Skip to content

Commit

Permalink
Merge pull request #31 from GilesStrong/new_live
Browse files Browse the repository at this point in the history
New live
  • Loading branch information
GilesStrong authored Feb 12, 2020
2 parents 1ed79d7 + b3d7a05 commit 8675b72
Show file tree
Hide file tree
Showing 16 changed files with 2,669 additions and 2,454 deletions.
15 changes: 15 additions & 0 deletions CHANGES.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,23 +2,38 @@

## Important changes

- New live plot for losses during training (`MetricLogger`):
- Provides additional information
- Only updates after every epoch (previously every subepoch) reducing training times
- Nicer appearance and automatic log scale for y-axis

## Breaking

## Additions

- New live plot for losses during training (`MetricLogger`):
- Provides additional information
- Only updates after every epoch (previously every subepoch) reducing training times
- Nicer appearance and automatic log scale for y-axis

## Removals

## Fixes

- Fixed error in documentation which removed the ToC for the nn module

## Changes

## Depreciations

- `plots` argument in `fold_train_ensemble`. The plots argument is now depreciated and ignored. Loss history will always be shown, lr history will no longer be shown separately, and live feedback is now controlled by the four live_fdbk arguments. This argument will be removed in V0.6.

## Comments

# V0.5 - The Gradient Must Flow

## Important changes

- Added support for processing and embedding of matrix data
- `MultiHead` to allow the use of multiple head blocks to handle input data containing flat and matrix inputs
- `AbsMatrixHead` abstract class for head blocks designed to process matrix data
Expand Down
1 change: 1 addition & 0 deletions docs/source/lumin.nn.models.rst
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@ Subpackages

.. toctree::
:maxdepth: 1

lumin.nn.models.blocks
lumin.nn.models.layers

Expand Down
1 change: 1 addition & 0 deletions docs/source/lumin.nn.rst
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@ Subpackages

.. toctree::
:maxdepth: 1

lumin.nn.callbacks
lumin.nn.data
lumin.nn.ensemble
Expand Down
8 changes: 8 additions & 0 deletions docs/source/lumin.nn.training.rst
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,14 @@ lumin.nn.training.fold\_train module
:undoc-members:
:show-inheritance:

lumin.nn.training.metric\_logger module
---------------------------------------

.. automodule:: lumin.nn.training.metric_logger
:members:
:undoc-members:
:show-inheritance:


Module contents
---------------
Expand Down
1 change: 1 addition & 0 deletions docs/source/lumin.rst
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@ Subpackages

.. toctree::
:maxdepth: 1

lumin.data_processing
lumin.evaluation
lumin.inference
Expand Down
118 changes: 59 additions & 59 deletions examples/Advanced_Model_Building.ipynb

Large diffs are not rendered by default.

1,091 changes: 527 additions & 564 deletions examples/Binary_Classification.ipynb

Large diffs are not rendered by default.

468 changes: 235 additions & 233 deletions examples/Classification_of_earnings.ipynb

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion examples/Feature_Selection.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@
"metadata": {},
"outputs": [],
"source": [
"# !pip install fastprogress==0.1.21 lumin\n",
"# !pip install lumin\n",
"# !git clone https://github.com/SauceCat/PDPbox.git && cd PDPbox && pip install -e ."
]
},
Expand Down
Loading

0 comments on commit 8675b72

Please sign in to comment.