Huawei Sun

about evaluation

1

Dear authors, I read the code and found out that in the validate() function, you have this part: ``` input_img = rgb_data input_img_flip = torch.flip(input_img,[3]) with torch.no_grad(): _, output_depth =...

Dear authors, I install Deepspeed through pip install deepspeed. And my torch version is 1.12.1 and cuda 11.3 However, when i try to use following code to count the flops,...

Dear authors, Since my model contains also layers from torch_geometric, and my model has multiple inputs. Some of them have a predefined size but one input is the point cloud,...

question about training time

4

### System Info Dear authors, I have a question regarding the training time utilizing the peft package. I tried using LoRA with a swin transformer to reduce the parameter size....