qubvel-org/segmentation_models.pytorch

19.4

Adjusted Score

19.4

Raw Score

100%

Time Factor

2026-07-13

Last Push

11.7K

Stars

Python

Language

20.4K

Lines of Code

149

Files

255

Pattern Hits

2026-07-14

Scan Date

0.07

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 11MEDIUM 33LOW 211

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 255 distinct pattern matches across 12 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Decorative Section Separators21 hits · 85 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	examples/binary_segmentation_buildings.py	63	# ----------------------------	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	65	# ----------------------------	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	72	# ----------------------------	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	74	# ----------------------------	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	88	# ----------------------------	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	90	# ----------------------------	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	99	# ----------------------------	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	101	# ----------------------------	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	374	# ----------------------------	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	376	# ----------------------------	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	410	# ----------------------------	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	412	# ----------------------------	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	421	# ----------------------------	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	423	# ----------------------------	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	451	# ----------------------------	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	453	# ----------------------------	COMMENT
MEDIUM	segmentation_models_pytorch/encoders/mix_transformer.py	1	# ---------------------------------------------------------------	COMMENT
MEDIUM	segmentation_models_pytorch/encoders/mix_transformer.py	10	# ---------------------------------------------------------------	COMMENT
MEDIUM	segmentation_models_pytorch/encoders/mix_transformer.py	521	# ---------------------------------------------------------------	COMMENT
MEDIUM	segmentation_models_pytorch/encoders/mix_transformer.py	523	# ---------------------------------------------------------------	COMMENT
MEDIUM	segmentation_models_pytorch/encoders/_xception.py	188	# #-----------------------------	COMMENT

