【功能模块】

【操作步骤&问题现象】

1、在本地可以跑通的代码在model_art 无法跑通

2、错误代码 try to send request before open()

【截图信息】

【日志信息】（可选，上传日志内容或者附件）

• do nothing
• [modelarts service log]user: uid=1101(work) gid=1101(work) groups=1101(work),1000(hwhiaiuser)
• [modelarts service log]pwd: /home/work
• [modelarts service log]app_url: s3://sunzengguo-train/zlf/nst/
• [modelarts service log]boot_file: nst/train.py
• [modelarts service log]log_url: /tmp/log/zlf_nst.log
• [modelarts service log]command: nst/train.py --data_url=s3://sunzengguo-train/zlf/nst/img_data/ --train_url=s3://sunzengguo-train/zlf/nst/output/
• [modelarts service log]local_code_dir:
• [modelarts service log]training start at 2022-06-02-17:17:47
• [modelarts service log][modelarts_create_log] modelarts-pipe found
• [modelarts service log]modelarts-pipe: will create log file /tmp/log/zlf_nst.log
• [modelarts service log]handle inputs of training job
• info:root:using moxing-v2.0.0.rc2.4b57a67b-4b57a67b
• info:root:using obs-python-sdk-3.20.9.1
• [modelarts service log][info][2022/06/02 17:17:48]: env ma_inputs is not found, skip the inputs handler
• info:root:using moxing-v2.0.0.rc2.4b57a67b-4b57a67b
• info:root:using obs-python-sdk-3.20.9.1
• [modelarts service log]2022-06-02 17:17:49,416 - modelarts-downloader.py[line:623] - info: main: modelarts-downloader starting with namespace(dst='./', recursive=true, skip_creating_dir=false, src='s3://sunzengguo-train/zlf/nst/', trace=false, type='common', verbose=false)
• [modelarts service log][modelarts_logger] modelarts-pipe found
• [modelarts service log]modelarts-pipe: will create log file /tmp/log/zlf_nst.log
• /home/work/user-job-dir
• [modelarts service log]modelarts-pipe: will write log file /tmp/log/zlf_nst.log
• [modelarts service log]modelarts-pipe: param for max log length: 1073741824
• [modelarts service log]modelarts-pipe: param for whether exit on overflow: 0
• [modelarts service log]modelarts-pipe: total length: 24
• [modelarts service log][modelarts_logger] modelarts-pipe found
• [modelarts service log]modelarts-pipe: will create log file /tmp/log/zlf_nst.log
• [modelarts service log]modelarts-pipe: will write log file /tmp/log/zlf_nst.log
• [modelarts service log]modelarts-pipe: param for max log length: 1073741824
• [modelarts service log]modelarts-pipe: param for whether exit on overflow: 0
• info:root:using moxing-v2.0.0.rc2.4b57a67b-4b57a67b
• info:root:using obs-python-sdk-3.20.9.1
• [modelarts service log]2022-06-02 17:17:57,381 - info - background upload stdout log to s3://sunzengguo-train/zlf/logs/job386a315f-job-zlf-nst-0.log
• [modelarts service log]2022-06-02 17:17:57,390 - info - ascend driver: version=21.0.2.spc001
• [modelarts service log]2022-06-02 17:17:57,391 - info - you are advised to use ascend_device_id env instead of device_id, as the device_id env will be discarded in later versions
• [modelarts service log]2022-06-02 17:17:57,391 - info - particularly, ${ascend_device_id} == ${device_id}, it's the logical device id
• [modelarts service log]2022-06-02 17:17:57,391 - info - davinci training command
• [modelarts service log]2022-06-02 17:17:57,391 - info - ['/usr/bin/python', '/home/work/user-job-dir/nst/train.py', '--data_url=s3://sunzengguo-train/zlf/nst/img_data/', '--train_url=s3://sunzengguo-train/zlf/nst/output/']
• [modelarts service log]2022-06-02 17:17:57,391 - info - wait for rank table file ready
• [modelarts service log]2022-06-02 17:17:57,391 - info - rank table file (k8s generated) is ready for read
• [modelarts service log]2022-06-02 17:17:57,392 - info -
• {
• "status": "completed",
• "group_count": "1",
• "group_list": [
• {
• "group_name": "job-zlf-nst",
• "device_count": "1",
• "instance_count": "1",