Tensorflow에서 재현 가능한 결과(reproducible results) 얻기

webnautes 2024. 3. 28. 21:15

2024. 3. 28. 21:15

텐서플로우에서 다음과 같은 간단한 MNIST 예제를 실행시켜보면 매번 학습 결과가 다른 것을 확인할 수 있습니다.

실행할때마다 일정한 학습 결과를 얻는 방법을 다룹니다.

2021. 7. 29 - 최초작성

2024. 3. 21 - RANDOM_SEED 변경, Tensorflow 2.15에서 테스트

2024. 3. 28 재현가능한 결과 보장 방법 수정

# https://www.tensorflow.org/tutorials/quickstart/beginner
import tensorflow as tf

mnist = tf.keras.datasets.mnist

(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])

model.fit(x_train, y_train, epochs=5)

model.evaluate(x_test, y_test, verbose=2)

세번 연달아 실행시킨 결과인데 빨간색으로 표시한 train 데이터셋에 대한 수치와 파란색으로 표시한 test 데이터셋에 대한 수치가 일정하지 않습니다.

Epoch 1/5

2024-03-21 21:31:17.726368: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:117] Plugin optimizer for device_type GPU is enabled.

1875/1875 [==============================] - 10s 4ms/step - loss: 0.4016 - accuracy: 0.8839

Epoch 2/5

1875/1875 [==============================] - 7s 4ms/step - loss: 0.3636 - accuracy: 0.9006

Epoch 3/5

1875/1875 [==============================] - 7s 4ms/step - loss: 0.3803 - accuracy: 0.8968

Epoch 4/5

1875/1875 [==============================] - 7s 4ms/step - loss: 0.3978 - accuracy: 0.8955

Epoch 5/5

1875/1875 [==============================] - 7s 4ms/step - loss: 0.4053 - accuracy: 0.8933

313/313 - 1s - loss: 0.3092 - accuracy: 0.9190 - 958ms/epoch - 3ms/step

Epoch 1/5

2024-03-21 21:32:23.872847: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:117] Plugin optimizer for device_type GPU is enabled.

1875/1875 [==============================] - 8s 4ms/step - loss: 0.4064 - accuracy: 0.8833

Epoch 2/5

1875/1875 [==============================] - 7s 4ms/step - loss: 0.3709 - accuracy: 0.8987

Epoch 3/5

1875/1875 [==============================] - 7s 4ms/step - loss: 0.3858 - accuracy: 0.8957

Epoch 4/5

1875/1875 [==============================] - 7s 4ms/step - loss: 0.4018 - accuracy: 0.8930

Epoch 5/5

1875/1875 [==============================] - 7s 4ms/step - loss: 0.4110 - accuracy: 0.8922

313/313 - 1s - loss: 0.3157 - accuracy: 0.9170 - 926ms/epoch - 3ms/step

Epoch 1/5

2024-03-21 21:33:21.468247: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:117] Plugin optimizer for device_type GPU is enabled.

1875/1875 [==============================] - 7s 4ms/step - loss: 0.4073 - accuracy: 0.8830

Epoch 2/5

1875/1875 [==============================] - 7s 4ms/step - loss: 0.3660 - accuracy: 0.9006

Epoch 3/5

1875/1875 [==============================] - 7s 4ms/step - loss: 0.3765 - accuracy: 0.8978

Epoch 4/5

1875/1875 [==============================] - 7s 4ms/step - loss: 0.3911 - accuracy: 0.8967

Epoch 5/5

1875/1875 [==============================] - 7s 4ms/step - loss: 0.4060 - accuracy: 0.8944

313/313 - 1s - loss: 0.3500 - accuracy: 0.9090 - 946ms/epoch - 3ms/step

지난번 글 업데이트시 재현 가능한 결과가 보여지는 것을 확인한 후 문제 없는줄 알았는데 얼마전 다른 PC에서 확인했는데 전혀 재현 가능한 결과를 얻을 수 없었습니다. 정확한 원인은 알 수 없었지만 최근 업데이트된 케라스 문서에서 새로운 방법을 찾아서 해결했습니다.

