def preprocessing_manager(cfg):
if cfg["dataset"]["encoding"] == "inception":
img_model = InceptionV3(weights='imagenet')
dataset_preprocessor = PreProcessing(cfg, "inception", (299, 299))
dataset_preprocessor.run_one_time_encoding(img_model)
# Load train, validation sets from the pre-processor
return dataset_preprocessor.get_encoding_keras_generators("inception")
elif cfg["dataset"]["encoding"] == "resnet50":
img_model = ResNet50(weights='imagenet')
dataset_preprocessor = PreProcessing(cfg, "resnet50", (224, 224))
dataset_preprocessor.run_one_time_encoding(img_model)
# Load train, validation sets from the pre-processor
return dataset_preprocessor.get_encoding_keras_generators("resnet50")
elif cfg["dataset"]["encoding"] == "simple":
dataset_preprocessor = PreProcessing(cfg, None, (299, 299))
return dataset_preprocessor.get_image_keras_generators()
else:
RuntimeError("Unsupported encoding type!")
args = parser.parse_args()
with open(args.config) as fp:
cfg = yaml.load(fp)
dataset_cfg = get_dataset_metadata_cfg()
model_workspace_dir = os.path.join(cfg["workspace"]["directory"],
cfg["dataset"]["name"],
cfg["model"]["arch"])
utils.make_directories(model_workspace_dir)
img_model = ResNet50(weights='imagenet')
dataset_preprocessor = PreProcessing(cfg, "resnet50", False, False)
dataset_preprocessor.run_one_time_encoding(img_model)
# Load train, validation sets from the pre-processor
training_generator, validation_generator, test_generator = dataset_preprocessor.get_keras_generators(
"resnet50")
MAX_LEN = 40
EMBEDDING_DIM = 300
IMAGE_ENC_DIM = 300
vocab_size = get_line_count(
os.path.join(cfg["workspace"]["directory"], cfg["dataset"]["name"],
"word_dictionary.txt"))
img_input = Input(shape=(2048, ))
img_enc = Dense(300, activation="relu")(img_input)
images = RepeatVector(MAX_LEN)(img_enc)