model = torch.hub.load('hankyul2/EfficientNetV2-pytorch', 'efficientnet_v2_s', pretrained=True, nclass=1000) wrong

File "/root/.cache/torch/hub/hankyul2_EfficientNetV2-pytorch_master/efficientnetv2/pretrained_weight_loader.py", line 123, in load_npy
    param.data.copy_(npz_dim_convertor(name, weight.get(name)))
RuntimeError: output with shape [256, 1, 3, 3] doesn't match the broadcast shape [256, 256, 3, 3]