Recurrent-VLN-BERT
Recurrent VLN-BERT复现遇到的bug
create docker
sudo nvidia-docker run -it --mount type=bind,source=/home/oem/Desktop/Zeyue/Attack/Matterport3DSimulator,target=/home/oem/Desktop/Zeyue/Attack/Matterport3DSimulator --volume `pwd`:/root/mount/Matterport3DSimulator mattersim:9.2-devel-ubuntu18.04
BUG:
return [get_point_angle_feature(baseViewId) for baseViewId in range(36)]File "/home/oem/Desktop/Zeyue/Attack/Matterport3DSimulator/VLN/Recurrent-VLN-BERT/r2r_src/utils.py", line 378, in <listcomp>return [get_point_angle_feature(baseViewId) for baseViewId in range(36)]File "/home/oem/Desktop/Zeyue/Attack/Matterport3DSimulator/VLN/Recurrent-VLN-BERT/r2r_src/utils.py", line 363, in get_point_angle_featuresim.newEpisode('ZMojNkEp431', '2f4d90acd4024c269fb0efe49a8ac540', 0, math.radians(-30))
TypeError: newEpisode(): incompatible function arguments. The following argument types are supported:1. (self: MatterSim.Simulator, arg0: List[str], arg1: List[str], arg2: List[float], arg3: List[float]) -> NoneInvoked with: <MatterSim.Simulator object at 0x7fee5ec38180>, 'ZMojNkEp431', '2f4d90acd4024c269fb0efe49a8ac540', 0, -0.5235987755982988
sim = new_simulator()feature = np.empty((36, args.angle_feat_size), np.float32)
base_heading = (baseViewId % 12) * math.radians(30)
for ix in range(36):if ix == 0:sim.newEpisode(['ZMojNkEp431'], ['2f4d90acd4024c269fb0efe49a8ac540'], [0], [math.radians(-30)])elif ix % 12 == 0:sim.makeAction([0], [1.0], [1.0])else:sim.makeAction([0], [1.0], [0])state = sim.getState()[0]# print(state,ix)assert state.viewIndex == ix
解决方法:按格式改
AttributeError: 'list' object has no attribute 'viewIndex'
解决方法:state = sim.getState()改为state = sim.getState()[0]
ModuleNotFoundError: No module named 'transformers.pytorch_transformers'
解决方法: pytorch_transformers去掉
OSError: file Prevalent/pretrained_model/pytorch_model.bin not found
原因: 没有把预训练权重导进去
解决方法:把相应的地址改一下:
/home/tianzeyue/EQA_attack/Recurrent-VLN-BERT/weight/pytorch_model.bin
TypeError: init_weights() takes 1 positional argument but 2 were given
解决方法:
self.apply(self.init_weights)改为self.init_weights()
参考: https://github.com/lonePatient/Bert-Multi-Label-Text-Classification/issues/24
File "r2r_src/train.py", line 198, in train_valtrain_env = R2RBatch(feat_dict, batch_size=args.batchSize, splits=['train'], tokenizer=tok)File "/home/oem/Desktop/Zeyue/Attack/Matterport3DSimulator/VLN/Recurrent-VLN-BERT/r2r_src/env.py", line 96, in __init__self.env = EnvBatch(feature_store=feature_store, batch_size=batch_size)File "/home/oem/Desktop/Zeyue/Attack/Matterport3DSimulator/VLN/Recurrent-VLN-BERT/r2r_src/env.py", line 55, in __init__sim.init()
AttributeError: 'MatterSim.Simulator' object has no attribute 'init'
解决方法:
sim.init()改为sim.initialize()
作者提到是版本原因: https://github.com/YicongHong/Recurrent-VLN-BERT/issues/4
param.data = fn(param.data)File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 265, in <lambda>return self._apply(lambda t: t.cuda(device))File "/usr/local/lib/python3.6/dist-packages/torch/cuda/__init__.py", line 163, in _lazy_inittorch._C._cuda_init()
RuntimeError: cuda runtime error (38) : no CUDA-capable device is detected at /pytorch/aten/src/THC/THCGeneral.cpp:51
single GPU
解决方法: os.environ[‘CUDA_VISIBLE_DEVICES’] = ‘0’
File "/home/oem/Desktop/Zeyue/Attack/Matterport3DSimulator/VLN/Recurrent-VLN-BERT/r2r_src/agent.py", line 571, in loadstates = torch.load(path)File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 387, in loadreturn _load(f, map_location, pickle_module, **pickle_load_args)File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 560, in _loadraise RuntimeError("{} is a zip archive (did you mean to use torch.jit.load()?)".format(f.name))
RuntimeError: snap/VLNBERT-PREVALENT-final/state_dict/best_val_unseen is a zip archive (did you mean to use torch.jit.load()?)
解决方法: torch.jit.load()
update the pytorch version
File "/home/oem/Desktop/Zeyue/Attack/Matterport3DSimulator/VLN/Recurrent-VLN-BERT/r2r_src/vlnbert/vlnbert_PREVALENT.py", line 393, in forwardtoken_type_ids = torch.zeros_like(input_ids)
RuntimeError: CUDA error: no kernel image is available for execution on the device
解决方法:change the cuda version
https://blog.csdn.net/li4692625/article/details/123169438
Traceback (most recent call last):File "src/driver/driver.py", line 37, in <module>sim.makeAction(sim, [1], [1], [1])
TypeError: makeAction(): incompatible function arguments. The following argument types are supported:1. (self: MatterSim.Simulator, arg0: List[int], arg1: List[float], arg2: List[float]) -> None
# For now, the agent can't pick which forward move to make - just the one in the middleenv_actions = {'left': [[0],[-1], [0]], # left'right': [[0], [1], [0]], # right'up': [[0], [0], [1]], # up'down': [[0], [0],[-1]], # down'forward': [[1],[0], [0]], # forward'<end>': [[0], [0], [0]], # <end>'<start>': [[0], [0], [0]], # <start>'<ignore>': [[0], [0], [0]] # <ignore>}
解决方法:change the defined action ‘left’: (0, 0, 0) to ‘left’: [[0],[-1], [0]].
