Update README.md
Browse files
README.md
CHANGED
|
@@ -10,19 +10,21 @@ library_name: timm
|
|
| 10 |
|
| 11 |
# Model Card for Model ID
|
| 12 |
|
| 13 |
-
|
| 14 |
|
| 15 |
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).
|
| 16 |
|
|
|
|
|
|
|
| 17 |
## Model Details
|
| 18 |
|
| 19 |
### Model Description
|
| 20 |
|
| 21 |
-
|
| 22 |
|
| 23 |
|
| 24 |
|
| 25 |
-
- **Developed by:**
|
| 26 |
- **Funded by [optional]:** [More Information Needed]
|
| 27 |
- **Shared by [optional]:** [More Information Needed]
|
| 28 |
- **Model type:** [More Information Needed]
|
|
@@ -35,7 +37,7 @@ This modelcard aims to be a base template for new models. It has been generated
|
|
| 35 |
<!-- Provide the basic links for the model. -->
|
| 36 |
|
| 37 |
- **Repository:** [More Information Needed]
|
| 38 |
-
- **Paper [optional]:** [
|
| 39 |
- **Demo [optional]:** [More Information Needed]
|
| 40 |
|
| 41 |
## Uses
|
|
|
|
| 10 |
|
| 11 |
# Model Card for Model ID
|
| 12 |
|
| 13 |
+
Based on quaslinear hyperbolic systems of PDEs, the QLNet explores a new model space for ConvNets that uses multiplication (of same-sized tensors) instead of ReLU as the nonlinearity. It achieves comparable accuracy as ResNet50 on ImageNet-1k, demonstrating that it has the same level of capacity/expressivity, and deserves more study (hyper-paremeter tuning) that I alone am not able to do.
|
| 14 |
|
| 15 |
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).
|
| 16 |
|
| 17 |
+
|
| 18 |
+
|
| 19 |
## Model Details
|
| 20 |
|
| 21 |
### Model Description
|
| 22 |
|
| 23 |
+
Instead of the bottleneck of ResNet50 which consists of 1x1, 3x3, 1x1 in succession, we instead of make the 1x1, split into two equal halves and multiply them, then apply a 3x3 (depthwise), and a 1x1. All without activation functions except at the end of the block, where we apply a *radial activation function* that I call `hardball`.
|
| 24 |
|
| 25 |
|
| 26 |
|
| 27 |
+
- **Developed by:** Yao Liu 刘杳
|
| 28 |
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
- **Model type:** [More Information Needed]
|
|
|
|
| 37 |
<!-- Provide the basic links for the model. -->
|
| 38 |
|
| 39 |
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [A Novel ConvNet Architecture with a Continuous Symmetry](https://arxiv.org/abs/2308.01621)
|
| 41 |
- **Demo [optional]:** [More Information Needed]
|
| 42 |
|
| 43 |
## Uses
|