About the LightningModule category
|
|
0
|
46
|
August 26, 2020
|
Composition of PL modules
|
|
1
|
16
|
February 22, 2021
|
Training_epoch_end is never called
|
|
3
|
33
|
February 22, 2021
|
Best way to save training/validation tensors for epoch metrics
|
|
1
|
24
|
February 22, 2021
|
Regularization-based Continual Learning
|
|
1
|
80
|
February 22, 2021
|
Skip loss backward and optimizer step if loss undefined for one batch
|
|
1
|
71
|
February 22, 2021
|
Saving/loading LightningModule with injected network
|
|
1
|
95
|
February 22, 2021
|
LR Scheduler with interval="step" not working properly
|
|
1
|
23
|
February 16, 2021
|
Loading models with huggingface Automodel.from_pretrained
|
|
1
|
22
|
February 15, 2021
|
Get max steps inside configure_optimizers
|
|
2
|
52
|
February 4, 2021
|
Global step loaded by "load_from_check_point" is wrong
|
|
1
|
29
|
February 3, 2021
|
How to save model checkpoints every 1000 batches of data during training
|
|
2
|
48
|
January 23, 2021
|
Understanding self.log()
|
|
1
|
38
|
January 23, 2021
|
`.detach()` cannot stop backprop in `training_step`
|
|
4
|
48
|
January 21, 2021
|
ValueError: optimizer got an empty parameter list
|
|
2
|
61
|
January 13, 2021
|
OOM error due to tensor accumulation when trying to use functional metrics API
|
|
3
|
69
|
January 12, 2021
|
Validation Error: The validation bar turns red and no callbacks are called, no checkpoints are saved
|
|
5
|
57
|
December 21, 2020
|
EfficientNet SwishImplementation Error
|
|
2
|
136
|
December 14, 2020
|
Mypy issues with lightning module
|
|
1
|
87
|
December 8, 2020
|
TensorBoard Logger - no self.experiment?
|
|
1
|
147
|
November 23, 2020
|
How to save hparams when not provided as argument (apparently assigning to hparams is not recomended)?
|
|
7
|
320
|
November 5, 2020
|
Docker file is broken
|
|
1
|
64
|
November 3, 2020
|
BERT model throws error when used in Pytorch Lightning
|
|
2
|
312
|
October 17, 2020
|
Loading a checkpoint for trainer.test
|
|
2
|
134
|
October 16, 2020
|
Hparams not restored when using load_from_checkpoint (default argument values are the problem?)
|
|
2
|
432
|
October 8, 2020
|
How to use multiple train dataloaders with different lengths
|
|
1
|
425
|
September 27, 2020
|
How to switch dataloaders between epochs in Lightning
|
|
2
|
370
|
September 14, 2020
|
Validation sanity check
|
|
3
|
560
|
September 14, 2020
|
Combining loss for multiple dataloaders
|
|
9
|
305
|
September 12, 2020
|
How to move new torch tensor to device automatically
|
|
1
|
125
|
August 27, 2020
|