Defined classifier inputs and outputs #7
Conversation
There was a problem hiding this comment.
This is a good start! I've left some suggestions and comments here. Also wondering if @chris-soelistyo has any comments?
| input = K.Input(shape=(2,)) | ||
| encoder = layers.Encoder2D()(input) | ||
| dense = K.layers.Dense(512, activation="relu")(encoder) | ||
| output = K.layers.Dense(4, activation=tf.nn.softmax)(dense) | ||
|
|
||
| classifier_model = K.Model(inputs=input, outputs=output) |
There was a problem hiding this comment.
I think we should make this a function for now (and transition to a full model later), e.g.:
def build_classifier(shape: tuple, outputs: int, dense_filters: int = 512):
"""add docstrings :)"""
input = K.Input(shape=shape)
...
return classifier_model
Co-authored-by: Alan R Lowe <[email protected]>
|
|
||
| input = K.Input(shape=(2,)) | ||
| encoder = layers.Encoder2D()(input) | ||
| dense = K.layers.Dense(512, activation="relu")(encoder) |
There was a problem hiding this comment.
Also, I think you'll need a Flatten here:
flat = K.layers.Flatten()(encoder)
dense = ...(flat)
| from cellx import layers | ||
|
|
||
| input = K.Input(shape=(2,)) | ||
| encoder = layers.Encoder2D()(input) |
There was a problem hiding this comment.
Might perhaps be worth specifying the encoder layer when the build_classifier function is called as well, e.g.
encoder = layers.Encoder2D()
def build_classifier(shape: tuple, outputs: int, dense_filters: int = 512, encoder=encoder):
"""add docstrings :)"""
input = K.Input(shape=shape)
...
return classifier_model
seeing as it can be helpful to experiment with various instances of Encoder2D (with different numbers of layers, units per layer etc) and that would be served I think by being able to call Encoder2D outside of build_classifier and then incorporate it in after.
There was a problem hiding this comment.
Great point @chris-soelistyo ! Why don't we save this for a follow-up PR? Perhaps you can do that once we merge this.
No description provided.