Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

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

Open
WHUThcz opened this issue Sep 10, 2024 · 1 comment
Open

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

WHUThcz opened this issue Sep 10, 2024 · 1 comment

Comments

@WHUThcz
Copy link

WHUThcz commented Sep 10, 2024

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
Copy link
Author

WHUThcz commented Sep 10, 2024

When segmenting the Ade20k dataset, it is normal

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@WHUThcz