Hyper-Verbose Identifiers59 hits · 63 pts

Severity	File	Line	Snippet	Context
LOW	misc/generate_table_timm.py	5	def check_features_and_reduction(name):	CODE
LOW	misc/generate_table_timm.py	20	def valid_vit_encoder_for_dpt(name):	CODE
LOW	tests/conftest.py	7	def pytest_collection_modifyitems(config, items):	CODE
LOW	tests/test_losses.py	16	def test_focal_loss_from_logits_false_multiclass():	CODE
LOW	tests/test_losses.py	42	def test_focal_loss_with_logits():	CODE
LOW	tests/test_losses.py	52	def test_softmax_focal_loss_with_logits():	CODE
LOW	tests/test_losses.py	241	def test_multiclass_jaccard_loss():	CODE
LOW	tests/test_losses.py	268	def test_multilabel_jaccard_loss():	CODE
LOW	tests/test_losses.py	365	def test_class_weights_uniform_equivalent_to_no_weights_multiclass():	CODE
LOW	tests/test_losses.py	383	def test_class_weights_uniform_equivalent_to_no_weights_multilabel():	CODE
LOW	tests/test_losses.py	401	def test_class_weights_nonuniform_changes_loss_multiclass():	CODE
LOW	tests/test_losses.py	418	def test_class_weights_scale_invariant_multiclass():	CODE
LOW	tests/test_losses.py	438	def test_class_weights_binary_mode_raises():	CODE
LOW	tests/test_losses.py	446	def test_focal_class_weights_uniform_equivalent_to_no_weights():	CODE
LOW	tests/test_losses.py	461	def test_focal_class_weights_scale_invariant():	CODE
LOW	tests/test_preprocessing.py	39	def test_preprocessing_params():	CODE
LOW⚡	tests/utils.py	31	def requires_timm_greater_or_equal(version: str):	CODE
LOW⚡	tests/utils.py	40	def requires_torch_greater_or_equal(version: str):	CODE
LOW⚡	tests/utils.py	49	def check_run_test_on_diff_or_main(filepath_patterns: List[str]):	CODE
LOW	tests/utils.py	72	def check_two_models_strictly_equal(	CODE
LOW	tests/test_base.py	8	def test_from_pretrained_with_mismatched_keys():	CODE
LOW	tests/models/test_linknet.py	12	def test_timm_transformer_style_encoder(self):	CODE
LOW	tests/models/test_unetplusplus.py	11	def test_timm_transformer_style_encoder(self):	CODE
LOW	tests/models/base.py	94	def test_in_channels_and_depth_and_out_classes(	CODE
LOW	tests/models/base.py	174	def test_save_load_with_hub_mixin(self):	CODE
LOW	tests/models/base.py	207	def test_preserve_forward_output(self):	CODE
LOW	tests/encoders/test_common.py	13	def test_load_encoder_from_hub(encoder_name_and_weights):	CODE
LOW	tests/encoders/test_batchnorm_deprecation.py	11	def test_seg_models_before_after_use_norm(model_name, decoder_option):	CODE
LOW	tests/encoders/test_batchnorm_deprecation.py	35	def test_pspnet_before_after_use_norm(decoder_option):	CODE
LOW⚡	tests/encoders/test_timm_universal.py	28	def test_string_weights_emits_warning(self):	CODE
LOW⚡	tests/encoders/test_timm_universal.py	32	def test_true_weights_no_warning(self):	CODE
LOW⚡	tests/encoders/test_timm_universal.py	37	def test_none_weights_no_warning(self):	CODE
LOW	tests/encoders/base.py	47	def get_features_output_strides(self, sample, features):	CODE
LOW⚡	tests/base/test_freeze_encoder.py	5	def test_freeze_and_unfreeze_encoder():	CODE
LOW⚡	tests/base/test_freeze_encoder.py	8	def assert_encoder_params_trainable(expected: bool):	CODE
LOW⚡	tests/base/test_freeze_encoder.py	11	def assert_norm_layers_training(expected: bool):	CODE
LOW	tests/base/test_freeze_encoder.py	50	def test_freeze_encoder_stops_running_stats():	CODE
LOW	examples/binary_segmentation_buildings.py	247	def train_and_evaluate_one_epoch(	CODE
LOW	scripts/models-conversions/upernet-hf-to-smp.py	120	def convert_old_keys_to_new_keys(state_dict_keys: dict, keys_mapping: dict):	CODE
LOW	…odels-conversions/segformer-original-decoder-to-smp.py	13	def convert_state_dict_to_smp(state_dict: dict):	CODE
LOW	segmentation_models_pytorch/metrics/functional.py	357	def _positive_predictive_value(tp, fp, fn, tn):	CODE
LOW	segmentation_models_pytorch/metrics/functional.py	361	def _negative_predictive_value(tp, fp, fn, tn):	CODE
LOW	segmentation_models_pytorch/metrics/functional.py	381	def _positive_likelihood_ratio(tp, fp, fn, tn):	CODE
LOW	segmentation_models_pytorch/metrics/functional.py	385	def _negative_likelihood_ratio(tp, fp, fn, tn):	CODE
LOW	segmentation_models_pytorch/metrics/functional.py	546	def positive_predictive_value(	CODE
LOW	segmentation_models_pytorch/metrics/functional.py	568	def negative_predictive_value(	CODE
LOW	segmentation_models_pytorch/metrics/functional.py	678	def positive_likelihood_ratio(	CODE
LOW	segmentation_models_pytorch/metrics/functional.py	700	def negative_likelihood_ratio(	CODE
LOW	segmentation_models_pytorch/losses/_functional.py	100	def softmax_focal_loss_with_logits(	CODE
LOW	segmentation_models_pytorch/encoders/timm_vit.py	10	def sample_block_indices_uniformly(n: int, total_num_blocks: int) -> list[int]:	CODE
LOW	segmentation_models_pytorch/encoders/timm_vit.py	35	def preprocess_output_indices(	CODE
LOW	segmentation_models_pytorch/encoders/timm_vit.py	149	def _forward_with_prefix_tokens(	CODE
LOW	segmentation_models_pytorch/encoders/timm_vit.py	164	def _forward_without_prefix_tokens(self, x: torch.Tensor) -> list[torch.Tensor]:	CODE
LOW	segmentation_models_pytorch/encoders/__init__.py	58	def is_equivalent_to_timm_universal(name):	CODE
LOW	…mentation_models_pytorch/encoders/timm_efficientnet.py	57	def gen_efficientnet_lite_kwargs(	CODE
LOW	segmentation_models_pytorch/encoders/timm_universal.py	232	def _merge_kwargs_no_duplicates(a: dict[str, Any], b: dict[str, Any]) -> dict[str, Any]:	CODE
LOW	segmentation_models_pytorch/encoders/_efficientnet.py	436	def get_width_and_height_from_size(x):	CODE
LOW	segmentation_models_pytorch/encoders/_efficientnet.py	453	def calculate_output_image_size(input_image_size, stride):	CODE
LOW	segmentation_models_pytorch/encoders/_utils.py	46	def replace_strides_with_dilation(module, dilation_rate):	CODE

