Spaces:
Running
Running
File size: 2,878 Bytes
28c256d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 |
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
import argparse
import subprocess
from collections import OrderedDict
import torch
from mmengine.runner import CheckpointLoader
def swin_converter(ckpt):
new_ckpt = OrderedDict()
def correct_unfold_reduction_order(x):
out_channel, in_channel = x.shape
x = x.reshape(out_channel, 4, in_channel // 4)
x = x[:, [0, 2, 1, 3], :].transpose(1,
2).reshape(out_channel, in_channel)
return x
def correct_unfold_norm_order(x):
in_channel = x.shape[0]
x = x.reshape(4, in_channel // 4)
x = x[[0, 2, 1, 3], :].transpose(0, 1).reshape(in_channel)
return x
for k, v in ckpt.items():
if k.startswith('backbone.layers'):
new_v = v
if 'attn.' in k:
new_k = k.replace('attn.', 'attn.w_msa.')
elif 'mlp.' in k:
if '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.')
else:
new_k = k.replace('mlp.', 'ffn.')
elif 'downsample' in k:
new_k = k
if 'reduction.' in k:
new_v = correct_unfold_reduction_order(v)
elif 'norm.' in k:
new_v = correct_unfold_norm_order(v)
else:
new_k = k
new_k = new_k.replace('layers', 'stages', 1)
elif k.startswith('backbone.patch_embed'):
new_v = v
if 'proj' in k:
new_k = k.replace('proj', 'projection')
else:
new_k = k
else:
new_v = v
new_k = k
new_ckpt[new_k] = new_v
return new_ckpt
def main():
parser = argparse.ArgumentParser(
description='Convert keys to mmdet 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:
state_dict = checkpoint['state_dict']
else:
state_dict = checkpoint
torch.save(swin_converter(state_dict), args.dst)
sha = subprocess.check_output(['sha256sum', args.dst]).decode()
final_file = args.dst.replace('.pth', '') + '-{}.pth'.format(sha[:8])
subprocess.Popen(['mv', args.dst, final_file])
print(f'Done!!, save to {final_file}')
if __name__ == '__main__':
main()
|