braindecode 0.1.6__tar.gz → 0.1.6.2__tar.gz

{Braindecode-0.1.6 → Braindecode-0.1.6.2}/Braindecode.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 1.1
 Name: Braindecode
-Version: 0.1.6
+Version: 0.1.6.2
 Summary: A deep learning toolbox to decode raw time-domain EEG.
 Home-page: https://github.com/robintibor/braindecode
 Author: Robin Tibor Schirrmeister
@@ -12,10 +12,12 @@ Description: Note: The old braindecode repository has been moved to
         Braindecode
         ===========
         
-        **Under construction**
-        
         A deep learning toolbox to decode raw time-domain EEG.
         
+        For EEG researchers that want to want to work with deep learning and
+        deep learning researchers that want to work with EEG data.
+        For now focussed on convolutional networks.
+        
         
         Installation
         ============

{Braindecode-0.1.6 → Braindecode-0.1.6.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 1.1
 Name: Braindecode
-Version: 0.1.6
+Version: 0.1.6.2
 Summary: A deep learning toolbox to decode raw time-domain EEG.
 Home-page: https://github.com/robintibor/braindecode
 Author: Robin Tibor Schirrmeister
@@ -12,10 +12,12 @@ Description: Note: The old braindecode repository has been moved to
         Braindecode
         ===========
         
-        **Under construction**
-        
         A deep learning toolbox to decode raw time-domain EEG.
         
+        For EEG researchers that want to want to work with deep learning and
+        deep learning researchers that want to work with EEG data.
+        For now focussed on convolutional networks.
+        
         
         Installation
         ============

{Braindecode-0.1.6 → Braindecode-0.1.6.2}/README.rst

@@ -4,10 +4,12 @@ https://github.com/robintibor/braindevel.
 Braindecode
 ===========
 
-**Under construction**
-
 A deep learning toolbox to decode raw time-domain EEG.
 
+For EEG researchers that want to want to work with deep learning and
+deep learning researchers that want to work with EEG data.
+For now focussed on convolutional networks.
+
 
 Installation
 ============

{Braindecode-0.1.6 → Braindecode-0.1.6.2}/braindecode/datasets/bbci.py

@@ -157,7 +157,7 @@ class BBCIDataset(object):
                 zip(event_times_in_samples, event_classes)):
             if i_sample == previous_i_sample:
                 log.warning("Same sample has at least two markers.\n"
-                            "{:d}: ({:d} and {:d}).\n".format(i_sample,
+                            "{:d}: ({:.0f} and {:.0f}).\n".format(i_sample,
                                                               event_classes[
                                                                   i_event - 1],
                                                               event_classes[

{Braindecode-0.1.6 → Braindecode-0.1.6.2}/braindecode/models/deep4.py

@@ -16,8 +16,8 @@ class Deep4Net(object):
 
     .. [1] Schirrmeister, R. T., Springenberg, J. T., Fiederer, L. D. J., 
        Glasstetter, M., Eggensperger, K., Tangermann, M., ... & Ball, T. (2017).
-       Deep learning with convolutional neural networks for brain mapping and
-       decoding of movement-related information from the human EEG.
+       Deep learning with convolutional neural networks for EEG decoding and
+       visualization.
        arXiv preprint arXiv:1703.05051.
     """
     def __init__(self, in_chans,

{Braindecode-0.1.6 → Braindecode-0.1.6.2}/braindecode/models/shallow_fbcsp.py

@@ -16,8 +16,8 @@ class ShallowFBCSPNet(object):
 
     .. [2] Schirrmeister, R. T., Springenberg, J. T., Fiederer, L. D. J., 
        Glasstetter, M., Eggensperger, K., Tangermann, M., ... & Ball, T. (2017).
-       Deep learning with convolutional neural networks for brain mapping and
-       decoding of movement-related information from the human EEG.
+       Deep learning with convolutional neural networks for EEG decoding and
+       visualization.
        arXiv preprint arXiv:1703.05051.
     """
     def __init__(self, in_chans,

{Braindecode-0.1.6 → Braindecode-0.1.6.2}/braindecode/torch_ext/constraints.py

@@ -11,8 +11,8 @@ class MaxNormDefaultConstraint(object):
 
     .. [1] Schirrmeister, R. T., Springenberg, J. T., Fiederer, L. D. J., 
        Glasstetter, M., Eggensperger, K., Tangermann, M., ... & Ball, T. (2017).
-       Deep learning with convolutional neural networks for brain mapping and
-       decoding of movement-related information from the human EEG.
+       Deep learning with convolutional neural networks for EEG decoding and
+       visualization.
        arXiv preprint arXiv:1703.05051.
     
     """

{Braindecode-0.1.6 → Braindecode-0.1.6.2}/docs/index.rst

@@ -1,10 +1,12 @@
 Welcome to Braindecode
 ======================
 
-**Under construction**
-
 A deep learning toolbox to decode raw time-domain EEG.
 
+For EEG researchers that want to want to work with deep learning and
+deep learning researchers that want to work with EEG data.
+For now focussed on convolutional networks.
+
 
 Installation
 ============
@@ -45,6 +47,11 @@ Tutorials
    notebooks/visualization/Perturbation.ipynb
 
 
+Troubleshooting
+===============
+Please report any issues on github: https://github.com/robintibor/braindecode
+
+
 API
 ===
 

{Braindecode-0.1.6 → Braindecode-0.1.6.2}/docs/notebooks/Cropped_Decoding.ipynb

@@ -149,7 +149,7 @@
    },
    "source": [
     "For cropped decoding, we now transform the model into a model that outputs a dense time series of predictions.\n",
-    "For this, we manually set the length of the final convolution layer to some length that makes the receptive field of the ConvNet smaller than the number of samples in a trial. Also, we use `to_dense_prediction_model`, which removes the strides in the ConvNet and instead uses dilated convolutions to get a dense output (see [Multi-Scale Context Aggregation by Dilated Convolutions](https://arxiv.org/abs/1511.07122) and our paper [Deep learning with convolutional neural networks for brain mapping and decoding of movement-related information from the human EEG](https://arxiv.org/abs/1703.05051) Section 2.5.4 for some background on this)."
+    "For this, we manually set the length of the final convolution layer to some length that makes the receptive field of the ConvNet smaller than the number of samples in a trial. Also, we use `to_dense_prediction_model`, which removes the strides in the ConvNet and instead uses dilated convolutions to get a dense output (see [Multi-Scale Context Aggregation by Dilated Convolutions](https://arxiv.org/abs/1511.07122) and our paper [Deep learning with convolutional neural networks for EEG decoding and visualization](https://arxiv.org/abs/1703.05051) Section 2.5.4 for some background on this)."
    ]
   },
   {

{Braindecode-0.1.6 → Braindecode-0.1.6.2}/docs/notebooks/TrialWise_Decoding.ipynb

@@ -199,7 +199,7 @@
     "editable": true
    },
    "source": [
-    "Braindecode comes with some predefined convolutional neural network architectures for raw time-domain EEG. Here, we use the shallow ConvNet model from [Deep learning with convolutional neural networks for brain mapping and decoding of movement-related information from the human EEG](https://arxiv.org/abs/1703.05051)."
+    "Braindecode comes with some predefined convolutional neural network architectures for raw time-domain EEG. Here, we use the shallow ConvNet model from [Deep learning with convolutional neural networks for EEG decoding and visualization](https://arxiv.org/abs/1703.05051)."
    ]
   },
   {