Is your feature request related to a problem? Please describe.
Nvidia Clara train 4.0 models (fully based on MONAI components) are now available, would be great to make them easily accessible from MONAI, in a similar manner to
|
def _load_state_dict(model, arch, progress): |
|
""" |
|
This function is used to load pretrained models. |
|
Adapted from `PyTorch Hub 2D version |
|
<https://github.com/pytorch/vision/blob/master/torchvision/models/densenet.py>`_ |
|
""" |
|
model_urls = { |
|
"densenet121": "https://download.pytorch.org/models/densenet121-a639ec97.pth", |
|
"densenet169": "https://download.pytorch.org/models/densenet169-b2777c0a.pth", |
|
"densenet201": "https://download.pytorch.org/models/densenet201-c1103571.pth", |
|
} |
see also:
clara train models: https://ngc.nvidia.com/catalog/models?orderBy=scoreDESC&pageNumber=0&query=clara_pt&quickFilter=&filters=
