sugarme
|
0ff2f910f2
|
BREAKING CHANGE: switch to auto-generated
|
2020-07-22 15:56:30 +10:00 |
|
sugarme
|
41f3f8af2a
|
BREAKING CHANGE(nn/linear): removed pointer receiver
|
2020-07-03 11:20:52 +10:00 |
|
sugarme
|
3c115ee79f
|
fix(tensor): free C memory at tensor.Values() method. fix(vision/resnet): free C memory
|
2020-07-02 21:30:45 +10:00 |
|
sugarme
|
9817f7393a
|
feat(nn/rnn): added rnn.go feat(nn/conv-transpose): added conv-transpose.go
|
2020-06-24 18:14:34 +10:00 |
|
sugarme
|
b792c6af3c
|
fix(nn/sequential): fixed wrong index at Forward method
|
2020-06-23 15:21:16 +10:00 |
|
sugarme
|
ed709027c0
|
fix(nn/sequential, linear): fixed memory held up due to undeleted middle tensors
|
2020-06-23 13:37:26 +10:00 |
|
sugarme
|
5861f3c525
|
chorus(clean-up) and change lr in example/mnist nn model
|
2020-06-22 15:14:32 +10:00 |
|
sugarme
|
f36d2482a1
|
feat(tensor): add option to delete tensor after applying operator to free up C memory
|
2020-06-21 23:37:42 +10:00 |
|
sugarme
|
4ffe5feb7a
|
chorus(example/mnist): cleanup. Still the memory blow-out issue
|
2020-06-21 10:57:29 +10:00 |
|
sugarme
|
e0d2e0ca7e
|
WIP(example/mnist): nn
|
2020-06-19 21:39:34 +10:00 |
|
sugarme
|
a0faf0799d
|
Fix(nn/varstore): temp fixed add not add new variable to TrainableVariable
WIP(example/mnist): nn working but take up memory. Need to free after each epoch
|
2020-06-19 20:22:51 +10:00 |
|
sugarme
|
a636372144
|
WIP(example/mnist): nn
|
2020-06-19 01:37:13 +10:00 |
|
sugarme
|
9be19702d1
|
WIP(example/mnist): nn
|
2020-06-18 17:14:48 +10:00 |
|