RokiesHy@cv comments

Results 5 comments of


                                            RokiesHy@cv

RUNNING --- results/tracking/dense/euroc/V1_01_easy/0 [W BinaryOps.cpp:467] Warning: floor_divide is deprecated, and will be removed in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). (function operator())

> and run without gui?

Add image encoder onnx export

> > > ![image](https://user-images.githubusercontent.com/120021259/239157871-2498affc-87ae-4eba-9f92-476d1c8d8fd6.png) 我转了之后生成很多这种小算子，这个转出结果是正常的吗？怎么合到一起呢？ > > > > > > 你导出的是vit_h模型吗？使用vit_h模型由于大小超过2g，pytorch会分别保存参数和网络结构，你在加载的时候将参数导入应该就行了，具体你看一下onnxruntime的文档吧 > > 是的，我用的vit_h模型，感谢回复！！你好，vit_h模型encoder和decoder转onnx你使用成功了吗？

too many values to unpack (expected 2)

same error

too many values to unpack (expected 2)

> 有人解决了吗 change app.py line 169 (outputs,_) = GLEEmodel(infer_image, prompt_list, task="coco", batch_name_list=batch_category_name, is_train=False) to (outputs,_) = GLEEmodel(infer_image, prompt_list, task="coco", batch_name_list=batch_category_name, is_train=False)[0] same for line 175

About Network Connect

> > > I have already solved this problem. Thank you for your help！ > > > > > > hello, same question we meet, could you share your step-by-step...