 FlyingQianMM
|
639820c46e
Merge pull request #875 from FlyingQianMM/develop_export
|
пре 4 година |
|
FlyingQianMM
|
47aab15235
add fixed_input_shape to self
|
пре 4 година |
 will-jl944
|
fd2093e6b6
train and quant_aware_train support resume_checkpoint
|
пре 4 година |
|
FlyingQianMM
|
3db888f2ce
add imagnet pretrain weigths downlink for deeplabv3p
|
пре 4 година |
|
will-jl944
|
2f573a3678
batch_prediction of segmenter returns list of dict
|
пре 4 година |
|
will-jl944
|
0c1a8ebb67
fix bug when pretrain_weights is None
|
пре 4 година |
|
will-jl944
|
2d8af5b3c3
raise error if pretrain weights is a directory instead of pdparams file
|
пре 4 година |
|
FlyingQianMM
|
3512d7d5c5
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleX into develop_fix
|
пре 4 година |
|
will-jl944
|
71ed1d640e
refine confusion matrix computation
|
пре 4 година |
|
will-jl944
|
8ab8cbc020
refine seg evaluation
|
пре 4 година |
|
FlyingQianMM
|
6973e5994d
fix conflicts
|
пре 4 година |
|
FlyingQianMM
|
4afdbdca12
fix input_shape
|
пре 4 година |
|
will-jl944
|
9ec76631c0
add confusion matrix computation to seg
|
пре 4 година |
|
will-jl944
|
748c2beafa
remove inference_image_shape in docstring
|
пре 4 година |
|
will-jl944
|
2213969dce
remove image_shape from quant_aware_train since no inference model is saved in qat process
|
пре 4 година |
|
will-jl944
|
978c98bfd7
decrease lr in qat_train
|
пре 4 година |
|
will-jl944
|
e1f495f55e
set pretrain_weights to None in qat
|
пре 4 година |
|
will-jl944
|
fce21d27e7
add qat
|
пре 4 година |
|
will-jl944
|
a94d27c639
compatible with static apis
|
пре 4 година |
|
will-jl944
|
769df760f4
disableprint while initiate backbones in seg models
|
пре 4 година |
|
will-jl944
|
0f89bd6e79
import from paddleseg submodule
|
пре 4 година |
|
will-jl944
|
79d4164c5c
move logging info out of build_dataloader
|
пре 4 година |
|
FlyingQianMM
|
d4f745add9
add dygrah
|
пре 4 година |
