def main():
parser = argparse.ArgumentParser()
parser.add_argument('def_path', help='Model definition (.prototxt) path')
parser.add_argument('data_path', help='Model data (.caffemodel) path')
parser.add_argument('data_output_path', help='Converted data output path')
parser.add_argument('code_output_path',
nargs='?',
help='Save generated source to this path')
parser.add_argument('-p',
'--phase',
default='test',
help='The phase to convert: test (default) or train')
args = parser.parse_args()
try:
transformer = TensorFlowTransformer(args.def_path,
args.data_path,
phase=args.phase)
print('Converting data...')
data = transformer.transform_data()
print('Saving data...')
with open(args.data_output_path, 'wb') as data_out:
np.save(data_out, data)
if args.code_output_path is not None:
print('Saving source...')
with open(args.code_output_path, 'wb') as src_out:
src_out.write(transformer.transform_source())
print('Done.')
except KaffeError as err:
print('Error encountered: %s' % err)
exit(-1)
def convert(def_path, caffemodel_path, data_output_path, phase):
assert '.npy' in data_output_path
code_output_path = data_output_path.replace('npy', 'py')
try:
transformer = TensorFlowTransformer(def_path, caffemodel_path, phase=phase)
print_stderr('Converting data...')
if caffemodel_path is not None:
data = transformer.transform_data()
print_stderr('Saving data...')
# create directory if not existing
dirname = os.path.dirname(data_output_path)
if not os.path.exists(dirname) and dirname != '':
os.makedirs(dirname)
with open(data_output_path, 'wb') as data_out:
np.save(data_out, data)
if code_output_path:
print_stderr('Saving source...')
# create directory if not existing
dirname = os.path.dirname(code_output_path)
if not os.path.exists(dirname) and dirname != '':
os.makedirs(dirname)
with open(code_output_path, 'wb') as src_out:
src_out.write(transformer.transform_source())
print_stderr('Done.')
except KaffeError as err:
fatal_error('Error encountered: {}'.format(err))
def main():
parser = argparse.ArgumentParser()
parser.add_argument('def_path', help='Model definition (.prototxt) path')
parser.add_argument('data_path', help='Model data (.caffemodel) path')
parser.add_argument('data_output_path', help='Converted data output path')
parser.add_argument(
'code_output_path', nargs='?', help='Save generated source to this path')
parser.add_argument('-p', '--phase', default='test',
help='The phase to convert: test (default) or train')
args = parser.parse_args()
try:
transformer = TensorFlowTransformer(
args.def_path, args.data_path, phase=args.phase)
print('Converting data...')
data = transformer.transform_data()
print('Saving data...')
with open(args.data_output_path, 'wb') as data_out:
np.save(data_out, data)
if args.code_output_path is not None:
print('Saving source...')
with open(args.code_output_path, 'wb') as src_out:
src_out.write(transformer.transform_source().encode('latin-1'))
print('Done.')
except KaffeError as err:
print(('Error encountered: %s' % err))
exit(-1)
def main():
args = sys.argv[1:]
if len(args) not in (3, 4, 5):
print(
'usage: %s path.prototxt path.caffemodel data-output-path [code-output-path.py] [phase=test]'
% os.path.basename(__file__))
exit(-1)
def_path, data_path, data_out_path = args[:3]
src_out_path = args[3] if len(args) >= 4 else None
phase = args[4] if len(args) >= 5 else 'test'
try:
transformer = TensorFlowTransformer(def_path, data_path, phase=phase)
print('Converting data...')
data = transformer.transform_data()
print('Saving data...')
with open(data_out_path, 'wb') as data_out:
np.save(data_out, data)
if src_out_path is not None:
print('Saving source...')
with open(src_out_path, 'wb') as src_out:
src_out.write(transformer.transform_source())
print('Done.')
except KaffeError as err:
print('Error encountered: %s' % err)
exit(-1)
def convert(def_path, caffemodel_path, data_output_path, code_output_path,
phase):
'''
用于对输入的模型进行加载，和进行模型装换
:param def_path: 输入的caffe网络结构文件prototxt格式
:param caffemodel_path: 输入的caffe训练的到的模型文件caffemodel格式
:param data_output_path: 输出的
:param code_output_path:输出的tensorflow的网络结构代码
:param phase:为网络的训练模式，test 或者是train
:return:
'''
try:
transformer = TensorFlowTransformer(def_path,
caffemodel_path,
phase=phase) #加载网络结构和加载模型文件
print_stderr('Converting data...') #开始转换数据
if caffemodel_path is not None:
data = transformer.transform_data() #转换权值和偏置数据
print_stderr('Saving data...')
with open(data_output_path, 'wb') as data_out:
np.save(data_out, data) #保存权值偏置数据
if code_output_path: #转化为tensorflow对应网络我心代码
print_stderr('Saving source...')
