Task Mate Kenyan Sign Language Classification Hackathon by #ZindiWeekendz
'/%3e%3c/defs%3e%3cpath fill='%23fff' d='M-120-80h240V80h-240z'/%3e%3cpath d='M-120-80h240v48h-240z'/%3e%3cpath fill='%23060' d='M-120 32h240v48h-240z'/%3e%3cg id='b'%3e%3cuse xlink:href='%23a' stroke='%23000'/%3e%3cuse xlink:href='%23a' fill='%23fff'/%3e%3c/g%3e%3cuse xlink:href='%23b' transform='scale(-1 1)'/%3e%3cpath fill='%23b00' d='M-120-24v48h101c3 8 13 24 19 24s16-16 19-24h101v-48H19C16-32 6-48 0-48s-16 16-19 24z'/%3e%3cpath id='c' d='M19 24c3-8 5-16 5-24s-2-16-5-24c-3 8-5 16-5 24s2 16 5 24'/%3e%3cuse xlink:href='%23c' transform='scale(-1 1)'/%3e%3cg fill='%23fff'%3e%3cellipse rx='4' ry='6'/%3e%3cpath id='d' d='M1 5.85s4 8 4 21-4 21-4 21z'/%3e%3cuse xlink:href='%23d' transform='scale(-1)'/%3e%3cuse xlink:href='%23d' transform='scale(-1 1)'/%3e%3cuse xlink:href='%23d' transform='scale(1 -1)'/%3e%3c/g%3e%3c/svg%3e)
Helping Kenya
$300 USD
Challenge completed ~4 years ago
Classification
Computer Vision
96 joined
43 active
Start
Nov 05, 21
Close
Nov 07, 21
Reveal
Nov 07, 21
Best Val_loss
Platform · 8 Nov 2021, 06:26 · 3
Hello guys,
Great job well done to you all on this interesting challenge. If you wouldn't mind, i will like to know your best "Val_loss" from any individual who took part in this awesome challenge.
Thanks.
MICADEE
Mine was around 0.08 with 80/20 train/val
Nice. Amazing!!! But are you sure this is your Valid_loss or error_rate? Seems to me this is your "error_rate" not Valid_loss. And if that be the case, what's your final Log_Loss of this (Valid_loss=0.08) on Public LB?
Thank you.
This is indeed the loss value, validation error_rate was around 0.02-0.03.
On public LB it got 0.17 and 0.14 with TTA.
I believe that the difference between val_loss\Public LB is due to some wrong images in the testset (which do not contain any of the classes). I cleared the training dataset from any of these wrong examples, so there loss was lower.