Quiz · 4 questions
⚡ TPUs & Distributed Training
From 1 GPU to a TPU pod — distribution strategies, mixed precision, scaling recipes
Level 0Level 0
0 XP0/78 lessons0/17 achievements
0/100 XP to next level100 XP to go0% complete
Quiz
01MirroredStrategy with 4 GPUs and per-replica batch 64. What's the global batch size from the optimizer's perspective?
02Why drop_remainder=True for TPU training?
03Correct mixed precision policy for TPU, and why?
04Role of TF_CONFIG in MultiWorkerMirroredStrategy?
Comments 0
🔔 Reply notifications (sign in)Sign in — Please sign in to comment.
No comments yet — be the first.