rapidtide 3.0a14__tar.gz → 3.0a15__tar.gz

{rapidtide-3.0a14 → rapidtide-3.0a15}/CHANGELOG.md

@@ -1,5 +1,15 @@
 # Release history
 
+## Version 3.0alpha15 (4/22/25)
+* (rapidtide) Fixed a bug in masking logic introduced in last version.
+* (rapidtide) Pullled regressor cleaning steps out into a separate routine.
+* (rapidtide) Removed unused "noiseregressor" code.  Its functionality is now covered with confound regression.
+* (rapidtide) Removed memory profiling code that relied on an unsupported library.
+* (rapidtide) Defined a new class to handle the input data.  This simplifies a lot of internal operations.
+* (happy) Updated deep learning filter training and inference code, and saved models, for better tensorflow 2 compatibility.
+* (docs) Updated installation instructions.
+* (package) Updated copyright notices.
+
 ## Version 3.0alpha14 (4/8/25)
 * (rapidtide) Rationalized handling of zero-mean data - now use the ``--dataiszeromean`` argument to tell rapidtide how to make masks.  ``--globalmaskmethod`` no longer exists.
 * (retroregress) Some bugfixes.

{rapidtide-3.0a14 → rapidtide-3.0a15}/INSTALL.rst

@@ -1,7 +1,7 @@
 Bare metal installation
 -----------------------
-This gives you the maximum flexibility if you want to look at the code and/or modify things.  It may seem a little daunting at first,
-but it's not that bad.  And if you want a simpler path, skip down to the Docker installation instructions
+This gives you the maximum flexibility if you want to look at the code and/or modify things.
+If you want a simpler path, skip down to the Docker/singularity installation instructions.
 
 Required dependencies
 `````````````````````
@@ -24,6 +24,8 @@ installed:
 -  pyqtgraph >= 0.13.4
 -  statsmodels
 -  tqdm
+-  tensorflow
+-  tf-keras
 
 Optional dependencies
 `````````````````````
@@ -33,92 +35,56 @@ The following optional dependencies will be used if present:
 -  numba (for faster performance)
 -  pyfftw (faster performance)
 -  mkl and mkl-service (faster performance on Intel CPUs)
--  memory_profiler (allows for more detailed memory usage stats)
 
-If you want to use the deep learning filter in happy, you’ll need Keras
-and some sort of backend. If you want to be able to train filters,
-you’ll probably want GPU support. This is currently an annoying,
-non-trivial thing to set up, especially on a Mac, which is where I do
-things, because Apple and Nvidia aren’t friends at the moment. If you
-are on a linux box (or maybe Windows - haven’t tested), WITH an Nvidia
-GPU, install:
 
--  keras
--  tensorflow-gpu (This assumes you have all the necessary CUDA
-   libraries. Making this all work together properly is a version
-   dependent moving target. Ask The Google the best way to do it this
-   week - anything I say here will probably be obsolete by the time you
-   read this.)
+Installing with pip from pypi
+`````````````````````````````
 
-If you are on linux (or Windows) WITHOUT an Nvidia GPU, or on a Mac, install:
-
-- keras
-- tensorflow (and make sure it doesn’t sneakily try to install the GPU version - that won’t work)
-
-
-Installing Python
-`````````````````
-
-The simplest way BY FAR to get this all done is to use Anaconda python
-from Continuum Analytics. It’s a free, curated scientific Python
-distribution that is easy to maintain and takes a lot of headaches out
-of maintaining a distribution. It also already comes with many of the
-dependencies for rapidtide installed by default. You can get it here:
-https://www.continuum.io. Rapidtide works with Python 3.9 or greater.
-
-After installing Anaconda python, install the remaining dependencies
-(including some good optional ones:
+This assumes you have a working python installation, and if you use virtual
+environments, you've set one up and activated it.  Once that's all ready, you can simply install
+with pip (this will pull everything it needs from pypi.org, the Python Package Index):
 
 ::
 
-   conda install nibabel "pyqtgraph>=0.12.0" pyfftw
-
-
-For the deep learning filter in happy, also do:
-
-::
-
-   conda install keras tensorflow-gpu
-
-
-(for Linux or Windows WITH Nvidia GPU)
-
-or:
-
-::
-
-   conda install keras tensorflow
-
-
-(for a Mac, or Linux or Windows WITHOUT Nvidia GPU)
+    pip install rapidtide
 
+This will install rapidtide and all dependencies direct from pypi.  You should be
+all set.
 
 Done.
 
-Installing the rapidtide package
-````````````````````````````````
+Installing from Github
+``````````````````````
 
-Once you have installed the prerequisites, cd into the package
-directory, and type the following:
+You can take this route if you want to poke around in the code, and perhaps modify it.
+As above, this assumes you have python installed and if you are using a virtual environment,
+you've activated it.  Go to the directory where you want to install the rapidtide
+source code, and type:
 
 ::
 
-   python install .
+   git clone https://github.com/bbfrederick/rapidtide.git
+   cd rapidtide
+   refresh
 
 
 to install all of the tools in the package. You should be able to run
-them from the command line then (after rehashing).
-
-Updating
-````````
+them from the command line then, and all the code is in your current directory (and
+subdirectories).
 
-If you’ve previously installed rapidtide and want to update, cd into the
-package directory and do a git pull first:
+If you’ve made edits to the code, or want to sync up with the current version on Github,
+cd into the
+package directory and type ``refresh``:
 
 ::
 
-   git pull
-   python setup.py install
+   refresh
+
+
+This will uninstall the current version, sync up to github, and reinstall
+the package (assuming you don't have any merge conflicts with the version on Github,
+which you have to resolve).  This will keep you on the bleeding edge of development,
+if that's your thing.
 
 
 Docker installation
@@ -131,9 +97,13 @@ first make sure you have docker installed and properly configured, then run the
 
 
 This will download the Docker container from dockerhub.
-It's around a 3GB download, so it may take some time, but it caches the file locally, so you won't have to do this again
-unless the container updates.  To use a particular version, replace "latest-release" with the version of the
-container you want.
+It's around a 3GB download, so it may take some time, but it caches the file locally,
+so you won't have to do this again
+unless the container updates.  To use a particular version,
+replace "latest-release" with the version of the
+container you want.  Please note that I generate amd64 and arm64 versions of the container,
+so it runs natively (the amd64 container will run on an Apple Silicon Mac in Docker, but,
+Docker will pull the arm64 version unless you tell it not to).
 
 If you like to live on the edge, just use:
 ::

{rapidtide-3.0a14/rapidtide.egg-info → rapidtide-3.0a15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rapidtide
-Version: 3.0a14
+Version: 3.0a15
 Summary: Tools for performing correlation analysis on fMRI data.
 Author: Taylor Salo, Daniel M. Drucker, Ph.D., Jeffrey N Stout, Yaroslav O. Halchenko, Derek Monroe
 Author-email: "Blaise deB. Frederick" <blaise.frederick@gmail.com>

{rapidtide-3.0a14 → rapidtide-3.0a15}/pyproject.toml

@@ -29,14 +29,14 @@ dependencies = [
   'scikit-learn',
   'nibabel',
   'nilearn',
-  'matplotlib>=3.3.0',
-  'pyqtgraph>=0.13.4',
+  'matplotlib >= 3.3.0',
+  'pyqtgraph >= 0.13.4',
   'pyqt6-sip',
   'pyqt6',
   'requests',
   'statsmodels',
   'pywavelets',
-  'tensorflow>=2.10.0',
+  'tensorflow >= 2.10.0',
   'tf-keras',
   'tqdm',
   'versioneer',

{rapidtide-3.0a14 → rapidtide-3.0a15}/rapidtide/Colortables.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-#   Copyright 2016-2024 Blaise Frederick
+#   Copyright 2016-2025 Blaise Frederick
 #
 #   Licensed under the Apache License, Version 2.0 (the "License");
 #   you may not use this file except in compliance with the License.

