def CaffeEmit(original_framework, architecture_name, architecture_path, weight_path, image_path):
import caffe
from mmdnn.conversion.caffe.caffe_emitter import CaffeEmitter
# IR to code
converted_file = original_framework + '_caffe_' + architecture_name + "_converted"
converted_file = converted_file.replace('.', '_')
emitter = CaffeEmitter((architecture_path, weight_path))
emitter.run(converted_file + '.py', converted_file + '.npy', 'test')
del emitter
del CaffeEmitter
# import converted model
imported = __import__(converted_file)
imported.make_net(converted_file + '.prototxt')
imported.gen_weight(converted_file + '.npy', converted_file + '.caffemodel', converted_file + '.prototxt')
model_converted = caffe.Net(converted_file + '.prototxt', converted_file + '.caffemodel', caffe.TEST)
func = TestKit.preprocess_func[original_framework][architecture_name]
img = func(image_path)
img = np.transpose(img, [2, 0, 1])
input_data = np.expand_dims(img, 0)
model_converted.blobs[model_converted._layer_names[0]].data[...] = input_data
predict = model_converted.forward()[model_converted._layer_names[-1]][0]
converted_predict = np.squeeze(predict)
del model_converted
del sys.modules[converted_file]
os.remove(converted_file + '.py')
os.remove(converted_file + '.npy')
os.remove(converted_file + '.prototxt')
os.remove(converted_file + '.caffemodel')
return converted_predict
def CaffeEmit(original_framework, architecture_name, architecture_path, weight_path, image_path):
import caffe
from mmdnn.conversion.caffe.caffe_emitter import CaffeEmitter
# IR to code
converted_file = original_framework + '_caffe_' + architecture_name + "_converted"
converted_file = converted_file.replace('.', '_')
emitter = CaffeEmitter((architecture_path, weight_path))
emitter.run(converted_file + '.py', converted_file + '.npy', 'test')
del emitter
del CaffeEmitter
# import converted model
imported = __import__(converted_file)
imported.make_net(converted_file + '.prototxt')
imported.gen_weight(converted_file + '.npy', converted_file + '.caffemodel', converted_file + '.prototxt')
model_converted = caffe.Net(converted_file + '.prototxt', converted_file + '.caffemodel', caffe.TEST)
func = TestKit.preprocess_func[original_framework][architecture_name]
img = func(image_path)
img = np.transpose(img, [2, 0, 1])
input_data = np.expand_dims(img, 0)
model_converted.blobs[model_converted._layer_names[0]].data[...] = input_data
predict = model_converted.forward()[model_converted._layer_names[-1]][0]
converted_predict = np.squeeze(predict)
del model_converted
del sys.modules[converted_file]
os.remove(converted_file + '.py')
os.remove(converted_file + '.npy')
os.remove(converted_file + '.prototxt')
os.remove(converted_file + '.caffemodel')
return converted_predict
def CaffeEmit(original_framework, architecture_name, architecture_path,
weight_path, test_input_path):
try:
import caffe
from mmdnn.conversion.caffe.caffe_emitter import CaffeEmitter
# IR to code
converted_file = original_framework + '_caffe_' + architecture_name + "_converted"
converted_file = converted_file.replace('.', '_')
emitter = CaffeEmitter((architecture_path, weight_path))
emitter.run(converted_file + '.py', converted_file + '.npy',
'test')
del emitter
del CaffeEmitter
# import converted model
imported = imp.load_source('CaffeModel', converted_file + '.py')
imported.make_net(converted_file + '.prototxt')
imported.gen_weight(converted_file + '.npy',
converted_file + '.caffemodel',
converted_file + '.prototxt')
model_converted = caffe.Net(converted_file + '.prototxt',
converted_file + '.caffemodel',
caffe.TEST)
original_framework = checkfrozen(original_framework)
func = TestKit.preprocess_func[original_framework][
architecture_name]
img = func(test_input_path(architecture_name))
img = np.transpose(img, [2, 0, 1])
input_data = np.expand_dims(img, 0)
model_converted.blobs[model_converted._layer_names[0]].data[
...] = input_data
predict = model_converted.forward()[
model_converted._layer_names[-1]]
converted_predict = np.squeeze(predict)
del model_converted
del sys.modules['CaffeModel']
del caffe
os.remove(converted_file + '.py')
os.remove(converted_file + '.npy')
os.remove(converted_file + '.prototxt')
os.remove(converted_file + '.caffemodel')
return converted_predict
except ImportError:
print("Cannot import Caffe. Caffe Emit is not tested.")
return None
def start(self):
print("start to do pytorch to IR")
self.parse.run(self.save_root)
print("done! then to do IR to caffe code")
emitter = CaffeEmitter(
(self.save['structurepb'], self.save['weights']))
emitter.run(self.save['caffenetwork'], self.save['caffeweights'],
'test')
print("done! then to do ccode to model")
MainModel = imp.load_source('MainModel', self.save['caffenetwork'])
save_model(
MainModel, self.save['caffenetwork'],
self.save['caffeweights', self.save['caffemodel'],
self.save['caffeproto']])
print("done!!!!!!")
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)
def start(self):
print("start to do pytorch to IR")
self.parse.run(self.save_root + self.save_name)
print("done! then to do IR to caffe code")
emitter = CaffeEmitter(
(self.save['structurepb'], self.save['weights']))
emitter.run(self.save['caffenetwork'], self.save['caffeweights'],
'test')
print("done! then to do ccode to model")
MainModel = imp.load_source('MainModel', self.save['caffenetwork'])
save_model(MainModel, self.save['caffenetwork'],
self.save['caffeweights'], self.save['caffemodel'])
print('start to rename inputs')
lines = open(self.save['caffemodel'] + '.prototxt', 'r').readlines()
new_lines = rename_input(lines, self.input_shape)
fp = open(self.save['caffemodel'] + '.prototxt', 'w')
fp.writelines(new_lines)
print("^~^^~^^~^^~^")
def _convert(args):
if args.dstFramework == 'caffe':
from mmdnn.conversion.caffe.caffe_emitter import CaffeEmitter
if args.IRWeightPath == None:
emitter = CaffeEmitter(args.IRModelPath)
else:
emitter = CaffeEmitter((args.IRModelPath, args.IRWeightPath))
elif args.dstFramework == 'keras':
from mmdnn.conversion.keras.keras2_emitter import Keras2Emitter
emitter = Keras2Emitter(args.IRModelPath)
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))
else:
assert False
emitter.run(args.dstModelPath, args.dstWeightPath, args.phase)
return 0
