Skip to content

Commit 1cd7e04

Browse files
thucbx99thucbx99
committed
update docs
1 parent d527e4e commit 1cd7e04

File tree

15 files changed

+107
-118
lines changed

15 files changed

+107
-118
lines changed

‎common/vision/datasets/_util.py

+2-2
Original file line numberDiff line numberDiff line change
@@ -29,8 +29,8 @@ def download(root: str, file_name: str, archive_name: str, url_link: str):
2929
download_and_extract_archive(url_link, download_root=root, filename=archive_name, remove_finished=False)
3030
except Exception:
3131
print("Fail to download {} from url link {}".format(archive_name, url_link))
32-
print('Please check you internet connection or '
33-
"reinstall DALIB by 'pip install --upgrade dalib'")
32+
print('Please check you internet connection.'
33+
"Simply trying again may be fine.")
3434
exit(0)
3535

3636

‎docs/dalib/benchmarks/image_classification.rst

+1-1
Original file line numberDiff line numberDiff line change
@@ -136,7 +136,7 @@ DomainNet accuracy on ResNet-101
136136
Methods c->p c->r c->s p->c p->r p->s r->c r->p r->s s->c s->p s->r Avg
137137
Source Only 32.7 50.6 39.4 41.1 56.8 35.0 48.6 48.8 36.1 49.0 34.8 46.1 43.3
138138
DANN 37.9 54.3 44.4 41.7 55.6 36.8 50.7 50.8 40.1 55.0 45.0 54.5 47.2
139-
ADDA
139+
ADDA 38.4 54.1 44.1 43.5 56.7 39.2 52.8 51.3 40.9 55.0 45.4 54.5 48.0
140140
ADDAgrl
141141
DAN 38.8 55.2 43.9 45.9 59.0 40.8 50.8 49.8 38.9 56.1 45.9 55.5 48.4
142142
JAN 40.5 56.7 45.1 47.2 59.9 43.0 54.2 52.6 41.9 56.6 46.2 55.5 50.0

‎docs/dalib/benchmarks/image_regression.rst

+10-2
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22
Image Regression
33
===============================================
44

5-
We provide benchmarks of different domain adaptation algorithms on `dSprites`_.
5+
We provide benchmarks of different domain adaptation algorithms on `dSprites`_ and `MPI3D`_ .
66
Those domain adaptation algorithms includes:
77

88
- :ref:`MDD`
@@ -28,8 +28,16 @@ dSprites error on ResNet-18
2828
=========== ====== ====== ====== ====== ====== ====== ======
2929
Methods Avg C → N C → S N → C N → S S → C S → N
3030
Source Only 0.157 0.232 0.271 0.081 0.220 0.038 0.092
31-
DD 0.057 0.047 0.080 0.030 0.095 0.053 0.037
31+
DD 0.057 0.047 0.080 0.030 0.095 0.053 0.037
3232
=========== ====== ====== ====== ====== ====== ====== ======
3333

3434

35+
.. _MPI3D:
3536

37+
MPI3D error on ResNet-18
38+
---------------------------------
39+
=========== ====== ====== ====== ====== ====== ====== ======
40+
Methods Avg RL → RC RL → T RC → RL RC → T T → RL T → RC
41+
Source Only 0.176 0.232 0.271 0.081 0.220 0.038 0.092
42+
DD 0.030 0.086 0.029 0.057 0.189 0.131 0.087
43+
=========== ====== ====== ====== ====== ====== ====== ======

‎docs/dglib/benchmarks/classification.rst renamed to ‎docs/dglib/benchmarks/image_classification.rst

+1-19
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22
Image Classification
33
===============================
44

5-
We provide benchmarks of different domain generalization algorithms on `PACS`_, `Office-Home`_, `DomainNet`_,
5+
We provide benchmarks of different domain generalization algorithms on `PACS`_, `Office-Home`_,
66
`iWildCam-Wilds`_, `Camelyon17-Wilds`_, `FMoW-Wilds`_.
77
Those domain generalization algorithms includes:
88

@@ -69,24 +69,6 @@ GroupDRO 70.0 66.7 55.2 78.8 79.9
6969
CORAL 70.9 68.3 55.4 78.8 81.0
7070
======== ===== ===== ===== ===== =====
7171