{rapidtide-3.0a14 → rapidtide-3.0a15}/rapidtide/DerivativeDelay.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-#   Copyright 2016-2024 Blaise Frederick
+#   Copyright 2016-2025 Blaise Frederick
 #
 #   Licensed under the Apache License, Version 2.0 (the "License");
 #   you may not use this file except in compliance with the License.

{rapidtide-3.0a14 → rapidtide-3.0a15}/rapidtide/OrthoImageItem.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-#   Copyright 2016-2024 Blaise Frederick
+#   Copyright 2016-2025 Blaise Frederick
 #
 #   Licensed under the Apache License, Version 2.0 (the "License");
 #   you may not use this file except in compliance with the License.

{rapidtide-3.0a14 → rapidtide-3.0a15}/rapidtide/RapidtideDataset.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-#   Copyright 2016-2024 Blaise Frederick
+#   Copyright 2016-2025 Blaise Frederick
 #
 #   Licensed under the Apache License, Version 2.0 (the "License");
 #   you may not use this file except in compliance with the License.
@@ -161,6 +161,7 @@ class Timecourse:
 
 class Overlay:
     "Store a data overlay and some information about it"
+
     LUTname = None
 
     def __init__(
@@ -489,6 +490,7 @@ class Overlay:
 
 class RapidtideDataset:
     "Store all the data associated with a rapidtide dataset"
+
     fileroot = None
     focusregressor = None
     regressorfilterlimits = None

{rapidtide-3.0a14 → rapidtide-3.0a15}/rapidtide/RegressorRefiner.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-#   Copyright 2016-2024 Blaise Frederick
+#   Copyright 2016-2025 Blaise Frederick
 #
 #   Licensed under the Apache License, Version 2.0 (the "License");
 #   you may not use this file except in compliance with the License.

{rapidtide-3.0a14 → rapidtide-3.0a15}/rapidtide/calcandfitcorrpairs.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-#   Copyright 2016-2024 Blaise Frederick
+#   Copyright 2016-2025 Blaise Frederick
 #
 #   Licensed under the Apache License, Version 2.0 (the "License");
 #   you may not use this file except in compliance with the License.

{rapidtide-3.0a14 → rapidtide-3.0a15}/rapidtide/calccoherence.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-#   Copyright 2016-2024 Blaise Frederick
+#   Copyright 2016-2025 Blaise Frederick
 #
 #   Licensed under the Apache License, Version 2.0 (the "License");
 #   you may not use this file except in compliance with the License.

{rapidtide-3.0a14 → rapidtide-3.0a15}/rapidtide/calcnullsimfunc.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-#   Copyright 2016-2024 Blaise Frederick
+#   Copyright 2016-2025 Blaise Frederick
 #
 #   Licensed under the Apache License, Version 2.0 (the "License");
 #   you may not use this file except in compliance with the License.

{rapidtide-3.0a14 → rapidtide-3.0a15}/rapidtide/calcsimfunc.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-#   Copyright 2016-2024 Blaise Frederick
+#   Copyright 2016-2025 Blaise Frederick
 #
 #   Licensed under the Apache License, Version 2.0 (the "License");
 #   you may not use this file except in compliance with the License.

{rapidtide-3.0a14 → rapidtide-3.0a15}/rapidtide/correlate.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-#   Copyright 2016-2024 Blaise Frederick
+#   Copyright 2016-2025 Blaise Frederick
 #
 #   Licensed under the Apache License, Version 2.0 (the "License");
 #   you may not use this file except in compliance with the License.

