You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
你好,我尝试将GOT-OCR导出为onnx,但是遭遇了如下错误: AttributeError: 'GOT' object has no attribute 'image_start_id'
我仔细查看后,发现GOT类和LLM类里都没有初始化self.image_start_id,翻看了相应的config.json文件,也没有image_start_id参数,只有一个image_start_token。
于是我手动在GOT类里初始化了一个self.image_start_id=151857,现在运行导出代码没有报错,结果如下:
你好,我尝试将GOT-OCR导出为onnx,但是遭遇了如下错误:
AttributeError: 'GOT' object has no attribute 'image_start_id'
我仔细查看后,发现GOT类和LLM类里都没有初始化
self.image_start_id
,翻看了相应的config.json文件,也没有image_start_id参数,只有一个image_start_token。于是我手动在GOT类里初始化了一个
self.image_start_id=151857
,现在运行导出代码没有报错,结果如下:但发现最终没有保存任何的onnx文件,文件夹里为空。这是哪里出了问题?我的执行命令如下:
python llm-export/llm_export.py --path="GOT_weights/" --export --export_test --onnx_path="onnx/"
The text was updated successfully, but these errors were encountered: