpu.pbtxt指定每一设备上放置的实例数量。 |
Beta Was this translation helpful? Give feedback.
-
|
你好,使用纯cpu跑,解析一个png大概需要多久,我本地解析很慢,大概需要几分钟,如果使用GPU会很快吗 |
Beta Was this translation helpful? Give feedback.
-
|
我在开启版面分析检测后,如果印章区域的内容与table部分也重叠,则table的部分未识别,如果解决这个问题? |
Beta Was this translation helpful? Give feedback.
-
|
文档里提到的参数markdown_ignore_labels,在框架中并没有得到支持ValueError: Unknown argument: markdown_ignore_labels |
Beta Was this translation helpful? Give feedback.
-
|
ModuleNotFoundError: No module named 'paddleformers.trl' |
Beta Was this translation helpful? Give feedback.
-
|
"您可以分别从 此处 和 此处 获取 Compose 文件与环境变量配置文件并下载到本地,然后在刚刚下载的文件所在目录下执行以下命令启动服务器" |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
main/version3.x/pipeline_usage/PaddleOCR-VL-NVIDIA-Blackwell
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
http://www.paddleocr.ai/main/version3.x/pipeline_usage/PaddleOCR-VL-NVIDIA-Blackwell.html
Beta Was this translation helpful? Give feedback.
All reactions