wofmanaf / rest Goto Github PK

你好，我想请问一下您训练的数据集是ImageNet-1K的哪一个呢

论文中的PVT[5]引用的全是ViT[5]，实际应该是：Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions，参考文献中没有，需要新加这个文献

或者那个V2百度网盘的提取密码能告知下吗？

maybe "Each head in MSA only responsible for a subset of channels of the input tokens".
According to the Transformer, each head is not responsible for part of input tokens, but part of channels of one input token.

Hi, thanks for your great work. Now I want to use your Rest as my backbone network for visual target tracking. How do I implement this operation? Can I directly download your pre-trained model for loading?

您好，我训练ResT-large到100多个epochs断了，输出文件有个checkpoint.pth.tar,我通过解压这个tar文件得到data.pkl和data，请问一下如果想获得pth权重文件，是解压data.pkl文件么

Hi~
Thanks for your excellent work! I see this words in your code:
x = self.avg_pool(x).flatten(1) # if use in MVS, should abandon this part
x = self.head(x) # if use in MVS, should abandon this part
It seems you have tried Rest in MVS task, I'm wandering what the perfomance of Rest in MVS, and what experiment you have tried.
Looking forward to your reply! Thanks!

Hello,when I use your ResT_base weight to my fine-frained image classification task, I use the "--finetune",but i got a mistake . in 264 line(main.py) :
**UnboundLocalError: local variable 'model_without_ddp' referenced before assignment.**how can i fix it?

by the way, in line 431 in main.py: n_parameters is not define,can you give the definition？

Hello, if I want to try your backborn on other visual tasks, can I call rest.py directly?

你好 很感谢你的工作。有一个问题想请教下：代码中class PA ()的作用是什么？感觉与论文2.4 Position Encoding不对应。因为代码中PA调用是在class PatchEmbed （认为与论文2.3 Patch Embedding相关）class BasicStem （the first patch embedding module）。综上 class PA ()与论文2.3 Patch Embedding相关，不与2.4 Position Encoding相关，但是论文2.4 Position Encoding中公式（8）描述了PA的Conv2d（）和Sigmoid() 。
再次谢谢

你好，v2百度网盘密码不知道，能给一份么谢谢

如题，baidu太不方便了~
感谢!

您好，我使用 convert_to_d2.py转换的权重文件，都加载不成功

您好

    我从https://arxiv.org/pdf/2105.13677v2.pdf下载了最新的版本，但是其中第5页的figure4存在排版问题。

zy

感谢这项开源代码!
请问预训练权重的网盘提取密码是?
感谢!

What's the password of the pretrained model in baiduYun ?
Thanks a lot!

Hi @wofmanaf

Thank you for your source code.
Can you share source code to calculate the number of FLOPS on ResT models ?

Best,

Chakkrit

Hi, thanks for your great work, and Is there any operation similar to 'padding mask' like as DERT to indicate where is the image and where is padding.

可以补发一下嘛

I think it is a necessary ablation study to make a quantitative comparison of performance and efficiency of the two modules. But it's not in the paper

FPS值大概多少呢，我看参数量不大

Hello. I want to train resT on my own dataset.
Therefore, I tried to write the model name 'rest_base' on args.model since this name exists in rest.py file.
However the error 'unrecognized arguments: -model rest_base' occured.

So which commands can I enter into args.model in order to train resT v1?

你好，我安装了detectron2，直接在d2文件夹下，运行./train_net.py --num-gpus 1
--config-file ./configs/COCO-InstanceSegmentation/mask_rcnn_rest_base_FPN_1x.yaml
SOLVER.IMS_PER_BATCH 2 SOLVER.BASE_LR 0.0025。
然后报错：KeyError: 'Non-existent config key: MODEL.REST'。
请问可以麻烦教一下，怎么运行成功在的detectron2中运行ResT么

做目标检测 类别为1 运行时出现下面的错误，这是什么原因？

大佬们江湖救急，我是新手想问一下ResT中的EMSA自注意力的泛化能力怎么样？能不能在别的transformer网络中替换MSA？EMSA的代码是rest.py中48-67行定义的Attention这个类吗？求告知，谢谢！

ImageNet-1k pytorch-1.8.0 train (lite) max acc 0.3