Barry (Xuanyi) Dong

- Adaptive Computation Time for Recurrent Neural Networks, arXiv 2016 - Spatially Adaptive Computation Time for Residual Networks, CVPR 2017 - More is Less: A More Complicated Network with Less...

Hi, should this line (https://github.com/deepmind/deepmind-research/blob/master/nfnets/nf_resnet.py#L181) be ``` out = self.activation(x / self.beta) ``` instead of ``` out = self.activation(x) * self.beta ``` Following the paper, h_{i+1} = h_{i} + \alpha...

Difference between GDAS variants

3

**Which Algorithm** GDAS: Searching for A Robust Neural Architecture in Four GPU Hours **Describe the Question** In [search_cells.py](https://github.com/D-X-Y/AutoDL-Projects/blob/main/xautodl/models/cell_searchs/search_cells.py), there are two kinds of GDAS implementations: - First, `self._ops[index](x) * weights[index]`...

Questions about the performances.

23

Hi, May I ask your final performance, the curves are a little confusing. I also implement a different version (https://github.com/D-X-Y/ResNeXt), my results are a little bit lower than the official...

Hi, thanks for this awesome repo. I noticed that all models use imagenet pre-trained initialization. I am wondering, would you mind to provide results without imagenet pre-training.

Change two lines: L241 in lib/models/hrnet.py, explicitly use align_corners=False, otherwise, it will raise a warning in PyTorch>1.3.0 L309, the kernel_size should be extra.FINAL_CONV_KERNEL (to align with L311).

mAP

1

Hi, Would you mind to show the mAP of the provided model file? Thanks a lot

The code to generate dataset lists

1

Hi kuangliu, Many thanks for your codes, it is awesome. Would you mind to provide the codes to generate the lists in https://github.com/kuangliu/torchcv/tree/master/torchcv/datasets ? Thanks a lot.

Example codes: ``` import typing import pyglove as pg class A(pg.Object): x : typing.Literal[" ", "+", "-"] print(A(x=" ")) ```

Dict is not accepting int as key.

1

``` import pyglove as pg class A(pg.Object): x: Annotated[Dict, "."] = dict() y: Annotated[str, "."] = ".." # Define a simple dictionary data = A(x={1:1}) ``` Most normal user may...