Image Classification
timm
PDE
ConvNet
liuyao commited on
Commit
c3cf389
1 Parent(s): cfc2d12

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -8,12 +8,12 @@ library_name: timm
8
 
9
  # Model Card for Model ID
10
 
11
- Based on **quasi-linear hyperbolic systems of PDEs** [[Liu et al, 2023](https://github.com/liuyao12/ConvNets-PDE-perspective)], the QLNet enters an uncharted water of ConvNet model space marked by the use of (element-wise) multiplication instead of ReLU as the primary nonlinearity. It achieves comparable performance as ResNet50 on ImageNet-1k (acc=78.4), demonstrating that it has the same level of capacity/expressivity, and deserves more study (hyper-paremeter tuning, optimizer, etc.) by the community.
12
 
13
 
14
  ![](https://huggingface.co/liuyao/QLNet/resolve/main/QLNet.jpeg)
15
 
16
- One notable feature is that the architecture (trained or not) admits a *continuous* symmetry in its parameters. Check out the [notebook](https://colab.research.google.com/#fileId=https://huggingface.co/liuyao/QLNet/blob/main/QLNet_symmetry.ipynb) for a demon that makes a particular transformation on the weights while leaving the output unchanged.
17
 
18
  *This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).*
19
 
 
8
 
9
  # Model Card for Model ID
10
 
11
+ Based on **quasi-linear hyperbolic systems of PDEs** [[Liu et al, 2023](https://github.com/liuyao12/ConvNets-PDE-perspective)], the QLNet enters an uncharted water of ConvNet model space marked by the use of (element-wise) multiplication instead of ReLU as the primary nonlinearity. It achieves comparable performance as ResNet50 on ImageNet-1k (acc=**78.4**), demonstrating that it has the same level of capacity/expressivity, and deserves more study (hyper-paremeter tuning, optimizer, etc.) by the community.
12
 
13
 
14
  ![](https://huggingface.co/liuyao/QLNet/resolve/main/QLNet.jpeg)
15
 
16
+ One notable feature is that the architecture (trained or not) admits a *continuous* symmetry in its parameters. Check out the [notebook](https://colab.research.google.com/#fileId=https://huggingface.co/liuyao/QLNet/blob/main/QLNet_symmetry.ipynb) for a demo that makes a particular transformation on the weights while leaving the output *unchanged*.
17
 
18
  *This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).*
19