with open(code_output_path, 'wb') as src_out:
src_out.write(transformer.transform_source()) #保存网络模型代码
print_stderr('Done.') #转换完成
except KaffeError as err: #捕获异常
fatal_error('Error encountered: {}'.format(err))
def convert(def_path, caffemodel_path, data_output_path, code_output_path, phase):
try:
transformer = TensorFlowTransformer(def_path, caffemodel_path, phase=phase)
print_stderr('Converting data...')
if caffemodel_path is not None:
data = transformer.transform_data()
print_stderr('Saving data...')
with open(data_output_path, 'wb') as data_out:
np.save(data_out, data)
if code_output_path:
print_stderr('Saving source...')
with open(code_output_path, 'w') as src_out:
src_out.write(transformer.transform_source())
print_stderr('Done.')
except KaffeError as err:
fatal_error('Error encountered: {}'.format(err))
def convert(def_path, caffemodel_path, data_output_path, code_output_path, phase):
try:
transformer = TensorFlowTransformer(def_path, caffemodel_path, phase=phase)
print_stderr('Converting data...')
if caffemodel_path is not None:
data = transformer.transform_data()
print_stderr('Saving data...')
with open(data_output_path, 'wb') as data_out:
np.save(data_out, data)
if code_output_path:
print_stderr('Saving source...')
with open(code_output_path, 'wb') as src_out:
src_out.write(transformer.transform_source().encode('utf-8'))
print_stderr('Done.')
except KaffeError as err:
fatal_error('Error encountered: {}'.format(err))
def convert(class_name, def_path, caffemodel_path, data_output_path,
code_output_path, phase, num_classes):
transformer = TensorFlowTransformer(class_name,
def_path,
caffemodel_path,
num_classes,
phase=phase)
print_stderr('Converting data...')
if caffemodel_path is not None:
data = transformer.transform_data()
print_stderr('Saving data...')
with open(data_output_path, 'wb') as data_out:
np.save(data_out, data)
if code_output_path:
print_stderr('Saving source...')
with open(code_output_path, 'wb') as src_out:
src_out.write(transformer.transform_source())
print_stderr('Done.')
def convert(def_path,
data_path=None,
data_output_path='mynet.npy',
code_output_path='mynet.py',
phase='test'):
try:
transformer = TensorFlowTransformer(def_path, data_path, phase=phase)
print('Converting data...')
if data_path is not None:
data = transformer.transform_data()
print('Saving data...')
with open(data_output_path, 'wb') as data_out:
np.save(data_out, data)
print('Saving source...')
with open(code_output_path, 'wb') as src_out:
src_out.write(transformer.transform_source())
print('Done.')
except KaffeError as err:
print('Error encountered: %s' % err)
exit(-1)
def convert(def_path,
data_path=None,
data_output_path='mynet.npy',
code_output_path='mynet.py',
phase='test'):
try:
transformer = TensorFlowTransformer(def_path, data_path, phase=phase)
print('Converting data...')
if data_path is not None:
data = transformer.transform_data()
print('Saving data...')
with open(data_output_path, 'wb') as data_out:
np.save(data_out, data)
print('Saving source...')
with open(code_output_path, 'wb') as src_out:
src_out.write(transformer.transform_source())
print('Done.')
except KaffeError as err:
print('Error encountered: %s'%err)
exit(-1)
def convert(def_path, caffemodel_path, data_output_path, code_output_path,
input_list_path, input_shape_list_path, output_list_path, phase):
try:
transformer = TensorFlowTransformer(def_path,
caffemodel_path,
phase=phase)
print_stderr('Converting data...')
if caffemodel_path is not None:
data = transformer.transform_data()
print_stderr('Saving data...')
with open(data_output_path, 'wb') as data_out:
np.save(data_out, data)
if code_output_path:
print_stderr('Saving source...')
with open(code_output_path, 'wb') as src_out:
source = transformer.transform_source()
src_out.write(source)
if input_list_path or input_shape_list_path or output_list_path:
mapper = TensorFlowMapper(transformer.graph)
chains = mapper.map()
inputs = [x.name for x in transformer.graph.get_input_nodes()]
input_shapes = [[
node.output_shape.width, node.output_shape.height,
node.output_shape.channels
] for node in transformer.graph.get_input_nodes()]
outputs = [x.name for x in transformer.graph.get_output_nodes()]
if input_list_path:
with open(input_list_path, 'wb') as input_list_out:
json.dump(inputs, input_list_out)
if input_shape_list_path:
with open(input_shape_list_path, 'wb') as input_shape_list_out:
json.dump(input_shapes, input_shape_list_out)
if output_list_path:
with open(output_list_path, 'wb') as output_list_out:
json.dump(outputs, output_list_out)
print_stderr('Done.')