Unused Imports61 hits · 61 pts

Severity	File	Line	Context
LOW	segmentation_models_pytorch/__init__.py	1	CODE
LOW	segmentation_models_pytorch/__init__.py	2	CODE
LOW	segmentation_models_pytorch/__init__.py	3	CODE
LOW	segmentation_models_pytorch/__init__.py	4	CODE
LOW	segmentation_models_pytorch/__init__.py	5	CODE
LOW	segmentation_models_pytorch/__init__.py	18	CODE
LOW	segmentation_models_pytorch/__init__.py	20	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	2	CODE
LOW	segmentation_models_pytorch/losses/lovasz.py	6	CODE
LOW	segmentation_models_pytorch/losses/lovasz.py	6	CODE
LOW	segmentation_models_pytorch/losses/__init__.py	1	CODE
LOW	segmentation_models_pytorch/losses/__init__.py	1	CODE
LOW	segmentation_models_pytorch/losses/__init__.py	1	CODE
LOW	segmentation_models_pytorch/losses/__init__.py	3	CODE
LOW	segmentation_models_pytorch/losses/__init__.py	4	CODE
LOW	segmentation_models_pytorch/losses/__init__.py	5	CODE
LOW	segmentation_models_pytorch/losses/__init__.py	6	CODE
LOW	segmentation_models_pytorch/losses/__init__.py	7	CODE
LOW	segmentation_models_pytorch/losses/__init__.py	8	CODE
LOW	segmentation_models_pytorch/losses/__init__.py	9	CODE
LOW	segmentation_models_pytorch/losses/__init__.py	10	CODE
LOW	segmentation_models_pytorch/datasets/__init__.py	1	CODE
LOW	segmentation_models_pytorch/datasets/__init__.py	1	CODE
LOW	segmentation_models_pytorch/utils/__init__.py	3	CODE
LOW	segmentation_models_pytorch/utils/__init__.py	4	CODE
LOW	segmentation_models_pytorch/utils/__init__.py	5	CODE
LOW	segmentation_models_pytorch/encoders/__init__.py	28	CODE
LOW	…gmentation_models_pytorch/decoders/linknet/__init__.py	1	CODE
LOW	…ation_models_pytorch/decoders/unetplusplus/__init__.py	1	CODE
LOW	segmentation_models_pytorch/decoders/pspnet/__init__.py	1	CODE
LOW	segmentation_models_pytorch/decoders/dpt/__init__.py	1	CODE
LOW	segmentation_models_pytorch/decoders/manet/__init__.py	1	CODE
LOW	segmentation_models_pytorch/decoders/unet/__init__.py	1	CODE
LOW	…entation_models_pytorch/decoders/segformer/__init__.py	1	CODE
LOW	…gmentation_models_pytorch/decoders/upernet/__init__.py	1	CODE
LOW	…entation_models_pytorch/decoders/deeplabv3/__init__.py	1	CODE
LOW	…entation_models_pytorch/decoders/deeplabv3/__init__.py	1	CODE
LOW	segmentation_models_pytorch/decoders/fpn/__init__.py	1	CODE
LOW	segmentation_models_pytorch/decoders/pan/__init__.py	1	CODE
LOW	segmentation_models_pytorch/base/__init__.py	1	CODE
LOW	segmentation_models_pytorch/base/__init__.py	3	CODE
LOW	segmentation_models_pytorch/base/__init__.py	3	CODE
LOW	segmentation_models_pytorch/base/__init__.py	5	CODE
1 more matches not shown…

