SYMBOL INDEX (1050 symbols across 111 files) FILE: RVT/callbacks/custom.py function get_ckpt_callback (line 8) | def get_ckpt_callback(config: DictConfig) -> ModelCheckpoint: function get_viz_callback (line 41) | def get_viz_callback(config: DictConfig) -> Callback: FILE: RVT/callbacks/detection.py class DetectionVizEnum (line 18) | class DetectionVizEnum(Enum): class DetectionVizCallback (line 24) | class DetectionVizCallback(VizCallbackBase): method __init__ (line 25) | def __init__(self, config: DictConfig): method on_train_batch_end_custom (line 36) | def on_train_batch_end_custom( method on_validation_batch_end_custom (line 82) | def on_validation_batch_end_custom(self, batch: Any, outputs: Any): method on_validation_epoch_end_custom (line 100) | def on_validation_epoch_end_custom(self, logger: WandbLogger): FILE: RVT/callbacks/gradflow.py class GradFlowLogCallback (line 10) | class GradFlowLogCallback(Callback): method __init__ (line 11) | def __init__(self, log_every_n_train_steps: int): method on_before_zero_grad (line 17) | def on_before_zero_grad( FILE: RVT/callbacks/utils/visualization.py function get_grad_flow_figure (line 5) | def get_grad_flow_figure(named_params): FILE: RVT/callbacks/viz_base.py class VizCallbackBase (line 16) | class VizCallbackBase(Callback): method __init__ (line 17) | def __init__(self, config: DictConfig, buffer_entries: Type[Enum]): method _reset_buffer (line 30) | def _reset_buffer(self): method add_to_buffer (line 35) | def add_to_buffer(self, key: Enum, value: Union[np.ndarray, th.Tensor]): method get_from_buffer (line 45) | def get_from_buffer(self, key: Enum) -> List[th.Tensor]: method on_train_batch_end_custom (line 51) | def on_train_batch_end_custom( method on_validation_batch_end_custom (line 61) | def on_validation_batch_end_custom(self, batch: Any, outputs: Any) -> ... method on_validation_epoch_end_custom (line 64) | def on_validation_epoch_end_custom(self, logger: WandbLogger) -> None: method on_train_batch_end (line 69) | def on_train_batch_end( method on_validation_batch_end (line 103) | def on_validation_batch_end( method on_validation_epoch_start (line 133) | def on_validation_epoch_start( method on_validation_epoch_end (line 139) | def on_validation_epoch_end( method on_train_batch_start (line 162) | def on_train_batch_start( method ev_repr_to_img (line 172) | def ev_repr_to_img(x: np.ndarray): FILE: RVT/config/modifier.py function dynamically_modify_train_config (line 10) | def dynamically_modify_train_config(config: DictConfig): function _get_modified_hw_multiple_of (line 59) | def _get_modified_hw_multiple_of( FILE: RVT/data/genx_utils/collate.py function collate_object_labels (line 10) | def collate_object_labels( function collate_sparsely_batched_object_labels (line 18) | def collate_sparsely_batched_object_labels( function custom_collate (line 33) | def custom_collate(batch: Any): function custom_collate_rnd (line 37) | def custom_collate_rnd(batch: Any): function custom_collate_streaming (line 48) | def custom_collate_streaming(batch: Any): FILE: RVT/data/genx_utils/collate_from_pytorch.py function collate (line 19) | def collate( function collate_tensor_fn (line 117) | def collate_tensor_fn( function collate_tensor_fn (line 134) | def collate_tensor_fn( function collate_numpy_array_fn (line 150) | def collate_numpy_array_fn( function collate_numpy_scalar_fn (line 163) | def collate_numpy_scalar_fn( function collate_float_fn (line 171) | def collate_float_fn( function collate_int_fn (line 179) | def collate_int_fn( function collate_str_fn (line 187) | def collate_str_fn( FILE: RVT/data/genx_utils/dataset_rnd.py class SequenceDataset (line 18) | class SequenceDataset(Dataset): method __init__ (line 19) | def __init__( method only_load_labels (line 65) | def only_load_labels(self): method load_everything (line 68) | def load_everything(self): method __len__ (line 71) | def __len__(self): method __getitem__ (line 74) | def __getitem__(self, index: int) -> LoaderDataDictGenX: class CustomConcatDataset (line 86) | class CustomConcatDataset(ConcatDataset): method __init__ (line 89) | def __init__(self, datasets: Iterable[SequenceDataset]): method only_load_labels (line 92) | def only_load_labels(self): method load_everything (line 96) | def load_everything(self): function build_random_access_dataset (line 101) | def build_random_access_dataset( function get_weighted_random_sampler (line 130) | def get_weighted_random_sampler(dataset: CustomConcatDataset) -> Weighte... FILE: RVT/data/genx_utils/dataset_streaming.py function build_streaming_dataset (line 18) | def build_streaming_dataset( function get_sequences (line 70) | def get_sequences( function partialclass (line 105) | def partialclass(cls, *args, **kwargs): function build_streaming_train_dataset (line 112) | def build_streaming_train_dataset( function build_streaming_evaluation_dataset (line 132) | def build_streaming_evaluation_dataset( FILE: RVT/data/genx_utils/labels.py class ObjectLabelBase (line 12) | class ObjectLabelBase: method __init__ (line 23) | def __init__(self, object_labels: th.Tensor, input_size_hw: Tuple[int,... method clamp_to_frame_ (line 35) | def clamp_to_frame_(self): method remove_flat_labels_ (line 50) | def remove_flat_labels_(self): method create_empty (line 55) | def create_empty(cls): method _assert_not_numpy (line 61) | def _assert_not_numpy(self): method to (line 67) | def to(self, *args, **kwargs): method numpy_ (line 74) | def numpy_(self) -> None: method input_size_hw (line 83) | def input_size_hw(self) -> Tuple[int, int]: method input_size_hw (line 87) | def input_size_hw(self, height_width: Tuple[int, int]): method get (line 94) | def get(self, request: str): method t (line 99) | def t(self): method x (line 103) | def x(self): method x (line 107) | def x(self, value: Union[th.Tensor, np.ndarray]): method y (line 111) | def y(self): method y (line 115) | def y(self, value: Union[th.Tensor, np.ndarray]): method w (line 119) | def w(self): method w (line 123) | def w(self, value: Union[th.Tensor, np.ndarray]): method h (line 127) | def h(self): method h (line 131) | def h(self, value: Union[th.Tensor, np.ndarray]): method class_id (line 135) | def class_id(self): method class_confidence (line 139) | def class_confidence(self): method dtype (line 143) | def dtype(self): method device (line 147) | def device(self): class ObjectLabelFactory (line 151) | class ObjectLabelFactory(ObjectLabelBase): method __init__ (line 152) | def __init__( method from_structured_array (line 170) | def from_structured_array( method __len__ (line 192) | def __len__(self): method __getitem__ (line 195) | def __getitem__(self, item: int) -> ObjectLabels: class ObjectLabels (line 218) | class ObjectLabels(ObjectLabelBase): method __init__ (line 219) | def __init__(self, object_labels: th.Tensor, input_size_hw: Tuple[int,... method __len__ (line 222) | def __len__(self) -> int: method rotate_ (line 225) | def rotate_(self, angle_deg: float): method zoom_in_and_rescale_ (line 275) | def zoom_in_and_rescale_( method zoom_out_and_rescale_ (line 317) | def zoom_out_and_rescale_( method scale_ (line 342) | def scale_(self, scaling_multiplier: float): method flip_lr_ (line 362) | def flip_lr_(self) -> None: method get_labels_as_tensors (line 367) | def get_labels_as_tensors(self, format_: str = "yolox") -> th.Tensor: method get_labels_as_batched_tensor (line 384) | def get_labels_as_batched_tensor( class SparselyBatchedObjectLabels (line 407) | class SparselyBatchedObjectLabels: method __init__ (line 408) | def __init__(self, sparse_object_labels_batch: List[Optional[ObjectLab... method __len__ (line 415) | def __len__(self) -> int: method __iter__ (line 418) | def __iter__(self): method __getitem__ (line 421) | def __getitem__(self, item: int) -> Optional[ObjectLabels]: method __add__ (line 426) | def __add__(self, other: SparselyBatchedObjectLabels): method set_empty_labels_to_none_ (line 434) | def set_empty_labels_to_none_(self): method input_size_hw (line 440) | def input_size_hw(self) -> Optional[Union[Tuple[int, int], Tuple[float... method zoom_in_and_rescale_ (line 446) | def zoom_in_and_rescale_(self, *args, **kwargs): method zoom_out_and_rescale_ (line 455) | def zoom_out_and_rescale_(self, *args, **kwargs): method