目錄

• 文章簡介
• Issues
• 環(huán)境配置
• Ref-Reasoning數(shù)據(jù)集格式
• • train(val)_expression.json
  • train(val)_sgs.json
  • train(val)_sg_seqs.json
  • gt_objects_info.json
  • *_sgs.json
  • *_sg_seqs.json

文章簡介

Graph-Structured Referring Expressions Reasoning in The Wild
代碼鏈接
論文鏈接

Issues

在作者代碼的README中，有環(huán)境配置的步驟，不過python2.7+pytorch0.4.0支持的cuda版本和本機(jī)顯卡支持的cuda版本存在沖突，無法正常運(yùn)行代碼，會(huì)出現(xiàn)以下錯(cuò)誤：

# 錯(cuò)誤1 RuntimeError: cuDNN version mismatch: PyTorch was compiled against 7102 but linked against 7605 # 錯(cuò)誤2 CUDNN_STATUS_EXECUTION_FAILED

錯(cuò)誤1可以通過以下命令解決：

conda install cudnn=7.1.2

錯(cuò)誤2是版本沖突，我沒解決，所以沒辦法和作者用一樣的環(huán)境。但是，在python3的環(huán)境下，作者的代碼稍作調(diào)整也可以運(yùn)行，具體配置步驟見下文。

環(huán)境配置

本機(jī)環(huán)境：

• ubuntu18.04
• rtx 2080ti
• NVIDIA-SMI 450.57

基于本機(jī)環(huán)境，我配置的conda虛擬環(huán)境中，各軟件版本如下：

• python 3.6.2
• pytorch 1.4.0 - py3.6_cuda10.0.130_cudnn7.6.3_0
• torchvision 0.5.0 - py36_cu100
• scipy 1.5.2
• numpy 1.19.1
• h5py 2.10.0
• cudatoolkit 10.0.130

在上述環(huán)境中，對(duì)代碼稍微修改一下（主要是python2$\to$ python3，如print xxx，改為print(xxx)），即可正常運(yùn)行。

環(huán)境配置代碼：

conda create -n lchpy36 python=3.6 source activate lchpy36 conda install pytorch torchvision cudatoolkit=10.0 -c pytorch pip install h5py pip install scipy

運(yùn)行程序代碼：

git clone https://github.com/sibeiyang/sgmn.git && cd sgmn # 建立軟鏈接一定要用絕對(duì)路徑 ln -s /home/mcislab/dist4T/chuanhao/dataset/Ref-Reasoning/refvg/ /home/mcislab/dist4T/chuanhao/code/sgmn/data/ ln -s /home/mcislab/dist4T/chuanhao/dataset/Ref-Reasoning/gt_objects/ /home/mcislab/dist4T/chuanhao/code/sgmn/data/ ln -s /home/mcislab/dist4T/chuanhao/others/sgmn_glove/word_embedding/ /home/mcislab/dist4T/chuanhao/code/sgmn/data/ bash experiments/script/train.sh $GPUs

Ref-Reasoning數(shù)據(jù)集格式

train(val)_expression.json

{"825670": {"num_nodes": 4, "referent_id": "4306103", "image_id": "2384229", "bbox": [215, 50, 43, 55], "expression": "There is a people to the right of man and to the left of a wine , and the man holding empty glass ."}, ... }

train(val)_sgs.json

{"800000": {"words_info": [[1, "det", 0, "a"], [1, "amod", 0, "yellow"], [1, "head", 0, "frisbee"], [1, "none", 1, "to"], [1, "none", 1, "the"], [1, "none", 1, "left"], [1, "none", 1, "of"], [1, "head", 2, "man"], [0, "none", 3, "that"], [0, "none", 3, "is"], [1, "none", 3, "wearing"], [1, "amod", 4, "white"], [1, "head", 4, "socks"], [1, "none", 5, "and"], [0, "none", 5, "is"], [1, "none", 5, "wearing"], [1, "head", 6, "shorts"], [1, "none", 7, "."]], "co_index": {}},... }

train(val)_sg_seqs.json

{"800000":{"seq_sg": [{"seq_rel": [], "type": "S", "seq": [7]}, {"seq_rel": [], "type": "SPO", "seq": [2, 5, 6]}, {"seq_rel": [[2, 1, "SUBANDSUB"]], "type": "SPO", "seq": [2, 3, 4]},{"seq_rel": [[3, 2, "OBJANDSUB"]], "type": "SPO", "seq": [0, 1, 2]}], "com_seq": [0, 3], "num_seq": 4, "split_to_seq": {"0": 3, "2": 3, "4": 2, "7": 0, "6": 1}},... }

gt_objects_info.json

{"2379671":{"width": 500, "idx": 1541, "file": 2, "objectsNum": 15, "height": 438},... }

*_sgs.json

basic info about language scene graph

{"expression_id":{"word_info": list of info (split id, dependent type, weight, word)"co_index": dictionary from one split id to its coreference's split id},... }

*_sg_seqs.json

structured info about language scene graph

{"expression_id":{"seq_sg": list of nodes and edges. Each node and edge includes its phrase listed by split ids, its relations to other nodes and edges, and its type info."com_seq": list of indexes of elements with zero out-degree in seq_sg"num_seq": number of nodes and edges"split_to_seq": dictionary from one split id to the index of seq_sg},... }

總結(jié)

以上是生活随笔為你收集整理的CVPR 2020 运行SGMN遇到的问题及解决办法的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。