Unanswered
Hi Guys,
I Managed To Set Up A Kubernetes Cluster And Install Trains Into It.
While Testing My Set-Up I Run The Test_Reporting.Py Example
` sdk {
# TRAINS - default SDK configuration
storage {
cache {
# Defaults to system temp folder / cache
default_base_dir: "~/.trains/cache"
}
direct_access: [
# Objects matching are considered to be available for direct access, i.e. they will not be downloaded
# or cached, and any download request will return a direct reference.
# Objects are specified in glob format, available for url and content_type.
{ url: "file://*" } # file-urls are always directly referenced
]
}
metrics {
# History size for debug files per metric/variant. For each metric/variant combination with an attached file
# (e.g. debug image event), file names for the uploaded files will be recycled in such a way that no more than
# X files are stored in the upload destination for each metric/variant combination.
file_history_size: 100
# Max history size for matplotlib imshow files per plot title.
# File names for the uploaded images will be recycled in such a way that no more than
# X images are stored in the upload destination for each matplotlib plot title.
matplotlib_untitled_history_size: 100
# Limit the number of digits after the dot in plot reporting (reducing plot report size)
# plot_max_num_digits: 5
# Settings for generated debug images
images {
format: JPEG
quality: 87
subsampling: 0
}
# Support plot-per-graph fully matching Tensorboard behavior (i.e. if this is set to true, each series should have its own graph)
tensorboard_single_series_per_graph: false
}
network {
metrics {
# Number of threads allocated to uploading files (typically debug images) when transmitting metrics for
# a specific iteration
file_upload_threads: 4
# Warn about upload starvation if no uploads were made in specified period while file-bearing events keep
# being sent for upload
file_upload_starvation_warning_sec: 120
}
iteration {
# Max number of retries when getting frames if the server returned an error (http code 500)
max_retries_on_server_error: 5
# Backoff factory for consecutive retry attempts.
# SDK will wait for {backoff factor} * (2 ^ ({number of total retries} - 1)) between retries.
retry_backoff_factor_sec: 10
}
}
aws {
s3 {
# S3 credentials, used for read/write access by various SDK elements
# default, used for any bucket not specified below
key: ""
secret: ""
region: ""
credentials: [
# specifies key/secret credentials to use when handling s3 urls (read or write)
# {
# bucket: "my-bucket-name"
# key: "my-access-key"
# secret: "my-secret-key"
# },
# {
# # This will apply to all buckets in this host (unless key/value is specifically provided for a given bucket)
# host: "my-minio-host:9000"
# key: "12345678"
# secret: "12345678"
# multipart: false
# secure: false
# }
]
}
boto3 {
pool_connections: 512
max_multipart_concurrency: 16
}
}
google.storage {
# # Default project and credentials file
# # Will be used when no bucket configuration is found
# project: "trains"
# credentials_json: "/path/to/credentials.json"
# # Specific credentials per bucket and sub directory
# credentials = [
# {
# bucket: "my-bucket"
# subdir: "path/in/bucket" # Not required
# project: "trains"
# credentials_json: "/path/to/credentials.json"
# },
# ]
}
azure.storage {
# containers: [
# {
# account_name: "trains"
# account_key: "secret"
# # container_name:
# }
# ]
}
log {
# debugging feature: set this to true to make null log propagate messages to root logger (so they appear in stdout)
null_log_propagate: false
task_log_buffer_capacity: 66
# disable urllib info and lower levels
disable_urllib3_info: true
}
development {
# Development-mode options
# dev task reuse window
task_reuse_time_window_in_hours: 72.0
# Run VCS repository detection asynchronously
vcs_repo_detect_async: true
# Store uncommitted git/hg source code diff in experiment manifest when training in development mode
# This stores "git diff" or "hg diff" into the experiment's "script.requirements.diff" section
store_uncommitted_code_diff: true
# Support stopping an experiment in case it was externally stopped, status was changed or task was reset
support_stopping: true
# Default Task output_uri. if output_uri is not provided to Task.init, default_output_uri will be used instead.
default_output_uri: ""
# Default auto generated requirements optimize for smaller requirements
# If True, analyze the entire repository regardless of the entry point.
# If False, first analyze the entry point script, if it does not contain other to local files,
# do not analyze the entire repository.
force_analyze_entire_repo: false
# If set to true, *trains* update message will not be printed to the console
# this value can be overwritten with os environment variable TRAINS_SUPPRESS_UPDATE_MESSAGE=1
suppress_update_message: false
# If this flag is true (default is false), instead of analyzing the code with Pigar, analyze with `pip freeze`
detect_with_pip_freeze: false
# Log specific environment variables. OS environments are enlisted in the "Environment" section
# of the Hyper-Parameters.
# multiple selected variables are supported including the suffix '*'.
# For example: "AWS_*" will log any OS environment variable starting with 'AWS_'.
# This value can be overwritten with os environment variable TRAINS_LOG_ENVIRONMENT="[AWS_*, CUDA_VERSION]"
# Example: log_os_environments: ["AWS_*", "CUDA_VERSION"]
log_os_environments: []
# Development mode worker
worker {
# Status report period in seconds
report_period_sec: 2
# ping to the server - check connectivity
ping_period_sec: 30
# Log all stdout & stderr
log_stdout: true
# compatibility feature, report memory usage for the entire machine
# default (false), report only on the running process and its sub-processes
report_global_mem_used: false
}
}
} `
149 Views
0
Answers
3 years ago
one year ago
Tags