-[Funnel Activation for Visual Recognition](https://arxiv.org/abs/2007.11824), Ma, Ningning, et al. "Funnel Activation for Visual Recognition." Proceedings of the European Conference on Computer Vision (ECCV). 2020.
<!-- section: en_US -->
All pre-trained models expect input images normalized in the same way,
i.e. input images must be 3-channel BGR images of shape `(H x W x 3)`, and reszied shortedge to `256`, center-cropped to `(224 x 224)`.
No normalization required.
Here's a sample execution.
```python
# Download an example image from the megengine data website
Currently we provide several pretrained models(see the table below), Their 1-crop accuracy on ImageNet validation dataset can be found in following table.
-[Funnel Activation for Visual Recognition](https://arxiv.org/abs/2007.11824), Ma, Ningning, et al. "Funnel Activation for Visual Recognition." Proceedings of the European Conference on Computer Vision (ECCV). 2020.
-[WeightNet: Revisiting the Design Space of Weight Network](https://arxiv.org/abs/2007.11823), Ma, Ningning, et al. "WeightNet: Revisiting the Design Space of Weight Network." Proceedings of the European Conference on Computer Vision (ECCV). 2020.
<!-- section: en_US -->
All pre-trained models expect input images normalized in the same way,
i.e. input images must be 3-channel BGR images of shape `(H x W x 3)`, and reszied shortedge to `256`, center-cropped to `(224 x 224)`.
No normalizations required.
Here's a sample execution.
```python
# Download an example image from the megengine data website
Currently we provide several pretrained models(see the table below), Their 1-crop accuracy on ImageNet validation dataset can be found in following table.
-[WeightNet: Revisiting the Design Space of Weight Network](https://arxiv.org/abs/2007.11823), Ma, Ningning, et al. "WeightNet: Revisiting the Design Space of Weight Network." Proceedings of the European Conference on Computer Vision (ECCV). 2020.