Lupin1998
commited on
Commit
•
cba7e3c
1
Parent(s):
df727d1
add figs
Browse files
README.md
CHANGED
|
@@ -1,10 +1,20 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
|
|
|
| 3 |
- image-classification
|
| 4 |
datasets:
|
| 5 |
- imagenet
|
|
|
|
|
|
|
| 6 |
library_tag: MogaNet
|
| 7 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
# Model card for moganet_xtiny_224_in1k
|
|
@@ -15,6 +25,8 @@ MogaNet a new family of efficient ConvNets with preferable parameter-performance
|
|
| 15 |
|
| 16 |
Since the recent success of Vision Transformers (ViTs), explorations toward ViT-style architectures have triggered the resurgence of ConvNets. In this work, we explore the representation ability of modern ConvNets from a novel view of multi-order game-theoretic interaction, which reflects inter-variable interaction effects w.r.t. contexts of different scales based on game theory. Within the modern ConvNet framework, we tailor the two feature mixers with conceptually simple yet effective depthwise convolutions to facilitate middle-order information across spatial and channel spaces respectively. In this light, a new family of pure ConvNet architecture, dubbed MogaNet, is proposed, which shows excellent scalability and attains competitive results among state-of-the-art models with more efficient use of parameters on ImageNet and multifarious typical vision benchmarks, including COCO object detection, ADE20K semantic segmentation, 2D\&3D human pose estimation and video prediction.Typically, MogaNet hits 80.0\% and 87.8\% top-1 accuracy with 5.2M and 181M parameters on ImageNet, outperforming ParC-Net-S and ConvNeXt-L while saving 59\% FLOPs and 17M parameters.
|
| 17 |
|
|
|
|
|
|
|
| 18 |
## Model Usage
|
| 19 |
|
| 20 |
Setup before using the model.
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
+
- vision
|
| 4 |
- image-classification
|
| 5 |
datasets:
|
| 6 |
- imagenet
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
library_tag: MogaNet
|
| 10 |
license: apache-2.0
|
| 11 |
+
language:
|
| 12 |
+
- en
|
| 13 |
+
library_name: timm
|
| 14 |
+
pipeline_tag: image-classification
|
| 15 |
+
widget:
|
| 16 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
|
| 17 |
+
example_title: Tiger
|
| 18 |
---
|
| 19 |
|
| 20 |
# Model card for moganet_xtiny_224_in1k
|
|
|
|
| 25 |
|
| 26 |
Since the recent success of Vision Transformers (ViTs), explorations toward ViT-style architectures have triggered the resurgence of ConvNets. In this work, we explore the representation ability of modern ConvNets from a novel view of multi-order game-theoretic interaction, which reflects inter-variable interaction effects w.r.t. contexts of different scales based on game theory. Within the modern ConvNet framework, we tailor the two feature mixers with conceptually simple yet effective depthwise convolutions to facilitate middle-order information across spatial and channel spaces respectively. In this light, a new family of pure ConvNet architecture, dubbed MogaNet, is proposed, which shows excellent scalability and attains competitive results among state-of-the-art models with more efficient use of parameters on ImageNet and multifarious typical vision benchmarks, including COCO object detection, ADE20K semantic segmentation, 2D\&3D human pose estimation and video prediction.Typically, MogaNet hits 80.0\% and 87.8\% top-1 accuracy with 5.2M and 181M parameters on ImageNet, outperforming ParC-Net-S and ConvNeXt-L while saving 59\% FLOPs and 17M parameters.
|
| 27 |
|
| 28 |
+
|
| 29 |
+
|
| 30 |
## Model Usage
|
| 31 |
|
| 32 |
Setup before using the model.
|