except KaffeError as err:
fatal_error('Error encountered: {}'.format(err))
def main():
args = sys.argv[1:]
if len(args) not in (3, 4):
print('usage: %s path.prototxt path.caffemodel data-output-path [code-output-path.py]'%os.path.basename(__file__))
exit(-1)
def_path, data_path, data_out_path = args[:3]
src_out_path = args[3] if len(args)==4 else None
try:
transformer = TensorFlowTransformer(def_path, data_path)
print('Converting data...')
data = transformer.transform_data()
print('Saving data...')
with open(data_out_path, 'wb') as data_out:
np.save(data_out, data)
if src_out_path is not None:
print('Saving source...')
with open(src_out_path, 'wb') as src_out:
src_out.write(transformer.transform_source())
print('Done.')
except KaffeError as err:
print('Error encountered: %s'%err)
exit(-1)
def convert(def_path, caffemodel_path, data_output_path, code_output_path,
phase, framework):
try:
if framework == 'tensorflow':
from kaffe.tensorflow import TensorFlowTransformer
transformer = TensorFlowTransformer(def_path,
caffemodel_path,
phase=phase)
elif framework == 'theano':
from kaffe.theano import TheanoTransformer
transformer = TheanoTransformer(def_path,
caffemodel_path,
phase=phase)
elif framework == 'tf_nchw':
from kaffe.tf_nchw import TF_NCHW_Transformer
transformer = TF_NCHW_Transformer(def_path,
caffemodel_path,
phase=phase)
else:
raise NotImplementedError('Not implemented target to convert')
print_stderr('Converting data...')
if caffemodel_path is not None:
data = transformer.transform_data()
print_stderr('Saving data...')
with open(data_output_path, 'wb') as data_out:
np.save(data_out, data)
if code_output_path:
print_stderr('Saving source...')
with open(code_output_path, 'w') as src_out:
src_out.write(transformer.transform_source())
print_stderr('Done.')
except KaffeError as err:
fatal_error('Error encountered: {}'.format(err))
except NotImplementedError as err:
raise
def convert(def_path, caffemodel_path, data_output_path, code_output_path,
standalone_output_path, phase):
try:
sess = tf.InteractiveSession()
transformer = TensorFlowTransformer(def_path,
caffemodel_path,
phase=phase)
print_stderr('Converting data...')
if data_output_path is not None:
data = transformer.transform_data()
print_stderr('Saving data...')
with open(data_output_path, 'wb') as data_out:
np.save(data_out, data)
if code_output_path is not None:
print_stderr('Saving source...')
with open(code_output_path, 'wb') as src_out:
src_out.write(transformer.transform_source())
if standalone_output_path:
filename, _ = os.path.splitext(
os.path.basename(standalone_output_path))
temp_folder = os.path.join(os.path.dirname(standalone_output_path),
'.tmp')
try:
os.makedirs(temp_folder)
except:
pass
if data_output_path is None:
data = transformer.transform_data()
print_stderr('Saving data...')
data_output_path = os.path.join(temp_folder, filename) + '.npy'
with open(data_output_path, 'wb') as data_out:
np.save(data_out, data)
if code_output_path is None:
print_stderr('Saving source...')
code_output_path = os.path.join(temp_folder, filename) + '.py'
with open(code_output_path, 'wb') as src_out:
src_out.write(transformer.transform_source())
checkpoint_path = os.path.join(temp_folder, filename + '.ckpt')
graph_name = os.path.basename(standalone_output_path)
graph_folder = os.path.dirname(standalone_output_path)
input_node = transformer.graph.nodes[0].name
output_node = transformer.graph.nodes[-1].name
tensor_shape = transformer.graph.get_node(input_node).output_shape
tensor_shape_list = [
tensor_shape.batch_size, tensor_shape.height,
tensor_shape.width, tensor_shape.channels
]
sys.path.append(os.path.dirname(code_output_path))
module = os.path.splitext(os.path.basename(code_output_path))[0]
class_name = transformer.graph.name
KaffeNet = getattr(__import__(module), class_name)
data_placeholder = tf.placeholder(tf.float32,
tensor_shape_list,
name=input_node)
net = KaffeNet({input_node: data_placeholder})
# load weights stored in numpy format
net.load(data_output_path, sess)
print_stderr('Saving checkpoint...')
saver = tf.train.Saver()
saver.save(sess, checkpoint_path)
print_stderr('Saving graph definition as protobuf...')
tf.train.write_graph(sess.graph.as_graph_def(), graph_folder,
graph_name, False)
input_graph_path = standalone_output_path
input_saver_def_path = ""
input_binary = True
input_checkpoint_path = checkpoint_path
output_node_names = output_node
restore_op_name = 'save/restore_all'
filename_tensor_name = 'save/Const:0'
output_graph_path = standalone_output_path
clear_devices = True
print_stderr('Saving standalone model...')
