Instructions to use timm/vit_huge_patch14_224_in21k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use timm/vit_huge_patch14_224_in21k with timm:
import timm model = timm.create_model("hf_hub:timm/vit_huge_patch14_224_in21k", pretrained=True) - Transformers
How to use timm/vit_huge_patch14_224_in21k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="timm/vit_huge_patch14_224_in21k") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("timm/vit_huge_patch14_224_in21k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Initial commit
Browse files- README.md +2 -0
- config.json +23 -0
- pytorch_model.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# ViT-H/14 (ImageNet-21k)
|
| 2 |
+
...
|
config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architecture": "vit_huge_patch14_224_in21k",
|
| 3 |
+
"num_classes": 21843,
|
| 4 |
+
"input_size": [
|
| 5 |
+
3,
|
| 6 |
+
224,
|
| 7 |
+
224
|
| 8 |
+
],
|
| 9 |
+
"crop_pct": 0.9,
|
| 10 |
+
"interpolation": "bicubic",
|
| 11 |
+
"mean": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"std": [
|
| 17 |
+
0.5,
|
| 18 |
+
0.5,
|
| 19 |
+
0.5
|
| 20 |
+
],
|
| 21 |
+
"first_conv": "patch_embed.proj",
|
| 22 |
+
"classifier": "head"
|
| 23 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44efe50e6b889e919b8cd7feb35b6114a0a75a9bee17bc3597df36a66a3aeab1
|
| 3 |
+
size 2641619129
|