Update README.md
Browse files
README.md
CHANGED
@@ -1,8 +1,6 @@
|
|
1 |
---
|
2 |
datasets:
|
3 |
- imagenet-1k
|
4 |
-
language:
|
5 |
-
- en
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
library_name: timm
|
@@ -10,7 +8,7 @@ library_name: timm
|
|
10 |
|
11 |
# Model Card for Model ID
|
12 |
|
13 |
-
Based on **quasi-linear hyperbolic systems of PDEs**, the QLNet enters an uncharted water of ConvNet model space marked by the use of
|
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 |
|
@@ -25,7 +23,7 @@ Instead of the `bottleneck` block of ResNet50 which consists of 1x1, 3x3, 1x1 in
|
|
25 |
|
26 |
|
27 |
- **Developed by:** Yao Liu 刘杳
|
28 |
-
- **Model type:**
|
29 |
- **License:** [More Information Needed]
|
30 |
- **Finetuned from model:** N/A (*trained from scratch*)
|
31 |
|
@@ -33,8 +31,8 @@ Instead of the `bottleneck` block of ResNet50 which consists of 1x1, 3x3, 1x1 in
|
|
33 |
|
34 |
<!-- Provide the basic links for the model. -->
|
35 |
|
36 |
-
- **Repository:** [
|
37 |
-
- **Paper
|
38 |
- **Demo [optional]:** [More Information Needed]
|
39 |
|
40 |
## How to Get Started with the Model
|
|
|
1 |
---
|
2 |
datasets:
|
3 |
- imagenet-1k
|
|
|
|
|
4 |
metrics:
|
5 |
- accuracy
|
6 |
library_name: timm
|
|
|
8 |
|
9 |
# Model Card for Model ID
|
10 |
|
11 |
+
Based on **quasi-linear hyperbolic systems of PDEs**, the QLNet enters an uncharted water of ConvNet model space marked by the use of (element-wise) multiplication instead of ReLU as the primary nonlinearities. It achieves comparable accuracy as ResNet50 on ImageNet-1k, demonstrating that it is endowed with the same level of capacity/expressivity, and deserves more study (hyper-paremeter tuning, optimizer, etc.) by the broader community.
|
12 |
|
13 |
*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).*
|
14 |
|
|
|
23 |
|
24 |
|
25 |
- **Developed by:** Yao Liu 刘杳
|
26 |
+
- **Model type:** Convolutional Neural Network (ConvNet)
|
27 |
- **License:** [More Information Needed]
|
28 |
- **Finetuned from model:** N/A (*trained from scratch*)
|
29 |
|
|
|
31 |
|
32 |
<!-- Provide the basic links for the model. -->
|
33 |
|
34 |
+
- **Repository:** [ConvNet from the PDE perspective](https://github.com/liuyao12/ConvNets-PDE-perspective)
|
35 |
+
- **Paper:** [A Novel ConvNet Architecture with a Continuous Symmetry](https://arxiv.org/abs/2308.01621)
|
36 |
- **Demo [optional]:** [More Information Needed]
|
37 |
|
38 |
## How to Get Started with the Model
|