-
Notifications
You must be signed in to change notification settings - Fork 9.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Question about MultiDatasetsEvaluator #11796
Comments
I recently developed a project where I used MultiDatasetsEvaluator val_dataloader = dict(
batch_size=BATCH//2,
num_workers=BATCH//2,
drop_last=False,
persistent_workers=True,
sampler=dict(type="DefaultSampler", shuffle=False),
dataset=dict(
type="ConcatDataset",
datasets=[val_real_dataset, val_synth_dataset],
),
) and if use_segm:
metrics.append("segm")
val_evaluator = dict(
type='MultiDatasetsEvaluator',
metrics=[
dict(type=metric_type, metric=metrics, classwise=True),
dict(type=metric_type, metric=metrics, classwise=True),
],
dataset_prefixes=["real", "synth"]
) Everything worked great |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
When using MultiDatasetsEvaluator, I find that it will show that the evaluator shows no cumulative_sizes making it impossible to proceed, but my val_dataloader uses concatdatasets.
Here is my config:
val_evaluator = dict(
type='MultiDatasetsEvaluator',
metrics=metrics,
dataset_prefixes=dataset_prefixes
)
val_dataloader = dict(
batch_size=val_batch_size_per_gpu,
num_workers=val_num_workers,
persistent_workers=persistent_workers,
pin_memory=True,
drop_last=False,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type='ConcatDataset',
datasets=[
A3_roi1_dataset_val,
A3_roi2_dataset_val,
A3_roi3_dataset_val,
A3_roi4_dataset_val,
A3_roi5_dataset_val
]
)
)
The text was updated successfully, but these errors were encountered: