mirror of
https://github.com/lucidrains/vit-pytorch.git
synced 2025-12-30 08:02:29 +00:00
Update README.md (#283)
`patch_size` is size of patches, not number of patches
This commit is contained in:
@@ -92,7 +92,7 @@ preds = v(img) # (1, 1000)
|
|||||||
- `image_size`: int.
|
- `image_size`: int.
|
||||||
Image size. If you have rectangular images, make sure your image size is the maximum of the width and height
|
Image size. If you have rectangular images, make sure your image size is the maximum of the width and height
|
||||||
- `patch_size`: int.
|
- `patch_size`: int.
|
||||||
Number of patches. `image_size` must be divisible by `patch_size`.
|
Size of patches. `image_size` must be divisible by `patch_size`.
|
||||||
The number of patches is: ` n = (image_size // patch_size) ** 2` and `n` **must be greater than 16**.
|
The number of patches is: ` n = (image_size // patch_size) ** 2` and `n` **must be greater than 16**.
|
||||||
- `num_classes`: int.
|
- `num_classes`: int.
|
||||||
Number of classes to classify.
|
Number of classes to classify.
|
||||||
|
|||||||
Reference in New Issue
Block a user