[Keras] 모델 플롯 유틸리티

plot_model 함수

 

keras.utils.plot_model(
    model,
    to_file="model.png",
    show_shapes=False,
    show_dtype=False,
    show_layer_names=False,
    rankdir="TB",
    expand_nested=False,
    dpi=200,
    show_layer_activations=False,
    show_trainable=False,
    **kwargs
)

 

model_to_dot 함수

 

keras.utils.model_to_dot(
    model,
    show_shapes=False,
    show_dtype=False,
    show_layer_names=True,
    rankdir="TB",
    expand_nested=False,
    dpi=200,
    subgraph=False,
    show_layer_activations=False,
    show_trainable=False,
    **kwargs
)

 

예시

 

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

# 모델 생성
model = Sequential()
model.add(Dense(64, activation='relu', input_shape=(10,)))
model.add(Dense(64, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

# 모델 시각화
keras.utils.plot_model(model, to_file='model.png', show_shapes=True, show_layer_names=True)

 

 

 

https://keras.io/api/utils/model_plotting_utils/

Keras documentation: Model plotting utilities