Swin-Transformer

Swin-Transformer copied to clipboard

When HTC++ availabel

3

Hi, I think the sota model HTC++ multi-scale is not released yet?

Dreamer312

Object Detection/ Instance Segmentation config details and pre-trained models

1

I was wondering when the pre-trained models (checkpoints) and corresponding config files for Swin Transformer V2(object detection/ instance segmentation) will be released? In the github repo, only V1 was provided....

abbasmammadov

I want to train swinv2 for classification with single GPU

1

studygogogo1

`torch.clamp` issue due to update of pytorch 1.12.0

2

Since `torch.clamp` was updated in 1.12.0, the latest version of Pytorch, `torch.clamp`'s min, max argument should be loaded on same device with input tensor. https://github.com/pytorch/pytorch/pull/77035 I got an error with...

CryptoSalamander

how mask and pos bias infuence the training precise?

1

Hi, Thank for your great job. I have a small question. I want to know how important is mask and position bias in out model as for final training precise?...

lw921014

Simplifying some code

1

Some code is simplifying and getting more pythonic.

Nourollah

Hey, i have just trained few models and realized that the accuracy is always times of 0.05. Is that supposed to be that way or should i change something in...

Darkalpy

window kernel compile error

3

env: ubuntau 20.04, pytorch==1.11.0, cuda_version=10.2 error logs: Traceback (most recent call last): File "setup.py", line 12, in cmdclass={'build_ext': BuildExtension}) File "/home/hanqi/miniconda3/envs/glom/lib/python3.7/site-packages/setuptools/__init__.py", line 87, in setup return distutils.core.setup(**attrs) File "/home/hanqi/miniconda3/envs/glom/lib/python3.7/site-packages/setuptools/_distutils/core.py", line...

Hanqer

pretrained

cts4444

the config of swinv2-huge

1

stonewjf