aws / sagemaker-huggingface-inference-toolkit

Intro

Conditional complexity (also called cyclomatic complexity) is a term used to measure the complexity of software. The term refers to the number of possible paths through a program function. A higher value ofter means higher maintenance and testing costs (infosecinstitute.com).
Conditional complexity is calculated by counting all conditions in the program that can affect the execution path (e.g. if statement, loops, switches, and/or operators, try and catch blocks...).
Conditional complexity is measured at the unit level (methods, functions...).
Units are classified in four categories based on the measured McCabe index: 1-5 (simple units), 6-10 (medium complex units), 11-25 (complex units), 26+ (very complex units).

Learn more...

Conditional Complexity Overall

There are 45 units with 524 lines of code in units (61.3% of code).

0 very complex units (0 lines of code)
0 complex units (0 lines of code)
4 medium complex units (170 lines of code)
6 simple units (89 lines of code)
35 very simple units (265 lines of code)

Legend:

51+

26-50

11-25

6-10

1-5

Alternative Visuals

3D view of all units

Conditional Complexity per Extension

51+

26-50

11-25

6-10

1-5

Conditional Complexity per Logical Component

primary logical decomposition

51+

26-50

11-25

6-10

1-5

Most Complex Units

Top 45 most complex units

Unit	# lines	McCabe index	# params
def start_model_server() in src/sagemaker_huggingface_inference_toolkit/mms_model_server.py	47	14	1
def get_input_shapes() in src/sagemaker_huggingface_inference_toolkit/optimum_utils.py	41	14	1
def get_pipeline() in src/sagemaker_huggingface_inference_toolkit/transformers_utils.py	34	12	4
def validate_and_initialize_user_module() in src/sagemaker_huggingface_inference_toolkit/handler_service.py	48	11	1
def handle() in src/sagemaker_huggingface_inference_toolkit/handler_service.py	25	8	3
def __init__() in src/sagemaker_huggingface_inference_toolkit/diffusers_utils.py	10	6	3
def get_optimum_neuron_pipeline() in src/sagemaker_huggingface_inference_toolkit/optimum_utils.py	16	6	2
def _build_storage_path() in src/sagemaker_huggingface_inference_toolkit/transformers_utils.py	10	6	3
def decode_csv() in src/sagemaker_huggingface_inference_toolkit/decoder_encoder.py	12	6	1
def default() in src/sagemaker_huggingface_inference_toolkit/decoder_encoder.py	16	6	2
def preprocess() in src/sagemaker_huggingface_inference_toolkit/handler_service.py	11	5	4
def _is_gpu_available() in src/sagemaker_huggingface_inference_toolkit/transformers_utils.py	11	4	0
def infer_task_from_model_architecture() in src/sagemaker_huggingface_inference_toolkit/transformers_utils.py	16	4	2
def load() in src/sagemaker_huggingface_inference_toolkit/handler_service.py	15	4	3
def function_extra_arg() in src/sagemaker_huggingface_inference_toolkit/handler_service.py	19	4	3
def strtobool() in src/sagemaker_huggingface_inference_toolkit/transformers_utils.py	8	3	1
def _get_framework() in src/sagemaker_huggingface_inference_toolkit/transformers_utils.py	11	3	0
def predict() in src/sagemaker_huggingface_inference_toolkit/handler_service.py	8	3	4
def decode() in src/sagemaker_huggingface_inference_toolkit/decoder_encoder.py	8	3	2
def _retry_if_error() in src/sagemaker_huggingface_inference_toolkit/serving.py	2	2	1
def _adapt_to_mms_format() in src/sagemaker_huggingface_inference_toolkit/mms_model_server.py	20	2	2
def get_diffusers_pipeline() in src/sagemaker_huggingface_inference_toolkit/diffusers_utils.py	4	2	4
def create_artifact_filter() in src/sagemaker_huggingface_inference_toolkit/transformers_utils.py	8	2	1
def infer_task_from_hub() in src/sagemaker_huggingface_inference_toolkit/transformers_utils.py	10	2	3
def get_device() in src/sagemaker_huggingface_inference_toolkit/handler_service.py	5	2	1
def log_func_implementation_found_or_not() in src/sagemaker_huggingface_inference_toolkit/handler_service.py	9	2	2
def encode_csv() in src/sagemaker_huggingface_inference_toolkit/decoder_encoder.py	9	2	2
def encode_image() in src/sagemaker_huggingface_inference_toolkit/decoder_encoder.py	5	2	2
def encode() in src/sagemaker_huggingface_inference_toolkit/decoder_encoder.py	6	2	2
def _start_mms() in src/sagemaker_huggingface_inference_toolkit/serving.py	2	1	0
def main() in src/sagemaker_huggingface_inference_toolkit/serving.py	2	1	0
def is_diffusers_available() in src/sagemaker_huggingface_inference_toolkit/diffusers_utils.py	2	1	0
def __call__() in src/sagemaker_huggingface_inference_toolkit/diffusers_utils.py	4	1	0
def is_optimum_neuron_available() in src/sagemaker_huggingface_inference_toolkit/optimum_utils.py	2	1	0
def is_aws_neuron_available() in src/sagemaker_huggingface_inference_toolkit/transformers_utils.py	2	1	0
def _load_model_from_hub() in src/sagemaker_huggingface_inference_toolkit/transformers_utils.py	2	1	0
def __init__() in src/sagemaker_huggingface_inference_toolkit/handler_service.py	16	1	1
def initialize() in src/sagemaker_huggingface_inference_toolkit/handler_service.py	12	1	2
def postprocess() in src/sagemaker_huggingface_inference_toolkit/handler_service.py	2	1	4
def transform_fn() in src/sagemaker_huggingface_inference_toolkit/handler_service.py	14	1	6
def decode_json() in src/sagemaker_huggingface_inference_toolkit/decoder_encoder.py	2	1	1
def decode_image() in src/sagemaker_huggingface_inference_toolkit/decoder_encoder.py	3	1	1
def decode_audio() in src/sagemaker_huggingface_inference_toolkit/decoder_encoder.py	2	1	1
def encode_json() in src/sagemaker_huggingface_inference_toolkit/decoder_encoder.py	9	1	2
def _array_to_npy() in src/sagemaker_huggingface_inference_toolkit/decoder_encoder.py	4	1	2