Discussions

• 2 You must be logged in to vote

  ⚡

  set with model.no_sync() in lightning training step

  maxmatical asked Nov 28, 2021 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Unanswered

  

  

  

  

  4
• 1 You must be logged in to vote

  ⚡

  Question: How to switch models ?

  yukkyo asked Aug 13, 2019 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Unanswered

  

  

  

  

  15
• 1 You must be logged in to vote

  ⚡

  GPU usage maxed at 10%

  cowwoc asked Jan 23, 2022 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Unanswered

  

  

  8
• 1 You must be logged in to vote

  ⚡

  Multi-GPU Tensor Initialization Question

  xsys-technology asked Feb 6, 2022 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Answered

  

  

  9
• 16 You must be logged in to vote

  🤖

  Pipeline Parallelism with DeepSpeed

  amorehead asked Feb 8, 2022 in DDP / multi-GPU / multi-node · Unanswered

  

  

  0
• 2 You must be logged in to vote

  😎

  Different predictions after loading model in different jupyter notebook

  shmahaj asked Feb 7, 2022 in code help: CV · Unanswered

  

  

  0
• 1 You must be logged in to vote

  ⚡

  Log one Image after every layer

  V-Krause asked Feb 6, 2022 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Unanswered

  

  

  8
• 1 You must be logged in to vote

  ⚡

  Saving checkpoint, hparams & tfevents after training to separate folder

  dispoth asked Feb 7, 2022 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Answered

  

  

  2
• 2 You must be logged in to vote

  ⚡

  Any plans to update the IPU strategy API?

  strategy strategy: ipu (removed)

  daniellepintz asked Feb 4, 2022 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Unanswered

  

  

  

  

  5
• 2 You must be logged in to vote

  ⚡

  weights_save_path vs ckpt_path

  daniellepintz asked Nov 15, 2021 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Unanswered

  

  

  

  

  2
• 3 You must be logged in to vote

  💡

  Should the LightningModule have a property for a datamodule?

  ananthsub started Feb 5, 2022 in Idea pool

  

  

  0
• 1 You must be logged in to vote

  ⚡

  Enabling dropout during trainer.predict

  standard-aaron asked Feb 3, 2022 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Answered

  

  

  2
• 3 You must be logged in to vote

  ⚡

  Script Killed with DDP + wandb?

  logger: wandb Weights & Biases

  dmandair asked Feb 3, 2022 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Unanswered

  

  

  0
• 1 You must be logged in to vote

  👾

  How to use pytorch-lightning for meta learning

  wheatdog asked Jan 10, 2020 in code help: RL / MetaLearning · Unanswered

  

  

  

  

  17
• 1 You must be logged in to vote

  ⚡

  How do training_step wrappers affect backprop?

  OverLordGoldDragon asked Feb 3, 2022 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Unanswered

  

  

  0
• 1 You must be logged in to vote

  ⚡

  Question about load checkpoint for my own model

  exiawsh asked Feb 3, 2022 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Unanswered

  

  

  1
• 1 You must be logged in to vote

  ⚡

  Hook for Fully Formed Checkpoints

  dcharatan asked Feb 2, 2022 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Answered

  

  

  2
• 1 You must be logged in to vote

  ⚡

  Hook for Fully Formed Checkpoints

  dcharatan asked Feb 2, 2022 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Answered

  

  

  1
• 1 You must be logged in to vote

  ⚡

  Best practice for re-using arguments between multiple parent classes in pl cli

  Jimmy2027 asked Jan 28, 2022 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Unanswered

  

  

  

  

  8
• 1 You must be logged in to vote

  🤖

  Get batch’s datapoints across all GPUs

  fmorenopino asked Jan 31, 2022 in DDP / multi-GPU / multi-node · Answered

  

  

  6
• 2 You must be logged in to vote

  🤖

  Memory use different on both gpus using ddp

  accelerator: cuda Compute Unified Device Architecture GPU performance

  surya-narayanan asked Feb 1, 2022 in DDP / multi-GPU / multi-node · Unanswered

  

  

  0
• 2 You must be logged in to vote

  ⚡

  Gradient accumulation + DeepSpeed LR scheduler

  gahdritz asked Feb 1, 2022 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Answered

  

  

  1
• 1 You must be logged in to vote

  ⚡

  What if I load data in __init__ function of LightningDataModule

  zhiqiangdon asked Nov 26, 2021 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Answered

  

  

  

  

  7
• 1 You must be logged in to vote

  ⚡

  Link arguments from Datamodule into init_args of lr_scheduler

  LourencoVazPato asked Jan 26, 2022 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Closed · Answered

  

  

  

  

  2
• 1 You must be logged in to vote

  ⚡

  Question about the log system

  exiawsh asked Jan 31, 2022 in Lightning Trainer API: Trainer, LightningModule, LightningDataModule · Answered

  

  

  5