Kittywyk

6.4节的 rnn(input,state,params) 函数理解

2

请问其中的 H,=state 怎么理解？ ,=是什么意思？ 请问最后 return outputs, (H,) 中的 (H,) 又该如何理解？

您好，我运行了experiments.m，但是提示如下错误。请问可能是什么原因？谢谢帮助。 > >> experiments > data\MYDATA\out\TestReport.csv > 结构体内容引用自非结构体数组对象。 > > 出错 TestImage/save (line 114) > writetable(this.Report.Data, file); > > 出错 experiments (line 22) > save(Test); % %save(Test, ['TestReport__' name{n} '.csv']);

Error in downloading dataset

2

I ran "python pascal_voc.py --download-dir .../datasets/voc" to download voc dataset, and the dataset was successfully downloaded. But then the error occured, "NotADirectoryError: [Errno 20] Not a directory: '.../datasets/voc/VOCdevkit' ". Is...

Hi, I'm confused that why you minus 1 in this function of ade.py. `def _mask_transform(self, mask): return torch.LongTensor(np.array(mask).astype('int32') - 1)` Thx for ur explanation.

Hi, thanks for your great work. When I tried to run Yolo-SwinTransformer(small), and enabled several augmentations(JITTER_CROP, MOSAIC_AND_MIXUP, etc), an error occcurs. The training command is: python train_custom_dataset.py --config-file configs/mydataset/swin_s.yaml --num-gpus...

关于统计移动平均特征的代码问题

1

您好，首先非常感谢您solid的工作。 但在我看具体代码时，有一些问题想要请教： 在 lvis1.0\mmdet\models\roi_heads\bbox_heads\convfc_bbox_head.py 文件中的 update_embed 函数里： ``` def update_embed(self, targets, gt_label): if self.training: # remove background with torch.no_grad(): fg_target = targets[gt_label > 0].clone().detach().mean(0, keepdim=True) self.causal_embed = self.MU * self.causal_embed...

Hi, I have a question about the validate function of classification stage. The codes are in def validate(net,data_loader), train50_cls_cce.py. ` for j in range(msks.shape[0]): # msks.shape[0] is batch size tp[4]...