freeze_graph(input_graph_path, input_saver_def_path, input_binary,
input_checkpoint_path, output_node_names,
restore_op_name, filename_tensor_name,
output_graph_path, clear_devices, '')
shutil.rmtree(temp_folder)
print_stderr('Done.')
except KaffeError as err:
fatal_error('Error encountered: {}'.format(err))
def convert(def_path, caffemodel_path, data_output_path, code_output_path, standalone_output_path,
phase, freeze):
try:
sess = tf.InteractiveSession()
transformer = TensorFlowTransformer(def_path, caffemodel_path, phase=phase)
print_stderr('Converting data...')
if data_output_path is not None:
data = transformer.transform_data()
print_stderr('Saving data...')
with open(data_output_path, 'wb') as handle:
pickle.dump(data, handle, protocol=pickle.HIGHEST_PROTOCOL)
if code_output_path is not None:
print_stderr('Saving source...')
with open(code_output_path, 'wb') as src_out:
src_out.write(transformer.transform_source())
if standalone_output_path:
filename, _ = os.path.splitext(os.path.basename(standalone_output_path))
temp_folder = os.path.join(os.path.dirname(standalone_output_path), '.tmp')
if not os.path.exists(temp_folder):
os.makedirs(temp_folder)
shutil.rmtree(temp_folder) # Delete old graphs
if data_output_path is None:
data = transformer.transform_data()
print_stderr('Saving data...')
data_output_path = os.path.join(temp_folder, filename) + '.npy'
with open(data_output_path, 'wb') as handle:
pickle.dump(data, handle, protocol=pickle.HIGHEST_PROTOCOL)
if code_output_path is None:
print_stderr('Saving source...')
code_output_path = os.path.join(temp_folder, filename) + '.py'
with open(code_output_path, 'wb') as src_out:
src_out.write(transformer.transform_source())
checkpoint_path = os.path.join(temp_folder, filename + '.ckpt')
graph_name = os.path.basename(standalone_output_path)
graph_folder = os.path.dirname(standalone_output_path)
input_node = transformer.graph.nodes[0].name
output_node = transformer.graph.nodes[-1].name
tensor_shape = transformer.graph.get_node(input_node).output_shape
tensor_shape_list = [tensor_shape.batch_size, tensor_shape.height,
tensor_shape.width, tensor_shape.channels]
sys.path.append(os.path.dirname(code_output_path))
module = os.path.splitext(os.path.basename(code_output_path))[0]
class_name = transformer.graph.name
KaffeNet = getattr(__import__(module), class_name)
data_placeholder = tf.compat.v1.placeholder(
tf.float32, tensor_shape_list, name=input_node)
net = KaffeNet({input_node: data_placeholder})
# load weights stored in numpy format
net.load(data_output_path, sess)
print_stderr('Saving checkpoint...')
saver = tf.compat.v1.train.Saver()
saver.save(sess, checkpoint_path)
print_stderr('Saving graph definition as protobuf...')
tf.io.write_graph(sess.graph.as_graph_def(), graph_folder, graph_name, False)
writer = tf.compat.v1.summary.FileWriter('.tmp', sess.graph)
writer.close()
input_graph_path = standalone_output_path
input_saver_def_path = ""
input_binary = True
input_checkpoint_path = checkpoint_path
output_node_names = output_node
restore_op_name = 'save/restore_all'
filename_tensor_name = 'save/Const:0'
output_graph_path = standalone_output_path
clear_devices = True
print_stderr('Saving standalone model...')
output_node_names = '{0}/{0}'.format(output_node_names)
if freeze == 'freeze_graph':
freeze_graph(input_graph_path, input_saver_def_path,
input_binary, input_checkpoint_path,
output_node_names, restore_op_name,
filename_tensor_name, output_graph_path,
clear_devices, '')
elif freeze == 'optimize_for_inference':
graph_def = sess.graph.as_graph_def()
graph_def = tf.graph_util.convert_variables_to_constants(
sess, graph_def, [output_node_names])
graph_def_f32 = optimize_for_inference_lib.optimize_for_inference(
graph_def, ['data'], [output_node_names], tf.float32.as_datatype_enum)
tf.train.write_graph(
graph_def_f32, "", standalone_output_path.rsplit('.',1)[0] + '.pb', as_text=False)
tf.train.write_graph(
graph_def_f32, "", standalone_output_path.rsplit('.',1)[0] + '.pbtxt', as_text=True)
#f = shutil.rmtree(temp_folder)
writer = tf.compat.v1.summary.FileWriter('.tmp', sess.graph)
writer.close()
print_stderr('Done.')
except KaffeError as err:
fatal_error('Error encountered: {}'.format(err))
