YanChuan

Results 10 issues of YanChuan

按照官方教程配置好环境后,报如下错: Now, onnx2paddle support convert onnx model opset_verison [9],opset_verison of your onnx model is 12, automatically treated as op_set: 9. Total nodes: 248 Nodes converting ... Converting node 327 ......

按照官方配置好环境后,运行报错: ![image](https://user-images.githubusercontent.com/64970397/188051340-35e051fb-207a-4640-b584-5b56b0465066.png) 按照https://github.com/PaddlePaddle/X2Paddle/issues/494 的方法 更新x2paddle后,又报下面的错: ![image](https://user-images.githubusercontent.com/64970397/188051444-07c1121b-793b-4244-b33c-a05ca73c7049.png) PaddlePaddle = 2.3.2 x2paddle 是develop分支代码git后安装 更新onnx 版本和 x2paddle后又报这个错 ![image](https://user-images.githubusercontent.com/64970397/188053687-9787a408-5b6b-4465-9537-6e8f2a14595d.png) 目前没有找到解决方法。 麻烦看一下 谢谢 wechat : ST_YangMu

ONNX

直接跑源码的qlora.py,报错 ![image](https://github.com/THUDM/SwissArmyTransformer/assets/64970397/1a231ac7-d43e-414c-a1d0-73a5c1c6180d) 给model.child = LoraLinear(100, 200, 10)改为model.child = LoraLinear(100, 200, 10,10,2)后,又报错 ![image](https://github.com/THUDM/SwissArmyTransformer/assets/64970397/a2d16427-e2a4-4178-807a-55af76c48589)

### Prerequisite - [X] I have searched [the existing and past issues](https://github.com/open-mmlab/mmyolo/issues) but cannot get the expected help. - [X] I have read the [FAQ documentation](https://mmyolo.readthedocs.io/en/latest/faq.html) but cannot get the...

能麻烦说一下eval具体该怎么做吗,非常感谢

![image](https://github.com/WangRongsheng/XrayGLM/assets/64970397/51a5f0d8-007d-46c8-8a62-2e778acca74c)

![image](https://github.com/WangRongsheng/XrayGLM/assets/64970397/db9afc1f-550f-4312-8a46-75747089a45f)

![image](https://github.com/THUDM/VisualGLM-6B/assets/64970397/f1318b9f-4b17-4035-8011-f90d0f457528)

![image](https://user-images.githubusercontent.com/64970397/184318939-c4fdb221-d7b5-48c9-b23f-bc7b739af2a7.png) ![image](https://user-images.githubusercontent.com/64970397/184318968-6376b607-3c1c-49e0-a526-1bbfddeff4b8.png) 你好,我用facev2代码和yolov5s的6.1版本训练widerface,30个epoch,怎么还没有v5s的指标高呢。是有训练方法吗?预训练权重使用的是yolov5s.pt。 (上图是yolofacev2,下图是yolov5s)

loss.py 213行报错 f self.u > 0: obji = self.BCEobj(pi[..., 4], tobj, auto_iou)