Swin-Transformer
Swin-Transformer copied to clipboard
microsoft
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Traceback (most recent call last): File "main.py", line 21, in from config import get_config File "/root/paddlejob/workspace/env_run/video_tag/code/swin/config.py", line 70, in _C.MODEL.SWIN.QK_SCALE = None File "/root/paddlejob/workspace/env_run/video_tag/food/lib/python3.7/site-packages/yacs/config.py", line 158, in __setattr__ type(value), name,...
Hi Thank you for your great work. My Image size is 112x112 and the head is 12 and my window size is 7. It does not work for me. Traceback...
The base tagging of the original imagenet21K is single label. I wonder how to get multi-label information for each image in ImageNet22K.
Has the ImageNet1K validation data and Imagenet21K training data been de-duplicated?
When I use the amp-opt-level O1 to train the swin-large_patch4_window7_224 on imagenet22k, I get a nan loss and grad_norm ever since epoch [1/60] iter [880/3466]。The training process is normal before,...
My system envs is CentOS7/cuda 10.1.243 /cudnn 7.6.5，which is exactly the same envs as the tutorial envs. However, when I run the command line on the title, I got "RuntimeError:...
We know that two linear transformations in a row can be merged into one linear transformation, if there's no activation function between them. In https://github.com/microsoft/Swin-Transformer/blob/main/models/swin_transformer.py#L141-L142 ``` x = (attn @...
How can I run just simple inference for one image ? somethink like model = load_model(weight_path, config_path) image = cv2.imread(image_path) prediction = model(image) is there a way ?
