search

open-mmlab / mmsegmentation

OpenMMLab Semantic Segmentation Toolbox and Benchmark.
https://mmsegmentation.readthedocs.io/en/main/
Apache License 2.0
8.35k stars 2.63k forks source link

When segmenting the Pascal VOC 2012 dataset, one class resulted in NaN. #3768

Open WHUThcz opened 2 months ago

WHUThcz commented 2 months ago

QPQYNVHLLH{Z58{BDE{BUK1 the config and dataset

# Copyright (c) OpenMMLab. All rights reserved.
import os.path as osp

import mmengine.fileio as fileio

from mmseg.registry import DATASETS
from .basesegdataset import BaseSegDataset

@DATASETS.register_module()
class PascalVOCDataset(BaseSegDataset):
    """Pascal VOC dataset.

    Args:
        split (str): Split txt file for Pascal VOC.
    """
    METAINFO = dict(
        classes=('background', 'aeroplane', 'bicycle', 'bird', 'boat',
                 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable',
                 'dog', 'horse', 'motorbike', 'person', 'pottedplant', 'sheep',
                 'sofa', 'train', 'tvmonitor'),
        palette=[[0, 0, 0], [128, 0, 0], [0, 128, 0], [128, 128, 0],
                 [0, 0, 128], [128, 0, 128], [0, 128, 128], [128, 128, 128],
                 [64, 0, 0], [192, 0, 0], [64, 128, 0], [192, 128, 0],
                 [64, 0, 128], [192, 0, 128], [64, 128, 128], [192, 128, 128],
                 [0, 64, 0], [128, 64, 0], [0, 192, 0], [128, 192, 0],
                 [0, 64, 128]])

    def __init__(self,
                 ann_file,
                 img_suffix='.jpg',
                 seg_map_suffix='.png',
                 **kwargs) -> None:
        super().__init__(
            img_suffix=img_suffix,
            seg_map_suffix=seg_map_suffix,
            ann_file=ann_file,
            **kwargs)
        assert fileio.exists(self.data_prefix['img_path'],
                             self.backend_args) and osp.isfile(self.ann_file)

crop_size = (
    512,
    512,
)
data_preprocessor = dict(
    bgr_to_rgb=True,
    mean=[
        123.675,
        116.28,
        103.53,
    ],
    pad_val=0,
    seg_pad_val=255,
    size=(
        512,
        512,
    ),
    std=[
        58.395,
        57.12,
        57.375,
    ],
    type='SegDataPreProcessor')
data_root = 'data/VOCdevkit/VOC2012'
dataset_type = 'PascalVOCDataset'
default_hooks = dict(
    checkpoint=dict(by_epoch=False, interval=5000, type='CheckpointHook'),
    logger=dict(interval=50, log_metric_by_epoch=False, type='LoggerHook'),
    param_scheduler=dict(type='ParamSchedulerHook'),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    timer=dict(type='IterTimerHook'),
    visualization=dict(type='SegVisualizationHook'))
default_scope = 'mmseg'
env_cfg = dict(
    cudnn_benchmark=True,
    dist_cfg=dict(backend='nccl'),
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
img_ratios = [
    0.5,
    0.75,
    1.0,
    1.25,
    1.5,
    1.75,
]
launcher = 'pytorch'
load_from = 'fpvt_pretrained.pth'
log_level = 'INFO'
log_processor = dict(by_epoch=False)
model = dict(
    backbone=dict(
        type='fpvt_tiny'),
    data_preprocessor=dict(
        bgr_to_rgb=True,
        mean=[
            123.675,
            116.28,
            103.53,
        ],
        pad_val=0,
        seg_pad_val=255,
        size=(
            512,
            512,
        ),
        std=[
            58.395,
            57.12,
            57.375,
        ],
        type='SegDataPreProcessor'),
    decode_head=dict(
        align_corners=False,
        channels=128,
        dropout_ratio=0.1,
        feature_strides=[
            4,
            8,
            16,
            32,
        ],
        in_channels=[
            256,
            256,
            256,
            256,
        ],
        in_index=[
            0,
            1,
            2,
            3,
        ],
        loss_decode=dict(
            loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=False),
        norm_cfg=dict(requires_grad=True, type='SyncBN'),
        num_classes=21,
        type='FPNHead'),
    neck=dict(
        in_channels=[
            32,
            64,
            160,
            256,
        ],
        num_outs=4,
        out_channels=256,
        type='FPN'),
    pretrained=True,
    test_cfg=dict(mode='whole'),
    train_cfg=dict(),
    type='EncoderDecoder')
norm_cfg = dict(requires_grad=True, type='SyncBN')
optim_wrapper = dict(
    optimizer=dict(
        betas=(
            0.9,
            0.999,
        ), lr=4e-05, type='AdamW', weight_decay=0.01),
    # optimizer=dict(lr=0.01, momentum=0.9, type='SGD', weight_decay=0.0005),
    paramwise_cfg=dict(
        bypass_duplicate=True,
        custom_keys=dict(
            head=dict(lr_mult=10.0),
            norm=dict(decay_mult=0.0),
            pos_block=dict(decay_mult=0.0))),
    type='OptimWrapper')

