KevinLi-167

icon location A student at CNU.

Results 7 comments of KevinLi-167

assert len(data_loader) > 0，AssertionError

Run './scripts/coop/main.sh imagenet rn50_ep50 end 16 1 False' faild. Using `https://kkgithub.com/soumith/imagenetloader.torch/blob/master/valprep.sh` to divide the val. After the val division, the good news is that the 4 PKLs have content. The...

About how to connect a Bluetooth device with a 16-bit UUID

有人尝试过连接其他蓝牙模块通讯么，用代码形式而不是原本固件AT指令

The parameter `test.combine_ratio` seem invalid when running inference

1. My statement is inappropriate. I trained 3 models and tried to modify `w` on 2 to test. The data just shown above is a training effect after I **changed**...

The parameter `test.combine_ratio` seem invalid when running inference

1. As you said, I noticed that the accuracy really didn't change much before and after training the unet on the dataset CUB (every 40 steps), as shown in the...

Asking for questions about evaluation

I'm having a similar issue. I use the CUB dataset and modify the smaller batch_size for the 2-stage training. train_token I use the default float32. Since I only have 8g...

Asking for questions about evaluation

Thank you for your reply! I did realize the problem with `fr`. (And just found out that the loss is always nan in the log of training unet, so my...

At the end of the CoOp train main.sh an additional progress bar indicates the accuracy of the output, whether the test was executed in train?

![0424-确定train内置test](https://github.com/KaiyangZhou/CoOp/assets/101034034/8fbd81ba-e599-4106-abcf-e9acc5c2b677) Or rather, the reason for the registration function of dassl. Where should I find out how train calls test?