Deprecated deep learning (#666)

* MNT: fixing the numpy 2.0 * DOC: fixing the docstring * DOC: fixing the docstring * DOC: fixing more numpy * DOC: deprecated braindecode inside moabb module in favor of braindecode * DOC: updating whats_new.rst file * DOC: fixing whats_new.rst * DOC: fixing api doc rst * DOC: removing braindecode * DOC: removing braindecode * [FIX] removing optional poetry dependancy. * [FIX] removing options about braindecode * [FIX] removing options about braindecode * [FIX] removing braindecode * [FIX] removing braindecode
NeuroTechX · Jan 28, 2025 · fa295b1 · fa295b1
1 parent 0c2cd0a
commit fa295b1
Show file tree

Hide file tree

Showing 17 changed files with 5 additions and 1,117 deletions.
diff --git a/docs/source/pipelines.rst b/docs/source/pipelines.rst
@@ -44,5 +44,3 @@ Base & Utils
     utils_deep_model.EEGNet
     utils_deep_model.EEGNet_TC
     utils_deep_model.TCN_block
-    utils_pytorch.BraindecodeDatasetLoader
-    utils_pytorch.InputShapeSetterEEG
diff --git a/docs/source/whats_new.rst b/docs/source/whats_new.rst
@@ -33,6 +33,7 @@ Bugs
 
 API changes
 ~~~~~~~~~~~
+- Removing the braindecode module from inside moabb (:gh:`666` by `Bruno Aristimunha`_ )
 
 Version - 1.1.1  (Stable - PyPi)
 ---------------------------------

diff --git a/examples/load_model.py b/examples/load_model.py
@@ -1,6 +1,6 @@
 """
 ==============================================
-Load Model (Scikit, Pytorch, Keras) with MOABB
+Load Model (Scikit, Keras) with MOABB
 ==============================================
 
 This example shows how to use load the pretrained pipeline in MOABB.
@@ -13,13 +13,8 @@
 from pickle import load
 
 import keras
-import torch
-from braindecode import EEGClassifier
-from braindecode.models import EEGInception
 from scikeras.wrappers import KerasClassifier
-from sklearn.pipeline import Pipeline, make_pipeline
-from skorch.callbacks import EarlyStopping, EpochScoring
-from skorch.dataset import ValidSplit
+from sklearn.pipeline import Pipeline
 
 from moabb import set_log_level
 from moabb.pipelines.features import StandardScaler_Epoch
@@ -66,46 +61,3 @@
         ("Keras_DeepConvNet_Trained", Keras_DeepConvNet_Trained),
     ]
 )
-
-###############################################################################
-# Loading the PyTorch model
-
-# Hyperparameter
-LEARNING_RATE = 0.0001
-WEIGHT_DECAY = 0
-BATCH_SIZE = 64
-SEED = 42
-VERBOSE = 1
-EPOCH = 2
-PATIENCE = 3
-
-# Define a Skorch classifier
-clf = EEGClassifier(
-    module=EEGInception,
-    optimizer=torch.optim.Adam,
-    optimizer__lr=LEARNING_RATE,
-    batch_size=BATCH_SIZE,
-    max_epochs=EPOCH,
-    train_split=ValidSplit(0.2, random_state=SEED),
-    callbacks=[
-        EarlyStopping(monitor="valid_loss", patience=PATIENCE),
-        EpochScoring(
-            scoring="accuracy", on_train=True, name="train_acc", lower_is_better=False
-        ),
-        EpochScoring(
-            scoring="accuracy", on_train=False, name="valid_acc", lower_is_better=False
-        ),
-    ],
-    verbose=VERBOSE,  # Not printing the results for each epoch
-)
-
-clf.initialize()
-
-f_params = "./results/Models_CrossSession/BNCI2014-001/1/braindecode_EEGInception/EEGInception_fitted_best_model.pkl"
-f_optimizer = "./results/Models_CrossSession/BNCI2014-001/1/braindecode_EEGInception/EEGInception_fitted_best_optim.pkl"
-f_history = "./results/Models_CrossSession/BNCI2014-001/1/braindecode_EEGInception/EEGInception_fitted_best_history.json"
-
-clf.load_params(f_params=f_params, f_optimizer=f_optimizer, f_history=f_history)
-
-# Create the pipelines
-pipes_pytorch = make_pipeline(clf)
diff --git a/examples/pipelines_braindecode/braindecode_EEGInception.py b/examples/pipelines_braindecode/braindecode_EEGInception.py
diff --git a/examples/pipelines_braindecode/braindecode_EEGNetv4.py b/examples/pipelines_braindecode/braindecode_EEGNetv4.py
diff --git a/examples/pipelines_braindecode/braindecode_ShallowFBCSPNet.py b/examples/pipelines_braindecode/braindecode_ShallowFBCSPNet.py
diff --git a/examples/plot_benchmark_braindecode.py b/examples/plot_benchmark_braindecode.py