[인공지능] Tensorflow 테스트 코드 실행

참조

• https://www.tensorflow.org/install/pip?hl=ko
• https://github.com/tensorflow/tensorflow/releases

목적

• Tensorflow 설치 후, 학습이 정상적으로 이루어지는 지 확인하기 위해 테스트 진행하였습니다.
• Tensorflow 2.0 초보자용 에 나와있는 예제코드를 이용하여 실제로 학습이 이루어 지는지 확인하였습니다.

예제 코드

import os
import tensorflow as tf

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'

# MNIST 데이터셋을 로드하여 준비합니다. 샘플 값을 정수에서 부동소수로 변환합니다:
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

# 층을 차례대로 쌓아 tf.keras.Sequential 모델을 만듭니다. 훈련에 사용할 옵티마이저(optimizer)와 손실 함수를 선택합니다:
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'])

# 모델을 훈련하고 평가합니다:

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

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

실행 결과

• CUDA 설치가 안되어 있어서, cudart64_110.dll not found 에러가 출력 되었습니다.
• 하지만, CPU로 빌드하여 학습이 진행된 것을 확인할 수 있습니다.

2022-02-07 14:04:06.894328: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2022-02-07 14:04:06.899610: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2022-02-07 14:04:12.651941: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2022-02-07 14:04:12.658449: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cublas64_11.dll'; dlerror: cublas64_11.dll not found
2022-02-07 14:04:12.663857: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cublasLt64_11.dll'; dlerror: cublasLt64_11.dll not found
2022-02-07 14:04:12.670582: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cufft64_10.dll'; dlerror: cufft64_10.dll not found
2022-02-07 14:04:12.676903: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'curand64_10.dll'; dlerror: curand64_10.dll not found
2022-02-07 14:04:12.682391: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cusolver64_11.dll'; dlerror: cusolver64_11.dll not found
2022-02-07 14:04:12.687339: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cusparse64_11.dll'; dlerror: cusparse64_11.dll not found
2022-02-07 14:04:12.692407: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudnn64_8.dll'; dlerror: cudnn64_8.dll not found
2022-02-07 14:04:12.696573: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1850] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
Skipping registering GPU devices...
2022-02-07 14:04:12.706665: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
Epoch 1/5
1875/1875 [==============================] - 3s 2ms/step - loss: 0.2952 - accuracy: 0.9137
Epoch 2/5
1875/1875 [==============================] - 3s 1ms/step - loss: 0.1401 - accuracy: 0.9581
Epoch 3/5
1875/1875 [==============================] - 3s 1ms/step - loss: 0.1056 - accuracy: 0.9674
Epoch 4/5
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0873 - accuracy: 0.9735
Epoch 5/5
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0749 - accuracy: 0.9768
313/313 - 0s - loss: 0.0727 - accuracy: 0.9774 - 488ms/epoch - 2ms/step