def load_parameters(self, params):
reg_base64 = params.get('reg_base64', None)
if reg_base64 is None:
raise InvalidModelParamsException()
reg_bytes = base64.b64decode(reg_base64.encode('utf-8'))
self._reg = pickle.loads(reg_bytes)
def load_parameters(self, params):
# Load model parameters
clf_base64 = params['clf_base64']
if clf_base64 is None:
raise InvalidModelParamsException()
clf_bytes = base64.b64decode(clf_base64.encode('utf-8'))
self._clf = pickle.loads(clf_bytes)
def load_parameters(self, params):
# Load model parameters
h5_model_base64 = params.get('h5_model_base64', None)
if h5_model_base64 is None:
raise InvalidModelParamsException()
with tempfile.NamedTemporaryFile() as tmp:
# Convert back to bytes & write to temp file
h5_model_bytes = base64.b64decode(h5_model_base64.encode('utf-8'))
with open(tmp.name, 'wb') as f:
f.write(h5_model_bytes)
# Load model from temp file
with self._graph.as_default():
with self._sess.as_default():
self._model = keras.models.load_model(tmp.name)
def _build_classifier(self, n_estimators, min_child_weight, max_depth,
gamma, subsample, colsample_bytree, num_class):
if num_class < 2:
raise InvalidModelParamsException()
elif num_class == 2:
clf = xgb.XGBClassifier(n_estimators=n_estimators,
min_child_weight=min_child_weight,
max_depth=max_depth,
gamma=gamma,
subsample=subsample,
colsample_bytree=colsample_bytree)
else:
clf = xgb.XGBClassifier(n_estimators=n_estimators,
min_child_weight=min_child_weight,
max_depth=max_depth,
gamma=gamma,
subsample=subsample,
colsample_bytree=colsample_bytree,
objective='multi:softmax',
num_class=num_class)
return clf
def load_parameters(self, params):
h5_model_base64 = params.get('h5_model_base64', None)
if h5_model_base64 is None:
raise InvalidModelParamsException()
# TODO: Not save to & read from a file
# Convert back to bytes & write to temp file
tmp = tempfile.NamedTemporaryFile(delete=False)
h5_model_bytes = base64.b64decode(h5_model_base64.encode('utf-8'))
with open(tmp.name, 'wb') as f:
f.write(h5_model_bytes)
# Load model from temp file
with self._graph.as_default():
with self._sess.as_default():
self._model = keras.models.load_model(tmp.name)
# Remove temp file
os.remove(tmp.name)
if 'predict_label_mapping' in params:
self._predict_label_mapping = params['predict_label_mapping']