rotate_ (line 462) | def rotate_(self, *args, **kwargs): method scale_ (line 467) | def scale_(self, *args, **kwargs): method flip_lr_ (line 474) | def flip_lr_(self): method to (line 479) | def to(self, *args, **kwargs): method get_valid_labels_and_batch_indices (line 485) | def get_valid_labels_and_batch_indices( method transpose_list (line 497) | def transpose_list( FILE: RVT/data/genx_utils/sequence_base.py function get_event_representation_dir (line 15) | def get_event_representation_dir(path: Path, ev_representation_name: str... function get_objframe_idx_2_repr_idx (line 21) | def get_objframe_idx_2_repr_idx(path: Path, ev_representation_name: str)... class SequenceBase (line 29) | class SequenceBase(MapDataPipe): method __init__ (line 43) | def __init__( method _get_labels_from_repr_idx (line 99) | def _get_labels_from_repr_idx(self, repr_idx: int) -> Optional[ObjectL... method _get_event_repr_torch (line 103) | def _get_event_repr_torch(self, start_idx: int, end_idx: int) -> List[... method __len__ (line 115) | def __len__(self) -> int: method __getitem__ (line 118) | def __getitem__(self, index: int) -> Any: FILE: RVT/data/genx_utils/sequence_for_streaming.py function _scalar_as_1d_array (line 17) | def _scalar_as_1d_array(scalar: Union[int, float]): function _get_ev_repr_range_indices (line 21) | def _get_ev_repr_range_indices( class SequenceForIter (line 57) | class SequenceForIter(SequenceBase): method __init__ (line 58) | def __init__( method get_sequences_with_guaranteed_labels (line 100) | def get_sequences_with_guaranteed_labels( method padding_representation (line 133) | def padding_representation(self) -> torch.Tensor: method get_fully_padded_sample (line 139) | def get_fully_padded_sample(self) -> LoaderDataDictGenX: method __len__ (line 153) | def __len__(self): method __getitem__ (line 156) | def __getitem__(self, index: int) -> LoaderDataDictGenX: class RandAugmentIterDataPipe (line 205) | class RandAugmentIterDataPipe(IterDataPipe): method __init__ (line 206) | def __init__(self, source_dp: IterDataPipe, dataset_config: DictConfig): method __iter__ (line 223) | def __iter__(self): FILE: RVT/data/genx_utils/sequence_rnd.py class SequenceForRandomAccess (line 9) | class SequenceForRandomAccess(SequenceBase): method __init__ (line 10) | def __init__( method __len__ (line 44) | def __len__(self): method __getitem__ (line 47) | def __getitem__(self, index: int) -> LoaderDataDictGenX: method is_only_loading_labels (line 83) | def is_only_loading_labels(self) -> bool: method only_load_labels (line 86) | def only_load_labels(self): method load_everything (line 89) | def load_everything(self): FILE: RVT/data/utils/augmentor.py class ZoomOutState (line 24) | class ZoomOutState: class RotationState (line 32) | class RotationState: class AugmentationState (line 38) | class AugmentationState: class RandomSpatialAugmentorGenX (line 45) | class RandomSpatialAugmentorGenX: method __init__ (line 46) | def __init__( method randomize_augmentation (line 99) | def randomize_augmentation(self): method _zoom_out_and_rescale (line 145) | def _zoom_out_and_rescale( method _zoom_out_and_rescale_tensor (line 164) | def _zoom_out_and_rescale_tensor( method _zoom_out_and_rescale_recursive (line 194) | def _zoom_out_and_rescale_recursive( method _zoom_in_and_rescale (line 241) | def _zoom_in_and_rescale(self, data_dict: LoaderDataDictGenX) -> Loade... method _zoom_in_and_rescale_tensor (line 276) | def _zoom_in_and_rescale_tensor( method _zoom_in_and_rescale_recursive (line 306) | def _zoom_in_and_rescale_recursive( method _rotate (line 353) | def _rotate(self, data_dict: LoaderDataDictGenX) -> LoaderDataDictGenX: method _rotate_tensor (line 363) | def _rotate_tensor(input_: Any, angle_deg: float, datatype: DataType): method _rotate_recursive (line 372) | def _rotate_recursive(cls, input_: Any, angle_deg: float, datatype: Da... method _flip (line 402) | def _flip(data_dict: LoaderDataDictGenX, type_: str) -> LoaderDataDict... method _flip_tensor (line 412) | def _flip_tensor(input_: Any, flip_type: str, datatype: DataType): method _flip_recursive (line 427) | def _flip_recursive(cls, input_: Any, flip_type: str, datatype: DataTy... method _hw_from_data (line 461) | def _hw_from_data(data_dict: LoaderDataDictGenX) -> Tuple[int, int]: method __call__ (line 483) | def __call__(self, data_dict: LoaderDataDictGenX): function get_most_recent_objframe (line 503) | def get_most_recent_objframe( function randomly_sample_zoom_window_from_objframe (line 521) | def randomly_sample_zoom_window_from_objframe( function randomly_sample_zoom_window_from_label_rectangle (line 557) | def randomly_sample_zoom_window_from_label_rectangle( FILE: RVT/data/utils/representations.py class RepresentationBase (line 9) | class RepresentationBase(ABC): method construct (line 11) | def construct( method get_shape (line 16) | def get_shape(self) -> Tuple[int, int, int]: ... method get_numpy_dtype (line 20) | def get_numpy_dtype() -> np.dtype: ... method get_torch_dtype (line 24) | def get_torch_dtype() -> th.dtype: ... method dtype (line 27) | def dtype(self) -> th.dtype: method _is_int_tensor (line 31) | def _is_int_tensor(tensor: th.Tensor) -> bool: class StackedHistogram (line 35) | class StackedHistogram(RepresentationBase): method __init__ (line 36) | def __init__( method get_numpy_dtype (line 67) | def get_numpy_dtype() -> np.dtype: method get_torch_dtype (line 71) | def get_torch_dtype() -> th.dtype: method merge_channel_and_bins (line 74) | def merge_channel_and_bins(self, representation: th.Tensor): method get_shape (line 78) | def get_shape(self) -> Tuple[int, int, int]: method construct (line 81) | def construct( function cumsum_channel (line 137) | def cumsum_channel(x: th.Tensor, num_channels: int): class MixedDensityEventStack (line 143) | class MixedDensityEventStack(RepresentationBase): method __init__ (line 144) | def __init__( method get_numpy_dtype (line 173) | def get_numpy_dtype() -> np.dtype: method get_torch_dtype (line 177) | def get_torch_dtype() -> th.dtype: method get_shape (line 180) | def get_shape(self) -> Tuple[int, int, int]: method construct (line 183) | def construct( FILE: RVT/data/utils/spatial.py function get_original_hw (line 16) | def get_original_hw(dataset_type: DatasetType): function get_dataloading_hw (line 20) | def get_dataloading_hw(dataset_config: DictConfig): FILE: RVT/data/utils/stream_concat_datapipe.py class DummyIterDataPipe (line 15) | class DummyIterDataPipe(IterDataPipe): method __init__ (line 16) | def __init__(self, source_dp: IterDataPipe): method __iter__ (line 21) | def __iter__(self): class ConcatStreamingDataPipe (line 25) | class ConcatStreamingDataPipe(IterDataPipe): method __init__ (line 37) | def __init__( method random_torch_shuffle_list (line 61) | def random_torch_shuffle_list(data: List[Any]) -> Iterator[Any]: method _get_zipped_streams (line 65) | def _get_zipped_streams(self, datapipe_list: List[MapDataPipe], batch_... method _print_seed_debug_info (line 85) | def _print_seed_debug_info(self): method _get_zipped_streams_with_worker_id (line 103) | def _get_zipped_streams_with_worker_id(self): method __iter__ (line 113) | def __iter__(self): FILE: RVT/data/utils/stream_sharded_datapipe.py class ShardedStreamingDataPipe (line 15) | class ShardedStreamingDataPipe(IterDataPipe): method __init__ (line 16) | def __init__( method yield_pyramid_indices (line 34) | def yield_pyramid_indices(start_idx: int, end_idx: int): method assign_datapipes_to_worker (line 42) | def assign_datapipes_to_worker( method get_zipped_stream_from_worker_datapipes (line 64) | def get_zipped_stream_from_worker_datapipes( method __iter__ (line 89) | def __iter__(self): FILE: RVT/data/utils/types.py class DataType (line 14) | class DataType(Enum): class DatasetType (line 25) | class DatasetType(Enum): class DatasetMode (line 30) | class DatasetMode(Enum): class DatasetSamplingMode (line 36) | class DatasetSamplingMode(StrEnum): class ObjDetOutput (line 42) | class ObjDetOutput(Enum): FILE: RVT/loggers/utils.py function get_wandb_logger (line 10) | def get_wandb_logger(full_config: DictConfig) -> WandbLogger: function get_ckpt_path (line 37) | def get_ckpt_path(logger: WandbLogger, wandb_config: DictConfig) -> Unio... FILE: RVT/loggers/wandb_logger.py class WandbLogger (line 34) | class WandbLogger(Logger): method __init__ (line 38) | def __init__( method get_checkpoint (line 82) | def get_checkpoint( method __getstate__ (line 98) | def __getstate__(self) -> Dict[str, Any]: method experiment (line 112) | def experiment(self) -> Run: method watch (line 145) | def watch( method add_step_metric (line 154) | def add_step_metric(self, input_dict: dict, step: int) -> None: method log_hyperparams (line 158) | def log_hyperparams(self, params: Union[Dict[str, Any], Namespace]) ->... method log_metrics (line 165) | def log_metrics(self, metrics: Dict[str, Any], step: Optional[int] = N... method log_images (line 176) | def log_images( method log_videos (line 198) | def log_videos( method name (line 229) | def name(self) -> Optional[str]: method version (line 235) | def version(self) -> Optional[str]: method after_save_checkpoint (line 241) | def after_save_checkpoint( method finalize (line 254) | def finalize(self, status: str) -> None: method _get_public_run (line 259) | def _get_public_run(self): method _num_logged_artifact (line 273) | def _num_logged_artifact(self): method _scan_and_log_checkpoints (line 277) | def _scan_and_log_checkpoints( method _rm_but_top_k (line 387) | def _rm_but_top_k(self, top_k: int): FILE: RVT/models/detection/recurrent_backbone/__init__.py function build_recurrent_backbone (line 6) | def build_recurrent_backbone(backbone_cfg: DictConfig): FILE: RVT/models/detection/recurrent_backbone/base.py class BaseDetector (line 6) | class BaseDetector(nn.Module): method get_stage_dims (line 7) | def get_stage_dims(self, stages: Tuple[int, ...]) -> Tuple[int, ...]: method get_strides (line 10) | def get_strides(self, stages: Tuple[int, ...]) -> Tuple[int, ...]: FILE: RVT/models/detection/recurrent_backbone/maxvit_rnn.py class RNNDetector (line 27) | class RNNDetector(BaseDetector): method __init__ (line 28) | def __init__(self, mdl_config: DictConfig): method get_stage_dims (line 92) | def get_stage_dims(self, stages: Tuple[int, ...]) -> Tuple[int, ...]: method get_strides (line 98) | def get_strides(self, stages: Tuple[int, ...]) -> Tuple[int, ...]: method forward (line 104) | def forward( class MaxVitAttentionPairCl (line 129) | class MaxVitAttentionPairCl(nn.Module): method __init__ (line 130) | def __init__(self, dim: int, skip_first_norm: bool, attention_cfg: Dic... method forward (line 146) | def forward(self, x): class RNNDetectorStage (line 152) | class RNNDetectorStage(nn.Module): method __init__ (line 155) | def __init__( method forward (line 212) | def forward( FILE: RVT/models/detection/yolox/models/losses.py class IOUloss (line 9) | class IOUloss(nn.Module): method __init__ (line 10) | def __init__(self, reduction="none", loss_type="iou"): method forward (line 15) | def forward(self, pred, target): FILE: RVT/models/detection/yolox/models/network_blocks.py class SiLU (line 9) | class SiLU(nn.Module): method forward (line 13) | def forward(x): function get_activation (line 17) | def get_activation(name="silu", inplace=True): class BaseConv (line 29) | class BaseConv(nn.Module): method __init__ (line 32) | def __init__( method forward (line 50) | def forward(self, x): method fuseforward (line 53) | def fuseforward(self, x): class DWConv (line 57) | class DWConv(nn.Module): method __init__ (line 60) | def __init__(self, in_channels, out_channels, ksize, stride=1, act="si... method forward (line 74) | def forward(self, x): class Bottleneck (line 79) | class Bottleneck(nn.Module): method __init__ (line 81) | def __init__( method forward (line 97) | def forward(self, x): class CSPLayer (line 104) | class CSPLayer(nn.Module): method __init__ (line 107) | def __init__( method forward (line 137) | def forward(self, x): FILE: RVT/models/detection/yolox/models/yolo_head.py class YOLOXHead (line 23) | class YOLOXHead(nn.Module): method __init__ (line 24) | def __init__( method initialize_biases (line 158) | def initialize_biases(self, prior_prob): method forward (line 169) | def forward(self, xin, labels=None): method get_output_and_grid (line 250) | def get_output_and_grid(self, output, k, stride, dtype): method decode_outputs (line 268) | def decode_outputs(self, outputs): method get_losses (line 300) | def get_losses( method get_l1_target (line 454) | def get_l1_target(self, l1_target, gt, stride, x_shifts, y_shifts, eps... method get_assignments (line 462) | def get_assignments( method get_geometry_constraint (line 550) | def get_geometry_constraint( method simota_matching (line 589) | def simota_matching(self, cost, pair_wise_ious, gt_classes, num_gt, fg... FILE: RVT/models/detection/yolox/utils/boxes.py function filter_box (line 21) | def filter_box(output, scale_range): function postprocess (line 32) | def postprocess( function bboxes_iou (line 82) | def bboxes_iou(bboxes_a, bboxes_b, xyxy=True): function matrix_iou (line 108) | def matrix_iou(a, b): function adjust_box_anns (line 121) | def adjust_box_anns(bbox, scale_ratio, padw, padh, w_max, h_max): function xyxy2xywh (line 127) | def xyxy2xywh(bboxes): function xyxy2cxcywh (line 133) | def xyxy2cxcywh(bboxes): FILE: RVT/models/detection/yolox/utils/compat.py function meshgrid (line 11) | def meshgrid(*tensors): FILE: RVT/models/detection/yolox_extension/models/build.py function build_yolox_head (line 9) | def build_yolox_head( function build_yolox_fpn (line 24) | def build_yolox_fpn(fpn_cfg: DictConfig, in_channels: Tuple[int, ...]): FILE: RVT/models/detection/yolox_extension/models/detector.py class YoloXDetector (line 18) | class YoloXDetector(th.nn.Module): method __init__ (line 19) | def __init__(self, model_cfg: DictConfig): method forward_backbone (line 35) | def forward_backbone( method forward_detect (line 48) | def forward_detect( method forward (line 64) | def forward( FILE: RVT/models/detection/yolox_extension/models/yolo_pafpn.py class YOLOPAFPN (line 19) | class YOLOPAFPN(nn.Module): method __init__ (line 24) | def __init__( method forward (line 104) | def forward(self, input: BackboneFeatures): FILE: RVT/models/layers/maxvit/layers/activations.py function swish (line 14) | def swish(x, inplace: bool = False): class Swish (line 19) | class Swish(nn.Module): method __init__ (line 20) | def __init__(self, inplace: bool = False): method forward (line 24) | def forward(self, x): function mish (line 28) | def mish(x, inplace: bool = False): class Mish (line 35) | class Mish(nn.Module): method __init__ (line 38) | def __init__(self, inplace: bool = False): method forward (line 41) | def forward(self, x): function sigmoid (line 45) | def sigmoid(x, inplace: bool = False): class Sigmoid (line 50) | class Sigmoid(nn.Module): method __init__ (line 51) | def __init__(self, inplace: bool = False): method forward (line 55) | def forward(self, x): function tanh (line 59) | def tanh(x, inplace: bool = False): class Tanh (line 64) | class Tanh(nn.Module): method __init__ (line 65) | def __init__(self, inplace: bool = False): method forward (line 69) | def forward(self, x): function hard_swish (line 73) | def hard_swish(x, inplace: bool = False): class HardSwish (line 78) | class HardSwish(nn.Module): method __init__ (line 79) | def __init__(self, inplace: bool = False): method forward (line 83) | def forward(self, x): function hard_sigmoid (line 87) | def hard_sigmoid(x, inplace: bool = False): class HardSigmoid (line 94) | class HardSigmoid(nn.Module): method __init__ (line 95) | def __init__(self, inplace: bool = False): method forward (line 99) | def forward(self, x): function hard_mish (line 103) | def hard_mish(x, inplace: bool = False): class HardMish (line 114) | class HardMish(nn.Module): method __init__ (line 115) | def __init__(self, inplace: bool = False): method forward (line 119) | def forward(self, x): class PReLU (line 123) | class PReLU(nn.PReLU): method __init__ (line 126) | def __init__( method forward (line 131) | def forward(self, input: torch.Tensor) -> torch.Tensor: function gelu (line 135) | def gelu(x: torch.Tensor, inplace: bool = False) -> torch.Tensor: class GELU (line 139) | class GELU(nn.Module): method __init__ (line 142) | def __init__(self, inplace: bool = False): method forward (line 145) | def forward(self, input: torch.Tensor) -> torch.Tensor: FILE: RVT/models/layers/maxvit/layers/activations_jit.py function swish_jit (line 19) | def swish_jit(x, inplace: bool = False): function mish_jit (line 25) | def mish_jit(x, _inplace: bool = False): class SwishJit (line 30) | class SwishJit(nn.Module): method __init__ (line 31) | def __init__(self, inplace: bool = False): method forward (line 34) | def forward(self, x): class MishJit (line 38) | class MishJit(nn.Module): method __init__ (line 39) | def __init__(self, inplace: bool = False): method forward (line 42) | def forward(self, x): function hard_sigmoid_jit (line 47) | def hard_sigmoid_jit(x, inplace: bool = False): class HardSigmoidJit (line 52) | class HardSigmoidJit(nn.Module): method __init__ (line 53) | def __init__(self, inplace: bool = False): method forward (line 56) | def forward(self, x): function hard_swish_jit (line 61) | def hard_swish_jit(x, inplace: bool = False): class HardSwishJit (line 68) | class HardSwishJit(nn.Module): method __init__ (line 69) | def __init__(self, inplace: bool = False): method forward (line 72) | def forward(self, x): function hard_mish_jit (line 77) | def hard_mish_jit(x, inplace: bool = False): class HardMishJit (line 85) | class HardMishJit(nn.Module): method __init__ (line 86) | def __init__(self, inplace: bool = False): method forward (line 89) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/activations_me.py function swish_jit_fwd (line 18) | def swish_jit_fwd(x): function swish_jit_bwd (line 23) | def swish_jit_bwd(x, grad_output): class SwishJitAutoFn (line 28) | class SwishJitAutoFn(torch.autograd.Function): method symbolic (line 35) | def symbolic(g, x): method forward (line 39) | def forward(ctx, x): method backward (line 44) | def backward(ctx, grad_output): function swish_me (line 49) | def swish_me(x, inplace=False): class SwishMe (line 53) | class SwishMe(nn.Module): method __init__ (line 54) | def __init__(self, inplace: bool = False): method forward (line 57) | def forward(self, x): function mish_jit_fwd (line 62) | def mish_jit_fwd(x): function mish_jit_bwd (line 67) | def mish_jit_bwd(x, grad_output): class MishJitAutoFn (line 73) | class MishJitAutoFn(torch.autograd.Function): method forward (line 79) | def forward(ctx, x): method backward (line 84) | def backward(ctx, grad_output): function mish_me (line 89) | def mish_me(x, inplace=False): class MishMe (line 93) | class MishMe(nn.Module): method __init__ (line 94) | def __init__(self, inplace: bool = False): method forward (line 97) | def forward(self, x): function hard_sigmoid_jit_fwd (line 102) | def hard_sigmoid_jit_fwd(x, inplace: bool = False): function hard_sigmoid_jit_bwd (line 107) | def hard_sigmoid_jit_bwd(x, grad_output): class HardSigmoidJitAutoFn (line 112) | class HardSigmoidJitAutoFn(torch.autograd.Function): method forward (line 114) | def forward(ctx, x): method backward (line 119) | def backward(ctx, grad_output): function hard_sigmoid_me (line 124) | def hard_sigmoid_me(x, inplace: bool = False): class HardSigmoidMe (line 128) | class HardSigmoidMe(nn.Module): method __init__ (line 129) | def __init__(self, inplace: bool = False): method forward (line 132) | def forward(self, x): function hard_swish_jit_fwd (line 137) | def hard_swish_jit_fwd(x): function hard_swish_jit_bwd (line 142) | def hard_swish_jit_bwd(x, grad_output): class HardSwishJitAutoFn (line 148) | class HardSwishJitAutoFn(torch.autograd.Function): method forward (line 152) | def forward(ctx, x): method backward (line 157) | def backward(ctx, grad_output): method symbolic (line 162) | def symbolic(g, self): function hard_swish_me (line 180) | def hard_swish_me(x, inplace=False): class HardSwishMe (line 184) | class HardSwishMe(nn.Module): method __init__ (line 185) | def __init__(self, inplace: bool = False): method forward (line 188) | def forward(self, x): function hard_mish_jit_fwd (line 193) | def hard_mish_jit_fwd(x): function hard_mish_jit_bwd (line 198) | def hard_mish_jit_bwd(x, grad_output): class HardMishJitAutoFn (line 204) | class HardMishJitAutoFn(torch.autograd.Function): method forward (line 211) | def forward(ctx, x): method backward (line 216) | def backward(ctx, grad_output): function hard_mish_me (line 221) | def hard_mish_me(x, inplace: bool = False): class HardMishMe (line 225) | class HardMishMe(nn.Module): method __init__ (line 226) | def __init__(self, inplace: bool = False): method forward (line 229) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/adaptive_avgmax_pool.py function adaptive_pool_feat_mult (line 18) | def adaptive_pool_feat_mult(pool_type="avg"): function adaptive_avgmax_pool2d (line 25) | def adaptive_avgmax_pool2d(x, output_size=1): function adaptive_catavgmax_pool2d (line 31) | def adaptive_catavgmax_pool2d(x, output_size=1): function select_adaptive_pool2d (line 37) | def select_adaptive_pool2d(x, pool_type="avg", output_size=1): class FastAdaptiveAvgPool2d (line 52) | class FastAdaptiveAvgPool2d(nn.Module): method __init__ (line 53) | def __init__(self, flatten=False): method forward (line 57) | def forward(self, x): class AdaptiveAvgMaxPool2d (line 61) | class AdaptiveAvgMaxPool2d(nn.Module): method __init__ (line 62) | def __init__(self, output_size=1): method forward (line 66) | def forward(self, x): class AdaptiveCatAvgMaxPool2d (line 70) | class AdaptiveCatAvgMaxPool2d(nn.Module): method __init__ (line 71) | def __init__(self, output_size=1): method forward (line 75) | def forward(self, x): class SelectAdaptivePool2d (line 79) | class SelectAdaptivePool2d(nn.Module): method __init__ (line 82) | def __init__(self, output_size=1, pool_type="fast", flatten=False): method is_identity (line 105) | def is_identity(self): method forward (line 108) | def forward(self, x): method feat_mult (line 113) | def feat_mult(self): method __repr__ (line 116) | def __repr__(self): FILE: RVT/models/layers/maxvit/layers/attention_pool2d.py class RotAttentionPool2d (line 21) | class RotAttentionPool2d(nn.Module): method __init__ (line 32) | def __init__( method forward (line 54) | def forward(self, x): class AttentionPool2d (line 85) | class AttentionPool2d(nn.Module): method __init__ (line 95) | def __init__( method forward (line 122) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/blur_pool.py class BlurPool2d (line 16) | class BlurPool2d(nn.Module): method __init__ (line 30) | def __init__(self, channels, filt_size=3, stride=2) -> None: method forward (line 45) | def forward(self, x: torch.Tensor) -> torch.Tensor: FILE: RVT/models/layers/maxvit/layers/bottleneck_attn.py function rel_logits_1d (line 29) | def rel_logits_1d(q, rel_k, permute_mask: List[int]): class PosEmbedRel (line 57) | class PosEmbedRel(nn.Module): method __init__ (line 63) | def __init__(self, feat_size, dim_head, scale): method forward (line 72) | def forward(self, q): class BottleneckAttn (line 88) | class BottleneckAttn(nn.Module): method __init__ (line 111) | def __init__( method reset_parameters (line 152) | def reset_parameters(self): method forward (line 157) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/cbam.py class ChannelAttn (line 20) | class ChannelAttn(nn.Module): method __init__ (line 23) | def __init__( method forward (line 43) | def forward(self, x): class LightChannelAttn (line 49) | class LightChannelAttn(ChannelAttn): method __init__ (line 52) | def __init__( method forward (line 66) | def forward(self, x): class SpatialAttn (line 72) | class SpatialAttn(nn.Module): method __init__ (line 75) | def __init__(self, kernel_size=7, gate_layer="sigmoid"): method forward (line 80) | def forward(self, x): class LightSpatialAttn (line 88) | class LightSpatialAttn(nn.Module): method __init__ (line 91) | def __init__(self, kernel_size=7, gate_layer="sigmoid"): method forward (line 96) | def forward(self, x): class CbamModule (line 102) | class CbamModule(nn.Module): method __init__ (line 103) | def __init__( method forward (line 126) | def forward(self, x): class LightCbamModule (line 132) | class LightCbamModule(nn.Module): method __init__ (line 133) | def __init__( method forward (line 156) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/classifier.py function _create_pool (line 12) | def _create_pool(num_features, num_classes, pool_type="avg", use_conv=Fa... function _create_fc (line 26) | def _create_fc(num_features, num_classes, use_conv=False): function create_classifier (line 36) | def create_classifier(num_features, num_classes, pool_type="avg", use_co... class ClassifierHead (line 44) | class ClassifierHead(nn.Module): method __init__ (line 47) | def __init__( method forward (line 58) | def forward(self, x, pre_logits: bool = False): FILE: RVT/models/layers/maxvit/layers/cond_conv2d.py function get_condconv_initializer (line 21) | def get_condconv_initializer(initializer, num_experts, expert_shape): class CondConv2d (line 41) | class CondConv2d(nn.Module): method __init__ (line 51) | def __init__( method reset_parameters (line 101) | def reset_parameters(self): method forward (line 118) | def forward(self, x, routing_weights): FILE: RVT/models/layers/maxvit/layers/config.py function is_no_jit (line 31) | def is_no_jit(): class set_no_jit (line 35) | class set_no_jit: method __init__ (line 36) | def __init__(self, mode: bool) -> None: method __enter__ (line 41) | def __enter__(self) -> None: method __exit__ (line 44) | def __exit__(self, *args: Any) -> bool: function is_exportable (line 50) | def is_exportable(): class set_exportable (line 54) | class set_exportable: method __init__ (line 55) | def __init__(self, mode: bool) -> None: method __enter__ (line 60) | def __enter__(self) -> None: method __exit__ (line 63) | def __exit__(self, *args: Any) -> bool: function is_scriptable (line 69) | def is_scriptable(): class set_scriptable (line 73) | class set_scriptable: method __init__ (line 74) | def __init__(self, mode: bool) -> None: method __enter__ (line 79) | def __enter__(self) -> None: method __exit__ (line 82) | def __exit__(self, *args: Any) -> bool: class set_layer_config (line 88) | class set_layer_config: method __init__ (line 93) | def __init__( method __enter__ (line 114) | def __enter__(self) -> None: method __exit__ (line 117) | def __exit__(self, *args: Any) -> bool: FILE: RVT/models/layers/maxvit/layers/conv2d_same.py function conv2d_same (line 14) | def conv2d_same( class Conv2dSame (line 27) | class Conv2dSame(nn.Conv2d): method __init__ (line 30) | def __init__( method forward (line 45) | def forward(self, x): function create_conv2d_pad (line 57) | def create_conv2d_pad(in_chs, out_chs, kernel_size, **kwargs): FILE: RVT/models/layers/maxvit/layers/conv_bn_act.py class ConvNormAct (line 13) | class ConvNormAct(nn.Module): method __init__ (line 14) | def __init__( method in_channels (line 48) | def in_channels(self): method out_channels (line 52) | def out_channels(self): method forward (line 55) | def forward(self, x): function create_aa (line 64) | def create_aa(aa_layer, channels, stride=2, enable=True): class ConvNormActAa (line 78) | class ConvNormActAa(nn.Module): method __init__ (line 79) | def __init__( method in_channels (line 117) | def in_channels(self): method out_channels (line 121) | def out_channels(self): method forward (line 124) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/create_act.py function get_act_fn (line 106) | def get_act_fn(name: Union[Callable, str] = "relu"): function get_act_layer (line 126) | def get_act_layer(name: Union[Type[nn.Module], str] = "relu"): function create_act_layer (line 145) | def create_act_layer(name: Union[nn.Module, str], inplace=None, **kwargs): FILE: RVT/models/layers/maxvit/layers/create_attn.py function get_attn (line 22) | def get_attn(attn_type): function create_attn (line 85) | def create_attn(attn_type, channels, **kwargs): FILE: RVT/models/layers/maxvit/layers/create_conv2d.py function create_conv2d (line 11) | def create_conv2d(in_channels, out_channels, kernel_size, **kwargs): FILE: RVT/models/layers/maxvit/layers/create_norm.py function create_norm_layer (line 27) | def create_norm_layer( function get_norm_layer (line 35) | def get_norm_layer(norm_layer): FILE: RVT/models/layers/maxvit/layers/create_norm_act.py function create_norm_act_layer (line 51) | def create_norm_act_layer( function get_norm_act_layer (line 61) | def get_norm_act_layer(norm_layer, act_layer=None): FILE: RVT/models/layers/maxvit/layers/drop.py function drop_block_2d (line 23) | def drop_block_2d( function drop_block_fast_2d (line 92) | def drop_block_fast_2d( class DropBlock2d (line 142) | class DropBlock2d(nn.Module): method __init__ (line 145) | def __init__( method forward (line 164) | def forward(self, x): function drop_path (line 188) | def drop_path( class DropPath (line 212) | class DropPath(nn.Module): method __init__ (line 215) | def __init__(self, drop_prob: float = 0.0, scale_by_keep: bool = True): method forward (line 220) | def forward(self, x): method extra_repr (line 223) | def extra_repr(self): FILE: RVT/models/layers/maxvit/layers/eca.py class EcaModule (line 46) | class EcaModule(nn.Module): method __init__ (line 62) | def __init__( method forward (line 100) | def forward(self, x): class CecaModule (line 113) | class CecaModule(nn.Module): method __init__ (line 137) | def __init__( method forward (line 160) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/evo_norm.py function instance_std (line 37) | def instance_std(x, eps: float = 1e-5): function instance_std_tpu (line 48) | def instance_std_tpu(x, eps: float = 1e-5): function instance_rms (line 56) | def instance_rms(x, eps: float = 1e-5): function manual_var (line 61) | def manual_var(x, dim: Union[int, Sequence[int]], diff_sqm: bool = False): function group_std (line 71) | def group_std(x, groups: int = 32, eps: float = 1e-5, flatten: bool = Fa... function group_std_tpu (line 96) | def group_std_tpu( function group_rms (line 119) | def group_rms(x, groups: int = 32, eps: float = 1e-5): class EvoNorm2dB0 (line 135) | class EvoNorm2dB0(nn.Module): method __init__ (line 136) | def __init__(self, num_features, apply_act=True, momentum=0.1, eps=1e-... method reset_parameters (line 147) | def reset_parameters(self): method forward (line 153) | def forward(self, x): class EvoNorm2dB1 (line 177) | class EvoNorm2dB1(nn.Module): method __init__ (line 178) | def __init__(self, num_features, apply_act=True, momentum=0.1, eps=1e-... method reset_parameters (line 188) | def reset_parameters(self): method forward (line 192) | def forward(self, x): class EvoNorm2dB2 (line 217) | class EvoNorm2dB2(nn.Module): method __init__ (line 218) | def __init__(self, num_features, apply_act=True, momentum=0.1, eps=1e-... method reset_parameters (line 228) | def reset_parameters(self): method forward (line 232) | def forward(self, x): class EvoNorm2dS0 (line 257) | class EvoNorm2dS0(nn.Module): method __init__ (line 258) | def __init__( method reset_parameters (line 274) | def reset_parameters(self): method forward (line 280) | def forward(self, x): class EvoNorm2dS0a (line 292) | class EvoNorm2dS0a(EvoNorm2dS0): method __init__ (line 293) | def __init__( method forward (line 304) | def forward(self, x): class EvoNorm2dS1 (line 318) | class EvoNorm2dS1(nn.Module): method __init__ (line 319) | def __init__( method reset_parameters (line 347) | def reset_parameters(self): method forward (line 351) | def forward(self, x): class EvoNorm2dS1a (line 362) | class EvoNorm2dS1a(EvoNorm2dS1): method __init__ (line 363) | def __init__( method forward (line 382) | def forward(self, x): class EvoNorm2dS2 (line 392) | class EvoNorm2dS2(nn.Module): method __init__ (line 393) | def __init__( method reset_parameters (line 420) | def reset_parameters(self): method forward (line 424) | def forward(self, x): class EvoNorm2dS2a (line 435) | class EvoNorm2dS2a(EvoNorm2dS2): method __init__ (line 436) | def __init__( method forward (line 455) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/fast_norm.py function is_fast_norm (line 27) | def is_fast_norm(): function set_fast_norm (line 31) | def set_fast_norm(enable=True): function fast_group_norm (line 36) | def fast_group_norm( function fast_layer_norm (line 58) | def fast_layer_norm( FILE: RVT/models/layers/maxvit/layers/filter_response_norm.py function inv_instance_rms (line 15) | def inv_instance_rms(x, eps: float = 1e-5): class FilterResponseNormTlu2d (line 20) | class FilterResponseNormTlu2d(nn.Module): method __init__ (line 21) | def __init__(self, num_features, apply_act=True, eps=1e-5, rms=True, *... method reset_parameters (line 