Anybody have a code snip that allows looking at MAP5 as a metric during training?
Anyone have any thoughts on how they are applying new_whale as a lable?
Anybody have a code snip that allows looking at MAP5 as a metric during training?
Anyone have any thoughts on how they are applying new_whale as a lable?
Iām not in this challenge (yet), but for the playground version earlier this year I used a top-4 prediction and added new_whale to those 4 after inference.
That was my first thought on how to do it (havenāt yet.)
Other thoughts:
Option @1 above got me to just about the median of the leader board currently with a (I think?) well trained resnet34. I.E ā Right about at the āno informationā score lol.
I have dropped all new whales from my input set and then trying to train the model. But I am no where near to my target.
Whatās your target?
Hi gang - I believe this is an active competition. The Kaggle rules donāt allow any sharing outside teams other than on the kaggle forums. So you should move this discussion over there.
Thanks for the heads up ā FWIW, weāre hovering under the median score, but Iāll stop posting techniques. Slowly moving up the leaderboards
Without sharing methods ā hit .425 without doing anything clever (just throwing cycle time at the problem) so at least Iām beating no information now.
Hello All,
I have image databunch and any idea how i can access the validation data set? I can access data_whale.x but not getting how to access validation set X? What is the list name?
ImageDataBunch;
Train: LabelList
y: CategoryList (3473 items)
[Category w_f48451c, Category w_f48451c, Category w_f48451c, Category w_f48451c, Category w_f48451c]ā¦
Path: /home/nbuser/courses/fast-ai/course-v3/nbs/data/humpback_whale_kaggle
x: ImageItemList (3473 items)
[Image (3, 176, 264), Image (3, 176, 264), Image (3, 176, 264), Image (3, 176, 264), Image (3, 176, 264)]ā¦
Path: /home/nbuser/courses/fast-ai/course-v3/nbs/data/humpback_whale_kaggle;
Valid: LabelList
y: CategoryList (868 items)
[Category w_488865e, Category w_9b5109b, Category w_4bf625b, Category w_91cc02c, Category w_cd4cb49]ā¦
Path: /home/nbuser/courses/fast-ai/course-v3/nbs/data/humpback_whale_kaggle
x: ImageItemList (868 items)
[Image (3, 188, 264), Image (3, 150, 264), Image (3, 83, 264), Image (3, 113, 264), Image (3, 148, 264)]ā¦
Path: /home/nbuser/courses/fast-ai/course-v3/nbs/data/humpback_whale_kaggle;
Test: None
Thereās a current thread about doing predictions on a test set in the Course 1 v3 forum.
My aim is to to manually append these list but i donno how to get the validation list for X and Y oneā¦
Data.test_ds
I am getting error while tryingā¦I tried data_whale.test_ds
TypeError Traceback (most recent call last)
in ()
----> 1 dict(data_whale)
TypeError: āImageDataBunchā object is not iterable
Thanks for help. I have now got itā¦
data_whale.dict.keys()
data_whale.valid_dl.x