Zindi
CompeteJobsLearnChatLeaderboardFor Organisations
PartnersMeet the teamPressCase studiesAI4EAC
Primary competition visual

InstaDeep Enzyme Classification Challenge

Job Interview
Completed (over 5 years ago)
Classification
527 joined
70 active
InfoDataChatLeaderboard
Starti
17 Nov 20
Closei
21 Feb 21
Reveali
21 Feb 21
User avatar
laboratory
Trust Stamp
Reasonable epoch execution time
Help · 6 Feb 2021, 06:49 · 5

My model is taking forever (about 45-60 min) to complete an epoch (which I think is due to the long sequences) for a daily simple (baseline) network. I haven't even added "bells and whistles". So I want to find out what an ideal epoch execution time is. I am afraid I cannot even train larger and better networks with this execution time

With 5 epochs, I start at 30.0% accuracy and end at 29.9% (basically, no learning).

Is my architecture wrong? Am I calculating accuracy wrongly? I will appreciate any help.

Thanks.

Discussion 5 answers
User avatar
aninda_bitm
6 Feb 2021, 06:56

What model architecture you are using? Try using

Upvotes 0
User avatar
laboratory
6 Feb 2021, 07:02replied to aninda_bitm

1 embed -> 1 LSTM -> 2 Linear (relu and softmax)

Upvotes 0
User avatar
aninda_bitm
6 Feb 2021, 07:15replied to laboratory

Try TPU in colab. In GPU, the running time is very

Upvotes 0
User avatar
laboratory
6 Feb 2021, 07:19replied to aninda_bitm

Thanks for your assistance. I will try that.

However, your responses seem to be incomplete. Your initial reply said "try using..." this one says the running time is very..." both incomplete

I think you should check that. Thanks

Upvotes 0
User avatar
aninda_bitm
6 Feb 2021, 07:22 (edited 1 minute later)replied to laboratory

Sorry I don't know why the last word got cutoff. I meant that running time in GPU is very high. Try using colab tpu.

Upvotes 0

Join the largest network for
data scientists and AI builders

AboutFAQsPrivacy PolicyTerms of UseRules
Status
© Zindi 2026