Cross-File Repetition9 hits · 45 pts

Severity	File	Snippet	Context
HIGH	segmentation_models_pytorch/encoders/vgg.py	each encoder should have following attributes and methods and be inherited from `_base.encodermixin` attributes: _out_ch	STRING
HIGH	segmentation_models_pytorch/encoders/senet.py	each encoder should have following attributes and methods and be inherited from `_base.encodermixin` attributes: _out_ch	STRING
HIGH	segmentation_models_pytorch/encoders/densenet.py	each encoder should have following attributes and methods and be inherited from `_base.encodermixin` attributes: _out_ch	STRING
HIGH	segmentation_models_pytorch/encoders/inceptionv4.py	each encoder should have following attributes and methods and be inherited from `_base.encodermixin` attributes: _out_ch	STRING
HIGH	segmentation_models_pytorch/encoders/efficientnet.py	each encoder should have following attributes and methods and be inherited from `_base.encodermixin` attributes: _out_ch	STRING
HIGH	segmentation_models_pytorch/encoders/mobilenet.py	each encoder should have following attributes and methods and be inherited from `_base.encodermixin` attributes: _out_ch	STRING
HIGH	segmentation_models_pytorch/encoders/resnet.py	each encoder should have following attributes and methods and be inherited from `_base.encodermixin` attributes: _out_ch	STRING
HIGH	…mentation_models_pytorch/encoders/inceptionresnetv2.py	each encoder should have following attributes and methods and be inherited from `_base.encodermixin` attributes: _out_ch	STRING
HIGH	segmentation_models_pytorch/encoders/dpn.py	each encoder should have following attributes and methods and be inherited from `_base.encodermixin` attributes: _out_ch	STRING

AI Structural Patterns35 hits · 35 pts

Severity	File	Line	Context
LOW	segmentation_models_pytorch/losses/focal.py	13	CODE
LOW	segmentation_models_pytorch/losses/tversky.py	37	CODE
LOW	segmentation_models_pytorch/encoders/_dpn.py	164	CODE
LOW	segmentation_models_pytorch/encoders/_senet.py	56	CODE
LOW	segmentation_models_pytorch/encoders/mix_transformer.py	165	CODE
LOW	segmentation_models_pytorch/encoders/mix_transformer.py	272	CODE
LOW	segmentation_models_pytorch/encoders/_inceptionv4.py	42	CODE
LOW	segmentation_models_pytorch/encoders/_inceptionv4.py	65	CODE
LOW	segmentation_models_pytorch/encoders/_inceptionv4.py	78	CODE
LOW	segmentation_models_pytorch/encoders/_inceptionv4.py	108	CODE
LOW	segmentation_models_pytorch/encoders/_inceptionv4.py	129	CODE
LOW	segmentation_models_pytorch/encoders/_inceptionv4.py	162	CODE
LOW	segmentation_models_pytorch/encoders/_inceptionv4.py	188	CODE
LOW	segmentation_models_pytorch/encoders/_inceptionv4.py	242	CODE
LOW	…entation_models_pytorch/encoders/_inceptionresnetv2.py	59	CODE
LOW	…entation_models_pytorch/encoders/_inceptionresnetv2.py	92	CODE
LOW	…entation_models_pytorch/encoders/_inceptionresnetv2.py	114	CODE
LOW	…entation_models_pytorch/encoders/_inceptionresnetv2.py	141	CODE
LOW	…entation_models_pytorch/encoders/_inceptionresnetv2.py	172	CODE
LOW	segmentation_models_pytorch/encoders/mobileone.py	301	CODE
LOW	segmentation_models_pytorch/encoders/_efficientnet.py	433	CODE
LOW	segmentation_models_pytorch/decoders/linknet/model.py	74	CODE
LOW	…entation_models_pytorch/decoders/unetplusplus/model.py	79	CODE
LOW	segmentation_models_pytorch/decoders/pspnet/model.py	75	CODE
LOW	segmentation_models_pytorch/decoders/dpt/model.py	81	CODE
LOW	segmentation_models_pytorch/decoders/manet/model.py	79	CODE
LOW	segmentation_models_pytorch/decoders/unet/model.py	108	CODE
LOW	…mentation_models_pytorch/decoders/segformer/decoder.py	73	CODE
LOW	segmentation_models_pytorch/decoders/segformer/model.py	52	CODE
LOW	segmentation_models_pytorch/decoders/upernet/decoder.py	211	CODE
LOW	segmentation_models_pytorch/decoders/upernet/model.py	69	CODE
LOW	segmentation_models_pytorch/decoders/deeplabv3/model.py	59	CODE
LOW	segmentation_models_pytorch/decoders/deeplabv3/model.py	185	CODE
LOW	segmentation_models_pytorch/decoders/fpn/model.py	58	CODE
LOW	segmentation_models_pytorch/decoders/pan/model.py	61	CODE