{rapidtide-3.0a14 → rapidtide-3.0a15}/rapidtide/data/examples/src/test_findmaxlag.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-#   Copyright 2016-2024 Blaise Frederick
+#   Copyright 2016-2025 Blaise Frederick
 #
 #   Licensed under the Apache License, Version 2.0 (the "License");
 #   you may not use this file except in compliance with the License.

{rapidtide-3.0a14 → rapidtide-3.0a15}/rapidtide/data/examples/src/testfmri

@@ -2,10 +2,11 @@
 
 rapidtide \
     --spatialfilt -1 \
-    --delayoffsetspatialfilt -1 \
     --nprocs -1 \
     --searchrange -5 20 \
     --simcalcrange 50 -1 \
     --outputlevel max \
+    --acfix \
     sub-RAPIDTIDETEST.nii.gz \
-    ../dst/sub-RAPIDTIDETEST
+    ../dst/sub-RAPIDTIDETEST_main
+    

{rapidtide-3.0a14 → rapidtide-3.0a15}/rapidtide/data/examples/src/testfuncs

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-#   Copyright 2016-2024 Blaise Frederick
+#   Copyright 2016-2025 Blaise Frederick
 #
 #   Licensed under the Apache License, Version 2.0 (the "License");
 #   you may not use this file except in compliance with the License.

{rapidtide-3.0a14 → rapidtide-3.0a15}/rapidtide/data/examples/src/testhappy

@@ -65,5 +65,16 @@
 happy \
     sub-HAPPYTEST.nii.gz \
     sub-HAPPYTEST.json \
-    --spatialregression \
     ../dst/happy
+
+happy \
+    sub-HAPPYTEST.nii.gz \
+    sub-HAPPYTEST.json \
+    --model ~/code/rapidtide/rapidtide/data/models/model_cnn_w064_l13_fn20_fl08 \
+    ../dst/happy_newcnn
+
+#happy \
+    #sub-HAPPYTEST.nii.gz \
+    #sub-HAPPYTEST.json \
+    #../dst/happy
+#

rapidtide-3.0a15/rapidtide/data/examples/src/testmodels

@@ -0,0 +1,33 @@
+#!/bin/bash
+
+ROOTDIR=/data/frederic
+PCDIR=${ROOTDIR}/physioconn/output_2025
+
+rm ../dst/test_*txt
+
+#./144125/144125_REST1_RL_info.json,0.7202007666318957,0.8433922959142652,0.1885880669098923,0.16165008008446202,0.6377615782804948,-0.08267147123355054,2.6174440579296476,2.0755666381391205
+#./144125/144125_REST1_LR_info.json,0.808565698536329,0.9092988425552718,0.1964254075310612,0.14474567837066749,0.6483316301973894,-0.1649780161060566,2.675852113898243,1.9540795999118095
+#./144125/144125_REST2_RL_info.json,0.8797561606112176,0.9399168800183665,0.10131674249235224,0.14794551115545787,0.6022251227345572,-0.11661211769010084,2.594834129016148,1.9613812654056964
+#./144125/144125_REST2_LR_info.json,0.8945024253604358,0.9870236312805825,0.11015444842855743,0.15346602449619334,0.6273109523220333,-0.17124563603244516,2.3826604881557882,1.9571315095343715
+
+#for MODEL in model_revised_tf2 model_serdar_tf2 model_convautoencoder_en16_fn16 model_convautoencoder_en16_fn24 model_convautoencoder_en16_fn32
+#for MODEL in model_convautoencoder_en16_fn16 model_convautoencoder_en16_fn24 model_convautoencoder_en16_fn32
+#for MODEL in model_cnn_w112_l21_fn50_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w128_l21_fn50_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w032_l21_fn50_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w048_l21_fn50_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w064_l21_fn50_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w080_l21_fn50_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w096_l21_fn50_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned
+#for MODEL in model_cnn_w64_l21_fn35_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w64_l21_fn40_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w64_l21_fn45_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w64_l21_fn50_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w64_l21_fn55_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w64_l21_fn60_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned
+#for MODEL in model_cnn_w064_l21_fn20_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w064_l21_fn25_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w064_l21_fn30_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w064_l21_fn50_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w064_l21_fn60_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned
+
+for MODEL in model_cnn_w064_l03_fn20_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w064_l05_fn20_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w064_l07_fn20_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w064_l09_fn20_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w064_l11_fn20_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned model_cnn_w064_l13_fn20_fl5_e100_t4.0_ct0.72_s20_d1_relu_normaligned
+
+do
+    applydlfilter \
+        ${PCDIR}/144125/144125_REST1_LR_desc-stdrescardfromfmri_timeseries.json:cardiacfromfmri_25.0Hz \
+        ../dst/test_${MODEL}.txt \
+        --model ~/code/rapidtide/rapidtide/experimental/${MODEL} \
+        --nodisplay
+done
+
+showtc \
+    ../dst/test_model*txt \
+    ${PCDIR}/144125/144125_REST1_LR_desc-stdrescardfromfmri_timeseries.json:cardiacfromfmri_25.0Hz,pleth \
+    --samplerate 25.0 \
+    --format separate

