I'm testing Tensorflow but I can't figure out how the models are structered. For example, in the official documentation there are the following indications :
A Sequential model is appropriate for a plain stack of layers where each layer has exactly one input tensor and one output tensor.
...
A Sequential model is not appropriate when:
- Your model has multiple inputs or multiple outputs
- Any of your layers has multiple inputs or multiple outputs
- You need to do layer sharing
- You want non-linear topology (e.g. a residual connection, a multi-branch model)
Does this mean that the model only accepts 1 value type of data as Input/Output or just only 1 value as Input/Output?
What I want to do, is use two hexadecimals values predict a third hexadecimal value, for this i have the dataset structured in bits e.g:
hex0[0], hex0[1],.... hex0[n], hex1[0], hex1[1], ... hex1[n], result[0], result[1]... result[n]
0 ,1 ,..., 1 , 1 , 9 , ...,1 , 1 , 1 ,... , 0
The keras.Sequential model works for this type of problem?
CodePudding user response:
It means that it accepts only one type of data (all values numeric or all categorical) because in Sequential model all input values go thru all layers sequentialy.
I prefere documentation in keras.io https://keras.io/api/models/sequential/#sequential-class
In your case all input data are the same type so You can use sequential model.
input is: [hex0[0], hex1[0]
output result[0]
The shape of input and output array is very important.