How to use the new EVA models? (create_model reports Unknown model)

[BingliangLi]

Hi, I'm trying to use the exciting new EVA models as the backbone of my task, but I'm unable to create it using create_model, can anyone help me with it please?

>>> timm.__version__
'0.6.12'
>>> model = timm.create_model('eva_large_patch14_336', pretrained=True)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/local/miniconda3/lib/python3.9/site-packages/timm/models/factory.py", line 67, in create_model
    raise RuntimeError('Unknown model (%s)' % model_name)
RuntimeError: Unknown model (eva_large_patch14_336)

[BingliangLi]

It turns out that EVA is not released on pypi yet, use pip install git+https://github.com/rwightman/pytorch-image-models.git to install the dev works for me.

[rwightman]

yeah, it wasn't on pypi, but I just pushed another dev release with that plus a few newer things. But it's dev so beware as I've been refactoring and streamlining some things.

pip install --pre timm installs the latest 0.8.x pre release