assert len(indices) == len(self) #62
Comments
|
Could you post the full log here? |
|
thanks,
sys.platform: linux
TorchVision: 0.7.0
|
|
I am not sure what the problem is. I have tried to change the |
|
thanks a lot!!! |
|
Could you have a look at the json file and check whether correct number of instances is loaded? I have tried to build a similar python environment and similar config but it seems ok. |
|
I guess the parametyer epoch_length is too small for your dataset since I encountered the same problem in my medical daataset weeks ago and solved this simply by turning it bigger. I haven't carefully look at the sampler code so it's just a simple and maybe unreasonable guess. |
|
I am having this same issue. Regardless of what I set epoch_length to, _base_ = [parent_dir+'SoftTeacher/configs/soft_teacher/base.py']
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train = dict(
sup = dict(
ann_file=parent_dir+sup_data_path+'/train_data/annotations.json',
img_prefix=parent_dir+sup_data_path+'/train_data/',
classes=classes
),
unsup = dict(
ann_file=parent_dir+unsup_data_path+'/train_data/annotations.json',
img_prefix=parent_dir+unsup_data_path+'/train_data/',
classes=classes
),
),
val = dict(
ann_file=parent_dir+sup_data_path+'/val_data/annotations.json',
img_prefix=parent_dir+sup_data_path+'/val_data/',
classes=classes
),
test = dict(
ann_file=parent_dir+sup_data_path+'/val_data/annotations.json',
img_prefix=parent_dir+sup_data_path+'/val_data/',
classes=classes
),
sampler=dict(
train=dict(
type="SemiBalanceSampler",
sample_ratio=[1, 4],
by_prob=True,
# at_least_one=True,
epoch_length=1000,
)
),
)
evaluation = dict(interval=1000, metric='bbox', type='SubModulesDistEvalHook')
optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
evaluation = dict(type="SubModulesDistEvalHook", interval=4000)
optimizer = dict(type="SGD", lr=0.01, momentum=0.9, weight_decay=0.0001)
lr_config = dict(step=[3000, 4000])
runner = dict(_delete_=True, type="IterBasedRunner", max_iters=5000)
checkpoint_config = dict(by_epoch=False, interval=1000, max_keep_ckpts=2)
fp16 = dict(loss_scale="dynamic")
log_config = dict(
interval=49,
hooks=[
dict(type="TextLoggerHook", by_epoch=False),
dict(
type="WandbLoggerHook",
init_kwargs=dict(
project="pre_release",
name="${cfg_name}",
config=dict(
work_dirs="${work_dir}",
total_step="${runner.max_iters}",
),
),
by_epoch=False,
),
],
) |
|
@jessicametzger I have same problem. Did you solve this? |
|
@watermellon2018 I was able to to fix it by setting |
|
@winnerziqi how you solved this issue? |
|
where did you set self.by_prob =false exactly .. in the code its a part of if loop |
|
i got it. in my config, it already set to False . and i still have same problem .. what shall i do ? |
how did u solve the problem? |
my problem was in the present of mask annotaion, while my dataset dose not have any mask information and annotaion.
i hope this will help you. |
|
thank u, I'll have a try. |
hello,
When I use it, raise error: "assert len(indices) == len(self), f"{indices} not equal {len(self)} while offset is: {offset}""
then I print the length info, =====len of indices is 26865 - offset: 0 - len self 36650
below is the detail error info, Please help me.
Traceback (most recent call last): File "tools/train.py", line 198, in <module> main() File "tools/train.py", line 193, in main meta=meta, File "/data6/ziqiwen/code/softteacher/ssod/apis/train.py", line 206, in train_detector runner.run(data_loaders, cfg.workflow) File "/home/ziqiwen/anaconda3/envs/mm/lib/python3.7/site-packages/mmcv/runner/iter_based_runner.py", line 117, in run iter_loaders = [IterLoader(x) for x in data_loaders] File "/home/ziqiwen/anaconda3/envs/mm/lib/python3.7/site-packages/mmcv/runner/iter_based_runner.py", line 117, in <listcomp> iter_loaders = [IterLoader(x) for x in data_loaders] File "/home/ziqiwen/anaconda3/envs/mm/lib/python3.7/site-packages/mmcv/runner/iter_based_runner.py", line 23, in __init__ self.iter_loader = iter(self._dataloader) File "/home/ziqiwen/anaconda3/envs/mm/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 291, in __iter__ return _MultiProcessingDataLoaderIter(self) File "/home/ziqiwen/anaconda3/envs/mm/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 764, in __init__ self._try_put_index() File "/home/ziqiwen/anaconda3/envs/mm/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 994, in _try_put_index index = self._next_index() File "/home/ziqiwen/anaconda3/envs/mm/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 357, in _next_index return next(self._sampler_iter) # may raise StopIteration File "/home/ziqiwen/anaconda3/envs/mm/lib/python3.7/site-packages/torch/utils/data/sampler.py", line 208, in __iter__ for idx in self.sampler: File "/data6/ziqiwen/code/softteacher/ssod/datasets/samplers/semi_sampler.py", line 189, in __iter__ assert len(indices) == len(self) AssertionError Traceback (most recent call last): File "/home/ziqiwen/anaconda3/envs/mm/lib/python3.7/runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "/home/ziqiwen/anaconda3/envs/mm/lib/python3.7/runpy.py", line 85, in _run_code exec(code, run_globals) File "/home/ziqiwen/anaconda3/envs/mm/lib/python3.7/site-packages/torch/distributed/launch.py", line 261, in <module> main() File "/home/ziqiwen/anaconda3/envs/mm/lib/python3.7/site-packages/torch/distributed/launch.py", line 257, in main cmd=cmd)The text was updated successfully, but these errors were encountered: