deploy: NeuroTechX/moabb@fcfae76

NeuroTechX · Feb 1, 2024 · a172f9c · a172f9c
1 parent fa7bf3c
commit a172f9c
Show file tree

Hide file tree

Showing 69 changed files with 1,066 additions and 1,214 deletions.
diff --git a/docs/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip b/docs/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip
diff --git a/docs/_downloads/11d7e3106c779d2d16f2ad6e45bde649/plot_braindecode.ipynb b/docs/_downloads/11d7e3106c779d2d16f2ad6e45bde649/plot_braindecode.ipynb
@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: Igor Carrara <[email protected]>\n#          Bruno Aristimunha <[email protected]>\n#\n# License: BSD (3-clause)\n\nimport matplotlib.pyplot as plt\nimport mne\nimport seaborn as sns\nimport torch\nfrom braindecode import EEGClassifier\nfrom braindecode.models import EEGNetv4\nfrom sklearn.pipeline import Pipeline\nfrom skorch.callbacks import EarlyStopping, EpochScoring\nfrom skorch.dataset import ValidSplit\n\nfrom moabb.datasets import BNCI2014_001\nfrom moabb.evaluations import CrossSessionEvaluation\nfrom moabb.paradigms import MotorImagery\nfrom moabb.pipelines.utils_pytorch import BraindecodeDatasetLoader, InputShapeSetterEEG\nfrom moabb.utils import setup_seed\n\n\nmne.set_log_level(False)\n\n# Print Information PyTorch\nprint(f\"Torch Version: {torch.__version__}\")\n\n# Set up GPU if it is there\ncuda = torch.cuda.is_available()\ndevice = \"cuda\" if cuda else \"cpu\"\nprint(\"GPU is\", \"AVAILABLE\" if cuda else \"NOT AVAILABLE\")"
+        "# Authors: Igor Carrara <[email protected]>\n#          Bruno Aristimunha <[email protected]>\n#\n# License: BSD (3-clause)\n\nimport matplotlib.pyplot as plt\nimport mne\nimport seaborn as sns\nimport torch\nfrom braindecode import EEGClassifier\nfrom braindecode.models import EEGNetv4\nfrom sklearn.pipeline import make_pipeline\nfrom skorch.callbacks import EarlyStopping, EpochScoring\nfrom skorch.dataset import ValidSplit\n\nfrom moabb.datasets import BNCI2014_001\nfrom moabb.evaluations import CrossSessionEvaluation\nfrom moabb.paradigms import MotorImagery\nfrom moabb.utils import setup_seed\n\n\nmne.set_log_level(False)\n\n# Print Information PyTorch\nprint(f\"Torch Version: {torch.__version__}\")\n\n# Set up GPU if it is there\ncuda = torch.cuda.is_available()\ndevice = \"cuda\" if cuda else \"cpu\"\nprint(\"GPU is\", \"AVAILABLE\" if cuda else \"NOT AVAILABLE\")"
       ]
     },
     {
@@ -44,7 +44,7 @@
       },
       "outputs": [],
       "source": [
-        "# Set random seed to be able to reproduce results\nseed = 42\nsetup_seed(seed)\n\n# Ensure that all operations are deterministic on GPU (if used) for reproducibility\ntorch.backends.cudnn.deterministic = True\ntorch.backends.cudnn.benchmark = False\n\n# Hyperparameter\nLEARNING_RATE = 0.0625 * 0.01  # parameter taken from Braindecode\nWEIGHT_DECAY = 0  # parameter taken from Braindecode\nBATCH_SIZE = 64  # parameter taken from BrainDecode\nEPOCH = 10\nPATIENCE = 3\nfmin = 4\nfmax = 100\ntmin = 0\ntmax = None\n\n# Load the dataset\ndataset = BNCI2014_001()\nevents = [\"right_hand\", \"left_hand\"]\nparadigm = MotorImagery(\n    events=events, n_classes=len(events), fmin=fmin, fmax=fmax, tmin=tmin, tmax=tmax\n)\nsubjects = [1]\nX, _, _ = paradigm.get_data(dataset=dataset, subjects=subjects)\n# Define Transformer of Dataset compatible with Brain Decode\ncreate_dataset = BraindecodeDatasetLoader()"
+        "# Set random seed to be able to reproduce results\nseed = 42\nsetup_seed(seed)\n\n# Ensure that all operations are deterministic on GPU (if used) for reproducibility\ntorch.backends.cudnn.deterministic = True\ntorch.backends.cudnn.benchmark = False\n\n# Hyperparameter\nLEARNING_RATE = 0.0625 * 0.01  # parameter taken from Braindecode\nWEIGHT_DECAY = 0  # parameter taken from Braindecode\nBATCH_SIZE = 64  # parameter taken from BrainDecode\nEPOCH = 10\nPATIENCE = 3\nfmin = 4\nfmax = 100\ntmin = 0\ntmax = None\n\n# Load the dataset\ndataset = BNCI2014_001()\nevents = [\"right_hand\", \"left_hand\"]\nparadigm = MotorImagery(\n    events=events, n_classes=len(events), fmin=fmin, fmax=fmax, tmin=tmin, tmax=tmax\n)\nsubjects = [1]\nX, _, _ = paradigm.get_data(dataset=dataset, subjects=subjects)"
       ]
     },
     {
@@ -62,7 +62,7 @@
       },
       "outputs": [],
       "source": [
-        "model = EEGNetv4(in_chans=1, n_classes=1, input_window_samples=100)\n\n# Send model to GPU\nif cuda:\n    model.cuda()\n\n# Define a Skorch classifier\nclf = EEGClassifier(\n    module=model,\n    criterion=torch.nn.CrossEntropyLoss,\n    optimizer=torch.optim.Adam,\n    optimizer__lr=LEARNING_RATE,\n    batch_size=BATCH_SIZE,\n    max_epochs=EPOCH,\n    train_split=ValidSplit(0.2, random_state=seed),\n    device=device,\n    callbacks=[\n        EarlyStopping(monitor=\"valid_loss\", patience=PATIENCE),\n        EpochScoring(\n            scoring=\"accuracy\", on_train=True, name=\"train_acc\", lower_is_better=False\n        ),\n        EpochScoring(\n            scoring=\"accuracy\", on_train=False, name=\"valid_acc\", lower_is_better=False\n        ),\n        InputShapeSetterEEG(\n            params_list=[\"in_chans\", \"input_window_samples\", \"n_classes\"],\n        ),\n    ],\n    verbose=1,  # Not printing the results for each epoch\n)\n\n# Create the pipelines\npipes = {}\npipes[\"EEGNetV4\"] = Pipeline([(\"Braindecode_dataset\", create_dataset), (\"Net\", clf)])"
+        "# Define a Skorch classifier\nclf = EEGClassifier(\n    module=EEGNetv4,\n    optimizer=torch.optim.Adam,\n    optimizer__lr=LEARNING_RATE,\n    batch_size=BATCH_SIZE,\n    max_epochs=EPOCH,\n    train_split=ValidSplit(0.2, random_state=seed),\n    device=device,\n    callbacks=[\n        EarlyStopping(monitor=\"valid_loss\", patience=PATIENCE),\n        EpochScoring(\n            scoring=\"accuracy\", on_train=True, name=\"train_acc\", lower_is_better=False\n        ),\n        EpochScoring(\n            scoring=\"accuracy\", on_train=False, name=\"valid_acc\", lower_is_better=False\n        ),\n    ],\n    verbose=1,  # Not printing the results for each epoch\n)\n\n# Create the pipelines\npipes = {}\npipes[\"EEGNetV4\"] = make_pipeline(clf)"
       ]
     },
     {

