mmsegmentation
mmsegmentation copied to clipboard
open-mmlab
WHY IS BINARY SEGMENTATION SO DIFFICULT?
Hi
Im trying to do some binary segmentation and am receiving values that I should on validation and test data. After 3 iterations it says that the IOU is perfect. when it shouldn't be. its just black and white masks with shape (512,512). Im following this git repo for mae_unet https://github.com/implus/mae_segmentation.
I cant figure out how im supposed to make it work.
Test data:
+----------------------+-------+-------+
| Class | IoU | Acc |
+----------------------+-------+-------+
| obj of Interest | 100.0 | 100.0 |
| Background | 0.0 | nan |
+----------------------+-------+-------+
Summary:
+--------+------+-------+-------+
| Scope | mIoU | mAcc | aAcc |
+--------+------+-------+-------+
| global | 50.0 | 100.0 | 100.0 |
+--------+------+-------+-------+
validation:
+----------------------+-------+-------+
| Class | IoU | Acc |
+----------------------+-------+-------+
| obj of Interest | 100.0 | 100.0 |
| Background | 0.0 | nan |
+----------------------+-------+-------+
Summary:
+--------+------+-------+-------+
| Scope | mIoU | mAcc | aAcc |
+--------+------+-------+-------+
| global | 50.0 | 100.0 | 100.0 |
+--------+------+-------+-------+
Custom Dataloader:
from .custom import CustomDataset
from .builder import DATASETS
import os.path as osp
@DATASETS.register_module()
class CustomBinarySegDataset(CustomDataset):
CLASSES = ('Particle of Interest', 'Background', )
PALETTE = [ [1],[0],]
def __init__(self, **kwargs):
super(CustomBinarySegDataset, self).__init__(
img_suffix='.png',
seg_map_suffix='_mask.png',
reduce_zero_label=False,
**kwargs
)
assert osp.exists(self.img_dir)
config:
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained='/vast/home/mayolo/mae_git/mae/output_dir/checkpoint-799.pth',
backbone=dict(
type='MAE',
patch_size=16,
embed_dim=768,
depth=12,
num_heads=12,
mlp_ratio=4,
qkv_bias=True,
use_abs_pos_emb=True,
use_rel_pos_bias=True,
img_size=512,
init_values=1.0,
drop_path_rate=0.1,
out_indices=[3, 5, 7, 11]),
decode_head=dict(
type='UPerHead',
in_channels=[768, 768, 768, 768],
in_index=[0, 1, 2, 3],
pool_scales=(1, 2, 3, 6),
channels=768,
dropout_ratio=0.1,
num_classes=2,
norm_cfg=dict(type='SyncBN', requires_grad=True),
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
auxiliary_head=dict(
type='FCNHead',
in_channels=768,
in_index=2,
channels=256,
num_convs=1,
concat_input=False,
dropout_ratio=0.1,
num_classes=2,
norm_cfg=dict(type='SyncBN', requires_grad=True),
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
train_cfg=dict(),
test_cfg=dict(mode='slide', crop_size=(512, 512), stride=(341, 341)))
dataset_type = 'CustomBinarySegDataset'
data_root = '/vast/home/mayolo/512x512_Seg_Aug_images/base'
img_norm_cfg = dict(mean=[0, 0, 0], std=[254, 254, 254], to_rgb=True)
crop_size = (512, 512)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(reduce_zero_label=False, type='LoadAnnotations'),
dict(type='ConvertToGrayScaleMask'),
dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=(512, 512), cat_max_ratio=1),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Pad', size=(512, 512), pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 512),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='ConvertToGrayScaleMask'),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='CustomBinarySegDataset',
data_root='/vast/home/mayolo/512x512_Seg_Aug_images/base',
img_dir='/vast/home/mayolo/512x512_Seg_Aug_images/base/images/train',
ann_dir=
'/vast/home/mayolo/512x512_Seg_Aug_images/base/annotations/train',
pipeline=[
dict(type='LoadImageFromFile'),
dict(reduce_zero_label=False, type='LoadAnnotations'),
dict(type='ConvertToGrayScaleMask'),
dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=(512, 512), cat_max_ratio=1),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
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=dict(
type='CustomBinarySegDataset',
data_root='/vast/home/mayolo/512x512_Seg_Aug_images/base',
img_dir='/vast/home/mayolo/512x512_Seg_Aug_images/base/images/val',
ann_dir='/vast/home/mayolo/512x512_Seg_Aug_images/base/annotations/val',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 512),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='ConvertToGrayScaleMask'),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='CustomBinarySegDataset',
data_root='/vast/home/mayolo/512x512_Seg_Aug_images/base',
img_dir='/vast/home/mayolo/512x512_Seg_Aug_images/base/images/val',
ann_dir='/vast/home/mayolo/512x512_Seg_Aug_images/base/annotations/val',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 512),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='ConvertToGrayScaleMask'),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]))
log_config = dict(
interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
cudnn_benchmark = True
optimizer = dict(
type='AdamW',
lr=0.0001,
betas=(0.9, 0.999),
weight_decay=0.01,
constructor='LayerDecayOptimizerConstructor',
paramwise_cfg=dict(num_layers=12, layer_decay_rate=0.65))
optimizer_config = dict(
type='DistOptimizerHook',
update_interval=1,
grad_clip=None,
coalesce=True,
bucket_size_mb=-1,
use_fp16=True)
lr_config = dict(
policy='poly',
warmup='linear',
warmup_iters=1500,
warmup_ratio=1e-06,
power=1.0,
min_lr=0.0,
by_epoch=False)
max_iters = 200000
runner = dict(type='IterBasedRunnerAmp', max_iters=200000)
checkpoint_config = dict(by_epoch=False, interval=2000)
evaluation = dict(interval=100, metric='mIoU')
fp16 = None
work_dir = './work_dirs/upernet_mae_base_12_512_slide_160k_ade20k'
gpu_ids = range(0, 1)
greyscale transform acts as a normalization function also:
@PIPELINES.register_module()
class ConvertToGrayScaleMask(object):
"""Converts a segmentation map to a binary mask rather than the color coded one."""
def __init__(self):
pass
def __call__(self, results):
"""Call function to convert seg map to binary mask."""
for key in results.get("seg_fields", []):
if len(results[key].shape) == 3 and results[key].shape[2] == 3:
results[key] = cv2.cvtColor(results[key], cv2.COLOR_BGR2GRAY)
results[key] = cv2.normalize(results[key], None, alpha=0, beta=255, norm_type=cv2.NORM_MINMAX)
results[key] = np.where(results[key] > 0, 1, 0).astype(np.float32)#allows for test.py to work
return results
def __repr__(self):
return self.__class__.__name__
the main thing you can do is introduce dice loss along with IoU metric and then optimize your model based on results of both the losses.
