Terminal-plot for Tensorboard
A plotter for tensorboard, directly within your terminal. This is useful when you are training your neural network on a remote server, and you just want to quickly peek at the training curve without launching a tensorboard instance and mess with forwarding ports.
Install
You can install the package published in PyPI with
$ pip install tensorboard-termplot
# or install with an isolated environment
# $ pipx install tensorboard-termplot
Usage
$ tensorboard-termplot FOLDER
For example,
$ tensorboard-termplot ~/my_amazing_nn/runs
where runs is the folder that tensorboard had created.
Example
Running the executable on a tensorboard output folder:
Or with the consolidate flag -c/--consolidate to combine multiple stats with a common prefix (most stats in the bottom figure had empty values):
Help
$ tensorboard-termplot --help
usage: tensorboard-termplot [-h] [--canvas-color CANVAS_COLOR]
[--axes-color AXES_COLOR]
[--ticks-color TICKS_COLOR] [--colorless] [-d]
[--grid] [--plotsize WIDTH,HEIGHT] [--force-label]
[--no-iter-color] [-c] [-f] [-n secs]
[--log_interval LOG_INTERVAL]
FOLDER
positional arguments:
FOLDER Folder of a tensorboard runs
optional arguments:
-h, --help show this help message and exit
--canvas-color CANVAS_COLOR
set the color of the plot canvas (the area where the
data is plotted)
--axes-color AXES_COLOR
sets the background color of all the labels
surrounding the actual plot, i.e. the axes, axes
labels and ticks, title and legend, if present
--ticks-color TICKS_COLOR
sets the (full-ground) color of the axes ticks and of
the grid lines.
--colorless Remove color.
-d, --dark-theme A collection of flags. If set, it is equivalent to
setting canvas-color and axes-color to black, and
setting ticks-color to red. Can be overwritten
individually.
--grid Show grid.
--plotsize WIDTH,HEIGHT
Manually set the size of each subplot, e.g., 50,20.
--force-label Force showing label even for plot with one series.
--no-iter-color Stop iterating through different colors per plot.
-c, --consolidate Consolidate based on prefix.
-f, --follow Run in a loop to update display periodic.
-n secs, --interval secs
seconds to wait between updates
Metadata
Release files for tensorboard-termplot 1.3.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| tensorboard-termplot-1.3.2.tar.gz | 13.2 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| tensorboard_termplot-1.3.2-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 28.3 kB
Release files / tensorboard-termplot-1.3.2.tar.gz
| Download URL | tensorboard-termplot-1.3.2.tar.gz |
|---|---|
| Size | 13.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5a73b0ee37c22f5326283b492d93aaab705b09ee4d8d7ae908dace7fc6bdb852
|
|
BLAKE2b-256 checksum How to use checksums |
f3fdb1c720028601c187ffdfb63ea4ec609231be0583a5a8349d352a9a2391ef
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.7
|
Release files / tensorboard_termplot-1.3.2-py3-none-any.whl
| Download URL | tensorboard_termplot-1.3.2-py3-none-any.whl |
|---|---|
| Size | 15.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
818c19513a19f8a0a7f9319cfc7ae7f3be099a1f590a32a0e7a3a3bf1b023114
|
|
BLAKE2b-256 checksum How to use checksums |
2f26dc1e17d07b74627a32642154a60f85e731851f66eaff47c04f419fb13526
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.7
|