72-
.. _DomainNet:
73-
74-
-----------------------------------
75-
DomainNet accuracy on ResNet-50
76-
-----------------------------------
77-
78-
======== ===== ========= =========== ========== =========== ====== ========
79-
Methods avg clipart infograph painting quickdraw real sketch
80-
ERM
81-
IBN
82-
MixStyle
83-
MLDG
84-
IRM
85-
VREx
86-
GroupDRO
87-
CORAL
88-
======== ===== ========= =========== ========== =========== ====== ========
89-
9072
.. _iWildCam-Wilds:
9173

9274
-----------------------------------

‎docs/dglib/benchmarks/reid.rst renamed to ‎docs/dglib/benchmarks/re_identification.rst

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
===============================
2-
Person Re-Identification
2+
Re-Identification
33
===============================
44

55
We provide benchmarks of different domain generalization algorithms. Currently three datasets are supported:

‎docs/index.rst

+2-2
Original file line numberDiff line numberDiff line change
@@ -41,8 +41,8 @@ Transfer Learning
4141
:caption: Domain Generalization Settings
4242
:titlesonly:
4343

44-
dglib/benchmarks/classification
45-
dglib/benchmarks/reid
44+
dglib/benchmarks/image_classification
45+
dglib/benchmarks/re_identification
4646

4747

4848
.. toctree::

‎examples/domain_adaptation/image_regression/dann.sh

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# DSprites
2-
CUDA_VISIBLE_DEVICES=2 python dann.py data/dSprites -d DSprites -s C -t N -a resnet18 --epochs 40 --seed 0 --log logs/dann/DSprites_C2N
2+
CUDA_VISIBLE_DEVICES=0 python dann.py data/dSprites -d DSprites -s C -t N -a resnet18 --epochs 40 --seed 0 --log logs/dann/DSprites_C2N
33
CUDA_VISIBLE_DEVICES=0 python dann.py data/dSprites -d DSprites -s C -t S -a resnet18 --epochs 40 --seed 0 --log logs/dann/DSprites_C2S
44
CUDA_VISIBLE_DEVICES=0 python dann.py data/dSprites -d DSprites -s N -t C -a resnet18 --epochs 40 --seed 0 --log logs/dann/DSprites_N2C
55
CUDA_VISIBLE_DEVICES=0 python dann.py data/dSprites -d DSprites -s N -t S -a resnet18 --epochs 40 --seed 0 --log logs/dann/DSprites_N2S

‎examples/domain_adaptation/image_regression/dd.sh

+12-12
Original file line numberDiff line numberDiff line change
@@ -1,15 +1,15 @@
11
# DSprites
2-
CUDA_VISIBLE_DEVICES=0 python mdd.py data/dSprites -d DSprites -s C -t N -a resnet18 --epochs 40 --seed 0 -b 128 --log logs/mdd/dSprites_C2N --wd 0.0005
3-
CUDA_VISIBLE_DEVICES=0 python mdd.py data/dSprites -d DSprites -s C -t S -a resnet18 --epochs 40 --seed 0 -b 128 --log logs/mdd/dSprites_C2S --wd 0.0005
4-
CUDA_VISIBLE_DEVICES=0 python mdd.py data/dSprites -d DSprites -s N -t C -a resnet18 --epochs 40 --seed 0 -b 128 --log logs/mdd/dSprites_N2C --wd 0.0005
5-
CUDA_VISIBLE_DEVICES=0 python mdd.py data/dSprites -d DSprites -s N -t S -a resnet18 --epochs 40 --seed 0 -b 128 --log logs/mdd/dSprites_N2S --wd 0.0005
6-
CUDA_VISIBLE_DEVICES=0 python mdd.py data/dSprites -d DSprites -s S -t C -a resnet18 --epochs 40 --seed 0 -b 128 --log logs/mdd/dSprites_S2C --wd 0.0005
7-
CUDA_VISIBLE_DEVICES=0 python mdd.py data/dSprites -d DSprites -s S -t N -a resnet18 --epochs 40 --seed 0 -b 128 --log logs/mdd/dSprites_S2N --wd 0.0005
2+
CUDA_VISIBLE_DEVICES=0 python dd.py data/dSprites -d DSprites -s C -t N -a resnet18 --epochs 40 --seed 0 -b 128 --log logs/dd/dSprites_C2N --wd 0.0005
3+
CUDA_VISIBLE_DEVICES=0 python dd.py data/dSprites -d DSprites -s C -t S -a resnet18 --epochs 40 --seed 0 -b 128 --log logs/dd/dSprites_C2S --wd 0.0005
4+
CUDA_VISIBLE_DEVICES=0 python dd.py data/dSprites -d DSprites -s N -t C -a resnet18 --epochs 40 --seed 0 -b 128 --log logs/dd/dSprites_N2C --wd 0.0005
5+
CUDA_VISIBLE_DEVICES=0 python dd.py data/dSprites -d DSprites -s N -t S -a resnet18 --epochs 40 --seed 0 -b 128 --log logs/dd/dSprites_N2S --wd 0.0005
6+
CUDA_VISIBLE_DEVICES=0 python dd.py data/dSprites -d DSprites -s S -t C -a resnet18 --epochs 40 --seed 0 -b 128 --log logs/dd/dSprites_S2C --wd 0.0005
7+
CUDA_VISIBLE_DEVICES=0 python dd.py data/dSprites -d DSprites -s S -t N -a resnet18 --epochs 40 --seed 0 -b 128 --log logs/dd/dSprites_S2N --wd 0.0005
88