rapidtide-3.0a15/rapidtide/data/models/model_cnn_w064_l13_fn20_fl08/loss.txt

@@ -0,0 +1 @@
+model_cnn_w064_l13_fn20_fl08_e100_t4.0_ct0.72_s20_d1_relu_normaligned: Prediction Error: 0.1203965516546574 Raw Error: 0.3173622005504527

rapidtide-3.0a15/rapidtide/data/models/model_cnn_w064_l13_fn20_fl08/model_meta.json

@@ -0,0 +1,167 @@
+{
+    "dofft":false,
+    "dropout_rate":0.3,
+    "excludethresh":4.0,
+    "loss":[
+        0.24404260516166687,
+        0.17086537182331085,
+        0.1626913994550705,
+        0.15824666619300842,
+        0.1552937924861908,
+        0.15289536118507385,
+        0.15105026960372925,
+        0.14951278269290924,
+        0.1482943296432495,
+        0.14708851277828217,
+        0.14622007310390472,
+        0.14542174339294434,
+        0.14468203485012054,
+        0.14401927590370178,
+        0.14356881380081177,
+        0.1431567519903183,
+        0.1426767110824585,
+        0.14235283434391022,
+        0.14201760292053223,
+        0.1416827291250229,
+        0.14137786626815796,
+        0.1413171887397766,
+        0.1410050392150879,
+        0.14084799587726593,
+        0.14060942828655243,
+        0.14049473404884338,
+        0.14031948149204254,
+        0.14010609686374664,
+        0.13996371626853943,
+        0.13981428742408752,
+        0.1398046314716339,
+        0.13953782618045807,
+        0.13946935534477234,
+        0.13942097127437592,
+        0.13929858803749084,
+        0.1392415463924408,
+        0.13916631042957306,
+        0.13909123837947845,
+        0.13897807896137238,
+        0.13887859880924225,
+        0.13896194100379944,
+        0.13884522020816803,
+        0.13871248066425323,
+        0.13862736523151398,
+        0.13862277567386627,
+        0.13859069347381592,
+        0.13844624161720276,
+        0.1384449154138565,
+        0.13835109770298004,
+        0.13827572762966156,
+        0.1383543759584427,
+        0.1382092833518982,
+        0.1382567584514618,
+        0.13819508254528046,
+        0.13807587325572968,
+        0.1380884349346161,
+        0.13805615901947021,
+        0.1380653828382492,
+        0.13794268667697906,
+        0.13790026307106018,
+        0.13785326480865479,
+        0.13780032098293304,
+        0.13788530230522156,
+        0.1379043310880661,
+        0.13773661851882935,
+        0.13784055411815643,
+        0.13778267800807953,
+        0.13777196407318115,
+        0.13764862716197968,
+        0.1377096325159073,
+        0.13772279024124146,
+        0.13765718042850494,
+        0.1376623660326004,
+        0.13756607472896576,
+        0.13752040266990662
+    ],
+    "modelname":"model_cnn_w064_l13_fn20_fl08_e100_t4.0_ct0.72_s20_d1_relu_normaligned",
+    "num_epochs":100,
+    "num_layers":13,
+    "prediction_error":0.1203965516546574,
+    "raw_error":0.3173622005504527,
+    "train_arch":"linux",
+    "usebadpts":false,
+    "val_loss":[
+        0.14685764908790588,
+        0.1399032026529312,
+        0.1351466327905655,
+        0.13281379640102386,
+        0.13339294493198395,
+        0.13446921110153198,
+        0.12706875801086426,
+        0.12919315695762634,
+        0.12760485708713531,
+        0.12744316458702087,
+        0.12421777099370956,
+        0.1245395615696907,
+        0.12591569125652313,
+        0.12412194162607193,
+        0.12446551024913788,
+        0.12413788586854935,
+        0.12483581155538559,
+        0.12359398603439331,
+        0.1228623241186142,
+        0.12202053517103195,
+        0.12229941040277481,
+        0.12206815183162689,
+        0.12430140376091003,
+        0.12533128261566162,
+        0.12202366441488266,
+        0.12182188779115677,
+        0.1225178986787796,
+        0.12186575680971146,
+        0.12262368947267532,
+        0.1224021166563034,
+        0.12279072403907776,
+        0.12190253287553787,
+        0.12132854014635086,
+        0.1216944009065628,
+        0.1224927008152008,
+        0.12153491377830505,
+        0.1227400153875351,
+        0.12249016016721725,
+        0.12205129861831665,
+        0.12162687629461288,
+        0.12101034075021744,
+        0.12102416902780533,
+        0.12136662006378174,
+        0.12166453152894974,
+        0.12160247564315796,
+        0.12130823731422424,
+        0.12100188434123993,
+        0.12094895541667938,
+        0.12116464227437973,
+        0.12116051465272903,
+        0.12174172699451447,
+        0.12167128175497055,
+        0.1208944171667099,
+        0.12136266380548477,
+        0.12133347243070602,
+        0.1213330402970314,
+        0.12072943150997162,
+        0.12061811238527298,
+        0.12106341123580933,
+        0.1216120570898056,
+        0.12063194066286087,
+        0.12124799937009811,
+        0.12051121890544891,
+        0.12211091816425323,
+        0.12039653211832047,
+        0.12158545106649399,
+        0.12119194865226746,
+        0.12082452327013016,
+        0.12100724875926971,
+        0.12084666639566422,
+        0.12118947505950928,
+        0.12046029418706894,
+        0.12182389199733734,
+        0.12113787978887558,
+        0.12074936181306839
+    ],
+    "window_size":64
+}

{rapidtide-3.0a14/rapidtide/data/models/model_serdar → rapidtide-3.0a15/rapidtide/data/models/model_revised_tf2}/model_meta.json

@@ -1,5 +1,5 @@
 {
-    "modelname":"model_serdar",
+    "modelname":"model_revised_tf2",
     "usebadpts":false,
     "window_size":60
 }

{rapidtide-3.0a14/rapidtide/data/models/model_serdar2 → rapidtide-3.0a15/rapidtide/data/models/model_serdar2_tf2}/model_meta.json

@@ -1,5 +1,5 @@
 {
-    "modelname":"model_serdar2",
+    "modelname":"model_serdar2_tf2",
     "usebadpts":false,
     "window_size":60
 }

{rapidtide-3.0a14/rapidtide/data/models/model_revised → rapidtide-3.0a15/rapidtide/data/models/model_serdar_tf2}/model_meta.json

@@ -1,5 +1,5 @@
 {
-    "modelname":"model_revised",
+    "modelname":"model_serdar_tf2",
     "usebadpts":false,
     "window_size":60
 }