Maze
### Description ### Add fixed subnet state dict load operation and Autoformer evolution ### How to test ### ``` import nni.retiarii.hub.pytorch as hub from nni.retiarii.hub.pytorch.utils.fixed import FixedFactory from nni.retiarii.utils import...
A concise and easy to understand version ``` class CenterLoss(nn.Module): def __init__(self, num_class=10, num_feature=2): super(CenterLoss, self).__init__() self.num_class = num_class self.num_feature = num_feature self.centers = nn.Parameter(torch.randn(self.num_class, self.num_feature)) def forward(self, x, labels):...
**Describe the issue**: HPO experiment hyper-parameters page error. [experiment.zip](https://github.com/microsoft/nni/files/9570986/experiment.zip) **Environment**: - NNI version: dev - Training service (local|remote|pai|aml|etc): local - Client OS: Ubuntu - Server OS (for remote mode only):...
https://github.com/microsoft/Cream/blob/a857830192d472e6776e9af4bbd988f35ebf1f4d/AutoFormer/model/module/qkv_super.py#L72-L83 In the qkv_super the weight and bias sharing strategy is different. I think the selection of bias is unreasonable and should be modified in the following way. ``` def...
I find that in ST-GCN there is a pretrained model provided by autor, where is the pretrained model for this repo?
Dear TextDiffuser author: **I have read the paper and source code carefully.** but still have some confusion. The laion-ocr dataset provide ocr.txt, which use 4 point annotation not rectangle bbox,...
can you provide a demo for try?
This is your result.  but the result from mediapipe is  obviously, your reproduce result is tooooooo bad!
the output of controlnet tile is awasome, and i want to train a tile for custom dataset. However, the resultis strange. my training setup: use the [train_controlnet.py](https://github.com/huggingface/diffusers/blob/main/examples/controlnet/train_controlnet.py) script from diffusers....
Hi, thank you so much for the great work! The arcface provied in [https://huggingface.co/FoivosPar/Arc2Face/tree/main] is onnx format, can you provide the corresponding pytorch weights ?