mask2former预测为0

[kkfather]

我的数据集是tif四通道的图像，使用mask2former进行训练时，有些类预测的为0，这是什么原因，请求帮助

[kkfather]

System environment:
sys.platform: linux
Python: 3.8.20 (default, Oct 3 2024, 15:24:27) [GCC 11.2.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 921661533
GPU 0,1: NVIDIA GeForce RTX 4090
CUDA_HOME: /usr/local/cuda-11.8
NVCC: Cuda compilation tools, release 11.8, V11.8.89
GCC: gcc (Ubuntu 8.4.0-3ubuntu2) 8.4.0
PyTorch: 2.0.0
PyTorch compiling details: PyTorch built with:

• GCC 9.3

• C++ Version: 201703

• Intel(R) oneAPI Math Kernel Library Version 2023.1-Product Build 20230303 for Intel(R) 64 architecture applications

• Intel(R) MKL-DNN v2.7.3 (Git Hash 6dbeffbae1f23cbbeae17adb7b5b13f1f37c080e)

• OpenMP 201511 (a.k.a. OpenMP 4.5)

• LAPACK is enabled (usually provided by MKL)

• NNPACK is enabled

• CPU capability usage: AVX2

• CUDA Runtime 11.8

• NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90;-gencode;arch=compute_37,code=compute_37

• CuDNN 8.7

• Magma 2.6.1

• Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.8, CUDNN_VERSION=8.7.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.0.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,

  TorchVision: 0.15.0
  OpenCV: 4.13.0
  MMEngine: 0.10.7

Runtime environment:
cudnn_benchmark: True
mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0}
dist_cfg: {'backend': 'nccl'}
seed: 921661533
Distributed launcher: pytorch
Distributed training: True
GPU number: 2

