数据集处理问题 about vitae-transformer-remote-sensing HOT 3 OPEN

@Liwiman 您的问题缺乏细节，我无法回答，我不知道你有几类，也不知道你 forest land 是第几类，或者其对应的label index是多少，因此我无法给出修改config的意见

from vitae-transformer-remote-sensing.

感谢您的回答我已经解决了上诉问题，并将模型投入训练了，但我在训练过程中出现了问题，想恳请您解答。
我训练的数据集是128*128的100000张遥感图片，在

预训练权重的基础上进行训练，设置batch_size为16训练107500个iter后设置batch_size为40训练了22500个iter，但是模型效果很差（val的图片也是训练的图片，其实是在训练集的部分上val）：{"mode": "val", "epoch": 7, "iter": 5129, "lr": 5e-05, "aAcc": 0.6659, "mIoU": 0.4843, "mAcc": 0.6469, "mFscore": 0.6483, "mPrecision": 0.6688, "mRecall": 0.6469, "IoU.water": 0.5942, "IoU.transportation": 0.4205, "IoU.architecture": 0.5802, "IoU.farmland": 0.4988, "IoU.grassland": 0.3906, "IoU.forest land": 0.5741, "IoU.bare soil": 0.3818, "IoU.others": 0.4341, "Acc.water": 0.855, "Acc.transportation": 0.5327, "Acc.architecture": 0.6978, "Acc.farmland": 0.6573, "Acc.grassland": 0.6929, "Acc.forest land": 0.6918, "Acc.bare soil": 0.4493, "Acc.others": 0.5983, "Fscore.water": 0.7455, "Fscore.transportation": 0.592, "Fscore.architecture": 0.7343, "Fscore.farmland": 0.6656, "Fscore.grassland": 0.5617, "Fscore.forest land": 0.7294, "Fscore.bare soil": 0.5526, "Fscore.others": 0.6054, "Precision.water": 0.6608, "Precision.transportation": 0.6662, "Precision.architecture": 0.7749, "Precision.farmland": 0.6741, "Precision.grassland": 0.4723, "Precision.forest land": 0.7715, "Precision.bare soil": 0.7175, "Precision.others": 0.6128, "Recall.water": 0.855, "Recall.transportation": 0.5327, "Recall.architecture": 0.6978, "Recall.farmland": 0.6573, "Recall.grassland": 0.6929, "Recall.forest land": 0.6918, "Recall.bare soil": 0.4493, "Recall.others": 0.5983}，就算输入的是训练集图片，推断效果还是很差：

而该图片的label可视化应该是这样的：

我模型的config文件如下：
norm_cfg = dict(type='BN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained=
'work_dirs/cd_train/iter_25000.pth',
backbone=dict(
type='ViTAE_Window_NoShift_basic',
RC_tokens_type=['swin', 'swin', 'transformer', 'transformer'],
NC_tokens_type=['swin', 'swin', 'transformer', 'transformer'],
stages=4,
embed_dims=[64, 64, 128, 256],
token_dims=[64, 128, 256, 512],
downsample_ratios=[4, 2, 2, 2],
NC_depth=[2, 2, 8, 2],
NC_heads=[1, 2, 4, 8],
RC_heads=[1, 1, 2, 4],
mlp_ratio=4.0,
NC_group=[1, 32, 64, 128],
RC_group=[1, 16, 32, 64],
img_size=512,
window_size=7,
drop_path_rate=0.3),
decode_head=dict(
type='UPerHead',
in_channels=[64, 128, 256, 512],
in_index=[0, 1, 2, 3],
pool_scales=(1, 2, 3, 6),
channels=512,
dropout_ratio=0.1,
num_classes=8,
norm_cfg=dict(type='BN', requires_grad=True),
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
ignore_index=8),
auxiliary_head=dict(
type='FCNHead',
in_channels=256,
in_index=2,
channels=256,
num_convs=1,
concat_input=False,
dropout_ratio=0.1,
num_classes=8,
norm_cfg=dict(type='BN', requires_grad=True),
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4),
ignore_index=8),
train_cfg=dict(),
test_cfg=dict(mode='whole'))
dataset_type = 'HuaweiDataset'
data_root = '/output/mmsegmentation/small_train'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (512, 512)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='Resize', img_scale=(512, 512), ratio_range=(1.0, 1.0)),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='PhotoMetricDistortion'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size=(512, 512), pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
]
val_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(512, 512),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(256, 256),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='Resize', img_scale=(512, 512)),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=16,
workers_per_gpu=8,
train=dict(
type='HuaweiDataset',
data_root='/output/mmsegmentation/small_train',
img_dir='images',
ann_dir='labels',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='Resize', img_scale=(512, 512), ratio_range=(1.0, 1.0)),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='PhotoMetricDistortion'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size=(512, 512), pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
],
split='splits/train.txt'),
val=dict(
type='HuaweiDataset',
data_root='/output/mmsegmentation/small_train',
img_dir='images',
ann_dir='anns',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(256, 256),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='Resize', img_scale=(512, 512)),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
],
split='splits/val.txt'),
test=dict(
type='HuaweiDataset',
data_root='/output/mmsegmentation/small_train',
img_dir='images',
ann_dir='anns',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(256, 256),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='Resize', img_scale=(512, 512)),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
],
split='splits/val.txt'))
log_config = dict(
interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = '/home/mmsegmentation/work_dirs/cd_train/iter_25000.pth'
resume_from = '/home/mmsegmentation/work_dirs/cd_train/iter_25000.pth'
workflow = [('train', 1)]
cudnn_benchmark = True
optimizer = dict(
type='AdamW',
lr=6e-05,
betas=(0.9, 0.999),
weight_decay=0.01,
paramwise_cfg=dict(
custom_keys=dict(
absolute_pos_embed=dict(decay_mult=0.0),
relative_position_bias_table=dict(decay_mult=0.0),
norm=dict(decay_mult=0.0))))
optimizer_config = dict()
lr_config = dict(
policy='poly',
warmup='linear',
warmup_iters=1500,
warmup_ratio=1e-06,
power=1.0,
min_lr=0.0,
by_epoch=False)
runner = dict(type='IterBasedRunner', max_iters=10000)
checkpoint_config = dict(by_epoch=False, interval=1000)
evaluation = dict(interval=1000, metric=['mIoU', 'mFscore'], pre_eval=True)
find_unused_parameters = True
work_dir = './work_dirs/cd_train'
gpu_ids = range(0, 1)
auto_resume = False
seed = 0
device = 'cuda'

训练是采用tools/train.py这个文件进行训练的，您能帮我解答为什么训练效果不好吗？万分感谢！

from vitae-transformer-remote-sensing.

@Liwiman 从你给的图看，大概率是标签没对齐，标签和类别的配置需要针对不同数据集进行专门设置，您可以参考以下issue
#9
#21
#23

from vitae-transformer-remote-sensing.