31) | def reset_parameters(self): method forward (line 37) | def forward(self, x): class FilterResponseNormAct2d (line 52) | class FilterResponseNormAct2d(nn.Module): method __init__ (line 53) | def __init__( method reset_parameters (line 74) | def reset_parameters(self): method forward (line 78) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/gather_excite.py class GatherExcite (line 26) | class GatherExcite(nn.Module): method __init__ (line 29) | def __init__( method forward (line 101) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/global_context.py class GlobalContext (line 20) | class GlobalContext(nn.Module): method __init__ (line 21) | def __init__( method reset_parameters (line 62) | def reset_parameters(self): method forward (line 70) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/halo_attn.py function rel_logits_1d (line 31) | def rel_logits_1d(q, rel_k, permute_mask: List[int]): class PosEmbedRel (line 62) | class PosEmbedRel(nn.Module): method __init__ (line 69) | def __init__(self, block_size, win_size, dim_head, scale): method forward (line 83) | def forward(self, q): class HaloAttn (line 99) | class HaloAttn(nn.Module): method __init__ (line 128) | def __init__( method reset_parameters (line 185) | def reset_parameters(self): method forward (line 192) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/helpers.py function _ntuple (line 11) | def _ntuple(n): function make_divisible (line 27) | def make_divisible(v, divisor=8, min_value=None, round_limit=0.9): function extend_tuple (line 36) | def extend_tuple(x, n): FILE: RVT/models/layers/maxvit/layers/inplace_abn.py function inplace_abn (line 11) | def inplace_abn( function inplace_abn_sync (line 27) | def inplace_abn_sync(**kwargs): class InplaceAbn (line 31) | class InplaceAbn(nn.Module): method __init__ (line 52) | def __init__( method reset_parameters (line 95) | def reset_parameters(self): method forward (line 102) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/lambda_layer.py function rel_pos_indices (line 32) | def rel_pos_indices(size): class LambdaLayer (line 43) | class LambdaLayer(nn.Module): method __init__ (line 71) | def __init__( method reset_parameters (line 125) | def reset_parameters(self): method forward (line 132) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/linear.py class Linear (line 9) | class Linear(nn.Linear): method forward (line 16) | def forward(self, input: torch.Tensor) -> torch.Tensor: FILE: RVT/models/layers/maxvit/layers/median_pool.py class MedianPool2d (line 10) | class MedianPool2d(nn.Module): method __init__ (line 20) | def __init__(self, kernel_size=3, stride=1, padding=0, same=False): method _padding (line 27) | def _padding(self, x): method forward (line 47) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/mixed_conv2d.py function _split_channels (line 14) | def _split_channels(num_chan, num_groups): class MixedConv2d (line 20) | class MixedConv2d(nn.ModuleDict): method __init__ (line 27) | def __init__( method forward (line 66) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/ml_decoder.py function add_ml_decoder_head (line 9) | def add_ml_decoder_head(model): class TransformerDecoderLayerOptimal (line 43) | class TransformerDecoderLayerOptimal(nn.Module): method __init__ (line 44) | def __init__( method __setstate__ (line 71) | def __setstate__(self, state): method forward (line 76) | def forward( class GroupFC (line 113) | class GroupFC(object): method __init__ (line 114) | def __init__(self, embed_len_decoder: int): method __call__ (line 117) | def __call__( class MLDecoder (line 126) | class MLDecoder(nn.Module): method __init__ (line 127) | def __init__( method forward (line 171) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/mlp.py class Mlp (line 11) | class Mlp(nn.Module): method __init__ (line 14) | def __init__( method forward (line 35) | def forward(self, x): class GluMlp (line 44) | class GluMlp(nn.Module): method __init__ (line 49) | def __init__( method init_weights (line 71) | def init_weights(self): method forward (line 77) | def forward(self, x): class GatedMlp (line 87) | class GatedMlp(nn.Module): method __init__ (line 90) | def __init__( method forward (line 120) | def forward(self, x): class ConvMlp (line 130) | class ConvMlp(nn.Module): method __init__ (line 133) | def __init__( method forward (line 154) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/non_local_attn.py class NonLocalAttn (line 17) | class NonLocalAttn(nn.Module): method __init__ (line 24) | def __init__( method forward (line 44) | def forward(self, x): method reset_parameters (line 66) | def reset_parameters(self): class BilinearAttnTransform (line 80) | class BilinearAttnTransform(nn.Module): method __init__ (line 81) | def __init__( method resize_mat (line 107) | def resize_mat(self, x, t: int): method forward (line 120) | def forward(self, x): class BatNonLocalAttn (line 172) | class BatNonLocalAttn(nn.Module): method __init__ (line 177) | def __init__( method forward (line 204) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/norm.py class GroupNorm (line 15) | class GroupNorm(nn.GroupNorm): method __init__ (line 16) | def __init__(self, num_channels, num_groups=32, eps=1e-5, affine=True): method forward (line 23) | def forward(self, x): class GroupNorm1 (line 30) | class GroupNorm1(nn.GroupNorm): method __init__ (line 35) | def __init__(self, num_channels, **kwargs): method forward (line 41) | def forward(self, x: torch.Tensor) -> torch.Tensor: class LayerNorm (line 48) | class LayerNorm(nn.LayerNorm): method __init__ (line 51) | def __init__(self, num_channels, eps=1e-6, affine=True): method forward (line 57) | def forward(self, x: torch.Tensor) -> torch.Tensor: class LayerNorm2d (line 67) | class LayerNorm2d(nn.LayerNorm): method __init__ (line 70) | def __init__(self, num_channels, eps=1e-6, affine=True): method forward (line 76) | def forward(self, x: torch.Tensor) -> torch.Tensor: function _is_contiguous (line 88) | def _is_contiguous(tensor: torch.Tensor) -> bool: function _layer_norm_cf (line 97) | def _layer_norm_cf( function _layer_norm_cf_sqm (line 106) | def _layer_norm_cf_sqm( class LayerNormExp2d (line 116) | class LayerNormExp2d(nn.LayerNorm): method __init__ (line 125) | def __init__(self, num_channels, eps=1e-6): method forward (line 128) | def forward(self, x) -> torch.Tensor: FILE: RVT/models/layers/maxvit/layers/norm_act.py class BatchNormAct2d (line 27) | class BatchNormAct2d(nn.BatchNorm2d): method __init__ (line 35) | def __init__( method forward (line 76) | def forward(self, x): class SyncBatchNormAct (line 131) | class SyncBatchNormAct(nn.SyncBatchNorm): method forward (line 136) | def forward(self, x: torch.Tensor) -> torch.Tensor: function convert_sync_batchnorm (line 147) | def convert_sync_batchnorm(module, process_group=None): function _num_groups (line 189) | def _num_groups(num_channels, num_groups, group_size): class GroupNormAct (line 196) | class GroupNormAct(nn.GroupNorm): method __init__ (line 198) | def __init__( method forward (line 225) | def forward(self, x): class LayerNormAct (line 235) | class LayerNormAct(nn.LayerNorm): method __init__ (line 236) | def __init__( method forward (line 258) | def forward(self, x): class LayerNormAct2d (line 270) | class LayerNormAct2d(nn.LayerNorm): method __init__ (line 271) | def __init__( method forward (line 293) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/padding.py function get_padding (line 13) | def get_padding(kernel_size: int, stride: int = 1, dilation: int = 1, **... function get_same_padding (line 19) | def get_same_padding(x: int, k: int, s: int, d: int): function is_static_pad (line 24) | def is_static_pad(kernel_size: int, stride: int = 1, dilation: int = 1, ... function pad_same (line 29) | def pad_same(x, k: List[int], s: List[int], d: List[int] = (1, 1), value... function get_padding_value (line 43) | def get_padding_value(padding, kernel_size, **kwargs) -> Tuple[Tuple, bo... FILE: RVT/models/layers/maxvit/layers/patch_embed.py class PatchEmbed (line 16) | class PatchEmbed(nn.Module): method __init__ (line 19) | def __init__( method forward (line 42) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/pool2d_same.py function avg_pool2d_same (line 15) | def avg_pool2d_same( class