Functional API — DAGs and Skip Connections

Where production models live

The Functional API treats layer calls as function calls operating on symbolic tensors. You start with keras.Input(...), pipe tensors through layers, and pass the resulting tensors to keras.Model(inputs, outputs). This supports any directed acyclic graph (DAG) — branches, skip connections, multi-input, multi-output.

Almost every model in keras.applications (ResNet, EfficientNet, MobileNet) uses the Functional API. Reading those implementations is good practice — they're the canonical examples.

The two patterns you'll use most: residual blocks (add skip connection back into the main path) and multi-input models (image branch + metadata branch, concatenated before the classifier).

Code

Residual block — Functional 스타일·python

import keras
from keras import layers

inputs = keras.Input(shape=(32, 32, 3))

# First conv block
x = layers.Conv2D(32, 3, activation='relu', padding='same')(inputs)
x = layers.Conv2D(32, 3, activation='relu', padding='same')(x)
block1_out = layers.MaxPooling2D(2)(x)         # (16, 16, 32)

# Second block with skip connection
x = layers.Conv2D(64, 3, activation='relu', padding='same')(block1_out)
x = layers.Conv2D(64, 3, activation='relu', padding='same')(x)
shortcut = layers.Conv2D(64, 1, padding='same')(block1_out)  # 1x1 conv to match channels
block2_out = layers.add([x, shortcut])         # residual connection

x = layers.GlobalAveragePooling2D()(block2_out)
outputs = layers.Dense(10, activation='softmax')(x)

model = keras.Model(inputs, outputs, name="mini_resnet")
print(f"Parameters: {model.count_params():,}")

Multi-input + multi-output·python

import keras
from keras import layers

image_input = keras.Input(shape=(224, 224, 3), name="image")
meta_input  = keras.Input(shape=(16,), name="metadata")

x = layers.Conv2D(32, 3, activation='relu')(image_input)
x = layers.GlobalAveragePooling2D()(x)
x = layers.Dense(64, activation='relu')(x)

m = layers.Dense(32, activation='relu')(meta_input)
combined = layers.concatenate([x, m])

class_out = layers.Dense(10, activation='softmax', name="class_output")(combined)
conf_out  = layers.Dense(1, activation='sigmoid', name="confidence_output")(combined)

model = keras.Model(
    inputs=[image_input, meta_input],
    outputs=[class_out, conf_out],
    name="multi_modal"
)

model.compile(
    optimizer='adam',
    loss={'class_output': 'sparse_categorical_crossentropy',
          'confidence_output': 'binary_crossentropy'},
    metrics={'class_output': ['accuracy'],
             'confidence_output': ['accuracy']},
)

Functional API — DAGs and Skip Connections

Where production models live

Code

External links

Progress

Comments 0