 will-jl944
|
ce45d7df9b
set batch_size to 1 if train rcnn with negative samples
|
4 years ago |
|
will-jl944
|
838809a031
add hubserving
|
4 years ago |
 FlyingQianMM
|
1df905b8ee
fix some wrong links in docs
|
4 years ago |
|
FlyingQianMM
|
92034f01e2
fix some wrong links in docs
|
4 years ago |
|
will-jl944
|
353aa81884
init attribute downsample_ratios regardless whether net is initialized or not
|
4 years ago |
|
FlyingQianMM
|
6dba2ab54e
Merge pull request #1067 from will-jl944/develop_jf
|
4 years ago |
|
FlyingQianMM
|
ca8f5b9cc2
fix input shape when exporting ppyolo serials
|
4 years ago |
|
will-jl944
|
eb2e2952cc
rcnn models support prediction w/ bs greater than 1
|
4 years ago |
|
will-jl944
|
b3bd512d18
merge develop
|
4 years ago |
|
FlyingQianMM
|
90aacf1efe
Merge pull request #1049 from will-jl944/deploy_jf
|
4 years ago |
|
will-jl944
|
a1ca94c3a8
add fake batch prediction for rcnn models
|
4 years ago |
|
will-jl944
|
031992d6f6
disable training for exported inference model
|
4 years ago |
|
FlyingQianMM
|
78f064d6ec
set image_shape from test_transforms when do not set fixed_input_shape (#1052)
|
4 years ago |
|
will-jl944
|
683a44be2b
add python deploy
|
4 years ago |
|
will-jl944
|
d05f2ad919
models can be initilized without building net
|
4 years ago |
|
will-jl944
|
b6a5fd6f1d
add python deploy
|
4 years ago |
|
will-jl944
|
dd7d8de2ed
models can be initilized without building net
|
4 years ago |
 何秦
|
8d4e3214dc
fix the backbone message
|
4 years ago |
|
will-jl944
|
d7e7f72979
fix ppyolor18vd downsample ratio bug
|
4 years ago |
|
FlyingQianMM
|
ecefcd9c2b
mv dygraph to home directory
|
4 years ago |
