def convert(tf_path, output_dir, version, half, align=False,
input_path=None, refer_path=None, debug_mode: bool = False):
checker.check_file_exist(tf_path)
model_name = os.path.basename(tf_path)
if output_dir is None or not os.path.isdir(output_dir):
output_dir = os.path.dirname(tf_path)
checker.check_file_exist(output_dir)
model_name = model_name[:-len(".tflite")]
if tflite2tnn(tf_path, output_dir, half) is False:
logging.error("Oh No, tflite2tnn failed :(\n")
sys.exit(return_code.CONVERT_FAILED)
else:
logging.info("Convert TensorFlowLite to TNN model succeed!\n")
if version is None:
version = "v1.0"
if align == 'output':
proto_suffix = '.tnnproto'
model_suffix = '.tnnmodel'
tnn_proto_name = model_name + proto_suffix
tnn_model_name = model_name + model_suffix
tnn_proto_path = os.path.join(output_dir, tnn_proto_name)
tnn_model_path = os.path.join(output_dir, tnn_model_name)
align_model.align_model(tf_path, tnn_proto_path, tnn_model_path, input_path, refer_path, None, True,
debug_mode=debug_mode)
def convert(proto_path,
model_path,
output_dir,
version,
optimize,
half,
align=False,
input_path=None,
refer_path=None):
logging.info("Converter Caffe to ONNX Model\n")
checker.check_file_exist(proto_path)
checker.check_file_exist(model_path)
if output_dir is None:
output_dir = os.path.dirname(proto_path)
checker.check_file_exist(output_dir)
proto_name = os.path.basename(proto_path)
proto_name = proto_name[:-len(".prototxt")]
onnx_path = os.path.join(output_dir, proto_name + ".onnx")
if caffe2onnx(proto_path, model_path, onnx_path) is False:
logging.error("Oh No, caff2onnx failed :(\n")
sys.exit(return_code.CONVERT_FAILED)
else:
logging.info("Congratulations! caffe2onnx succeed!\n")
if version is None:
version = "v1.0"
is_ssd = checker.is_ssd_model(proto_path)
if is_ssd:
onnx2tnn.convert(onnx_path,
output_dir,
version,
False,
half,
is_ssd=True)
else:
onnx2tnn.convert(onnx_path, output_dir, version, optimize, half)
if is_ssd and ((input_path is None) or (refer_path is None)):
align = False
optimize = False
if align is True:
proto_suffix = '.tnnproto'
model_suffix = '.tnnmodel'
onnx_base_name = os.path.basename(onnx_path)
if optimize is True:
tnn_proto_name = onnx_base_name[:-len('.onnx'
)] + '.opt' + proto_suffix
tnn_model_name = onnx_base_name[:-len('.onnx'
)] + '.opt' + model_suffix
else:
tnn_proto_name = onnx_base_name[:-len('.onnx')] + proto_suffix
tnn_model_name = onnx_base_name[:-len('.onnx')] + model_suffix
tnn_proto_path = os.path.join(output_dir, tnn_proto_name)
tnn_model_path = os.path.join(output_dir, tnn_model_name)
align_model.align_model(onnx_path, tnn_proto_path, tnn_model_path,
input_path, refer_path)
def convert(tf_path,
input_names,
output_names,
output_dir,
version,
optimize,
half,
align=False,
not_fold_const=False,
input_path=None,
refer_path=None,
debug: bool = False,
debug_mode: bool = False):
logging.info("Converter Tensorflow to TNN model\n")
checker.check_file_exist(tf_path)
model_name = os.path.basename(tf_path)
if output_dir is None or not os.path.isdir(output_dir):
output_dir = os.path.dirname(tf_path)
checker.check_file_exist(output_dir)
model_name = model_name[:-len(".pb")]
onnx_path = os.path.join(output_dir, model_name + ".onnx")
if tf2onnx(tf_path, input_names, output_names, onnx_path,
not_fold_const) is False:
logging.error("Oh No, tf2onnx failed :(\n")
