vgg16, inception v3 코드

https://github.com/sagarvegad/Video-Classification-CNN-and-LSTM-

Keras documentation: Video Classification with a CNN-RNN Architecture

vgg16 inception v3
data bring_data_from_directory() / ImageDataGenerator 사용 / train_generator , validation_generator / 5개 분류 / target_size = (224,224) , batch_size =128 tran_df , test_df / crop_center_square(), load_video() / IMG_SIZE = 224 / BATCH_SIZE = 64 / epochs=10 / max_seq_length=20 / num_features=2048
모델 적용 load_VGG16_model() / base_model=VGG16(weights='imagenet', include_top=False, input_shape=(224,224,3)) build_feature_extractor() : feature_extractor= keras.applications.InceptionV3 (weights=”imagenet”, include_top=False, pooling=”avg”,input_shape(IMG_SIZE,IMG_SIZE,3))
extract_features_and_store(train_generator,validation_generator,base_model)

vgg 16

## 데이터 셋 구성
def bring_data_from_directory():
  datagen = ImageDataGenerator(rescale=1. / 255)
  train_generator = datagen.flow_from_directory(
          'train',
          target_size=(224, 224),
          batch_size=batch_size,
          class_mode='categorical',  # this means our generator will only yield batches of data, no labels
          shuffle=True,
          classes=['class_1','class_2','class_3','class_4','class_5'])

  validation_generator = datagen.flow_from_directory(
          'validate',
          target_size=(224, 224),
          batch_size=batch_size,
          class_mode='categorical',  # this means our generator will only yield batches of data, no labels
          shuffle=True,
          classes=['class_1','class_2','class_3','class_4','class_5'])
  return train_generator,validation_generator

## 모델 로드
def load_VGG16_model():
  base_model = VGG16(weights='imagenet', include_top=False, input_shape=(224,224,3))
  print "Model loaded..!"
  print base_model.summary()
  return base_model