Closed ashoknar closed 6 years ago
I have tried to train the model using varying number of input files. The error is the same, only the array shape shown above changes.
The error occurred because there wasn't enough fields labeled as header in the training data. At least one header field must be specified in each training set.
Please elaborate on this issue and how you solved this. I am using 5 input files to train my model and it has skills as the only header after annotation
ValueError: You are passing a target array of shape (3, 1) while using as loss
categorical_crossentropy
.categorical_crossentropy
expects targets to be binary matrices (1s and 0s) of shape (samples, classes). If your targets are integer classes, you can convert them to the expected format via:Alternatively, you can use the loss function
sparse_categorical_crossentropy
instead, which does expect integer targets.