Rafael Valle
|
6d0635e8c1
|
train.py: printing correct variable
|
4 years ago |
Rafael Valle
|
70d37f9e7d
|
train.py: reporting the right variable
|
5 years ago |
rafaelvalle
|
0274619e45
|
train.py: using amp for mixed precision training
|
5 years ago |
Rafael Valle
|
ece7d3f568
|
train.py: changing dataloder params given sampler
|
5 years ago |
rafaelvalle
|
f37998c59d
|
train.py: shuffling at every epoch
|
5 years ago |
rafaelvalle
|
3869781877
|
train.py: adding routine to warm start and ignore layers, e.g. embedding.weight
|
5 years ago |
rafaelvalle
|
6e430556bd
|
train.py: val logger on gpu 0 only
|
6 years ago |
rafaelvalle
|
0ad65cc053
|
train.py: renaming variable to n_gpus
|
6 years ago |
rafaelvalle
|
f06063f746
|
train.py: renaming function, removing dataparallel
|
6 years ago |
rafaelvalle
|
ce29e13959
|
train.py: updating
|
6 years ago |
rafaelvalle
|
5f0ea06c41
|
hparams.py: adding use saved learning rate param
|
6 years ago |
Rafael Valle
|
27b1767cb2
|
train.py: fixing typo
|
6 years ago |
Rafael Valle
|
1071023017
|
train.py: patching score_mask_value formerly inf, not concrete value, for compatibility with pytorch
|
6 years ago |
Rafael Valle
|
be5fdd6d20
|
train.py: layout changes
|
6 years ago |
Raul Puri
|
4d5826e894
|
train.py typo
|
6 years ago |
Raul Puri
|
0d4218fb20
|
single variable for single gpu model
|
6 years ago |
Rafael Valle
|
646ab0d8c8
|
model.py removing top of three code, cleanup
|
6 years ago |
Raul Puri
|
9343f34b0b
|
train.py single gpu and 0.4 update
|
6 years ago |
Rafael Valle
|
09bbec073d
|
adding python files
|
6 years ago |