This is the Army Research Laboratory (ARL) EEGModels Project: A Collection of Convolutional Neural Network (CNN) models for EEG signal classification, using Keras and Tensorflow
Hello,
I 'm a freshman in AI and recently studying your model. I try to load the pretrained weight into EEGNet but it comes out there's a shape mise match at the first Conv2D layer:
ValueError: Shapes (1, 64, 1, 8) and (8, 1, 1, 32) are incompatible
the code I use is this:
model = EEGNet(nb_classes=3)
model.load_weights('examples/EEGNet-8-2-weights.h5')
Hello, I 'm a freshman in AI and recently studying your model. I try to load the pretrained weight into EEGNet but it comes out there's a shape mise match at the first Conv2D layer: ValueError: Shapes (1, 64, 1, 8) and (8, 1, 1, 32) are incompatible
the code I use is this: model = EEGNet(nb_classes=3) model.load_weights('examples/EEGNet-8-2-weights.h5')
Any advice will be appreciated Regards Asagiri