def KerasEmit(original_framework, architecture_name, architecture_path,
weight_path, image_path):
print("Testing {} from {} to Keras.".format(architecture_name,
original_framework))
# IR to code
emitter = Keras2Emitter((architecture_path, weight_path))
emitter.run("converted_model.py", None, 'test')
del emitter
# import converted model
import converted_model
reload_module(converted_model)
model_converted = converted_model.KitModel(TestModels.tmpdir +
architecture_name +
"_converted.npy")
func = TestKit.preprocess_func[original_framework][architecture_name]
img = func(image_path)
input_data = np.expand_dims(img, 0)
predict = model_converted.predict(input_data)
converted_predict = np.squeeze(predict)
del model_converted
del converted_model
import keras.backend as K
K.clear_session()
os.remove("converted_model.py")
return converted_predict
def CntkEmit(original_framework, architecture_name, architecture_path,
weight_path, image_path):
print("Testing {} from {} to CNTK.".format(architecture_name,
original_framework))
# IR to code
emitter = CntkEmitter((architecture_path, weight_path))
emitter.run("converted_model.py", None, 'test')
del emitter
# import converted model
import converted_model
reload_module(converted_model)
model_converted = converted_model.KitModel(TestModels.tmpdir +
architecture_name +
"_converted.npy")
func = TestKit.preprocess_func[original_framework][architecture_name]
img = func(image_path)
predict = model_converted.eval({model_converted.arguments[0]: [img]})
converted_predict = np.squeeze(predict)
del model_converted
del converted_model
os.remove("converted_model.py")
return converted_predict
def TensorflowEmit(original_framework, architecture_name,
architecture_path, weight_path, image_path):
print("Testing {} from {} to Tensorflow.".format(
architecture_name, original_framework))
# IR to code
emitter = TensorflowEmitter((architecture_path, weight_path))
emitter.run("converted_model.py", None, 'test')
del emitter
# import converted model
import converted_model
reload_module(converted_model)
model_converted = converted_model.KitModel(TestModels.tmpdir +
architecture_name +
"_converted.npy")
input_tf, model_tf = model_converted
func = TestKit.preprocess_func[original_framework][architecture_name]
img = func(image_path)
input_data = np.expand_dims(img, 0)
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
predict = sess.run(model_tf, feed_dict={input_tf: input_data})
del model_converted
del converted_model
os.remove("converted_model.py")
converted_predict = np.squeeze(predict)
return converted_predict
def CaffeEmit(original_framework, architecture_name, architecture_path, weight_path, image_path):
print("Testing {} from {} to Caffe.".format(architecture_name, original_framework))
# IR to code
emitter = CaffeEmitter((architecture_path, weight_path))
emitter.run("converted_model.py", None, 'test')
del emitter
# import converted model
import converted_model
reload_module (converted_model)
model_converted = converted_model.KitModel(TestModels.tmpdir + architecture_name + "_converted.npy")
# input_tf, model_tf = model_converted
func = TestKit.preprocess_func[original_framework][architecture_name]
img = func(image_path)