diff --git a/docs/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip b/docs/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip
diff --git a/docs/_downloads/744775bda3ec8d62d828dcc3cff768f5/load_model.ipynb b/docs/_downloads/744775bda3ec8d62d828dcc3cff768f5/load_model.ipynb
@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: Igor Carrara <[email protected]>\n#\n# License: BSD (3-clause)\n\nfrom pickle import load\n\nimport keras\nimport torch\nfrom braindecode import EEGClassifier\nfrom braindecode.models import EEGInception\nfrom scikeras.wrappers import KerasClassifier\nfrom sklearn.pipeline import Pipeline\nfrom skorch.callbacks import EarlyStopping, EpochScoring\nfrom skorch.dataset import ValidSplit\n\nfrom moabb import set_log_level\nfrom moabb.pipelines.features import StandardScaler_Epoch\nfrom moabb.pipelines.utils_pytorch import BraindecodeDatasetLoader, InputShapeSetterEEG\nfrom moabb.utils import setup_seed\n\n\nset_log_level(\"info\")"
+        "# Authors: Igor Carrara <[email protected]>\n#\n# License: BSD (3-clause)\n\nfrom pickle import load\n\nimport keras\nimport torch\nfrom braindecode import EEGClassifier\nfrom braindecode.models import EEGInception\nfrom scikeras.wrappers import KerasClassifier\nfrom sklearn.pipeline import Pipeline, make_pipeline\nfrom skorch.callbacks import EarlyStopping, EpochScoring\nfrom skorch.dataset import ValidSplit\n\nfrom moabb import set_log_level\nfrom moabb.pipelines.features import StandardScaler_Epoch\nfrom moabb.utils import setup_seed\n\n\nset_log_level(\"info\")"
       ]
     },
     {
@@ -98,7 +98,7 @@
       },
       "outputs": [],
       "source": [
-        "# Set EEG Inception model\nmodel = EEGInception(in_channels=22, n_classes=2)\n\n# Hyperparameter\nLEARNING_RATE = 0.0001\nWEIGHT_DECAY = 0\nBATCH_SIZE = 64\nSEED = 42\nVERBOSE = 1\nEPOCH = 2\nPATIENCE = 3\n\n# Define a Skorch classifier\nclf = EEGClassifier(\n    module=model,\n    criterion=torch.nn.CrossEntropyLoss,\n    optimizer=torch.optim.Adam,\n    optimizer__lr=LEARNING_RATE,\n    batch_size=BATCH_SIZE,\n    max_epochs=EPOCH,\n    train_split=ValidSplit(0.2, random_state=SEED),\n    callbacks=[\n        EarlyStopping(monitor=\"valid_loss\", patience=PATIENCE),\n        EpochScoring(\n            scoring=\"accuracy\", on_train=True, name=\"train_acc\", lower_is_better=False\n        ),\n        EpochScoring(\n            scoring=\"accuracy\", on_train=False, name=\"valid_acc\", lower_is_better=False\n        ),\n        InputShapeSetterEEG(\n            params_list=[\"in_channels\", \"input_window_samples\", \"n_classes\"],\n        ),\n    ],\n    verbose=VERBOSE,  # Not printing the results for each epoch\n)\n\nclf.initialize()\n\nf_params = \"./results/Models_CrossSession/BNCI2014-001/1/braindecode_EEGInception/EEGInception_fitted_best_model.pkl\"\nf_optimizer = \"./results/Models_CrossSession/BNCI2014-001/1/braindecode_EEGInception/EEGInception_fitted_best_optim.pkl\"\nf_history = \"./results/Models_CrossSession/BNCI2014-001/1/braindecode_EEGInception/EEGInception_fitted_best_history.json\"\n\nclf.load_params(f_params=f_params, f_optimizer=f_optimizer, f_history=f_history)\n\n# Create the dataset\ncreate_dataset = BraindecodeDatasetLoader(drop_last_window=False)\n\n# Create the pipelines\npipes_pytorch = Pipeline([(\"Braindecode_dataset\", create_dataset), (\"EEGInception\", clf)])"
+        "# Hyperparameter\nLEARNING_RATE = 0.0001\nWEIGHT_DECAY = 0\nBATCH_SIZE = 64\nSEED = 42\nVERBOSE = 1\nEPOCH = 2\nPATIENCE = 3\n\n# Define a Skorch classifier\nclf = EEGClassifier(\n    module=EEGInception,\n    optimizer=torch.optim.Adam,\n    optimizer__lr=LEARNING_RATE,\n    batch_size=BATCH_SIZE,\n    max_epochs=EPOCH,\n    train_split=ValidSplit(0.2, random_state=SEED),\n    callbacks=[\n        EarlyStopping(monitor=\"valid_loss\", patience=PATIENCE),\n        EpochScoring(\n            scoring=\"accuracy\", on_train=True, name=\"train_acc\", lower_is_better=False\n        ),\n        EpochScoring(\n            scoring=\"accuracy\", on_train=False, name=\"valid_acc\", lower_is_better=False\n        ),\n    ],\n    verbose=VERBOSE,  # Not printing the results for each epoch\n)\n\nclf.initialize()\n\nf_params = \"./results/Models_CrossSession/BNCI2014-001/1/braindecode_EEGInception/EEGInception_fitted_best_model.pkl\"\nf_optimizer = \"./results/Models_CrossSession/BNCI2014-001/1/braindecode_EEGInception/EEGInception_fitted_best_optim.pkl\"\nf_history = \"./results/Models_CrossSession/BNCI2014-001/1/braindecode_EEGInception/EEGInception_fitted_best_history.json\"\n\nclf.load_params(f_params=f_params, f_optimizer=f_optimizer, f_history=f_history)\n\n# Create the pipelines\npipes_pytorch = make_pipeline(clf)"
       ]
     }
   ],

diff --git a/docs/_downloads/8fed52c2a57f02454c33ebb464a390de/load_model.py b/docs/_downloads/8fed52c2a57f02454c33ebb464a390de/load_model.py
@@ -16,13 +16,12 @@
 from braindecode import EEGClassifier
 from braindecode.models import EEGInception
 from scikeras.wrappers import KerasClassifier
-from sklearn.pipeline import Pipeline
+from sklearn.pipeline import Pipeline, make_pipeline
 from skorch.callbacks import EarlyStopping, EpochScoring
 from skorch.dataset import ValidSplit
 
 from moabb import set_log_level
 from moabb.pipelines.features import StandardScaler_Epoch
-from moabb.pipelines.utils_pytorch import BraindecodeDatasetLoader, InputShapeSetterEEG
 from moabb.utils import setup_seed
 
 
@@ -70,9 +69,6 @@
 ###############################################################################
 # Loading the PyTorch model
 
-# Set EEG Inception model
-model = EEGInception(in_channels=22, n_classes=2)
-
 # Hyperparameter
 LEARNING_RATE = 0.0001
 WEIGHT_DECAY = 0
@@ -84,8 +80,7 @@
 
 # Define a Skorch classifier
 clf = EEGClassifier(
-    module=model,
-    criterion=torch.nn.CrossEntropyLoss,
+    module=EEGInception,
     optimizer=torch.optim.Adam,
     optimizer__lr=LEARNING_RATE,
     batch_size=BATCH_SIZE,
@@ -99,9 +94,6 @@
         EpochScoring(
             scoring="accuracy", on_train=False, name="valid_acc", lower_is_better=False
         ),
-        InputShapeSetterEEG(
-            params_list=["in_channels", "input_window_samples", "n_classes"],
-        ),
     ],
     verbose=VERBOSE,  # Not printing the results for each epoch
 )
@@ -114,8 +106,5 @@
 
 clf.load_params(f_params=f_params, f_optimizer=f_optimizer, f_history=f_history)
 
-# Create the dataset
-create_dataset = BraindecodeDatasetLoader(drop_last_window=False)
-
 # Create the pipelines
-pipes_pytorch = Pipeline([("Braindecode_dataset", create_dataset), ("EEGInception", clf)])
+pipes_pytorch = make_pipeline(clf)
diff --git a/docs/_downloads/97a1de59bce682890841bb846e3dd09c/auto_tutorials_jupyter.zip b/docs/_downloads/97a1de59bce682890841bb846e3dd09c/auto_tutorials_jupyter.zip
diff --git a/docs/_downloads/c9b0437022c98a63476dd3cad6cb69c7/plot_braindecode.py b/docs/_downloads/c9b0437022c98a63476dd3cad6cb69c7/plot_braindecode.py
@@ -16,14 +16,13 @@
 import torch
 from braindecode import EEGClassifier
 from braindecode.models import EEGNetv4
-from sklearn.pipeline import Pipeline
+from sklearn.pipeline import make_pipeline
 from skorch.callbacks import EarlyStopping, EpochScoring
 from skorch.dataset import ValidSplit
 
 from moabb.datasets import BNCI2014_001
 from moabb.evaluations import CrossSessionEvaluation
 from moabb.paradigms import MotorImagery
-from moabb.pipelines.utils_pytorch import BraindecodeDatasetLoader, InputShapeSetterEEG
 from moabb.utils import setup_seed
 
 
@@ -81,8 +80,6 @@
 )
 subjects = [1]
 X, _, _ = paradigm.get_data(dataset=dataset, subjects=subjects)
-# Define Transformer of Dataset compatible with Brain Decode
-create_dataset = BraindecodeDatasetLoader()
 
 ##############################################################################
 # Create Pipelines
@@ -94,16 +91,9 @@
 # callbacks InputShapeSetterEEG, where we have to specify the correct name of the parameter.
 # Here, we will use the EEGNet v4 model [1]_ .
 
-model = EEGNetv4(in_chans=1, n_classes=1, input_window_samples=100)
-
-# Send model to GPU
-if cuda:
-    model.cuda()
-
 # Define a Skorch classifier
 clf = EEGClassifier(
-    module=model,
-    criterion=torch.nn.CrossEntropyLoss,
+    module=EEGNetv4,
     optimizer=torch.optim.Adam,
     optimizer__lr=LEARNING_RATE,
     batch_size=BATCH_SIZE,
@@ -118,16 +108,13 @@
         EpochScoring(
             scoring="accuracy", on_train=False, name="valid_acc", lower_is_better=False
         ),
-        InputShapeSetterEEG(
-            params_list=["in_chans", "input_window_samples", "n_classes"],
-        ),
     ],
     verbose=1,  # Not printing the results for each epoch
 )
 
 # Create the pipelines
 pipes = {}
-pipes["EEGNetV4"] = Pipeline([("Braindecode_dataset", create_dataset), ("Net", clf)])
+pipes["EEGNetV4"] = make_pipeline(clf)
 
 ##############################################################################
 # Evaluation

diff --git a/docs/_downloads/cab7a090c4183ca69dc0cd84d3b04413/auto_tutorials_python.zip b/docs/_downloads/cab7a090c4183ca69dc0cd84d3b04413/auto_tutorials_python.zip
diff --git a/docs/_images/sphx_glr_plot_benchmark_001.png b/docs/_images/sphx_glr_plot_benchmark_001.png
diff --git a/docs/_images/sphx_glr_plot_benchmark_DL_001.png b/docs/_images/sphx_glr_plot_benchmark_DL_001.png
diff --git a/docs/_images/sphx_glr_plot_benchmark_DL_thumb.png b/docs/_images/sphx_glr_plot_benchmark_DL_thumb.png
diff --git a/docs/_images/sphx_glr_plot_benchmark_braindecode_001.png b/docs/_images/sphx_glr_plot_benchmark_braindecode_001.png
diff --git a/docs/_images/sphx_glr_plot_benchmark_braindecode_thumb.png b/docs/_images/sphx_glr_plot_benchmark_braindecode_thumb.png
diff --git a/docs/_images/sphx_glr_plot_benchmark_thumb.png b/docs/_images/sphx_glr_plot_benchmark_thumb.png
diff --git a/docs/_images/sphx_glr_plot_braindecode_001.png b/docs/_images/sphx_glr_plot_braindecode_001.png
diff --git a/docs/_images/sphx_glr_plot_braindecode_thumb.png b/docs/_images/sphx_glr_plot_braindecode_thumb.png
diff --git a/docs/_images/sphx_glr_plot_filterbank_csp_vs_csp_001.png b/docs/_images/sphx_glr_plot_filterbank_csp_vs_csp_001.png
diff --git a/docs/_images/sphx_glr_plot_filterbank_csp_vs_csp_thumb.png b/docs/_images/sphx_glr_plot_filterbank_csp_vs_csp_thumb.png
diff --git a/docs/_images/sphx_glr_plot_learning_curve_motor_imagery_001.png b/docs/_images/sphx_glr_plot_learning_curve_motor_imagery_001.png
diff --git a/docs/_images/sphx_glr_plot_learning_curve_motor_imagery_thumb.png b/docs/_images/sphx_glr_plot_learning_curve_motor_imagery_thumb.png
diff --git a/docs/_images/sphx_glr_plot_learning_curve_p300_001.png b/docs/_images/sphx_glr_plot_learning_curve_p300_001.png
diff --git a/docs/_images/sphx_glr_plot_learning_curve_p300_external_001.png b/docs/_images/sphx_glr_plot_learning_curve_p300_external_001.png
diff --git a/docs/_images/sphx_glr_plot_learning_curve_p300_external_thumb.png b/docs/_images/sphx_glr_plot_learning_curve_p300_external_thumb.png
diff --git a/docs/_images/sphx_glr_plot_learning_curve_p300_thumb.png b/docs/_images/sphx_glr_plot_learning_curve_p300_thumb.png
diff --git a/docs/_images/sphx_glr_plot_within_session_ssvep_002.png b/docs/_images/sphx_glr_plot_within_session_ssvep_002.png
diff --git a/docs/_images/sphx_glr_tutorial_3_benchmarking_multiple_pipelines_001.png b/docs/_images/sphx_glr_tutorial_3_benchmarking_multiple_pipelines_001.png
diff --git a/docs/_images/sphx_glr_tutorial_3_benchmarking_multiple_pipelines_thumb.png b/docs/_images/sphx_glr_tutorial_3_benchmarking_multiple_pipelines_thumb.png
diff --git a/docs/auto_examples/advanced_examples/plot_filterbank_csp_vs_csp.html b/docs/auto_examples/advanced_examples/plot_filterbank_csp_vs_csp.html
@@ -781,7 +781,7 @@ <h2>Evaluation<a class="headerlink" href="#evaluation" title="Permalink to this
  &#39;right_hand&#39;: 12&gt;
   warn(f&quot;warnEpochs {epochs}&quot;)
 
