Add map_location='cpu' to ModelEma resume, should improve #72

Author: rwightman

timm/utils.py

@@ -259,7 +259,7 @@ def __init__(self, model, decay=0.9999, device='', resume=''):
             p.requires_grad_(False)
 
     def _load_checkpoint(self, checkpoint_path):
-        checkpoint = torch.load(checkpoint_path)
+        checkpoint = torch.load(checkpoint_path, map_location='cpu')
         assert isinstance(checkpoint, dict)
         if 'state_dict_ema' in checkpoint:
             new_state_dict = OrderedDict()