99
# MPI3D
10-
CUDA_VISIBLE_DEVICES=0 python mdd.py data/mpi3d -d MPI3D -s RL -t RC -a resnet18 --epochs 60 --seed 0 -b 36 --log logs/mdd/MPI3D_RL2RC --normalization IN --resize-size 224 --weight-decay 0.001
11-
CUDA_VISIBLE_DEVICES=0 python mdd.py data/mpi3d -d MPI3D -s RL -t T -a resnet18 --epochs 60 --seed 0 -b 36 --log logs/mdd/MPI3D_RL2T --normalization IN --resize-size 224 --weight-decay 0.001
12-
CUDA_VISIBLE_DEVICES=0 python mdd.py data/mpi3d -d MPI3D -s RC -t RL -a resnet18 --epochs 60 --seed 0 -b 36 --log logs/mdd/MPI3D_RC2RL --normalization IN --resize-size 224 --weight-decay 0.001
13-
CUDA_VISIBLE_DEVICES=0 python mdd.py data/mpi3d -d MPI3D -s RC -t T -a resnet18 --epochs 60 --seed 0 -b 36 --log logs/mdd/MPI3D_RC2T --normalization IN --resize-size 224 --weight-decay 0.001
14-
CUDA_VISIBLE_DEVICES=0 python mdd.py data/mpi3d -d MPI3D -s T -t RL -a resnet18 --epochs 60 --seed 0 -b 36 --log logs/mdd/MPI3D_T2RL --normalization IN --resize-size 224 --weight-decay 0.001
15-
CUDA_VISIBLE_DEVICES=0 python mdd.py data/mpi3d -d MPI3D -s T -t RC -a resnet18 --epochs 60 --seed 0 -b 36 --log logs/mdd/MPI3D_T2RC --normalization IN --resize-size 224 --weight-decay 0.001
10+
CUDA_VISIBLE_DEVICES=0 python dd.py data/mpi3d -d MPI3D -s RL -t RC -a resnet18 --epochs 60 --seed 0 -b 36 --log logs/dd/MPI3D_RL2RC --normalization IN --resize-size 224 --weight-decay 0.001
11+
CUDA_VISIBLE_DEVICES=0 python dd.py data/mpi3d -d MPI3D -s RL -t T -a resnet18 --epochs 60 --seed 0 -b 36 --log logs/dd/MPI3D_RL2T --normalization IN --resize-size 224 --weight-decay 0.001
12+
CUDA_VISIBLE_DEVICES=0 python dd.py data/mpi3d -d MPI3D -s RC -t RL -a resnet18 --epochs 60 --seed 0 -b 36 --log logs/dd/MPI3D_RC2RL --normalization IN --resize-size 224 --weight-decay 0.001
13+
CUDA_VISIBLE_DEVICES=0 python dd.py data/mpi3d -d MPI3D -s RC -t T -a resnet18 --epochs 60 --seed 0 -b 36 --log logs/dd/MPI3D_RC2T --normalization IN --resize-size 224 --weight-decay 0.001
14+
CUDA_VISIBLE_DEVICES=0 python dd.py data/mpi3d -d MPI3D -s T -t RL -a resnet18 --epochs 60 --seed 0 -b 36 --log logs/dd/MPI3D_T2RL --normalization IN --resize-size 224 --weight-decay 0.001
15+
CUDA_VISIBLE_DEVICES=0 python dd.py data/mpi3d -d MPI3D -s T -t RC -a resnet18 --epochs 60 --seed 0 -b 36 --log logs/dd/MPI3D_T2RC --normalization IN --resize-size 224 --weight-decay 0.001

