44 panoptic docs #94
44 panoptic docs #94
Conversation
alodataset/coco_panoptic_dataset.py
Outdated
| @@ -44,6 +45,9 @@ class CocoPanopticDataset(BaseDataset, SplitMixin): | |||
| Include masks labels in the output, by default True | |||
| classes : list, optional | |||
| List of classes to be filtered in the annotation reading process, by default None | |||
| fix_classes_len : int, optional | |||
| Fix to a specific number the number of classes, filling the rest with "N/A" value. | |||
| Use when the number of model outputs does not match with the number of classes in the dataset, by default 250 | |||
There was a problem hiding this comment.
Why is the default value 250 ? To match the model ? If so, I guess the default value should be None.
There was a problem hiding this comment.
@thibo73800 Ok, I will change in #89
alodataset/coco_panoptic_dataset.py
Outdated
| @@ -101,6 +111,23 @@ def __init__( | |||
| items.append(self.items[i]) | |||
| self.items = items | |||
|
|
|||
| # Fix label_types | |||
There was a problem hiding this comment.
Can you give more details about what the following is doing ?
| # import wandb | ||
|
|
||
|
|
||
| class BaseMetricsCallback(pl.Callback): |
There was a problem hiding this comment.
Not sure BaseMetricsCallback is descriptive enough about the kind of data handle by this class. Currently BaseMetricsCallback is used for Panoptic & mAp right ? But not for ANY type of metrics. Just Objects/instance based metrics. So i'm not sure which name could be the most appropriate but, probably not this one.
There was a problem hiding this comment.
@thibo73800 fix in #89
|
@thibo73800: For this branch, is required merge first #89 to see the docs changes only |
|
@thibo73800 : I updated the Ready to merge |
New documentations:
Update documentation of:
And fix link by new DataConnectors modules (explained in #89 )
**Important note: Not merge until merge first #89 **
Closes #2 - #44 - #104