royalvane / asm

( NeurIPS 2020 ) Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation

ASM

Introduction

This is an official implementation for our NeurIPS 2020 paper: Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation. In this paper, we aim at the problem named One-Shot Unsupervised Domain Adaptation. Unlike traditional Unsupervised Domain Adaptation, it assumes that only one unlabeled target sample can be available when learning to adapt.

Presentation Video

Usage

Prerequisites

• Python 3.6
• GPU Memory >= 32G

Download ImageNet-pretained DeepLab:

• Download DeepLab_resnet_pretrained_init-f81d91e8.pth and put it under pretrained/.

Download Pretained RAIN

• Download vgg_normalized.pth/decoder_iter_160000.pth/fc_encoder_iter_160000.pth/fc_decoder_iter_160000.pth and put them under pretrained/.

Download DataSets

• Download GTA5
• Download Cityscapes

Modify data path to your own

• ASM/ASM/ASM_train.py

  Line 67 in 1dac4bf

  DATA_DIRECTORY = '/data02/yawei/Data/GTA5/'

• ASM/ASM/ASM_train.py

  Line 83 in 1dac4bf

  DATA_DIRECTORY_TARGET = '/data02/yawei/Data/Cityscapes/'

• ASM/ASM/ASM_evaluate.py

  Line 14 in 1dac4bf

  DATA_DIRECTORY = '/data02/yawei/Data/Cityscapes/'

Train

CUDA_VISIBLE_DEVICES=<gpu_id> python ASM_train.py --snapshot-dir ./snapshots/GTA2Cityscapes

Test

CUDA_VISIBLE_DEVICES==<gpu_id> python ASM_evaluate.py

Compute IOU

python ASM_IOU.py

Our Pretrained Model

We also provide our Pretrained ASM models for direct evaluation. These models are trained using 32G V100.

• The first model is consist with our reported IoU result in the paper. mIoU = 44.53:

• The second model is trained recently, whose performance is slightly higher than the paper. mIoU = 44.78:

Citation

• If you find this code useful, please consider citing

@inproceedings{Luo2020ASM,
title={Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation},
  author={Luo, Yawei and Liu, Ping and Guan, Tao and Yu, Junqing and Yang, Yi},
  booktitle={Advances in Neural Information Processing Systems},
year={2020}
}

Related Works

• CLAN: One-shot UDA is a realistic but more challenging setting than UDA, which we tried to solve in our CVPR2019 oral paper "Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation".

• Copy and Paste GAN: RAIN is also employed as a strong data augmentation module in our CVPR2020 oral paper "Copy and Paste GAN: Face Hallucination from Shaded Thumbnails".

asm's Issues

About the train model of ASM

Hi, I have a question. I hope to get your answer.
When you train the segmentation model, you add a new module (self.PAM = PAM_Module(2048)) in Res_Deeplab model. Why not just train on the original Res_Deeplab model? You didn't do ablation experiments in your paper. How much would your method improve (mIOU) if you trained directly on the original Res_Deeplab model?

ASM_train.py运行报错

您好，我在Linux服务器上运行ASM_train.py时，出现以下报错：
`Fatal Python error: Cannot recover from stack overflow.

