def transform(self, X: dt.Frame):
if not os.path.exists(self.model_path):
with open(self.model_path, 'wb') as f:
f.write(self.model_bytes)
import h2oaicore.keras as keras
from h2oaicore.models import TensorFlowModel
self.tf_config = TensorFlowModel.ConfigProto()
# self.tf_config.gpu_options.allow_growth = True
self.tf_config.gpu_options.per_process_gpu_memory_fraction = 0.3
keras.backend.set_session(
session=TensorFlowModel.make_sess(self.tf_config))
# importlib.reload(keras)
self.model = keras.models.load_model(self.model_path)
# remove(self.model_path) # can't remove, used by other procs or later
values = X[:, self.col_name].to_numpy().ravel()
self.batch_size = min(len(values), self.batch_size)
values_ = np.array_split(values,
int(len(values) / self.batch_size) + 1)
print(values_)
results = []
for v in values_:
images = []
for x in v:
if True or x[-4:] in [".jpg", ".png", ".jpeg"]:
image = self.preprocess_image(x)
images.append(image)
else:
raise NotImplementedError
# deal with missing images (None in images)
good_imagei = None
for imagei, image in enumerate(images):
if image is not None:
good_imagei = imagei
break
if len(images) > 0:
msg = "no good images out of %d images" % len(images)
if False:
assert good_imagei is not None, msg
elif good_imagei is None:
pass
# print_debug(msg)
if good_imagei is not None:
for imagei, image in enumerate(images):
if image is None:
images[imagei] = images[
good_imagei] * 0 # impute 0 for missing images
images = np.vstack(images)
results.append(self.model.predict(images))
if len(results) > 0:
return dt.Frame(np.vstack(results))
else:
return dt.Frame([0] * X.shape[0])
def __init__(self, batch_size=32, **kwargs):
TensorFlowModel.__init__(self, **kwargs)
super().__init__(**kwargs)
self.batch_size = batch_size
self.model_name = "resnet_keras.h5p"
self.uuid = "%s-img-data-" % self.__class__.__name__ + self.model_name # + str(uuid.uuid4())[:6] # no, keeps changing and re-loadeing every init
self.uuid_tmp = str(uuid.uuid4())[:6]
self.col_name = self.input_feature_names[0]
self.model_path = os.path.join(user_dir(), self.uuid + ".model")
self.model_tmp_path = self.model_path + "_" + self.uuid_tmp + ".tmp"
if not os.path.exists(self.model_path):
self.download(
url=
"http://s3.amazonaws.com/artifacts.h2o.ai/releases/ai/h2o/recipes/transformers/img/%s"
% self.model_name,
dest=self.model_path)
with open(self.model_path, 'rb') as f:
self.model_bytes = f.read()