MPViT

MPViT copied to clipboard

what is the meaning of the following code in''MPViT-main\semantic_segmentation\configs\_base_\models''

1

这段代码具体对应于文中的哪个模块呀？为什么会牵扯到相对位置编码呢？ class ConvRelPosEnc(nn.Module): """Convolutional relative position encoding.""" def __init__(self, Ch, h, window): """Initialization. Ch: Channels per head. h: Number of heads. window: Window size(s) in convolutional relative positional encoding. It...

zhouqunbing

About the parameters of drop_path_rate

1

@youngwanLEE Hi, I have a question about the drop_path_rate used for small and base models: When I provide the parameter of drop_path, e.g., 0.1, and run the code from your...

go-ahead-maker

Hello @youngwanLEE, How i can visualize multi-scale patches from an image? I would like to look the multi-scale patches generated from image. Regards, Khawar

khawar-islam

about the channels

1

Thanks for the great work ! I wonder why the in_channels of decode_head is [ 224, 368, 480, 480 ] rather than [ 128, 224, 368, 480 ] for the...

BingyuanW

Have you ever tried to train bigger models?

1

Have you ever tried to train bigger models? Like L, H or G? If yes, what were the results

christophschuhmann

zxf29

I can not download pretrained model from dropbox, can anyone help me? Is there any other place to download pretrained model such as Baidu Netdisk

RundongCao

Thank you for writing good paper! It is mentioned in the paper as follows. "MPViT embeds features of the same size (i.e., sequence length) with patches of different scales simultaneously...

Dayoung-Kil

Thanks for the amazing work! When trying to use the semantic segmentation part, I miss some libraries, so I had to install them like pip install einops timm []s

weberhen

@youngwanLEE Thanks for your excellent work. When I train the code on two GPU, there are a error that torch.distributed.elastic.multiprocessing.api:failed(exitcode:-9). when I train on single GPU with 'tools/dist_train.sh configs/... 1',...

1787648106