‎examples/domain_adaptation/image_regression/rsd.sh

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# DSprites
2-
CUDA_VISIBLE_DEVICES=1 python rsd.py data/dSprites -d DSprites -s C -t N -a resnet18 --epochs 40 --seed 0 --log logs/rsd/DSprites_C2N
2+
CUDA_VISIBLE_DEVICES=0 python rsd.py data/dSprites -d DSprites -s C -t N -a resnet18 --epochs 40 --seed 0 --log logs/rsd/DSprites_C2N
33
CUDA_VISIBLE_DEVICES=0 python rsd.py data/dSprites -d DSprites -s C -t S -a resnet18 --epochs 40 --seed 0 --log logs/rsd/DSprites_C2S
44
CUDA_VISIBLE_DEVICES=0 python rsd.py data/dSprites -d DSprites -s N -t C -a resnet18 --epochs 40 --seed 0 --log logs/rsd/DSprites_N2C
55
CUDA_VISIBLE_DEVICES=0 python rsd.py data/dSprites -d DSprites -s N -t S -a resnet18 --epochs 40 --seed 0 --log logs/rsd/DSprites_N2S

‎examples/domain_adaptation/re_identification/README.md

+9-10
Original file line numberDiff line numberDiff line change
@@ -55,18 +55,17 @@ If you use these methods in your research, please consider citing.
5555

5656
```
5757
@inproceedings{IBN-Net,
58-
author = {Xingang Pan, Ping Luo, Jianping Shi, and Xiaoou Tang},
59-
title = {Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net},
60-
booktitle = {ECCV},
61-
year = {2018}
58+
author = {Xingang Pan, Ping Luo, Jianping Shi, and Xiaoou Tang},
59+
title = {Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net},
60+
booktitle = {ECCV},
61+
year = {2018}
6262
}
6363
6464
@inproceedings{
65-
MMT,
66-
title={Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification},
67-
author={Yixiao Ge and Dapeng Chen and Hongsheng Li},
68-
booktitle={International Conference on Learning Representations},
69-
year={2020},
70-
url={https://openreview.net/forum?id=rJlnOhVYPS}
65+
MMT,
66+
title={Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification},
67+
author={Yixiao Ge and Dapeng Chen and Hongsheng Li},
68+
booktitle={ICLR},
69+
year={2020},
7170
}
7271
```

‎examples/domain_adaptation/re_identification/ibn.sh

+12-12
Original file line numberDiff line numberDiff line change
@@ -1,36 +1,36 @@
11
#!/usr/bin/env bash
22
# Market1501 -> Duke
33
CUDA_VISIBLE_DEVICES=0 python baseline.py data data -s Market1501 -t DukeMTMC -a resnet50_ibn_a \
4-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/Market2Duke
4+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/ibn/Market2Duke
55
CUDA_VISIBLE_DEVICES=0 python baseline.py data data -s Market1501 -t DukeMTMC -a resnet50_ibn_b \
6-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/Market2Duke
6+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/ibn/Market2Duke
77

88
# Duke -> Market1501
99
CUDA_VISIBLE_DEVICES=0 python baseline.py data data -s DukeMTMC -t Market1501 -a resnet50_ibn_a \
10-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/Duke2Market
10+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/ibn/Duke2Market
1111
CUDA_VISIBLE_DEVICES=0 python baseline.py data data -s DukeMTMC -t Market1501 -a resnet50_ibn_b \
12-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/Duke2Market
12+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/ibn/Duke2Market
1313

1414
# Market1501 -> MSMT
1515
CUDA_VISIBLE_DEVICES=0 python baseline.py data data -s Market1501 -t MSMT17 -a resnet50_ibn_a \
16-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/Market2MSMT
16+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/ibn/Market2MSMT
1717
CUDA_VISIBLE_DEVICES=0 python baseline.py data data -s Market1501 -t MSMT17 -a resnet50_ibn_b \
18-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/Market2MSMT
18+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/ibn/Market2MSMT
1919

2020
# MSMT -> Market1501
2121
CUDA_VISIBLE_DEVICES=0 python baseline.py data data -s MSMT17 -t Market1501 -a resnet50_ibn_a \
22-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/MSMT2Market
22+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/ibn/MSMT2Market
2323
CUDA_VISIBLE_DEVICES=0 python baseline.py data data -s MSMT17 -t Market1501 -a resnet50_ibn_b \
24-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/MSMT2Market
24+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/ibn/MSMT2Market
2525

