Skip to content

Commit 3810d21

Browse files
authored
fix cat 🐈
1 parent 6f7443f commit 3810d21

File tree

1 file changed

+3
-1
lines changed

1 file changed

+3
-1
lines changed

README.md

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -28,7 +28,7 @@ Pip install the `nbdt` utility and run it on an image of your choosing. This can
2828

2929
```bash
3030
pip install nbdt
31-
nbdt https://images.pexels.com/photos/1170986/pexels-photo-1170986.jpeg?auto=compress&cs=tinysrgb&dpr=2&w=32
31+
nbdt https://images.pexels.com/photos/126407/pexels-photo-126407.jpeg?auto=compress&cs=tinysrgb&dpr=2&w=32
3232
```
3333

3434
This outputs both the class prediction and all the intermediate decisions, like below:
@@ -67,6 +67,8 @@ pip install nbdt
6767

6868
Then, pick an NBDT inference mode (hard or soft), dataset, and backbone. By default, we support ResNet18 and WideResNet28x10 for CIFAR10, CIFAR100, and TinyImagenet200. See [nbdt-pytorch-image-models](https://github.com/alvinwan/nbdt-pytorch-image-models) for EfficientNet-EdgeTPUSmall on ImageNet.
6969

70+
<sub>[Try below script on Google Colab]()</sub>
71+
7072
```python
7173
from nbdt.model import SoftNBDT
7274
from nbdt.models import ResNet18, wrn28_10_cifar10, wrn28_10_cifar100, wrn28_10 # use wrn28_10 for TinyImagenet200

0 commit comments

Comments
 (0)