ShenZheng2000

Results 30 comments of ShenZheng2000

为何我分割出的obj文件，用MeshLab查看，只显示白色？

我遇到同样的问题。答主知道怎么做吗

Question about batch_size and training time

When you increase the batch size, you are training more images in each iteration. Therefore, you spend more time in each iteration. It is true that you can increase the...

metric of Tab.5

I appreciate your inquiry. Currently, I'm occupied with another project deadline, but I plan to go through and tidy up the old code repository within the next 2 weeks. As...

Import error

I met the same problem. Have u managed to solve this problem?

Multi-GPU Training Issue

I found a solution by modifying [train.py](https://github.com/sapphire497/query-selected-attention/blob/main/train.py#L46). Replace this ``` model.optimize_parameters() # calculate loss functions, get gradients, update network weights ``` with this ``` model.set_input(data) model.optimize_parameters() # calculate loss functions,...

Training time of Unpaired Day2night

I'm also training BDD100K Day2Night. It takes about 16 hours on four 4090 GPUs to complete 25,000 training steps.

Training time of Unpaired Day2night

@tfriedel No, training with 512x512 resolution doesn't fit into 24GB of memory; it may require 48GB or more. However, I experimented with `resize_286_randomcrop_256x256_hflip` and found that: * it fits within...

Training stuck after index is created when training from checkpoint

Same problem.

在使用resume文件继续训练时卡在了advance dataloader步骤中

我debug了好几天才发现，是因为新版的mmengine的问题。Try this: ``` mim install mmengine==0.10.2 ```

在使用resume文件继续训练时卡在了advance dataloader步骤中

@nyjshinibaba Yes. 保存的是Iter