I need to set a breakpoint to a old model in keras:
import tensorflow as tf
inputs = tf.keras.Input(shape=(3,))
x = tf.keras.layers.Dense(4, activation=tf.nn.relu)(inputs)
x1 = tf.keras.layers.Dense(5, activation=tf.nn.softmax)(x)
outputs = tf.keras.layers.Dense(5, activation=tf.nn.softmax)(x1)
model = tf.keras.Model(inputs=inputs, outputs=outputs)
model.compile()
The actual model is a lot complicated and I am just providing a snippet. Is there a way for me to set a breakpoint in the forward pass? Just trying to see the intermediate model output.
Thanks
CodePudding user response:
It might depend a bit on your actual setting but you could split your model via its layers - similar like you set up an autoencoder. And forward pass through the backbone, look at it -> pass through the head -> output.
import tensorflow as tf
inputs = tf.keras.Input(shape=(3,))
x = tf.keras.layers.Dense(4, activation=tf.nn.relu)(inputs)
x1 = tf.keras.layers.Dense(5, activation=tf.nn.softmax)(x)
outputs = tf.keras.layers.Dense(5, activation=tf.nn.softmax)(x1)
model = tf.keras.Model(inputs=inputs, outputs=outputs)
model.compile()
back = tf.keras.Sequential(model.layers[:2])
head = tf.keras.Sequential(model.layers[2:])
# Instead of doing model(input) you can now do
inter = back(input)
print(inter)
result = head(inter)
Alternatively you could also define multiple outputs, which are a bit uglier to train but for testing purposes you can pull the trained weights to this cloned model
inputs = tf.keras.Input(shape=(3,))
x = tf.keras.layers.Dense(4, activation=tf.nn.relu)(inputs)
x1 = tf.keras.layers.Dense(5, activation=tf.nn.softmax)(x)
outputs = tf.keras.layers.Dense(5, activation=tf.nn.softmax)(x1)
model = tf.keras.Model(inputs=inputs, outputs=[outputs, x1]) #<-- adding your intermediate layer as a second output
model.compile()