-
Notifications
You must be signed in to change notification settings - Fork 142
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
add a config for Mask2Former+BEiT-Adapter-L
ade20k 160k iters without coco-stuff
- Loading branch information
Showing
2 changed files
with
173 additions
and
11 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
153 changes: 153 additions & 0 deletions
153
segmentation/configs/ade20k/mask2former_beitv2_adapter_large_896_160k_ade20k_ss.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,153 @@ | ||
| # Copyright (c) Shanghai AI Lab. All rights reserved. | ||
| _base_ = [ | ||
| '../_base_/models/mask2former_beit.py', | ||
| '../_base_/datasets/ade20k.py', | ||
| '../_base_/default_runtime.py', | ||
| '../_base_/schedules/schedule_160k.py' | ||
| ] | ||
| crop_size = (896, 896) | ||
| # pretrained = 'https://conversationhub.blob.core.windows.net/beit-share-public/beitv2/beitv2_large_patch16_224_pt1k_ft21k.pth' | ||
| pretrained = 'pretrained/beitv2_large_patch16_224_pt1k_ft21k.pth' | ||
| model = dict( | ||
| type='EncoderDecoderMask2Former', | ||
| pretrained=pretrained, | ||
| backbone=dict( | ||
| type='BEiTAdapter', | ||
| img_size=896, | ||
| patch_size=16, | ||
| embed_dim=1024, | ||
| depth=24, | ||
| num_heads=16, | ||
| mlp_ratio=4, | ||
| qkv_bias=True, | ||
| use_abs_pos_emb=False, | ||
| use_rel_pos_bias=True, | ||
| init_values=1e-6, | ||
| drop_path_rate=0.3, | ||
| conv_inplane=64, | ||
| n_points=4, | ||
| deform_num_heads=16, | ||
| cffn_ratio=0.25, | ||
| deform_ratio=0.5, | ||
| with_cp=True, # set with_cp=True to save memory | ||
| interaction_indexes=[[0, 5], [6, 11], [12, 17], [18, 23]], | ||
| ), | ||
| decode_head=dict( | ||
| in_channels=[1024, 1024, 1024, 1024], | ||
| feat_channels=1024, | ||
| out_channels=1024, | ||
| num_queries=200, | ||
| pixel_decoder=dict( | ||
| type='MSDeformAttnPixelDecoder', | ||
| num_outs=3, | ||
| norm_cfg=dict(type='GN', num_groups=32), | ||
| act_cfg=dict(type='ReLU'), | ||
| encoder=dict( | ||
| type='DetrTransformerEncoder', | ||
| num_layers=6, | ||
| transformerlayers=dict( | ||
| type='BaseTransformerLayer', | ||
| attn_cfgs=dict( | ||
| type='MultiScaleDeformableAttention', | ||
| embed_dims=1024, | ||
| num_heads=32, | ||
| num_levels=3, | ||
| num_points=4, | ||
| im2col_step=64, | ||
| dropout=0.0, | ||
| batch_first=False, | ||
| norm_cfg=None, | ||
| init_cfg=None), | ||
| ffn_cfgs=dict( | ||
| type='FFN', | ||
| embed_dims=1024, | ||
| feedforward_channels=4096, | ||
| num_fcs=2, | ||
| ffn_drop=0.0, | ||
| with_cp=True, # set with_cp=True to save memory | ||
| act_cfg=dict(type='ReLU', inplace=True)), | ||
| operation_order=('self_attn', 'norm', 'ffn', 'norm')), | ||
| init_cfg=None), | ||
| positional_encoding=dict( | ||
| type='SinePositionalEncoding', num_feats=512, normalize=True), | ||
| init_cfg=None), | ||
| positional_encoding=dict( | ||
| type='SinePositionalEncoding', num_feats=512, normalize=True), | ||
| transformer_decoder=dict( | ||
| type='DetrTransformerDecoder', | ||
| return_intermediate=True, | ||
| num_layers=9, | ||
| transformerlayers=dict( | ||
| type='DetrTransformerDecoderLayer', | ||
| attn_cfgs=dict( | ||
| type='MultiheadAttention', | ||
| embed_dims=1024, | ||
| num_heads=32, | ||
| attn_drop=0.0, | ||
| proj_drop=0.0, | ||
| dropout_layer=None, | ||
| batch_first=False), | ||
| ffn_cfgs=dict( | ||
| embed_dims=1024, | ||
| feedforward_channels=4096, | ||
| num_fcs=2, | ||
| act_cfg=dict(type='ReLU', inplace=True), | ||
| ffn_drop=0.0, | ||
| dropout_layer=None, | ||
| with_cp=True, # set with_cp=True to save memory | ||
| add_identity=True), | ||
| feedforward_channels=4096, | ||
| operation_order=('cross_attn', 'norm', 'self_attn', 'norm', | ||
| 'ffn', 'norm')), | ||
| init_cfg=None) | ||
| ), | ||
| test_cfg=dict(mode='slide', crop_size=crop_size, stride=(512, 512)) | ||
| ) | ||
| # dataset settings | ||
| img_norm_cfg = dict( | ||
| mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) | ||
| train_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict(type='LoadAnnotations', reduce_zero_label=True), | ||
| dict(type='Resize', img_scale=(3584, 896), ratio_range=(0.5, 2.0)), | ||
| dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75), | ||
| dict(type='RandomFlip', prob=0.5), | ||
| dict(type='PhotoMetricDistortion'), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255), | ||
| dict(type='ToMask'), | ||
| dict(type='DefaultFormatBundle'), | ||
| dict(type='Collect', keys=['img', 'gt_semantic_seg', 'gt_masks', 'gt_labels']) | ||
| ] | ||
| test_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict( | ||
| type='MultiScaleFlipAug', | ||
| img_scale=(3584, 896), | ||
| # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75], | ||
| flip=False, | ||
| transforms=[ | ||
| dict(type='Resize', keep_ratio=True), | ||
| dict(type='ResizeToMultiple', size_divisor=32), | ||
| dict(type='RandomFlip'), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='ImageToTensor', keys=['img']), | ||
| dict(type='Collect', keys=['img']), | ||
| ]) | ||
| ] | ||
| optimizer = dict(_delete_=True, type='AdamW', lr=2e-5, betas=(0.9, 0.999), weight_decay=0.05, | ||
| constructor='LayerDecayOptimizerConstructor', | ||
| paramwise_cfg=dict(num_layers=24, layer_decay_rate=0.90)) | ||
| lr_config = dict(_delete_=True, | ||
| policy='poly', | ||
| warmup='linear', | ||
| warmup_iters=1500, | ||
| warmup_ratio=1e-6, | ||
| power=1.0, min_lr=0.0, by_epoch=False) | ||
| data = dict(samples_per_gpu=1, | ||
| train=dict(pipeline=train_pipeline), | ||
| val=dict(pipeline=test_pipeline), | ||
| test=dict(pipeline=test_pipeline)) | ||
| runner = dict(type='IterBasedRunner') | ||
| checkpoint_config = dict(by_epoch=False, interval=1000, max_keep_ckpts=1) | ||
| evaluation = dict(interval=8000, metric='mIoU', save_best='mIoU') |