nlpodyssey / cybertron

Cybertron: the home planet of the Transformers in Go
BSD 2-Clause "Simplified" License
280 stars 26 forks source link

How to build a model layers #36

Open ior308 opened 9 months ago

ior308 commented 9 months ago

Dear,

I'm looking for how to write the following model built in Keras using cybertron or spago:

model = tf.keras.models.Sequential()

Input - Layer\n",

model.add(layers.Dense(8, activation=\"relu\", input_shape=(10000, )))

Hidden - Layers

model.add(layers.Dense(4, activation=\"relu\")) model.add(layers.Dense(2, activation=\"relu\"))

Output- Layer\n",

model.add(layers.Dense(1, activation=\"sigmoid\"))

report architettura modello

model.summary()

Could you give me an example ? Obviously it's a simple example, but if it were possible, as with Keras, complex architectures can be built, even CCN and RNN or Seq2Seq.

Regards