다음 링크에서 소개하는 방법입니다.

https://keras.io/examples/keras_recipes/reproducibility_recipes/

import tensorflow as tf

# Set the seed using keras.utils.set_random_seed. This will set:
# 1) `numpy` seed
# 2) backend random seed
# 3) `python` random seed
tf.keras.utils.set_random_seed(812)

# If using TensorFlow, this will make GPU ops as deterministic as possible,
# but it will affect the overall performance, so be mindful of that.
tf.config.experimental.enable_op_determinism()

세번 실행하여 똑같은 학습 결과를 얻었습니다. 빨간색으로 표시한 train 데이터셋에 대한 수치와 파란색으로 표시한 test 데이터셋에 대한 수치가 일정합니다.

Epoch 1/5

2024-03-28 20:45:23.575054: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:117] Plugin optimizer for device_type GPU is enabled.

1875/1875 [==============================] - 10s 5ms/step - loss: 0.4142 - accuracy: 0.8810

Epoch 2/5

1875/1875 [==============================] - 9s 5ms/step - loss: 0.3737 - accuracy: 0.8973

Epoch 3/5

1875/1875 [==============================] - 9s 5ms/step - loss: 0.3852 - accuracy: 0.8968

Epoch 4/5

1875/1875 [==============================] - 9s 5ms/step - loss: 0.4024 - accuracy: 0.8930

Epoch 5/5

1875/1875 [==============================] - 9s 5ms/step - loss: 0.4193 - accuracy: 0.8901

313/313 - 1s - loss: 0.3629 - accuracy: 0.9024 - 1s/epoch - 4ms/step

Epoch 1/5

2024-03-28 20:47:19.116479: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:117] Plugin optimizer for device_type GPU is enabled.

1875/1875 [==============================] - 9s 5ms/step - loss: 0.4142 - accuracy: 0.8810

Epoch 2/5

1875/1875 [==============================] - 9s 5ms/step - loss: 0.3737 - accuracy: 0.8973

Epoch 3/5

1875/1875 [==============================] - 9s 5ms/step - loss: 0.3852 - accuracy: 0.8968

Epoch 4/5

1875/1875 [==============================] - 9s 5ms/step - loss: 0.4024 - accuracy: 0.8930

Epoch 5/5

1875/1875 [==============================] - 9s 5ms/step - loss: 0.4193 - accuracy: 0.8901

313/313 - 1s - loss: 0.3629 - accuracy: 0.9024 - 1s/epoch - 4ms/step

Epoch 1/5

2024-03-28 20:49:01.188213: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:117] Plugin optimizer for device_type GPU is enabled.

1875/1875 [==============================] - 9s 5ms/step - loss: 0.4142 - accuracy: 0.8810

Epoch 2/5

1875/1875 [==============================] - 9s 5ms/step - loss: 0.3737 - accuracy: 0.8973

Epoch 3/5

1875/1875 [==============================] - 9s 5ms/step - loss: 0.3852 - accuracy: 0.8968

Epoch 4/5

1875/1875 [==============================] - 9s 5ms/step - loss: 0.4024 - accuracy: 0.8930

Epoch 5/5

1875/1875 [==============================] - 9s 5ms/step - loss: 0.4193 - accuracy: 0.8901

313/313 - 1s - loss: 0.3629 - accuracy: 0.9024 - 1s/epoch - 4ms/step

https://toss.me/momo2024

momo2024님에게 보내주세요

토스아이디로 안전하게 익명 송금하세요.

toss.me

저작자표시 비영리 동일조건

'Deep Learning > 강좌&예제 코드' 카테고리의 다른 글

AUC - ROC Curve 이해하기 (0)	2024.04.01
onnx 파일의 shape 확인하기 (0)	2023.11.05
캐글 딥러닝 강좌 정리 3 - 과적합(Overfitting)과 해결 방법(dropout, batch normalization) (0)	2023.10.26
캐글 딥러닝 강좌 정리 2 - 확률적 경사 하강법(Stochastic Gradient Descent), 손실함수, 옵티마이저 (0)	2023.10.26
캐글 딥러닝 강좌 정리 1 - 뉴런(Neuron)과 깊은 신경망(DNN) (0)	2023.10.26

멈춤보단 천천히라도