def get_raw_image_set(self, with_label):
resource_path = os.path.join(os.path.split(__file__)[0], "../../resources")
if with_label:
image_folder = os.path.join(resource_path, "cat_dog")
else:
image_folder = os.path.join(resource_path, "cat_dog/*")
image_set = ImageSet.read(image_folder, with_label=with_label, sc=get_spark_context(),
one_based_label=False)
return image_set
def input_fn(mode):
import os
resource_path = os.path.join(
os.path.split(__file__)[0], "../resources")
if mode == tf.estimator.ModeKeys.TRAIN:
image_folder = os.path.join(resource_path, "cat_dog")
image_set = ImageSet.read(image_folder,
with_label=True,
sc=self.sc,
one_based_label=False)
transformer = ChainedPreprocessing([
ImageResize(256, 256),
ImageRandomCrop(224, 224, True),
ImageMatToTensor(format="NHWC"),
ImageSetToSample(input_keys=["imageTensor"],
target_keys=["label"])
])
image_set = image_set.transform(transformer)
dataset = TFDataset.from_image_set(image_set,
image=(tf.float32,
[224, 224, 3]),
label=(tf.int32, [1]),
batch_size=8)
elif mode == tf.estimator.ModeKeys.EVAL:
image_folder = os.path.join(resource_path, "cat_dog")
image_set = ImageSet.read(image_folder,
with_label=True,
sc=self.sc,
one_based_label=False)
transformer = ChainedPreprocessing([
ImageResize(256, 256),
ImageRandomCrop(224, 224, True),
ImageMatToTensor(format="NHWC"),
ImageSetToSample(input_keys=["imageTensor"],
target_keys=["label"])
])
image_set = image_set.transform(transformer)
dataset = TFDataset.from_image_set(image_set,
image=(tf.float32,
[224, 224, 3]),
label=(tf.int32, [1]),
batch_per_thread=8)
else:
image_folder = os.path.join(resource_path, "cat_dog/*/*")
image_set = ImageSet.read(image_folder,
with_label=False,
sc=self.sc,
one_based_label=False)
transformer = ChainedPreprocessing([
ImageResize(256, 256),
ImageRandomCrop(224, 224, True),
ImageMatToTensor(format="NHWC"),
ImageSetToSample(input_keys=["imageTensor"])
])
image_set = image_set.transform(transformer)
dataset = TFDataset.from_image_set(image_set,
image=(tf.float32,
[224, 224, 3]),
batch_per_thread=8)
return dataset
parser = OptionParser()
parser.add_option("--image",
type=str,
dest="img_path",
help="The path where the images are stored, "
"can be either a folder or an image path")
parser.add_option("--model",
type=str,
dest="model_path",
help="Path to the TensorFlow model file")
(options, args) = parser.parse_args(sys.argv)
sc = init_nncontext("OpenVINO Object Detection Inference Example")
images = ImageSet.read(options.img_path,
sc,
resize_height=600,
resize_width=600).get_image().collect()
input_data = np.concatenate(
[image.reshape((1, 1) + image.shape) for image in images], axis=0)
model_path = options.model_path
model = InferenceModel()
model.load_openvino(model_path,
weight_path=model_path[:model_path.rindex(".")] +
".bin")
predictions = model.predict(input_data)
# Print the detection result of the first image.
print(predictions[0])
print("finished...")
sc.stop()