Skip to content Skip to sidebar Skip to footer

Dataset Shape Mismatch Conv1d Input Layer

Trying to set up a Conv1D layer to be the input layer in keras. The dataset is 1000 timesteps, and each timestep has 1 feature. After reading a bunch of answers I reshaped my datas

Solution 1:

Under the line model.add(MaxPooling1D(pool_size=2)), add one line model.add(Flatten()), your problem will be solved. Flatten function will help you convert your data into correct shape, please see this site for more information https://www.tensorflow.org/api_docs/python/tf/keras/layers/Flatten


Post a Comment for "Dataset Shape Mismatch Conv1d Input Layer"