English
self-supervised learning
barlow-twins
6 papers
wgcban commited on
Commit
2c3a53e
1 Parent(s): b0ac186

Rename checkpoints/test.py to checkpoints/CHECKPOINTS.md

Browse files
Files changed (2) hide show
  1. checkpoints/CHECKPOINTS.md +30 -0
  2. checkpoints/test.py +0 -0
checkpoints/CHECKPOINTS.md ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Initial release of pre-trained models of Mixed Barlow Twins.
2
+
3
+ ## ResNet-18
4
+ | Dataset | d | Lambda_BT | Lambda_Reg | Path to Pretrained Model | KNN Acc. | Linear Acc. |
5
+ | ---------- | --- | ---------- | ---------- | ------------------------ | -------- | ----------- |
6
+ | CIFAR-10 | 1024 | 0.0078125 | 4.0 | 4wdhbpcf_0.0078125_1024_256_cifar10_model.pth | 90.52 | 92.58 |
7
+ | CIFAR-100 | 1024 | 0.0078125 | 4.0 | 76kk7scz_0.0078125_1024_256_cifar100_model.pth | 61.25 | 69.31 |
8
+ | TinyImageNet | 1024 | 0.0009765 | 4.0 | 02azq6fs_0.0009765_1024_256_tiny_imagenet_model.pth | 38.11 | 51.67 |
9
+ | STL-10 | 1024 | 0.0078125 | 2.0 | i7det4xq_0.0078125_1024_256_stl10_model.pth | 88.94 | 91.02 |
10
+
11
+ ## ResNet-50
12
+ | Dataset | d | Lambda_BT | Lambda_Reg | Path to Pretrained Model | KNN Acc. | Linear Acc. |
13
+ | ---------- | --- | ---------- | ---------- | ------------------------ | -------- | ----------- |
14
+ | CIFAR-10 | 1024 | 0.0078125 | 4.0 | v3gwgusq_0.0078125_1024_256_cifar10_model.pth | 91.39 | 93.89 |
15
+ | CIFAR-100 | 1024 | 0.0078125 | 4.0 | z6ngefw7_0.0078125_1024_256_cifar100_model.pth | 64.32 | 72.51 |
16
+ | TinyImageNet | 1024 | 0.0009765 | 4.0 | kxlkigsv_0.0009765_1024_256_tiny_imagenet_model.pth | 42.21 | 51.84 |
17
+ | STL-10 | 1024 | 0.0078125 | 2.0 | pbknx38b_0.0078125_1024_256_stl10_model.pth | 87.79 | 91.70 |
18
+
19
+ **On ImageNet**
20
+
21
+ | # Epochs | $d$ | $\lambda_{BT}$ | $\lambda_{reg}$ | Download Link to Pretrained Model | Linear Acc. |
22
+ | ---------- | --- | ---------- | ---------- | ------------------------ | ----------- |
23
+ | 300 | 8192 | 0.0051 | 0.0 (i.e., BT) | [3on0l4wl_0.0000_8192_1024_imagenet_resnet50.pth](https://github.com/wgcban/mix-bt/releases/download/v1.0.0/3on0l4wl_0.0000_8192_1024_imagenet_resnet50.pth) | 71.3 |
24
+ | 300 | 8192 | 0.0051 | 0.0025 | [l418b9zw_0.0025_8192_1024_imagenet_resnet50.pth](https://github.com/wgcban/mix-bt/releases/download/v1.0.0/l418b9zw_0.0025_8192_1024_imagenet_resnet50.pth) | 70.9 |
25
+ | 300 | 8192 | 0.0051 | 0.1 | [13awtq23_0.1000_8192_1024_imagenet_resnet50](https://github.com/wgcban/mix-bt/releases/download/v1.0.0/13awtq23_0.1000_8192_1024_imagenet_resnet50.pth) | 71.6 |
26
+ | 300 | 8192 | 0.0051 | 1.0 | [3fb1op86_1.0000_8192_1024_imagenet_resnet50.pth](https://github.com/wgcban/mix-bt/releases/download/v1.0.0/3fb1op86_1.0000_8192_1024_imagenet_resnet50.pth) | 72.2 |
27
+ | 300 | 8192 | 0.0051 | 3.0 | []() | xx.x |
28
+ | 300 | 8192 | 0.0051 | 5.0 | []() | xx.x |
29
+
30
+ Download the pre-trained models and store them in the `checkpoints/` folder.
checkpoints/test.py DELETED
File without changes