mirror of
https://github.com/open-mmlab/mmsegmentation.git
synced 2025-06-03 22:03:48 +08:00
b4fd32d049
* [Feature]Segformer re-implementation * Using act_cfg and norm_cfg to control activation and normalization * Split this PR into several little PRs * Fix lint error * Remove SegFormerHead * [Feature] Add segformer decode head and related train config * Add ade20K trainval support for segformer 1. Add related train and val configs; 2. Add AlignedResize; * Set arg: find_unused_parameters = True * parameters init refactor * 1. Refactor segformer backbone parameters init; 2. Remove rebundant functions and unit tests; * Remove rebundant codes * Replace Linear Layer to 1X1 Conv * Use nn.ModuleList to refactor segformer head. * Remove local to_xtuple * 1. Remove rebundant codes; 2. Modify module name; * Refactor the backbone of segformer using mmcv.cnn.bricks.transformer.py * Fix some code logic bugs. * Add mit_convert.py to match pretrain keys of segformer. * Resolve some comments. * 1. Add some assert to ensure right params; 2. Support flexible peconv position; * Add pe_index assert and fix unit test. * 1. Add doc string for MixVisionTransformer; 2. Add some unit tests for MixVisionTransformer; * Use hw_shape to pass shape of feature map. * 1. Fix doc string of MixVisionTransformer; 2. Simplify MixFFN; 3. Modify H, W to hw_shape; * Add more unit tests. * Add doc string for shape convertion functions. * Add some unit tests to improve code coverage. * Fix Segformer backbone pretrain weights match bug. * Modify configs of segformer. * resolve the shape convertion functions doc string. * Add pad_to_patch_size arg. * Support progressive test with fewer memory cost. * Modify default value of pad_to_patch_size arg. * Temp code * Using processor to refactor evaluation workflow. * refactor eval hook. * Fix process bar. * Fix middle save argument. * Modify some variable name of dataset evaluate api. * Modify some viriable name of eval hook. * Fix some priority bugs of eval hook. * Fix some bugs about model loading and eval hook. * Add ade20k 640x640 dataset. * Fix related segformer configs. * Depreciated efficient_test. * Fix training progress blocked by eval hook. * Depreciated old test api. * Modify error patch size. * Fix pretrain of mit_b0 * Fix the test api error. * Modify dataset base config. * Fix test api error. * Modify outer api. * Build a sampler test api. * TODO: Refactor format_results. * Modify variable names. * Fix num_classes bug. * Fix sampler index bug. * Fix grammaly bug. * Add part of benchmark results. * Support batch sampler. * More readable test api. * Remove some command arg and fix eval hook bug. * Support format-only arg. * Modify format_results of datasets. * Modify tool which use test apis. * Update readme. * Update readme of segformer. * Updata readme of segformer. * Update segformer readme and fix segformer mit_b4. * Update readme of segformer. * Clean AlignedResize related config. * Clean code from pr #709 * Clean code from pr #709 * Add 512x512 segformer_mit-b5. * Fix lint. * Fix some segformer head bugs. * Add segformer unit tests. * Replace AlignedResize to ResizeToMultiple. * Modify readme of segformer. * Fix bug of ResizeToMultiple. * Add ResizeToMultiple unit tests. * Resolve conflict. * Simplify the implementation of ResizeToMultiple. * Update test results. * Fix multi-scale test error when resize_ratio=1.75 and input size=640x640. * Update segformer results. * Update Segformer results. * Fix some url bugs and pipelines bug. * Move ckpt convertion to tools. * Add segformer official pretrain weights usage. * Clean redundant codes. * Remove redundant codes. * Unfied format. * Add description for segformer converter. * Update workers.
91 lines
2.8 KiB
Python
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
|