Current thread 0x00007f153c87f700 (most recent call first):
File "/usr/local/miniconda3/envs/dl10/lib/python3.6/site-packages/PIL/util.py", line 16 in isPath
File "/usr/local/miniconda3/envs/dl10/lib/python3.6/site-packages/PIL/Image.py", line 2766 in open
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 76 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASFatal Python error: Cannot recover from stack overflow.
M/
dCurrent thread 0xa00007f153c87f700t (most recent call first):
a File s"e/tu/sgrt/al5o_cdaalt/amsienti.cpoyn"d, line a1213 in /e_ngvest/idtle1m0/l
i File b"//pryotohto/np3r.o6j/escitt/eA-SpMa/cAkSaMg/edsa/tPaIsLe/t/ugttial5.pdya"t, line a16s in eits.Ppayt"h, line
121 File in "/ugsert/iltoecma_l/
m File i"n/ircooontd/ap3r/oejnevcst//dAlS1M0//AlSiMb//dpayttahsoent3/.g6t/as5i_tdea-tpaascekta.gpeys"/, line P121I in L/Igmeatgiet.epmy", line
2766 File in "o/preono
t File /"p/rroojoetc/tp/rAoSjMe/cAtS/MA/SdMa/tAaSsMe/td/agttaas5e_td/agttaas5e_td.aptya"s, line e121t in .p_yg"e, line t76i in t_e_mg_e_t
i File t"e/mr_o_o
t File /"p/rroojoetc/tp/rAoSjMe/cAtS/MA/SdMa/tAaSsMe/td/agttaas5e_td/agttaas5e_td.aptya"s, line e121t in .p_yg"e, line t121i in t_e_mg_e_t
i File t"e/mr_o_o
t File /"p/rroojoetc/tp/rAoSjMe/cAtS/MA/SdMa/tAaSsMe/td/agttaas5e_td/agttaas5e_td.aptya"s, line e121t in .p_yg"e, line t121i in t_e_mg_e_t
i File t"e/mr_o_o
t File /"p/rroojoetc/tp/rAoSjMe/cAtS/MA/SdMa/tAaSsMe/td/agttaas5e_td/agttaas5e_td.aptya"s, line e121t in .p_yg"e, line t121i in t_e_mg_e_t
i File t"e/mr_o_o
t File /"p/rroojoetc/tp/rAoSjMe/cAtS/MA/SdMa/tAaSsMe/td/agttaas5e_td/agttaas5e_td.aptya"s, line e121t in .p_gye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t File i"t/ermo_o_t
/ File p"r/orjoeoctt//pArSoMj/eAcStM//AdSaMt/aAsSeMt//dgattaa5s_edta/tgatsae5t.dpayt"a, line s121e in t_.pgye"t, line i121t in e_m__g_e
t ...
item_
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
File "/root/project/ASM/ASM/dataset/gta5_dataset.py", line 121 in getitem
...
Traceback (most recent call last):
File "/root/project/ASM/ASM/ASM_train.py", line 481, in
main()
File "/root/project/ASM/ASM/ASM_train.py", line 369, in main
set=args.set),
File "/root/project/ASM/ASM/dataset/cityscapes_dataset.py", line 40, in init
img_file = osp.join(self.root, "leftImg8bit/%s/%s" % (self.set, name))
File "/usr/local/miniconda3/envs/dl10/lib/python3.6/site-packages/torch/utils/data/_utils/signal_handling.py", line 66, in handler
_error_if_any_worker_fails()
RuntimeError: DataLoader worker (pid 7929) is killed by signal: Aborted.

Process finished with exit code 1
`

能否麻烦您看一下是什么原因呢？

Error Happened While Running train.py in RAIN

Hi author, thanks for sharing the code.
While I was running your code for training RAIN module, I got such a error:

Traceback (most recent call last):
File "train.py", line 182, in
loss_de.backward()
File "/home/fei/anaconda3/lib/python3.7/site-packages/torch/tensor.py", line 221, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/home/fei/anaconda3/lib/python3.7/site-packages/torch/autograd/init.py", line 132, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [1024, 1024]], which is output 0 of TBackward, is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).
0%| | 0/160000 [00:16<?, ?it/s]

and I was wondering if this error happens to you either.

Regards,

Digits benchmark dataloaders

Hello,

I was wondering if you will make available the data loaders and related code for training and testing your method on the digits benchmark.

Thanks.

Broken link for wikiart dataset

I would like to download the wikiart dataset but found its link is broken. Could you please provide an updated one or let us know where to download wikiart dataset?

evaluate运行

您好，下载了您训练好的模型之后进行evaluate，出现 Cannot recover from stack overflow. 请问是什么原因呢