-BNCI2014-001-CrossSession:  50%|#####     | 1/2 [00:05&lt;00:05,  5.58s/it]/home/runner/work/moabb/moabb/moabb/datasets/preprocessing.py:273: UserWarning: warnEpochs &lt;Epochs |  24 events (all good), 2 – 6 s, baseline off, ~4.1 MB, data loaded,
+BNCI2014-001-CrossSession:  50%|#####     | 1/2 [00:05&lt;00:05,  5.56s/it]/home/runner/work/moabb/moabb/moabb/datasets/preprocessing.py:273: UserWarning: warnEpochs &lt;Epochs |  24 events (all good), 2 – 6 s, baseline off, ~4.1 MB, data loaded,
  &#39;left_hand&#39;: 12
  &#39;right_hand&#39;: 12&gt;
   warn(f&quot;warnEpochs {epochs}&quot;)
@@ -878,8 +878,8 @@ <h2>Evaluation<a class="headerlink" href="#evaluation" title="Permalink to this
  &#39;right_hand&#39;: 12&gt;
   warn(f&quot;warnEpochs {epochs}&quot;)
 
-BNCI2014-001-CrossSession: 100%|##########| 2/2 [00:10&lt;00:00,  5.39s/it]
-BNCI2014-001-CrossSession: 100%|##########| 2/2 [00:10&lt;00:00,  5.42s/it]
+BNCI2014-001-CrossSession: 100%|##########| 2/2 [00:11&lt;00:00,  5.51s/it]
+BNCI2014-001-CrossSession: 100%|##########| 2/2 [00:11&lt;00:00,  5.52s/it]
 </pre></div>
 </div>
 <p>After processing the two, we simply concatenate the results.</p>
@@ -924,7 +924,7 @@ <h2>Plot Results<a class="headerlink" href="#plot-results" title="Permalink to t
 <a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.show.html#matplotlib.pyplot.show" title="matplotlib.pyplot.show" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">show</span></a><span class="p">()</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_plot_filterbank_csp_vs_csp_001.png" srcset="../../_images/sphx_glr_plot_filterbank_csp_vs_csp_001.png" alt="plot filterbank csp vs csp" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  13.040 seconds)</p>
+<img src="../../_images/sphx_glr_plot_filterbank_csp_vs_csp_001.png" srcset="../../_images/sphx_glr_plot_filterbank_csp_vs_csp_001.png" alt="plot filterbank csp vs csp" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  13.249 seconds)</p>
 <p><strong>Estimated memory usage:</strong>  282 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-advanced-examples-plot-filterbank-csp-vs-csp-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">

diff --git a/docs/auto_examples/advanced_examples/plot_grid_search_withinsession.html b/docs/auto_examples/advanced_examples/plot_grid_search_withinsession.html
@@ -762,8 +762,8 @@ <h2>Running the Evaluation<a class="headerlink" href="#running-the-evaluation" t
  &#39;left_hand&#39;: 12&gt;
   warn(f&quot;warnEpochs {epochs}&quot;)
 
-BNCI2014-001-WithinSession: 100%|##########| 1/1 [00:10&lt;00:00, 10.78s/it]
-BNCI2014-001-WithinSession: 100%|##########| 1/1 [00:10&lt;00:00, 10.78s/it]
+BNCI2014-001-WithinSession: 100%|##########| 1/1 [00:10&lt;00:00, 10.41s/it]
+BNCI2014-001-WithinSession: 100%|##########| 1/1 [00:10&lt;00:00, 10.41s/it]
 </pre></div>
 </div>
 </section>
@@ -837,8 +837,8 @@ <h2>Load Best Model Parameter<a class="headerlink" href="#load-best-model-parame
 Best Parameter l1_ratio Session_T VanillaEN:  0.75
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  13.269 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  181 MB</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  12.873 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  143 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-advanced-examples-plot-grid-search-withinsession-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/b298e4b36adf2bb5cb6f65682eec852f/plot_grid_search_withinsession.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">plot_grid_search_withinsession.py</span></code></a></p>