-
Wow, congratulations on SOTA
I am looking for a highly accurate model for human segmentation (single or group) for a mobile device for still images.
Would ResNeSt work for this?
-
蔺一迪：
安装成功pytorch与pycharm，进一步学习了resnest模型，总结出了train以及test代码，正在努力写出其他代码。
-
I tried the 3rd party tensorflow implementation in the README: https://github.com/QiaoranC/tf_ResNeSt_RegNet_model, but it doesn't provide pretrained weights.
Any other solution for tf2.x/keras v…
-
I have read your codes about split-attention and I found that you use ReLU before split-attention.
https://github.com/zhanghang1989/ResNeSt/blob/76debaa9b9444742599d104609b8ee984b207332/resnest/torch…
-
Hello, while this used to work fine a couple of days ago, now it is giving HTTP Eroor 403: Forbidden.
from resnest.torch import resnest101
self.model = resnest101(pretrained=True)
any idea what…
-
-
Hello,
How can I use it on a custom data set for object detection? Is there any documentation regarding this ? Format of data for training. Is it similar to detectron2 ?
-
Hello,
Thanks for sharing your ready to train code, I was wondering if there any hope to have the pretrained weights on Image-Net ? I can contribute by adding Cascade-RCNN and Faster-RCNN to the m…
-
Thanks for your great work.
In your provided pre-trained weights for detectron2, I notice that the names of tensors start with `backbone.bottom_up` (eg. `backbone.bottom_up.stem.conv1_1.weight`), a…
-
hi, can i download pretrained-resnest50 model? How download?
https://s3.us-west-1.wasabisys.com/resnest/torch/528c19ca-resnest50.pth current web indicate:
AccessDenied
Access Denied
66677888F1B8…