Loading pretrained 22k small error！！

[hjb2333]

('Error(s) in loading state_dict for VisionTransformer:\n\tsize mismatch for patch_embed_t.proj.weight: copying a param with shape torch.Size([384, 3, 32, 32]) from checkpoint, the shape in current model is torch.Size([384, 3, 16, 16]).',) 在训练tracking_small时，加载预训练模型遇到了这个问题

[dawnyc]

Sorry for that and the late reply. The link I provided is for patch size 32. You can try this: https://storage.googleapis.com/vit_models/augreg/S_16-i21k-300ep-lr_0.001-aug_light1-wd_0.03-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.03-res_224.npz . This is for patch size 16.