qingqinghu1026

Results 9 comments of qingqinghu1026

terminate called after throwing an instance of 'cv::Exception' what(): OpenCV(4.0.1) /.../workspace/opencv-4/opencv-4.0.1/modules/dnn/src/layers/eltwise_layer.cpp:110: error: (-215:Assertion failed) inputs.size() >= 2 in function 'getMemoryShapes' 已放弃 (核心已转储) 必须使用4.5以上的版本吗?这个core是因为版本不对造成的吗

Package Version ------------------ ----------- accelerate 0.27.2 aiohttp 3.9.3 aiosignal 1.3.1 async-timeout 4.0.3 attrs 23.2.0 auto_gptq 0.7.1 Brotli 1.0.9 certifi 2024.2.2 chardet 5.2.0 charset-normalizer 2.0.4 coloredlogs 15.0.1 datasets 2.18.0 dill 0.3.8...

> auto_gptq的版本太高了,降回0.4.2就可以了 安装auto_gptq 0.4.2后,显示不支持 ImportError: Found an incompatible version of auto-gptq. Found version 0.4.2+cu117, but only version above 0.4.99 are supported

> > > auto_gptq的版本太高了,降回0.4.2就可以了 > > > 安装auto_gptq 0.4.2后,显示不支持 > > > ImportError: Found an incompatible version of auto-gptq. Found version 0.4.2+cu117, but only version above 0.4.99 are supported >...

> > > > > auto_gptq的版本太高了,降回0.4.2就可以了 > > > > > 安装auto_gptq 0.4.2后,显示不支持 > > > > > ImportError: Found an incompatible version of auto-gptq. Found version 0.4.2+cu117, but only...

> 这个问题我换成了14b-int4就没问题了,我之前跑的是14b-int8,感觉是机器跑int8的量化处理不过来 >我的还是不行,7B-int4 报这个错误,7B-int8能运行,但是答非所问,类似出现幻觉

> 使用您提供的convert-onnx进行yolo fastest v2内pth转换时,提示以下报错 D:\labelImg\yolofastv2\convert_onnx>python pytorch2onnx.py --data coco.data --weights coco.pth load param... D:\labelImg\yolofastv2\convert_onnx\model\backbone\shufflenetv2.py:59: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't...