ResT icon indicating copy to clipboard operation
ResT copied to clipboard

This is an official implementation for "ResT: An Efficient Transformer for Visual Recognition".

Results 11 ResT issues
Sort by recently updated
recently updated
newest added

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

你好,我想请问一下您训练的数据集是ImageNet-1K的哪一个呢

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!

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...

您好,我使用 convert_to_d2.py转换的权重文件,都加载不成功

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...

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.

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