def TensorflowEmit(original_framework, architecture_name, architecture_path, weight_path, image_path):
import tensorflow as tf
from mmdnn.conversion.tensorflow.tensorflow_emitter import TensorflowEmitter
# IR to code
converted_file = original_framework + '_tensorflow_' + architecture_name + "_converted"
converted_file = converted_file.replace('.', '_')
emitter = TensorflowEmitter((architecture_path, weight_path))
emitter.run(converted_file + '.py', None, 'test')
del emitter
del TensorflowEmitter
# import converted model
model_converted = __import__(converted_file).KitModel(weight_path)
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 sys.modules[converted_file]
os.remove(converted_file + '.py')
converted_predict = np.squeeze(predict)
del tf
return converted_predict
def TensorflowEmit(original_framework, architecture_name, architecture_path, weight_path, image_path):
import tensorflow as tf
from mmdnn.conversion.tensorflow.tensorflow_emitter import TensorflowEmitter
original_framework = checkfrozen(original_framework)
# IR to code
converted_file = original_framework + '_tensorflow_' + architecture_name + "_converted"
converted_file = converted_file.replace('.', '_')
print(architecture_path)
print(weight_path)
emitter = TensorflowEmitter((architecture_path, weight_path))
emitter.run(converted_file + '.py', None, 'test')
del emitter
del TensorflowEmitter
# import converted model
model_converted = __import__(converted_file).KitModel(weight_path)
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 sys.modules[converted_file]
os.remove(converted_file + '.py')
converted_predict = np.squeeze(predict)
del tf
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 _convert(args):
if args.dstFramework == 'caffe':
from mmdnn.conversion.caffe.caffe_emitter import CaffeEmitter
if args.IRWeightPath is None:
emitter = CaffeEmitter(args.IRModelPath)
else:
assert args.dstWeightPath
emitter = CaffeEmitter((args.IRModelPath, args.IRWeightPath))
elif args.dstFramework == 'keras':
from mmdnn.conversion.keras.keras2_emitter import Keras2Emitter
emitter = Keras2Emitter((args.IRModelPath, args.IRWeightPath))
elif args.dstFramework == 'tensorflow':
from mmdnn.conversion.tensorflow.tensorflow_emitter import TensorflowEmitter
if args.IRWeightPath is None:
# Convert network architecture only
emitter = TensorflowEmitter(args.IRModelPath)
else:
emitter = TensorflowEmitter((args.IRModelPath, args.IRWeightPath))
elif args.dstFramework == 'cntk':
from mmdnn.conversion.cntk.cntk_emitter import CntkEmitter
if args.IRWeightPath is None:
emitter = CntkEmitter(args.IRModelPath)
else:
emitter = CntkEmitter((args.IRModelPath, args.IRWeightPath))
elif args.dstFramework == 'coreml':
raise NotImplementedError("CoreML emitter is not finished yet.")
elif args.dstFramework == 'pytorch':
if not args.dstWeightPath or not args.IRWeightPath:
raise ValueError("Need to set a target weight filename.")
from mmdnn.conversion.pytorch.pytorch_emitter import PytorchEmitter
emitter = PytorchEmitter((args.IRModelPath, args.IRWeightPath))
elif args.dstFramework == 'mxnet':
from mmdnn.conversion.mxnet.mxnet_emitter import MXNetEmitter
if args.IRWeightPath is None:
emitter = MXNetEmitter(args.IRModelPath)
else:
if args.dstWeightPath is None:
raise ValueError(
"MXNet emitter needs argument [dstWeightPath(dw)], like -dw mxnet_converted-0000.param"
)
emitter = MXNetEmitter(
(args.IRModelPath, args.IRWeightPath, args.dstWeightPath))
elif args.dstFramework == 'onnx':
from mmdnn.conversion.onnx.onnx_emitter import OnnxEmitter
if args.IRWeightPath is None:
raise NotImplementedError("ONNX emitter needs IR weight file")
else:
emitter = OnnxEmitter(args.IRModelPath, args.IRWeightPath)
else:
assert False
emitter.run(args.dstModelPath, args.dstWeightPath, args.phase)
return 0
def tensorflow_emit(original_framework, architecture_name,
architecture_path, weight_path, test_input_path):
import tensorflow as tf
from mmdnn.conversion.tensorflow.tensorflow_emitter import TensorflowEmitter
# IR to code
converted_file = TestModels.tmpdir + original_framework + '_tensorflow_' + architecture_name + "_converted"
converted_file = converted_file.replace('.', '_')
emitter = TensorflowEmitter((architecture_path, weight_path))
emitter.run(converted_file + '.py', None, 'test')
del emitter
del TensorflowEmitter
# import converted model
model_converted = imp.load_source('TFModel', converted_file +
'.py').KitModel(weight_path)
input_tf, model_tf = model_converted
original_framework = checkfrozen(original_framework)
if 'rnn' not in architecture_name:
func = TestKit.preprocess_func[original_framework][
architecture_name]
img = func(test_input_path(architecture_name))
input_data = np.expand_dims(img, 0)
else:
input_data = np.load(test_input_path(architecture_name))
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 sys.modules['TFModel']
os.remove(converted_file + '.py')
converted_predict = np.squeeze(predict)
del tf
return converted_predict
def _convert(args):
if args.dstModelFormat == 'caffe':
raise NotImplementedError("Destination [Caffe] is not implemented yet.")
elif args.dstModelFormat == 'keras':
from mmdnn.conversion.keras.keras2_emitter import Keras2Emitter
emitter = Keras2Emitter(args.IRModelPath)
elif args.dstModelFormat == 'tensorflow':
from mmdnn.conversion.tensorflow.tensorflow_emitter import TensorflowEmitter
if args.IRWeightPath == None:
emitter = TensorflowEmitter(args.IRModelPath)
else:
emitter = TensorflowEmitter((args.IRModelPath, args.IRWeightPath))
elif args.dstModelFormat == 'cntk':
from mmdnn.conversion.cntk.cntk_emitter import CntkEmitter
if args.IRWeightPath == None:
emitter = CntkEmitter(args.IRModelPath)
else:
emitter = CntkEmitter((args.IRModelPath, args.IRWeightPath))
elif args.dstModelFormat == 'coreml':
raise NotImplementedError("CoreML emitter is not finished yet.")
assert args.IRWeightPath != None
from mmdnn.conversion.coreml.coreml_emitter import CoreMLEmitter
emitter = CoreMLEmitter((args.IRModelPath, args.IRWeightPath))
model = emitter.gen_model()
print ("Saving the CoreML model [{}].".format(args.dstModelPath + '.mlmodel'))
model.save(args.dstModelPath + '.mlmodel')
print ("The converted CoreML model saved as [{}].".format(args.dstModelPath + '.mlmodel'))
return 0
elif args.dstModelFormat == 'pytorch':
if not args.dstWeightPath or not args.IRWeightPath:
raise ValueError("Need to set a target weight filename.")
from mmdnn.conversion.pytorch.pytorch_emitter import PytorchEmitter
emitter = PytorchEmitter((args.IRModelPath, args.IRWeightPath))
elif args.dstModelFormat == 'mxnet':
from mmdnn.conversion.mxnet.mxnet_emitter import MXNetEmitter
if args.IRWeightPath == None:
emitter = MXNetEmitter(args.IRModelPath)
else:
emitter = MXNetEmitter((args.IRModelPath, args.IRWeightPath, args.inputShape, args.dstWeightPath))
else:
assert False
emitter.run(args.dstModelPath, args.dstWeightPath, args.phase)
return 0
def _convert(args):
if args.dstModelFormat == 'caffe':
raise NotImplementedError(
"Destination [Caffe] is not implemented yet.")
elif args.dstModelFormat == 'keras':
from mmdnn.conversion.keras.keras2_emitter import Keras2Emitter
emitter = Keras2Emitter(args.IRModelPath)
elif args.dstModelFormat == 'tensorflow':
from mmdnn.conversion.tensorflow.tensorflow_emitter import TensorflowEmitter
if args.IRWeightPath == None:
emitter = TensorflowEmitter(args.IRModelPath)
else:
emitter = TensorflowEmitter((args.IRModelPath, args.IRWeightPath))
elif args.dstModelFormat == 'cntk':
from mmdnn.conversion.cntk.cntk_emitter import CntkEmitter
if args.IRWeightPath == None:
emitter = CntkEmitter(args.IRModelPath)
else:
emitter = CntkEmitter((args.IRModelPath, args.IRWeightPath))
elif args.dstModelFormat == 'coreml':
raise NotImplementedError("CoreML emitter is not finished yet.")
assert args.IRWeightPath != None
from mmdnn.conversion.coreml.coreml_emitter import CoreMLEmitter
emitter = CoreMLEmitter((args.IRModelPath, args.IRWeightPath))
model = emitter.gen_model()
print("Saving the CoreML model [{}].".format(args.dstModelPath +
'.mlmodel'))
model.save(args.dstModelPath + '.mlmodel')
print("The converted CoreML model saved as [{}].".format(
args.dstModelPath + '.mlmodel'))
return 0
elif args.dstModelFormat == 'pytorch':
if not args.dstWeightPath or not args.IRWeightPath:
raise ValueError("Need to set a target weight filename.")
from mmdnn.conversion.pytorch.pytorch_emitter import PytorchEmitter
emitter = PytorchEmitter((args.IRModelPath, args.IRWeightPath))
elif args.dstModelFormat == 'mxnet':
from mmdnn.conversion.mxnet.mxnet_emitter import MXNetEmitter
if args.IRWeightPath == None:
emitter = MXNetEmitter(args.IRModelPath)
else:
emitter = MXNetEmitter((args.IRModelPath, args.IRWeightPath,
args.inputShape, args.dstWeightPath))
else:
assert False
emitter.run(args.dstModelPath, args.dstWeightPath, args.phase)
return 0
