mmsegmentation/mmseg/models/utils/ckpt_convert.py

91 lines
2.8 KiB
Python

from collections import OrderedDict
def swin_convert(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('head'):
continue
elif k.startswith('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('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 vit_convert(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