-
Notifications
You must be signed in to change notification settings - Fork 61
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #122 from MouseLand/dev
Change display layout
- Loading branch information
Showing
10 changed files
with
1,256 additions
and
1,186 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,23 +1,24 @@ | ||
# Neural activity prediction | ||
|
||
This tutorial shows how to use the deep neural network encoding model for neural prediction using mouse orofacial behavior. | ||
This tutorial shows how to use the deep neural network encoding model to predict neural activity based on mouse orofacial behavior. | ||
|
||
To process neural activity prediction using pose estimates extracted using the tracker: | ||
To process neural activity prediction using pose estimates extracted using the keypoint tracker: | ||
|
||
1. Load or process keypoints ([see pose tracking tutorial](docs/pose_tracking_gui_tutorial.md)). | ||
2. Select `Neural activity` from file menu to `Load neural data`. | ||
3. Load neural activity data (2D-array stored in *.npy) and (optionally) timestamps for neural and behavioral data (1D-array stored in *.npy) then click `Done`. | ||
4. Select `Run neural prediction` from the `Neural activity` file menu. | ||
5. Select `Keypoints` as input data and set whether the output of the model's prediction to be `neural PCs` or neural activity. Use help button to set training parameters for the model. | ||
5. The predicted neural activity *.npy file will be saved in the selected output folder. | ||
1. Load or process keypoints ([see pose tracking tutorial](https://github.com/MouseLand/facemap/blob/main/docs/pose_tracking_gui_tutorial.md)). | ||
2. Select `Neural activity` from file menu. | ||
3. Click on `Launch neural activity window`. | ||
4. Select `Load neural activity` (2D-array stored in *.npy) and (optionally) timestamps for neural and behavioral data (1D-arrays stored in *.npy) then click `Done`. | ||
4. Once the neural data is loaded, click on `Run neural predictions`. | ||
5. Select `Keypoints` as input data and select one of the options for output of the model's prediction, which can be `Neural PCs` or neural activity. CLick on `Help` button for more information. | ||
5. The predicted neural activity (*.npy) file will be saved in the selected output folder. | ||
|
||
To process neural activity prediction using pose estimates extracted using the tracker: | ||
To predict neural activity using SVDs from Facemap: | ||
|
||
1. Load or process SVDs for the video. ([see SVD tutorial](docs/svd_tutorial.md)). | ||
1. Load or process SVDs for the video. ([see SVD tutorial](https://github.com/MouseLand/facemap/blob/main/docs/svd_python_tutorial.md)). | ||
2. Follow steps 2-5 above. | ||
|
||
Note: a linear model is used for prediction using SVDs. | ||
|
||
Predicted neural activity will be plotted in the bottom-right window of the GUI. You can highlight test data by selecting `Highlight test data` from the `Neural activity` file menu. Further information about neural prediction, including variance explained can be found in the saved neural prediction file. | ||
Predicted neural activity will be plotted in the neural activity window. Toggle `Highlight test data` to highlight time segments not used for training i.e. test data. Further information about neural prediction, including variance explained can be found in the saved neural prediction file (*.npy). | ||
|
||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,37 +1,36 @@ | ||
Neural activity prediction | ||
========================== | ||
|
||
This tutorial shows how to use the deep neural network encoding model | ||
for neural prediction using mouse orofacial behavior. | ||
This tutorial shows how to use the deep neural network encoding model to | ||
predict neural activity based on mouse orofacial behavior. | ||
|
||
To process neural activity prediction using pose estimates extracted | ||
using the tracker: | ||
using the keypoint tracker: | ||
|
||
1. Load or process keypoints (`see pose tracking | ||
tutorial <https://github.com/MouseLand/facemap/blob/main/docs/pose_tracking_gui_tutorial.md>`__). | ||
2. Select ``Neural activity`` from file menu to ``Load neural data``. | ||
3. Load neural activity data (2D-array stored in *.npy) and (optionally) | ||
timestamps for neural and behavioral data (1D-array stored in*.npy) | ||
then click ``Done``. | ||
4. Select ``Run neural prediction`` from the ``Neural activity`` file | ||
menu. | ||
5. Select ``Keypoints`` as input data and set whether the output of the | ||
model’s prediction to be ``neural PCs`` or neural activity. Use help | ||
button to set training parameters for the model. | ||
6. The predicted neural activity \*.npy file will be saved in the | ||
2. Select ``Neural activity`` from file menu. | ||
3. Click on ``Launch neural activity window``. | ||
4. Select ``Load neural activity`` (2D-array stored in \*.npy) and | ||
(optionally) timestamps for neural and behavioral data (1D-arrays | ||
stored in*.npy) then click ``Done``. | ||
5. Once the neural data is loaded, click on ``Run neural predictions``. | ||
6. Select ``Keypoints`` as input data and select one of the options for | ||
output of the model’s prediction, which can be ``Neural PCs`` or | ||
neural activity. CLick on ``Help`` button for more information. | ||
7. The predicted neural activity (\*.npy) file will be saved in the | ||
selected output folder. | ||
|
||
To process neural activity prediction using pose estimates extracted | ||
using the tracker: | ||
To predict neural activity using SVDs from Facemap: | ||
|
||
1. Load or process SVDs for the video. (`see SVD | ||
tutorial <https://github.com/MouseLand/facemap/blob/main/docs/svd_python_tutorial.md>`__). | ||
2. Follow steps 2-5 above. | ||
|
||
Note: a linear model is used for prediction using SVDs. | ||
|
||
Predicted neural activity will be plotted in the bottom-right window of | ||
the GUI. You can highlight test data by selecting | ||
``Highlight test data`` from the ``Neural activity`` file menu. Further | ||
information about neural prediction, including variance explained can be | ||
found in the saved neural prediction file. | ||
Predicted neural activity will be plotted in the neural activity window. | ||
Toggle ``Highlight test data`` to highlight time segments not used for | ||
training i.e. test data. Further information about neural prediction, | ||
including variance explained can be found in the saved neural prediction | ||
file (\*.npy). |
Oops, something went wrong.