 will-jl944
|
3934144f7b
show eval_metric on visualdl
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
69acc273c9
use deepcopy in ema
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
1e83b03e93
set dataloader worker_init_fn explictly
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
ea8b3d78fd
refine info message
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
a9a677d983
add imagenet weights for deeplabvep
|
%!s(int64=4) %!d(string=hai) anos |
 FlyingQianMM
|
1f90f463e7
Merge pull request #881 from FlyingQianMM/devellop_fix
|
%!s(int64=4) %!d(string=hai) anos |
|
FlyingQianMM
|
bc9c3d9c06
Merge pull request #853 from will-jl944/param_tuning
|
%!s(int64=4) %!d(string=hai) anos |
|
FlyingQianMM
|
d2be43d633
export pipeline info
|
%!s(int64=4) %!d(string=hai) anos |
|
FlyingQianMM
|
639820c46e
Merge pull request #875 from FlyingQianMM/develop_export
|
%!s(int64=4) %!d(string=hai) anos |
|
FlyingQianMM
|
47aab15235
add fixed_input_shape to self
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
fd2093e6b6
train and quant_aware_train support resume_checkpoint
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
6a94817fa4
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleX into param_tuning
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
491c5b88b2
not necessary to check shm size on non-Linux systems
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
a81f212002
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleX into param_tuning
|
%!s(int64=4) %!d(string=hai) anos |
|
FlyingQianMM
|
3512d7d5c5
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleX into develop_fix
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
3a519a241d
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleX into param_tuning
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
ed65b01157
convert tensor to list while saving pruner_inputs
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
bd785f12c0
no need to skip conv2d with small channel number with paddleslim 2.1
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
d31a7b6152
0
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
2275e8ea59
refine multi-card evaluation logistics, elaborate return value of evaluate only on card 0
|
%!s(int64=4) %!d(string=hai) anos |
|
FlyingQianMM
|
6973e5994d
fix conflicts
|
%!s(int64=4) %!d(string=hai) anos |
|
FlyingQianMM
|
4afdbdca12
fix input_shape
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
9ec76631c0
add confusion matrix computation to seg
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
62a0862f81
deal with comments
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
2213969dce
remove image_shape from quant_aware_train since no inference model is saved in qat process
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
c365a853ba
qat
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
598a8d446d
qat
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
620898b48a
quantization aware training
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
e1f495f55e
set pretrain_weights to None in qat
|
%!s(int64=4) %!d(string=hai) anos |
|
will-jl944
|
fce21d27e7
add qat
|
%!s(int64=4) %!d(string=hai) anos |
