Wenqiang Zhang

> Dear Author, > > I could reproduce task including MYTAG,PTC,NCl1,PROTEINS,IMDB-B,IMDB-M,RDT-M5K using the parameters of your paper, however, I could not reproduce the results for RDT-B and COLLAB using the...

> Would you share the mmdet configs for the object detection training? Link: https://pan.baidu.com/s/1lX0FeAWyYWccyLQzmoVCnQ (pwd: topf)

> > > Would you share the mmdet configs for the object detection training? > > > > > > Link: https://pan.baidu.com/s/1lX0FeAWyYWccyLQzmoVCnQ (pwd: topf) > > Many thanks, I use...

> Hi, would you be interested in adding TopFormer to Hugging Face? The Hub offers free hosting, and it would make your work more accessible and visible to the rest...

> We report the latency on mobile device. To test the inference speed in mobile device, please refer to [tnn_runtime](https://github.com/hustvl/TopFormer/blob/main/tnn_runtime.md). If you want to calculate the latency on `GPU`, you...

> Hi！Excuse me ,I have some question to ask you ? > > 1. Can I run the program in WIN10？ > 2. I try it but it have a...

> 您在文中并没有提到在imagenet上训练跑了多少epoch以及用了几块GPU，batch size是多大，还有优化器和学习率等参数。是否方便公布一下这些参数或者将预训练的log放出来？这会极大的帮助我们复现您的工作，非常感谢！ 600epoch, batchsize 128*8, rmsprop，lr=0.064

是在MMSeg下跑的，在mmseg下实现的EfficientNet，相同的setting下进行对比。MMseg已经有实现DeepLabV3+,只需要添加backbone即可。 Semantic FPN ConvMLP-S是引用的结果，可以到对应的paper中找到，他们也是基于mmseg实现的。

暂时没有。您可以尝试将模型利用ONNX等工具进行部署。

> Conifg: configs/queryrcnn.res50.100pro.3x.yaml Results: [07/02 18:39:24 d2.evaluation.testing]: copypaste: Task: bbox [07/02 18:39:24 d2.evaluation.testing]: copypaste: AP,AP50,AP75,APs,APm,APl [07/02 18:39:24 d2.evaluation.testing]: copypaste: 36.7532,53.7602,39.9495,22.2459,39.1920,46.0393 > > I use the default config, but the results...