Self-Referential Comments10 hits · 34 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	examples/binary_segmentation_buildings.py	84	# Create a directory to store the output masks	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	89	# Define the hyperparameters	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	100	# Define a custom dataset class for the CamVid dataset	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	375	# Define the data directories and create the datasets	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	411	# Create the dataloaders using the datasets	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	461	# Define the Adam optimizer	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	464	# Define the learning rate scheduler	COMMENT
MEDIUM⚡	examples/binary_segmentation_buildings.py	467	# Define the loss function	COMMENT
MEDIUM	examples/binary_segmentation_buildings.py	193	# Define a class for the CamVid model	COMMENT
MEDIUM	…odels-conversions/segformer-original-decoder-to-smp.py	78	# Create the model	COMMENT

Modern Structural Boilerplate29 hits · 29 pts

Severity	File	Line	Snippet	Context
LOW	segmentation_models_pytorch/__init__.py	72	__all__ = [	CODE
LOW	segmentation_models_pytorch/metrics/__init__.py	23	__all__ = [	CODE
LOW	segmentation_models_pytorch/metrics/functional.py	35	__all__ = [	CODE
LOW	segmentation_models_pytorch/losses/jaccard.py	9	__all__ = ["JaccardLoss"]	CODE
LOW	segmentation_models_pytorch/losses/focal.py	9	__all__ = ["FocalLoss"]	CODE
LOW	segmentation_models_pytorch/losses/soft_ce.py	7	__all__ = ["SoftCrossEntropyLoss"]	CODE
LOW	segmentation_models_pytorch/losses/lovasz.py	19	__all__ = ["LovaszLoss"]	CODE
LOW	segmentation_models_pytorch/losses/__init__.py	12	__all__ = [	CODE
LOW	segmentation_models_pytorch/losses/dice.py	9	__all__ = ["DiceLoss"]	CODE
LOW	segmentation_models_pytorch/losses/tversky.py	8	__all__ = ["TverskyLoss"]	CODE
LOW	segmentation_models_pytorch/losses/_functional.py	10	__all__ = [	CODE
LOW	segmentation_models_pytorch/losses/soft_bce.py	7	__all__ = ["SoftBCEWithLogitsLoss"]	CODE
LOW	segmentation_models_pytorch/datasets/__init__.py	3	__all__ = ["OxfordPetDataset", "SimpleOxfordPetDataset"]	CODE
LOW	segmentation_models_pytorch/utils/__init__.py	7	__all__ = ["train", "losses", "metrics"]	CODE
LOW	segmentation_models_pytorch/encoders/__init__.py	33	__all__ = [	CODE
LOW	segmentation_models_pytorch/encoders/mobileone.py	15	__all__ = ["MobileOne", "reparameterize_model"]	CODE
LOW	…gmentation_models_pytorch/decoders/linknet/__init__.py	3	__all__ = ["Linknet"]	CODE
LOW	…ation_models_pytorch/decoders/unetplusplus/__init__.py	3	__all__ = ["UnetPlusPlus"]	CODE
LOW	segmentation_models_pytorch/decoders/pspnet/__init__.py	3	__all__ = ["PSPNet"]	CODE
LOW	segmentation_models_pytorch/decoders/dpt/__init__.py	3	__all__ = ["DPT"]	CODE
LOW	segmentation_models_pytorch/decoders/manet/__init__.py	3	__all__ = ["MAnet"]	CODE
LOW	segmentation_models_pytorch/decoders/unet/__init__.py	3	__all__ = ["Unet"]	CODE
LOW	…entation_models_pytorch/decoders/segformer/__init__.py	3	__all__ = ["Segformer"]	CODE
LOW	…gmentation_models_pytorch/decoders/upernet/__init__.py	3	__all__ = ["UPerNet"]	CODE
LOW	…mentation_models_pytorch/decoders/deeplabv3/decoder.py	40	__all__ = ["DeepLabV3Decoder", "DeepLabV3PlusDecoder"]	CODE
LOW	…entation_models_pytorch/decoders/deeplabv3/__init__.py	3	__all__ = ["DeepLabV3", "DeepLabV3Plus"]	CODE
LOW	segmentation_models_pytorch/decoders/fpn/__init__.py	3	__all__ = ["FPN"]	CODE
LOW	segmentation_models_pytorch/decoders/pan/__init__.py	3	__all__ = ["PAN"]	CODE
LOW	segmentation_models_pytorch/base/__init__.py	7	__all__ = [	CODE

Excessive Try-Catch Wrapping11 hits · 14 pts

Severity	File	Line	Snippet	Context
LOW	misc/generate_table_timm.py	16	except Exception:	CODE
LOW	misc/generate_table_timm.py	97	except Exception:	CODE
LOW	misc/generate_table_timm.py	101	except Exception:	CODE
MEDIUM	misc/generate_table_timm.py	11	def has_dilation_support(name):	CODE
LOW⚡	tests/utils.py	58	except Exception:	CODE
LOW	segmentation_models_pytorch/encoders/__init__.py	139	except Exception as e:	CODE
LOW	segmentation_models_pytorch/encoders/__init__.py	193	except Exception as e:	CODE
LOW	segmentation_models_pytorch/encoders/timm_universal.py	98	except Exception:	CODE
LOW	segmentation_models_pytorch/base/utils.py	8	except Exception:	CODE
LOW	segmentation_models_pytorch/base/utils.py	13	except Exception:	CODE
MEDIUM	segmentation_models_pytorch/base/utils.py	5	def is_torch_compiling():	CODE

Deep Nesting12 hits · 12 pts

Severity	File	Line	Context
LOW	segmentation_models_pytorch/metrics/functional.py	255	CODE
LOW	segmentation_models_pytorch/losses/focal.py	77	CODE
LOW	segmentation_models_pytorch/encoders/_dpn.py	279	CODE
LOW	segmentation_models_pytorch/encoders/mix_transformer.py	113	CODE
LOW	segmentation_models_pytorch/encoders/mix_transformer.py	203	CODE
LOW	segmentation_models_pytorch/encoders/mix_transformer.py	250	CODE
LOW	segmentation_models_pytorch/encoders/mix_transformer.py	413	CODE
LOW	segmentation_models_pytorch/decoders/deeplabv3/model.py	125	CODE
LOW	segmentation_models_pytorch/base/model.py	97	CODE
LOW	segmentation_models_pytorch/base/initialization.py	4	CODE
LOW	segmentation_models_pytorch/base/modules.py	12	CODE
LOW	segmentation_models_pytorch/base/modules.py	152	CODE

Docstring Block Structure2 hits · 10 pts

Severity	File	Line	Snippet	Context
HIGH	segmentation_models_pytorch/metrics/functional.py	70	Compute true positive, false positive, false negative, true negative 'pixels' for each image and each class. Ar	STRING
HIGH	segmentation_models_pytorch/encoders/_efficientnet.py	728	Get a block through a string notation of arguments. Args: block_string (str): A string notation of	STRING

Redundant / Tautological Comments3 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW	tests/conftest.py	11	# Check if the test has no marks	COMMENT
LOW	segmentation_models_pytorch/encoders/timm_universal.py	101	# Check if model output is in channel-last format (NHWC)	COMMENT
LOW	segmentation_models_pytorch/encoders/mobileone.py	104	# Check if SE-ReLU is requested	COMMENT

Over-Commented Block3 hits · 3 pts

Severity	File	Line	Snippet	Context
LOW	docs/conf.py	1	# Configuration file for the Sphinx documentation builder.	COMMENT
LOW	segmentation_models_pytorch/losses/constants.py	1	#: Loss binary mode suppose you are solving binary segmentation task.	COMMENT
LOW	segmentation_models_pytorch/encoders/_efficientnet.py	341	################################################################################	COMMENT