Instructions to use SmilingWolf/wd-eva02-large-tagger-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use SmilingWolf/wd-eva02-large-tagger-v3 with timm:
import timm model = timm.create_model("hf_hub:SmilingWolf/wd-eva02-large-tagger-v3", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Maybe wrong input_size in config.json?
#8
by kingwingfly - opened
"input_size": [
3,
448,
448
],
But with onnx runtime loaded, its:
inputs: [
Outlet {
name: "input",
dtype: Tensor {
ty: Float32,
shape: [
-1,
448,
448,
3,
],
...
So 3, 448, 448 VS 448, 448, 3, which is correct?