04/01 18:09:49 - mmengine - INFO - Config:
auto_scale_lr = dict(base_batch_size=16, enable=False)
data_preprocessor = dict(
bgr_to_rgb=False,
mean=[
1021.7617119579807,
896.5843177778289,
686.5531715616888,
983.6205963500472,
],
pad_val=0,
seg_pad_val=255,
size=(
768,
768,
),
std=[
285.50654264183277,
275.29580010573426,
231.924369555635,
263.6894818950533,
],
type='SegDataPreProcessor')
data_root = '/data/ysk/datasize/768/'
dataset_type = 'CustomTifDataset'
default_hooks = dict(
checkpoint=dict(
by_epoch=False, interval=9000, save_best='mIoU',
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'
embed_multi = dict(decay_mult=0.0, lr_mult=1.0)
env_cfg = dict(
cudnn_benchmark=True,
dist_cfg=dict(backend='nccl'),
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
launcher = 'pytorch'
load_from = None
log_level = 'INFO'
log_processor = dict(by_epoch=False)
model = dict(
backbone=dict(
attn_drop_rate=0.0,
depths=[
2,
2,
18,
2,
],
drop_path_rate=0.1,
drop_rate=0.0,
embed_dims=128,
in_channels=4,
init_cfg=None,
mlp_ratio=4,
num_heads=[
4,
8,
16,
32,
],
out_indices=(
0,
1,
2,
3,
),
patch_norm=True,
pretrain_img_size=384,
qk_scale=None,
qkv_bias=True,
type='SwinTransformer',
use_abs_pos_embed=False,
window_size=12),
data_preprocessor=dict(
bgr_to_rgb=False,
mean=[
1021.7617119579807,
896.5843177778289,
686.5531715616888,
983.6205963500472,
],
pad_val=0,
seg_pad_val=255,
size=(
768,
768,
),
std=[
285.50654264183277,
275.29580010573426,
231.924369555635,
263.6894818950533,
],
type='SegDataPreProcessor'),
decode_head=dict(
align_corners=False,
enforce_decoder_input_project=False,
feat_channels=256,
in_channels=[
128,
256,
512,
1024,
],
loss_cls=dict(
class_weight=[
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.1,
],
loss_weight=2.0,
reduction='mean',
type='mmdet.CrossEntropyLoss',
use_sigmoid=False),
loss_dice=dict(
activate=True,
eps=1.0,
loss_weight=5.0,
naive_dice=True,
reduction='mean',
type='mmdet.DiceLoss',
use_sigmoid=True),
loss_mask=dict(
loss_weight=5.0,
reduction='mean',
type='mmdet.CrossEntropyLoss',
use_sigmoid=True),
num_classes=8,
num_queries=100,
num_transformer_feat_level=3,
out_channels=256,
pixel_decoder=dict(
act_cfg=dict(type='ReLU'),
encoder=dict(
init_cfg=None,
layer_cfg=dict(
ffn_cfg=dict(
act_cfg=dict(inplace=True, type='ReLU'),
embed_dims=256,
feedforward_channels=1024,
ffn_drop=0.0,
num_fcs=2),
self_attn_cfg=dict(
batch_first=True,
dropout=0.0,
embed_dims=256,
im2col_step=64,
init_cfg=None,
norm_cfg=None,
num_heads=8,
num_levels=3,
num_points=4)),
num_layers=6),
init_cfg=None,
norm_cfg=dict(num_groups=32, type='GN'),
num_outs=3,
positional_encoding=dict(normalize=True, num_feats=128),
type='mmdet.MSDeformAttnPixelDecoder'),
positional_encoding=dict(normalize=True, num_feats=128),
strides=[
4,
8,
16,
32,
],
train_cfg=dict(
assigner=dict(
match_costs=[
dict(type='mmdet.ClassificationCost', weight=2.0),
dict(
type='mmdet.CrossEntropyLossCost',
use_sigmoid=True,
weight=5.0),
dict(
eps=1.0,
pred_act=True,
type='mmdet.DiceCost',
weight=5.0),
],
type='mmdet.HungarianAssigner'),
importance_sample_ratio=0.75,
num_points=12544,
oversample_ratio=3.0,
sampler=dict(type='mmdet.MaskPseudoSampler')),
transformer_decoder=dict(
init_cfg=None,
layer_cfg=dict(
cross_attn_cfg=dict(
attn_drop=0.0,
batch_first=True,
dropout_layer=None,
embed_dims=256,
num_heads=8,
proj_drop=0.0),
ffn_cfg=dict(
act_cfg=dict(inplace=True, type='ReLU'),
add_identity=True,
dropout_layer=None,
embed_dims=256,
feedforward_channels=2048,
ffn_drop=0.0,
num_fcs=2),
self_attn_cfg=dict(
attn_drop=0.0,
batch_first=True,
dropout_layer=None,
embed_dims=256,
num_heads=8,
proj_drop=0.0)),
num_layers=9,
return_intermediate=True),
type='Mask2FormerHead'),
test_cfg=dict(mode='whole'),
train_cfg=dict(),
type='EncoderDecoder')
num_classes = 8
optim_wrapper = dict(
clip_grad=dict(max_norm=0.01, norm_type=2),
optimizer=dict(
betas=(
0.9,
0.999,
),
eps=1e-08,
lr=0.0001,
type='AdamW',
weight_decay=0.05),
paramwise_cfg=dict(
custom_keys=dict(
backbone=dict(decay_mult=1.0, lr_mult=0.1),
level_embed=dict(decay_mult=0.0, lr_mult=1.0),
query_embed=dict(decay_mult=0.0, lr_mult=1.0),
query_feat=dict(decay_mult=0.0, lr_mult=1.0)),
norm_decay_mult=0.0),
type='OptimWrapper')
optimizer = dict(
betas=(
0.9,
0.999,
),
eps=1e-08,
lr=0.0001,
type='AdamW',
weight_decay=0.05)
param_scheduler = [
dict(
begin=0,
by_epoch=False,
end=90000,
eta_min=0,
power=0.9,
type='PolyLR'),
]
resume = False
test_cfg = dict(type='TestLoop')
test_dataloader = dict(
batch_size=1,
dataset=dict(
data_prefix=dict(
img_path='images_compare/val', seg_map_path='labels_compare/val'),
data_root='/data/ysk/datasize/768/',
pipeline=[
dict(type='LoadTifImageFromFile'),
dict(keep_ratio=True, scale=(
768,
768,
), type='Resize'),
dict(reduce_zero_label=False, type='LoadAnnotations'),
dict(type='PackSegInputs'),
],
type='CustomTifDataset'),
num_workers=4,
persistent_workers=True,
sampler=dict(shuffle=False, type='DefaultSampler'))
test_evaluator = dict(
iou_metrics=[
'mIoU',
], type='IoUMetric')
test_pipeline = [
dict(type='LoadTifImageFromFile'),
dict(keep_ratio=True, scale=(
768,
768,
), type='Resize'),
dict(reduce_zero_label=False, type='LoadAnnotations'),
dict(type='PackSegInputs'),
]
train_cfg = dict(max_iters=90000, type='IterBasedTrainLoop', val_interval=5000)
train_dataloader = dict(
batch_size=2,
dataset=dict(
data_prefix=dict(
img_path='images_compare/train',
seg_map_path='labels_compare/train'),
data_root='/data/ysk/datasize/768/',
pipeline=[
dict(type='LoadTifImageFromFile'),
dict(reduce_zero_label=False, type='LoadAnnotations'),
dict(
keep_ratio=True,
ratio_range=(
0.5,
2.0,
),
scale=(
768,
768,
),
type='RandomResize'),
dict(
cat_max_ratio=0.75, crop_size=(
768,
768,
), type='RandomCrop'),
dict(prob=0.5, type='RandomFlip'),
dict(type='PackSegInputs'),
],
type='CustomTifDataset'),
num_workers=4,
persistent_workers=True,
sampler=dict(shuffle=True, type='InfiniteSampler'))
train_pipeline = [
dict(type='LoadTifImageFromFile'),
dict(reduce_zero_label=False, type='LoadAnnotations'),
dict(
keep_ratio=True,
ratio_range=(
0.5,
2.0,
),
scale=(
768,
768,
),
type='RandomResize'),
dict(cat_max_ratio=0.75, crop_size=(
768,
768,
), type='RandomCrop'),
dict(prob=0.5, type='RandomFlip'),
dict(type='PackSegInputs'),
]
val_cfg = dict(type='ValLoop')
val_dataloader = dict(
batch_size=1,
dataset=dict(
data_prefix=dict(
img_path='images_compare/val', seg_map_path='labels_compare/val'),
data_root='/data/ysk/datasize/768/',
pipeline=[
dict(type='LoadTifImageFromFile'),
dict(keep_ratio=True, scale=(
768,
768,
), type='Resize'),
dict(reduce_zero_label=False, type='LoadAnnotations'),
dict(type='PackSegInputs'),
],
type='CustomTifDataset'),
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/mask2former_swin-b'