Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,36 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- ILSVRC/imagenet-1k
|
| 5 |
+
model-index:
|
| 6 |
+
- name: MaskBit-Tokenizer-16bits
|
| 7 |
+
results:
|
| 8 |
+
- task:
|
| 9 |
+
type: image-generation
|
| 10 |
+
dataset:
|
| 11 |
+
name: ILSVRC/imagenet-1k
|
| 12 |
+
type: ILSVRC/imagenet-1k
|
| 13 |
+
metrics:
|
| 14 |
+
- name: rFID
|
| 15 |
+
type: rFID
|
| 16 |
+
value: 1.29
|
| 17 |
+
- name: InceptionScore
|
| 18 |
+
type: InceptionScore
|
| 19 |
+
value: 193.6
|
| 20 |
+
- name: LPIPS
|
| 21 |
+
type: LPIPS
|
| 22 |
+
value: 0.278
|
| 23 |
+
- name: PSNR
|
| 24 |
+
type: PSNR
|
| 25 |
+
value: 21.8
|
| 26 |
+
- name: SSIM
|
| 27 |
+
type: SSIM
|
| 28 |
+
value: 0.58
|
| 29 |
+
- name: CodebookUsage
|
| 30 |
+
type: CodebookUsage
|
| 31 |
+
value: 1.0
|
| 32 |
+
---
|
| 33 |
+
|
| 34 |
+
This model is the MaskBit tokenizer with a vocabulary size of 16bits. It uses a downsampling factor of 16 and is trained on ImageNet for images of resolution 256.
|
| 35 |
+
|
| 36 |
+
You can find more details on the [project page](https://weber-mark.github.io/projects/maskbit.html) and in the [paper](https://arxiv.org/abs/2409.16211).
|