Result:
Loaded the listener model at iter 114000 from snap/VLNBERT-PREVALENT-final/state_dict/best_val_unseen
result length 1501
Env name: val_train_seen, nav_error: 0.8354, oracle_error: 0.6634, steps: 5.1839, lengths: 10.0262, success_rate: 0.9394, oracle_rate: 0.9520, spl: 0.9125
result length 1021
Env name: val_seen, nav_error: 2.8973, oracle_error: 1.9402, steps: 5.5436, lengths: 11.1393, success_rate: 0.7228, oracle_rate: 0.7826, spl: 0.6774
result length 2349
Env name: val_unseen, nav_error: 3.9281, oracle_error: 2.5456, steps: 6.1235, lengths: 12.0003, success_rate: 0.6275, oracle_rate: 0.7020, spl: 0.5684
Recurrent-VLN-BERT相关推荐
- 吴琦:AI研究一路走到“黑”, 从VQA到VLN
作者 | 吴琦,阿德莱德大学助理教授 本文作者为阿德莱德大学助理教授吴琦,他详细介绍有关从VQA到VLN的详细内容: VLN之来龙去脉篇 VLN之任务数据篇 VLN之方法创新篇 VLN之未来思考篇 V ...
- VLN阅读报告1:Vision-and-Language Navigation综述(2022ACL)
本博文是结合论文Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions,对VLN进行学习总结 ...
- VLN: 基于全局对比训练的视觉-语言导航方法
每天给你送来NLP技术干货! 来自:CAAI认知系统与信息处理专委会 视觉-语言导航任务(Vision-Language Navigation, VLN)是指在陌生环境中,无人系统依据语言指示和观测图 ...
- CVPR 2021 论文和开源项目合集(Papers with Code)
摘自:https://github.com/amusi/CVPR2021-Papers-with-Code CVPR 2021 论文和开源项目合集 CVPR 2021 论文和开源项目合集(Papers ...
- ICLR 2020论文投稿2600篇,GNN、BERT、Transformer领跑热门研究方向
(图片由AI科技大本营付费下载自视觉中国) 出品 | AI科技大本营(ID:rgznai100) 2019 年 4,ICLR 2020 论文征集活动开始,截止 9 月 25 日,大会共收到近 2600 ...
- 如何使用 BERT 进行自然语言处理?
点击上方"视学算法",选择加"星标"或"置顶" 重磅干货,第一时间送达 来源:AI前线本文大约7510字,阅读时间约10分钟.本文介绍并探索 ...
- 谁说GPT只擅长生成?清华研究力证:GPT语言理解能力不输BERT
点击上方"视学算法",选择加"星标"或"置顶" 重磅干货,第一时间送达 作者|张倩.小舟 来源|机器之心 一直以来,GPT 模型的语言生成能 ...
- 超越BERT的模型有哪些?
机器之心 & ArXiv Weekly Radiostation 参与:杜伟.楚航.罗若天 本周的重要论文包括依图推出的预训练语言理解新模型 ConvBERT,以及关于机器学习模型安全性与隐私 ...
- 《预训练周刊》第5期:智源等研究力证:GPT语言理解能力不输BERT、盘点NLP预训练「兵器谱」...
No.05 智源社区 预训练组 预 训 练 研究 观点 资源 活动 关于周刊 超大规模预训练模型是当前人工智能领域研究的热点,为了帮助研究与工程人员了解这一领域的进展和资讯,智源社区整理了第5期< ...
- 智源青年科学家杨植麟:为什么预处理模型XLNet比BERT、RoBERTa更加优越
在2020年2月11日下午的"智源论坛Live | 青年科学家线上报告会"中,智源青年科学家.Recurrent AI联合创始人杨植麟做了题为<Latest Advances ...
最新文章
- Stream流与Lambda表达式(一) 杂谈
- LVS +DR +keepalived高可用性web集群
- 微信小程序红包开发 小程序发红包 开发过程中遇到的坑 微信小程序红包接口的...
- Java语言的循环控制结构
- 使用FULL OUTER JOIN拼接表数据
- hive连接mysql的配置_Dbeaver连接Hive和Mysql的配置
- C语言标识符的链接属性
- 安装+wordpress+出现403+forbidden_教程篇 | WordPress网站搭建详细教程
- 【Apache JMeter】JMeter接口压测实例
- 《代码之美》第六章:菜鸟的自圆其说
- 安装 Windows Server 2008
- 122 - Trees on the level(模拟内存池解法)
- python打开txt文件找不到-Docker Python脚本找不到文件
- NLP︱高级词向量表达(三)——WordRank(简述)
- IDEA用maven创建springMVC项目和配置
- 领导者核心能力七力模型
- 基于go语言的史上最流弊的学生成绩管理系统
- 【毕设选题推荐】机器人工程专业毕设选题推荐
- JS 报错getElementsByClassName.appendChild报错“Uncaught TypeError: s.appendChild is not a function”
- Android Studio Template模板 制作模板