2626
# Duke -> MSMT
2727
CUDA_VISIBLE_DEVICES=0 python baseline.py data data -s DukeMTMC -t MSMT17 -a resnet50_ibn_a \
28-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/Duke2MSMT
28+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/ibn/Duke2MSMT
2929
CUDA_VISIBLE_DEVICES=0 python baseline.py data data -s DukeMTMC -t MSMT17 -a resnet50_ibn_b \
30-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/Duke2MSMT
30+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/ibn/Duke2MSMT
3131

3232
# MSMT -> Duke
3333
CUDA_VISIBLE_DEVICES=0 python baseline.py data data -s MSMT17 -t DukeMTMC -a resnet50_ibn_a \
34-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/MSMT2Duke
34+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/ibn/MSMT2Duke
3535
CUDA_VISIBLE_DEVICES=0 python baseline.py data data -s MSMT17 -t DukeMTMC -a resnet50_ibn_b \
36-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/MSMT2Duke
36+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/ibn/MSMT2Duke

‎examples/domain_adaptation/re_identification/spgan.sh

+6-6
Original file line numberDiff line numberDiff line change
@@ -4,44 +4,44 @@ CUDA_VISIBLE_DEVICES=0 python spgan.py data -s Market1501 -t DukeMTMC \
44
--log logs/spgan/Market2Duke --translated-root data/spganM2D --seed 0
55
# step2: train baseline on translated source dataset
66
CUDA_VISIBLE_DEVICES=0 python baseline.py data/spganM2D data -s Market1501 -t DukeMTMC -a reid_resnet50 \
7-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/Market2Duke
7+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/spgan/Market2Duke
88

99
# Duke -> Market1501
1010
# step1: train SPGAN
1111
CUDA_VISIBLE_DEVICES=0 python spgan.py data -s DukeMTMC -t Market1501 \
1212
--log logs/spgan/Duke2Market --translated-root data/spganD2M --seed 0
1313
# step2: train baseline on translated source dataset
1414
CUDA_VISIBLE_DEVICES=0 python baseline.py data/spganD2M data -s DukeMTMC -t Market1501 -a reid_resnet50 \
15-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/Duke2Market
15+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/spgan/Duke2Market
1616

1717
# Market1501 -> MSMT17
1818
# step1: train SPGAN
1919
CUDA_VISIBLE_DEVICES=0 python spgan.py data -s Market1501 -t MSMT17 \
2020
--log logs/spgan/Market2MSMT --translated-root data/spganM2S --seed 0
2121
# step2: train baseline on translated source dataset
2222
CUDA_VISIBLE_DEVICES=0 python baseline.py data/spganM2S data -s Market1501 -t MSMT17 -a reid_resnet50 \
23-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/Market2MSMT
23+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/spgan/Market2MSMT
2424

2525
# MSMT -> Market1501
2626
# step1: train SPGAN
2727
CUDA_VISIBLE_DEVICES=0 python spgan.py data -s MSMT17 -t Market1501 \
2828
--log logs/spgan/MSMT2Market --translated-root data/spganS2M --seed 0
2929
# step2: train baseline on translated source dataset
3030
CUDA_VISIBLE_DEVICES=0 python baseline.py data/spganS2M data -s MSMT17 -t Market1501 -a reid_resnet50 \
31-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/MSMT2Market
31+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/spgan/MSMT2Market
3232

3333
# Duke -> MSMT
3434
# step1: train SPGAN
3535
CUDA_VISIBLE_DEVICES=0 python spgan.py data -s DukeMTMC -t MSMT17 \
3636
--log logs/spgan/Duke2MSMT --translated-root data/spganD2S --seed 0
3737
# step2: train baseline on translated source dataset
3838
CUDA_VISIBLE_DEVICES=0 python baseline.py data/spganD2S data -s DukeMTMC -t MSMT17 -a reid_resnet50 \
39-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/Duke2MSMT
39+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/spgan/Duke2MSMT
4040

4141
# MSMT -> Duke
4242
# step1: train SPGAN
4343
CUDA_VISIBLE_DEVICES=0 python spgan.py data -s MSMT17 -t DukeMTMC \
4444
--log logs/spgan/MSMT2Duke --translated-root data/spganS2D --seed 0
4545
# step2: train baseline on translated source dataset
4646
CUDA_VISIBLE_DEVICES=0 python baseline.py data/spganS2D data -s MSMT17 -t DukeMTMC -a reid_resnet50 \
47-
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/baseline/MSMT2Duke
47+
--iters-per-epoch 800 --print-freq 80 --finetune --seed 0 --log logs/spgan/MSMT2Duke

0 commit comments

Comments
 (0)