sys.exit(return_code.CONVERT_FAILED)
else:
logging.info("Convert TensorFlow to ONNX model succeed!\n")
if version is None:
version = time.strftime('%Y%m%d%H%M', time.localtime())
checker.check_file_exist(onnx_path)
onnx2tnn.convert(onnx_path, output_dir, version, optimize, half)
if align is True:
proto_suffix = '.tnnproto'
model_suffix = '.tnnmodel'
onnx_base_name = os.path.basename(onnx_path)
if optimize is True:
tnn_proto_name = onnx_base_name[:-len('.onnx'
)] + '.opt' + proto_suffix
tnn_model_name = onnx_base_name[:-len('.onnx'
)] + '.opt' + model_suffix
else:
tnn_proto_name = onnx_base_name[:-len('.onnx')] + proto_suffix
tnn_model_name = onnx_base_name[:-len('.onnx')] + model_suffix
tnn_proto_path = os.path.join(output_dir, tnn_proto_name)
tnn_model_path = os.path.join(output_dir, tnn_model_name)
align_model.align_model(onnx_path,
tnn_proto_path,
tnn_model_path,
input_path,
refer_path,
debug_mode=debug_mode)
onnx_base_name = os.path.basename(onnx_path)
tnn_proto_name = onnx_base_name[:-len('.onnx')] + (
'.opt.tnnproto' if optimize else ".tnnproto")
tnn_proto_path = os.path.join(output_dir, tnn_proto_name)
fix_tnn_output.fix_tnn_output(tnn_proto_path)
def convert(onnx_path,
output_dir=None,
version="v1.0",
optimize=True,
half=False,
align=False,
input_path=None,
refer_path=None,
input_names: str = None,
is_ssd=False):
"""
执行 onnx 转换为 tnn 的转换指令
:parameter:
onnx_path: 需要转换的 onnx 文件的路径
output_path: 生成的 tnn 文件的路径
version: 转换模型的版本号
optimize: 是否需要对模型进行优化,默认是需要进行优化
half: 是否需要转为 FP16 的模型,减小模型的大小
:return return_code
:exception 执行超时
"""
logging.info("Converter ONNX to TNN Model\n")
checker.check_file_exist(onnx_path)
if not is_ssd:
ret, current_shape = checker.check_onnx_dim(onnx_path)
if ret is False and current_shape is not None:
if input_names is None:
throw_exception(current_shape)
if input_names is not None and not ("[" in input_names
and "]" in input_names):
throw_exception(current_shape)
proto_suffix = '.tnnproto'
model_suffix = '.tnnmodel'
command = "python3 onnx2tnn.py " + onnx_path
command = command + " -version=v1.0"
checker.check_file_exist(onnx_path)
if optimize is True:
command = command + " -optimize=1"
else:
command = command + " -optimize=0"
if half is True:
command = command + " -half=1"
else:
command = command + " -half=0"
if output_dir is None:
output_dir = os.path.dirname(onnx_path)
checker.check_file_exist(output_dir)
command = command + " -o " + output_dir
if input_names is not None:
new_input_names = ""
for char in input_names:
if char == "[":
char = ":"
if char == "]":
continue
new_input_names += char
command = command + " -input_shape " + new_input_names
logging.debug("The onnx2tnn command:" + command + "\n")
work_dir = "../onnx2tnn/onnx-converter/"
result = cmd.run(command, work_dir=work_dir)
if result == 0:
logging.info("Converter ONNX to TNN model succeed!\n")
else:
logging.error("Converter ONNX to TNN model failed!\n")
sys.exit(return_code.CONVERT_FAILED)
onnx_base_name = os.path.basename(onnx_path)
if align is True:
if optimize is True:
tnn_proto_name = onnx_base_name[:-len('.onnx'
)] + '.opt' + proto_suffix
tnn_model_name = onnx_base_name[:-len('.onnx'
)] + '.opt' + model_suffix
else:
tnn_proto_name = onnx_base_name[:-len('.onnx')] + proto_suffix
tnn_model_name = onnx_base_name[:-len('.onnx')] + model_suffix
tnn_proto_path = os.path.join(output_dir, tnn_proto_name)
