upernet_flash_internimage_t_512_160k_ade20k.py

# --------------------------------------------------------
# DCNv4
# Copyright (c) 2024 OpenGVLab
# Licensed under The MIT License [see LICENSE for details]
# --------------------------------------------------------
_base_ = [
    '../_base_/models/upernet_r50.py', '../_base_/datasets/ade20k.py',
    '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
]
pretrained = 'https://huggingface.co/OpenGVLab/DCNv4/resolve/main/flash_intern_image_t_1k_224.pth'
model = dict(
    backbone=dict(
        _delete_=True,
        type='FlashInternImage',
        core_op='DCNv4',
        channels=64,
        depths=[4, 4, 18, 4],
        groups=[4, 8, 16, 32],
        mlp_ratio=4.,
        drop_path_rate=0.2,
        norm_layer='LN',
        layer_scale=1.0,
        offset_scale=1.0,
        post_norm=False,
        with_cp=True,
        out_indices=(0, 1, 2, 3),
        init_cfg=dict(type='Pretrained', checkpoint=pretrained)),
    decode_head=dict(num_classes=150, in_channels=[64, 128, 256, 512]),
    auxiliary_head=dict(num_classes=150, in_channels=256),
    test_cfg=dict(mode='whole')
)
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(2048, 512),
        # 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=0.00006, betas=(0.9, 0.999), weight_decay=0.05,
    constructor='CustomLayerDecayOptimizerConstructor',
    paramwise_cfg=dict(num_layers=30, layer_decay_rate=1.0,
                       depths=[4, 4, 18, 4]))
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)
# By default, models are trained on 8 GPUs with 2 images per GPU
data=dict(samples_per_gpu=2,
          # 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=16000, metric='mIoU', save_best='mIoU')
# fp16 = dict(loss_scale=dict(init_scale=512))