You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Having Datasets API for commonly used formats will come in handy.
Pitch
A non-exhaustive list of formats that are commonly used:
CSV file with image_id and target columns (Binary or Multi-Class Classification). There are two ways that are used most often in this:
image_id target
100011 1
100015 0
100007 2
Above has been implemented using CSVSingleLabelDataset. Should we add support for below in the same or should we create a separate one? I think we can have both in the same.
Above has been implemented using create_folder_dataset but we don't always need to split the train into train_set and valid_set. Because we may have cases where valid_set is pre-defined like below:
For object detection task, there are two other frequently used formats: Pascal VOC and MSCOCO, and it is supported in torchvision, I am not sure that we didn't mention this two Datasets is for we just use torchvision's implementation when we met this two datasets?
I think we should discuss more over this. Datasets is really tricky especially when it comes to object detection etc.
For the Torchvision models, we expect VOC format.
And for Detr, a normalized YOLO format.
We haven't enforced these as these have come from models themselves.
🚀 Feature
Having Datasets API for commonly used formats will come in handy.
Pitch
A non-exhaustive list of formats that are commonly used:
image_id
andtarget
columns (Binary or Multi-Class Classification
). There are two ways that are used most often in this:Above has been implemented using
CSVSingleLabelDataset
. Should we add support for below in the same or should we create a separate one? I think we can have both in the same.image_id
andtarget
columns (Multi-Label Classification
). Similarly, there are two ways that are used most often in this:Above has been implemented using
create_folder_dataset
but we don't always need to split thetrain
intotrain_set
andvalid_set
. Because we may have cases wherevalid_set
is pre-defined like below:image_id
andbbox
column (Object Detection
). Similar to classification tasks, there can be two ways that are used most often in this:Honestly, I have never seen the below format but still we can have support for this.
I have come across only the above four formats, but do let me know if I missed any. And also let me know your thoughts on the above.
cc @zhiqwang
The text was updated successfully, but these errors were encountered: