MintCoffeeCat

您好，我按照ReDet_mmcls分支中的getting_started.md所说，下载了ILSVRC 2012的train和val数据集，并分别解压到了data/train和data/val路径下。同时我根据Get Started所说，下载了checkpoint文件，放在了re_resnet50_c8_batch256路径下。当我继续执行如下的指令时 `python tools/test.py configs/imagenet/resnet50_batch256.py checkpoints/re_resnet50_c8_batch256/epoch_100.pth` 发生如下报错： `No such file or directory: 'data/imagenet/meta/val.txt'` 请问我该如何获得此文件呢？我在ImageNet上找到了ILSVRC 2012数据集对应的annotation标注文件，但是文件格式是xml。 请问此txt文件是根据xml转换得到，还是需要手动创建？麻烦您能帮忙解惑，十分感谢！

In the forward function of PatchMerging class, the msg_token and x was sent into self.reduction, which is a Conv2D layer with Conv2D(dim,2*dim,3,2,1) initialization. ``` msg_token = window_reverse(x[:, :, 0].unsqueeze(2), 1,...

could pyTorch be a higher version?

1

the module apex installation seems require a higher cuda verson to satisify my CPU, but pytorch official site did not give the installation command with 1.7 verson and cudatoolkit after...