Create README.md
#1
by
reach-vb
HF staff
- opened
README.md
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- image-classification
|
| 4 |
+
license: other
|
| 5 |
+
datasets:
|
| 6 |
+
- imagenet-1k
|
| 7 |
+
---
|
| 8 |
+
# Model card for fastvit_t8.apple_in1k
|
| 9 |
+
|
| 10 |
+
A FastViT image classification model. Trained on ImageNet-1k by paper authors.
|
| 11 |
+
|
| 12 |
+
Please observe [original license](https://github.com/apple/ml-fastvit/blob/8af5928238cab99c45f64fc3e4e7b1516b8224ba/LICENSE).
|
| 13 |
+
|
| 14 |
+
## Model Details
|
| 15 |
+
- **Model Type:** Image classification / feature backbone
|
| 16 |
+
- **Model Stats:**
|
| 17 |
+
- Params (M): 4.0
|
| 18 |
+
- GMACs: 0.7
|
| 19 |
+
- Activations (M): 8.6
|
| 20 |
+
- Image size: 256 x 256
|
| 21 |
+
- **Papers:**
|
| 22 |
+
- FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization: https://arxiv.org/abs/2303.14189
|
| 23 |
+
- **Original:** https://github.com/apple/ml-fastvit
|
| 24 |
+
- **Dataset:** ImageNet-1k
|