param_scheduler = [
    dict(
        begin=0, by_epoch=False, end=1500, start_factor=1e-06,
        type='LinearLR'),
    dict(
        begin=1500,
        by_epoch=False,
        end=320000,
        eta_min=0.0,
        power=0.9,
        type='PolyLR'),
]
resume = False
test_cfg = dict(type='TestLoop')
test_dataloader = dict(
    batch_size=1,
    dataset=dict(
        ann_file='ImageSets/Segmentation/val.txt',
        data_prefix=dict(
            img_path='JPEGImages', seg_map_path='SegmentationClass'),
        data_root='data/VOCdevkit/VOC2012',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(keep_ratio=True, scale=(
                2048,
                512,
            ), type='Resize'),
            dict(type='LoadAnnotations'),
            dict(type='PackSegInputs'),
        ],
        reduce_zero_label=True,
        type='PascalVOCDataset'),
    num_workers=4,
    persistent_workers=True,
    sampler=dict(shuffle=False, type='DefaultSampler'))
test_evaluator = dict(
    iou_metrics=[
        'mIoU',
    ], type='IoUMetric')
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(keep_ratio=True, scale=(
        2048,
        512,
    ), type='Resize'),
    dict(type='LoadAnnotations'),
    dict(type='PackSegInputs'),
]
train_cfg = dict(
    max_iters=320000, type='IterBasedTrainLoop', val_interval=5000)
train_dataloader = dict(
    batch_size=8,
    dataset=dict(
        ann_file='ImageSets/Segmentation/train.txt',
        data_prefix=dict(
            img_path='JPEGImages', seg_map_path='SegmentationClass'),
        data_root='data/VOCdevkit/VOC2012',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations'),
            dict(
                keep_ratio=True,
                ratio_range=(
                    0.5,
                    2.0,
                ),
                scale=(
                    2048,
                    512,
                ),
                type='RandomResize'),
            dict(
                cat_max_ratio=0.75, crop_size=(
                    512,
                    512,
                ), type='RandomCrop'),
            dict(prob=0.5, type='RandomFlip'),
            dict(type='PhotoMetricDistortion'),
            dict(type='PackSegInputs'),
        ],
        reduce_zero_label=True,
        type='PascalVOCDataset'),
    num_workers=2,
    persistent_workers=True,
    sampler=dict(shuffle=True, type='InfiniteSampler'))
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations'),
    dict(
        keep_ratio=True,
        ratio_range=(
            0.5,
            2.0,
        ),
        scale=(
            2048,
            512,
        ),
        type='RandomResize'),
    dict(cat_max_ratio=0.75, crop_size=(
        512,
        512,
    ), type='RandomCrop'),
    dict(prob=0.5, type='RandomFlip'),
    dict(type='PhotoMetricDistortion'),
    dict(type='PackSegInputs'),
]
tta_model = dict(type='SegTTAModel')
tta_pipeline = [
    dict(backend_args=None, type='LoadImageFromFile'),
    dict(
        transforms=[
            [
                dict(keep_ratio=True, scale_factor=0.5, type='Resize'),
                dict(keep_ratio=True, scale_factor=0.75, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.0, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.25, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.5, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.75, type='Resize'),
            ],
            [
                dict(direction='horizontal', prob=0.0, type='RandomFlip'),
                dict(direction='horizontal', prob=1.0, type='RandomFlip'),
            ],
            [
                dict(type='LoadAnnotations'),
            ],
            [
                dict(type='PackSegInputs'),
            ],
        ],
        type='TestTimeAug'),
]
val_cfg = dict(type='ValLoop')
val_dataloader = dict(
    batch_size=1,
    dataset=dict(
        ann_file='ImageSets/Segmentation/val.txt',
        data_prefix=dict(
            img_path='JPEGImages', seg_map_path='SegmentationClass'),
        data_root='data/VOCdevkit/VOC2012',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(keep_ratio=True, scale=(
                2048,
                512,
            ), type='Resize'),
            dict(type='LoadAnnotations'),
            dict(type='PackSegInputs'),
        ],
        reduce_zero_label=True,
        type='PascalVOCDataset'),
    num_workers=4,
    persistent_workers=True,
    sampler=dict(shuffle=False, type='DefaultSampler'))
val_evaluator = dict(
    iou_metrics=[
        'mIoU',
    ], type='IoUMetric')
vis_backends = [
    dict(type='LocalVisBackend'),
]
visualizer = dict(
    name='visualizer',
    type='SegLocalVisualizer',
    vis_backends=[
        dict(type='LocalVisBackend'),
    ])
work_dir = './work_dirs/fpn_fpvt_t_pascal_voc12_40k'
WHUThcz commented 2 months ago

When segmenting the Ade20k dataset, it is normal