Constant IoU after every validation
cspearl opened this issue · comments
Hi, I was a bit late to reply to my issue(assigned to @MengzhangLI ) that I was having so it probably got skipped. Please find the details of the issue and the log file here : #1988
Appreciate any help!
Hi @cspearl @MengzhangLI,
Faced the same issue when trained using latest codebase commit for binary class segmentation (roads class).
mIOU, aACC, mACC is the same through out training.
Attaching log file below.
20220907_152411.log
Thanks
Hi, @sainivedh19pt, try to set your dataset annotation 0
and 1
and set reduce_zero_label=False
in your config file.
You can check out what does reduce_zero_label
work from here.
Hi, @cspearl, could you try to set reduce_zero_label = False
, and num_classes = 1
and ensure your annotation files only have label 0
and label 1
?
Hi, @cspearl, could you try to set
reduce_zero_label = False
, andnum_classes = 1
and ensure your annotation files only have label0
and label1
?
Yes I tried but it gives the same result. My annotation files only have 0 - background and 1 - foreground labels.
Hi @cspearl, Could you try to set the different thresholds to the decode_head?
Can you elaborate a bit on what to add? In the decode head dict
Hi @cspearl, Could you try to set the different thresholds to the decode_head?
Can you elaborate a bit on what to add? In the decode head dict
Hi, @MengzhangLI
same problem..
in decode_head and auxiliary_head num_classes=2
2022-09-22 00:22:24,627 - mmseg - INFO -
+------------+-------+-------+--------+-----------+--------+
| Class | IoU | Acc | Fscore | Precision | Recall |
+------------+-------+-------+--------+-----------+--------+
| background | 44.56 | 45.68 | 61.65 | 94.78 | 45.68 |
| class | 0.01 | 0.31 | 0.03 | 0.01 | 0.31 |
+------------+-------+-------+--------+-----------+--------+
custom dataset:
from mmseg.datasets.builder import DATASETS
from mmseg.datasets.custom import CustomDataset
CLASSES = ['background', 'class']
PALETTE = [[0, 0, 0], [244, 35, 232]]
@DATASETS.register_module()
class MylDataset(CustomDataset):
CLASSES = CLASSES
PALETTE = PALETTE
def __init__(self, **kwargs):
super().__init__(
img_suffix='.png', seg_map_suffix='.png',
**kwargs
)
assert osp.exists(self.img_dir) #and self.split is not None```
Hi, sorry for late reply. Did you solve your problem?
You can have a look at #2201 by setting num_classes=1
and use_sigmoid=True
in CrossEntropyLoss
.
Hi @cspearl @MengzhangLI, Faced the same issue when trained using latest codebase commit for binary class segmentation (roads class). mIOU, aACC, mACC is the same through out training. Attaching log file below. 20220907_152411.log
Thanks
From your log could you keep every parameter in config except setting reduce_zero_label=False
? Thx.
Closing the issue, as there is no activity for a while.
We hope your issue has been resolved.
If not, please feel free to open a new one.