| 12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970 |
- # Copyright (c) OpenMMLab. All rights reserved.
- import argparse
- import os.path as osp
- from collections import OrderedDict
- import mmengine
- import torch
- from mmengine.runner import CheckpointLoader
- def convert_vit(ckpt):
- new_ckpt = OrderedDict()
- for k, v in ckpt.items():
- if k.startswith('head'):
- continue
- if k.startswith('norm'):
- new_k = k.replace('norm.', 'ln1.')
- elif k.startswith('patch_embed'):
- if 'proj' in k:
- new_k = k.replace('proj', 'projection')
- else:
- new_k = k
- elif k.startswith('blocks'):
- if 'norm' in k:
- new_k = k.replace('norm', 'ln')
- elif 'mlp.fc1' in k:
- new_k = k.replace('mlp.fc1', 'ffn.layers.0.0')
- elif 'mlp.fc2' in k:
- new_k = k.replace('mlp.fc2', 'ffn.layers.1')
- elif 'attn.qkv' in k:
- new_k = k.replace('attn.qkv.', 'attn.attn.in_proj_')
- elif 'attn.proj' in k:
- new_k = k.replace('attn.proj', 'attn.attn.out_proj')
- else:
- new_k = k
- new_k = new_k.replace('blocks.', 'layers.')
- else:
- new_k = k
- new_ckpt[new_k] = v
- return new_ckpt
- def main():
- parser = argparse.ArgumentParser(
- description='Convert keys in timm pretrained vit models to '
- 'MMSegmentation style.')
- parser.add_argument('src', help='src model path or url')
- # The dst path must be a full path of the new checkpoint.
- parser.add_argument('dst', help='save path')
- args = parser.parse_args()
- checkpoint = CheckpointLoader.load_checkpoint(args.src, map_location='cpu')
- if 'state_dict' in checkpoint:
- # timm checkpoint
- state_dict = checkpoint['state_dict']
- elif 'model' in checkpoint:
- # deit checkpoint
- state_dict = checkpoint['model']
- else:
- state_dict = checkpoint
- weight = convert_vit(state_dict)
- mmengine.mkdir_or_exist(osp.dirname(args.dst))
- torch.save(weight, args.dst)
- if __name__ == '__main__':
- main()
|