tnn_model_path = os.path.join(output_dir, tnn_model_name)
if input_names is None:
align_model.align_model(onnx_path, tnn_proto_path, tnn_model_path,
input_path, refer_path)
else:
align_model.align_model(onnx_path, tnn_proto_path, tnn_model_path,
input_path, refer_path, new_input_names)
def convert(onnx_path,
output_dir=None,
version="v1.0",
optimize=True,
half=False,
align='',
align_batch=False,
input_path=None,
refer_path=None,
input_names: str = None,
is_ssd=False,
debug_mode: bool = False):
"""
执行 onnx 转换为 tnn 的转换指令
:parameter:
onnx_path: 需要转换的 onnx 文件的路径
output_path: 生成的 tnn 文件的路径
version: 转换模型的版本号
optimize: 是否需要对模型进行优化,默认是需要进行优化
half: 是否需要转为 FP16 的模型,减小模型的大小
:return return_code
:exception 执行超时
"""
logging.info("Converter ONNX to TNN Model...\n")
checker.check_file_exist(onnx_path)
try:
if not is_ssd:
logging.info("Converter ONNX to TNN check_onnx_dim...\n")
ret, current_shape = checker.check_onnx_dim(onnx_path)
logging.info("Converter ONNX to TNN check_onnx_dim...\n")
if ret is False and current_shape is not None:
if input_names is None:
logging.info("Converter ONNX to TNN current_shape...\n")
throw_exception(current_shape)
if input_names is not None:
input_names = input_names.strip()
if ":" not in input_names and " " not in input_names:
input_names = list(
current_shape.keys())[0] + ":" + input_names
check_input_names(input_names, current_shape)
except Exception as e:
print(e)
logging.error(
"check_onnx_dim failed, next stage of convertion may failed too\n")
proto_suffix = '.tnnproto'
model_suffix = '.tnnmodel'
command = "python3 onnx2tnn.py " + onnx_path
command = command + " -version=" + version
checker.check_file_exist(onnx_path)
if optimize is True:
command = command + " -optimize=1"
else:
command = command + " -optimize=0"
if half is True:
command = command + " -half=1"
else:
command = command + " -half=0"
if output_dir is None:
output_dir = os.path.dirname(onnx_path)
checker.check_file_exist(output_dir)
command = command + " -o " + output_dir
if input_names is not None:
command = command + " -input_shape " + input_names
logging.debug("The onnx2tnn command:" + command + "\n")
work_dir = "../onnx2tnn/onnx-converter/"
result = cmd.run(command, work_dir=work_dir)
if result == 0:
logging.info("Converter ONNX to TNN model succeed!\n")
else:
logging.error("Converter ONNX to TNN model failed!\n")
sys.exit(return_code.CONVERT_FAILED)
onnx_base_name = os.path.basename(onnx_path)
if optimize is True:
tnn_proto_name = onnx_base_name[:-len('.onnx')] + '.opt' + proto_suffix
tnn_model_name = onnx_base_name[:-len('.onnx')] + '.opt' + model_suffix
else:
tnn_proto_name = onnx_base_name[:-len('.onnx')] + proto_suffix
tnn_model_name = onnx_base_name[:-len('.onnx')] + model_suffix
tnn_proto_path = os.path.join(output_dir, tnn_proto_name)
tnn_model_path = os.path.join(output_dir, tnn_model_name)
if align == 'output' or align_batch is True:
if input_names is None:
align_model.align_model(onnx_path,
tnn_proto_path,
tnn_model_path,
input_path,
refer_path,
debug_mode=debug_mode,
align_batch=align_batch)
else:
align_model.align_model(onnx_path,
tnn_proto_path,
tnn_model_path,
input_path,
refer_path,
input_names,
debug_mode=debug_mode,
align_batch=align_batch)
elif align == 'all':
is_align_all = (align == 'all')
align_model.align_all(onnx_path, tnn_proto_path, is_align_all,
input_names, input_path, refer_path)