AvgPool2dSame (line 28) | class AvgPool2dSame(nn.AvgPool2d): method __init__ (line 31) | def __init__( method forward (line 45) | def forward(self, x): function max_pool2d_same (line 57) | def max_pool2d_same( class MaxPool2dSame (line 69) | class MaxPool2dSame(nn.MaxPool2d): method __init__ (line 72) | def __init__( method forward (line 82) | def forward(self, x): function create_pool2d (line 89) | def create_pool2d(pool_type, kernel_size, stride=None, **kwargs): FILE: RVT/models/layers/maxvit/layers/pos_embed.py function pixel_freq_bands (line 8) | def pixel_freq_bands( function inv_freq_bands (line 24) | def inv_freq_bands( function build_sincos2d_pos_embed (line 38) | def build_sincos2d_pos_embed( function build_fourier_pos_embed (line 90) | def build_fourier_pos_embed( class FourierEmbed (line 147) | class FourierEmbed(nn.Module): method __init__ (line 148) | def __init__( method forward (line 164) | def forward(self, x): function rot (line 191) | def rot(x): function apply_rot_embed (line 195) | def apply_rot_embed(x: torch.Tensor, sin_emb, cos_emb): function apply_rot_embed_list (line 199) | def apply_rot_embed_list(x: List[torch.Tensor], sin_emb, cos_emb): function apply_rot_embed_split (line 205) | def apply_rot_embed_split(x: torch.Tensor, emb): function build_rotary_pos_embed (line 210) | def build_rotary_pos_embed( class RotaryEmbedding (line 240) | class RotaryEmbedding(nn.Module): method __init__ (line 251) | def __init__(self, dim, max_res=224, linear_bands: bool = False): method get_embed (line 260) | def get_embed(self, shape: List[int]): method forward (line 263) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/selective_kernel.py function _kernel_valid (line 16) | def _kernel_valid(k): class SelectiveKernelAttn (line 23) | class SelectiveKernelAttn(nn.Module): method __init__ (line 24) | def __init__( method forward (line 46) | def forward(self, x): class SelectiveKernel (line 59) | class SelectiveKernel(nn.Module): method __init__ (line 60) | def __init__( method forward (line 148) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/separable_conv.py class SeparableConvNormAct (line 15) | class SeparableConvNormAct(nn.Module): method __init__ (line 18) | def __init__( method in_channels (line 59) | def in_channels(self): method out_channels (line 63) | def out_channels(self): method forward (line 66) | def forward(self, x): class SeparableConv2d (line 76) | class SeparableConv2d(nn.Module): method __init__ (line 79) | def __init__( method in_channels (line 112) | def in_channels(self): method out_channels (line 116) | def out_channels(self): method forward (line 119) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/space_to_depth.py class SpaceToDepth (line 5) | class SpaceToDepth(nn.Module): method __init__ (line 6) | def __init__(self, block_size=4): method forward (line 11) | def forward(self, x): class SpaceToDepthJit (line 24) | class SpaceToDepthJit(object): method __call__ (line 25) | def __call__(self, x: torch.Tensor): class SpaceToDepthModule (line 34) | class SpaceToDepthModule(nn.Module): method __init__ (line 35) | def __init__(self, no_jit=False): method forward (line 42) | def forward(self, x): class DepthToSpace (line 46) | class DepthToSpace(nn.Module): method __init__ (line 47) | def __init__(self, block_size): method forward (line 51) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/split_attn.py class RadixSoftmax (line 17) | class RadixSoftmax(nn.Module): method __init__ (line 18) | def __init__(self, radix, cardinality): method forward (line 23) | def forward(self, x): class SplitAttn (line 34) | class SplitAttn(nn.Module): method __init__ (line 37) | def __init__( method forward (line 88) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/split_batchnorm.py class SplitBatchNorm2d (line 19) | class SplitBatchNorm2d(torch.nn.BatchNorm2d): method __init__ (line 20) | def __init__( method forward (line 41) | def forward(self, input: torch.Tensor): function convert_splitbn_model (line 56) | def convert_splitbn_model(module, num_splits=2): FILE: RVT/models/layers/maxvit/layers/squeeze_excite.py class SEModule (line 20) | class SEModule(nn.Module): method __init__ (line 30) | def __init__( method forward (line 54) | def forward(self, x): class EffectiveSEModule (line 68) | class EffectiveSEModule(nn.Module): method __init__ (line 73) | def __init__(self, channels, add_maxpool=False, gate_layer="hard_sigmo... method forward (line 79) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/std_conv.py class StdConv2d (line 27) | class StdConv2d(nn.Conv2d): method __init__ (line 34) | def __init__( method forward (line 60) | def forward(self, x): class StdConv2dSame (line 75) | class StdConv2dSame(nn.Conv2d): method __init__ (line 82) | def __init__( method forward (line 110) | def forward(self, x): class ScaledStdConv2d (line 127) | class ScaledStdConv2d(nn.Conv2d): method __init__ (line 136) | def __init__( method forward (line 166) | def forward(self, x): class ScaledStdConv2dSame (line 181) | class ScaledStdConv2dSame(nn.Conv2d): method __init__ (line 190) | def __init__( method forward (line 222) | def forward(self, x): FILE: RVT/models/layers/maxvit/layers/test_time_pool.py class TestTimePoolHead (line 16) | class TestTimePoolHead(nn.Module): method __init__ (line 17) | def __init__(self, base, original_pool=7): method forward (line 32) | def forward(self, x): function apply_test_time_pool (line 40) | def apply_test_time_pool(model, config, use_test_size=False): FILE: RVT/models/layers/maxvit/layers/trace_utils.py function _assert (line 5) | def _assert(condition: bool, message: str): function _float_to_int (line 9) | def _float_to_int(x: float) -> int: FILE: RVT/models/layers/maxvit/layers/weight_init.py function _trunc_normal_ (line 8) | def _trunc_normal_(tensor, mean, std, a, b): function trunc_normal_ (line 45) | def trunc_normal_(tensor, mean=0.0, std=1.0, a=-2.0, b=2.0): function trunc_normal_tf_ (line 72) | def trunc_normal_tf_(tensor, mean=0.0, std=1.0, a=-2.0, b=2.0): function variance_scaling_ (line 101) | def variance_scaling_(tensor, scale=1.0, mode="fan_in", distribution="no... function lecun_normal_ (line 126) | def lecun_normal_(tensor): FILE: RVT/models/layers/maxvit/maxvit.py class PartitionType (line 26) | class PartitionType(Enum): function nChw_2_nhwC (line 31) | def nChw_2_nhwC(x: torch.Tensor): function nhwC_2_nChw (line 37) | def nhwC_2_nChw(x: torch.Tensor): class LayerScale (line 43) | class LayerScale(nn.Module): method __init__ (line 44) | def __init__(self, dim: int, init_values: float = 1e-5, inplace: bool ... method forward (line 49) | def forward(self, x): class GLU (line 54) | class GLU(nn.Module): method __init__ (line 55) | def __init__( method forward (line 83) | def forward(self, x: torch.Tensor): class MLP (line 88) | class MLP(nn.Module): method __init__ (line 89) | def __init__( method forward (line 146) | def forward(self, x): class DownsampleBase (line 150) | class DownsampleBase(nn.Module): method __init__ (line 151) | def __init__(self): method output_is_normed (line 155) | def output_is_normed(): function get_downsample_layer_Cf2Cl (line 159) | def get_downsample_layer_Cf2Cl( class ConvDownsampling_Cf2Cl (line 173) | class ConvDownsampling_Cf2Cl(DownsampleBase): method __init__ (line 178) | def __init__( method forward (line 209) | def forward(self, x: torch.Tensor): method output_is_normed (line 216) | def output_is_normed(): class PartitionAttentionCl (line 220) | class PartitionAttentionCl(nn.Module): method __init__ (line 228) | def __init__( method _partition_attn (line 301) | def _partition_attn(self, x): method forward (line 320) | def forward(self, x): function window_partition (line 326) | def window_partition(x, window_size: Tuple[int, int]): function window_reverse (line 347) | def window_reverse(windows, window_size: Tuple[int, int], img_size: Tupl... function grid_partition (line 357) | def grid_partition(x, grid_size: Tuple[int, int]): function grid_reverse (line 372) | def grid_reverse(windows, grid_size: Tuple[int, int], img_size: Tuple[in... class TorchMHSAWrapperCl (line 382) | class TorchMHSAWrapperCl(nn.Module): method __init__ (line 385) | def __init__(self, dim: int, dim_head: int = 32, bias: bool = True): method forward (line 393) | def forward(self, x: torch.Tensor): class SelfAttentionCl (line 402) | class SelfAttentionCl(nn.Module): method __init__ (line 405) | def __init__(self, dim: int, dim_head: int = 32, bias: bool = True): method forward (line 414) | def forward(self, x: torch.Tensor): function assert_activation_string (line 433) | def assert_activation_string( function assert_norm2d_layer_string (line 467) | def assert_norm2d_layer_string( FILE: RVT/models/layers/rnn.py class DWSConvLSTM2d (line 7) | class DWSConvLSTM2d(nn.Module): method __init__ (line 10) | def __init__( method forward (line 43) | def forward( FILE: RVT/models/layers/s5/jax_func.py function safe_map (line 31) | def safe_map(f: Callable[[T1], T], __arg1: Iterable[T1]) -> List[T]: ... function safe_map (line 35) | def safe_map( function safe_map (line 41) | def safe_map( function safe_map (line 50) | def safe_map( function safe_map (line 60) | def safe_map(f, *args): function combine (line 68) | def combine(tree, operator, a_flat, b_flat): function _scan (line 77) | def _scan(tree, operator, elems, axis: int): function associative_scan (line 129) | def associative_scan(operator: Callable, elems, axis: int = 0, reverse: ... function test_associative_scan (line 155) | def test_associative_scan(shape=(1, 24, 24)): function _interleave (line 185) | def _interleave(a, b, axis: int): function test_interleave (line 205) | def test_interleave(): function _compute_fans (line 238) | def _compute_fans(shape, fan_in_axes=None): function uniform (line 260) | def uniform(shape, dtype=torch.float, minval=0.0, maxval=1.0, device=None): function _complex_uniform (line 268) | def _complex_uniform(shape: Sequence[int], dtype, device=None) -> torch.... function complex_as_float_dtype (line 278) | def complex_as_float_dtype(dtype): function _complex_truncated_normal (line 290) | def _complex_truncated_normal( function _truncated_normal (line 309) | def _truncated_normal(lower, upper, shape, dtype=torch.float): function variance_scaling (line 330) | def variance_scaling( function lecun_normal (line 384) | def lecun_normal(fan_in_axes=None, dtype=torch.float): function test_variance_scaling (line 418) | def test_variance_scaling(): FILE: RVT/models/layers/s5/s5_init.py function make_HiPPO (line 9) | def make_HiPPO(N): function make_NPLR_HiPPO (line 23) | def make_NPLR_HiPPO(N): function make_DPLR_HiPPO (line 43) | def make_DPLR_HiPPO(N): function make_Normal_S (line 70) | def make_Normal_S(N): function make_Normal_HiPPO (line 79) | def make_Normal_HiPPO(N, B=1): function log_step_initializer (line 108) | def log_step_initializer(dt_min=0.001, dt_max=0.1): function init_log_steps (line 132) | def init_log_steps(H, dt_min, dt_max): function init_VinvB (line 149) | def init_VinvB(init_fun, Vinv): function trunc_standard_normal (line 171) | def trunc_standard_normal(shape): function init_CV (line 187) | def init_CV(init_fun, shape, V) -> torch.Tensor: function init_columnwise_B (line 204) | def init_columnwise_B(shape, dtype): function init_columnwise_VinvB (line 228) | def init_columnwise_VinvB(init_fun, Vinv): function init_rowwise_C (line 244) | def init_rowwise_C(shape, dtype): FILE: RVT/models/layers/s5/s5_model.py function binary_operator (line 19) | def binary_operator( function apply_ssm (line 35) | def apply_ssm( function apply_ssm_liquid (line 77) | def apply_ssm_liquid( function discretize_bilinear (line 109) | def discretize_bilinear(Lambda, B_tilde, Delta): function discretize_zoh (line 132) | def discretize_zoh(Lambda, B_tilde, Delta): function as_complex (line 148) | def as_complex(t: torch.Tensor, dtype=torch.complex64): class S5SSM (line 159) | class S5SSM(torch.nn.Module): method __init__ (line 160) | def __init__( method initial_state (line 271) | def initial_state(self, batch_size: Optional[int]): method get_BC_tilde (line 277) | def get_BC_tilde(self): method forward_rnn (line 287) | def forward_rnn(self, signal, prev_state, step_scale: float | torch.Te... method forward (line 311) | def forward(self, signal, prev_state, step_scale: float | torch.Tensor... class S5 (line 334) | class S5(torch.nn.Module): method __init__ (line 335) | def __init__( method initial_state (line 390) | def initial_state(self, batch_size: Optional[int] = None): method forward (line 393) | def forward(self, signal, prev_state, step_scale: float | torch.Tensor... class GEGLU (line 404) | class GEGLU(torch.nn.Module): method forward (line 405) | def forward(self, x): class S5Block (line 410) | class S5Block(torch.nn.Module): method __init__ (line 411) | def __init__( method forward (line 447) | def forward(self, x, states): function tensor_stats (line 472) | def tensor_stats(t: torch.Tensor): # Clone of lovely_tensors for comple... FILE: RVT/models/layers/s5/triton_comparison.py function to_triton (line 17) | def to_triton(x: np.ndarray, device="cuda", dst_type=None): function to_numpy (line 35) | def to_numpy(x): function sum_op (line 79) | def sum_op(a, b): function kernel (line 83) | def kernel(X, Z, BLOCK_M: tl.constexpr, BLOCK_N: tl.constexpr, AXIS: tl.... function f (line 121) | def f(carry, x): function _fake_scan (line 124) | def _fake_scan(f, init, x): function sum_op2 (line 155) | def sum_op2(a, b): FILE: RVT/modules/data/genx.py function get_dataloader_kwargs (line 20) | def get_dataloader_kwargs( class DataModule (line 82) | class DataModule(pl.LightningDataModule): method __init__ (line 83) | def __init__( method get_dataloading_hw (line 130) | def get_dataloading_hw(self): method set_mixed_sampling_mode_variables_for_train (line 133) | def set_mixed_sampling_mode_variables_for_train(self): method setup (line 174) | def setup(self, stage: Optional[str] = None) -> None: method train_dataloader (line 229) | def train_dataloader(self): method val_dataloader (line 250) | def val_dataloader(self): method test_dataloader (line 262) | def test_dataloader(self): FILE: RVT/modules/detection.py class Module (line 30) | class Module(pl.LightningModule): method __init__ (line 31) | def __init__(self, full_config: DictConfig): method setup (line 48) | def setup(self, stage: Optional[str] = None) -> None: method forward (line 105) | def forward( method get_worker_id_from_batch (line 119) | def get_worker_id_from_batch(self, batch: Any) -> int: method get_data_from_batch (line 122) | def get_data_from_batch(self, batch: Any): method training_step (line 125) | def training_step(self, batch: Any, batch_idx: int) -> STEP_OUTPUT: method _val_test_step_impl (line 272) | def _val_test_step_impl(self, batch: Any, mode: Mode) -> Optional[STEP... method validation_step (line 379) | def validation_step(self, batch: Any, batch_idx: int) -> Optional[STEP... method test_step (line 382) | def test_step(self, batch: Any, batch_idx: int) -> Optional[STEP_OUTPUT]: method run_psee_evaluator (line 385) | def run_psee_evaluator(self, mode: Mode): method on_train_epoch_end (line 446) | def on_train_epoch_end(self) -> None: method on_validation_epoch_end (line 457) | def on_validation_epoch_end(self) -> None: method on_test_epoch_end (line 463) | def on_test_epoch_end(self) -> None: method configure_optimizers (line 468) | def configure_optimizers(self) -> Any: FILE: RVT/modules/utils/detection.py class Mode (line 11) | class Mode(Enum): class BackboneFeatureSelector (line 24) | class BackboneFeatureSelector: method __init__ (line 25) | def __init__(self): method reset (line 29) | def reset(self): method add_backbone_features (line 32) | def add_backbone_features( method get_batched_backbone_features (line 49) | def get_batched_backbone_features(self) -> Optional[BackboneFeatures]: class EventReprSelector (line 55) | class EventReprSelector: method __init__ (line 56) | def __init__(self): method reset (line 60) | def reset(self): method __len__ (line 63) | def __len__(self): method add_event_representations (line 66) | def add_event_representations( method get_event_representations_as_list (line 77) | def get_event_representations_as_list( class RNNStates (line 88) | class RNNStates: method __init__ (line 89) | def __init__(self): method _has_states (line 92) | def _has_states(self): method recursive_detach (line 96) | def recursive_detach(cls, inp: Union[th.Tensor, List, Tuple, Dict]): method recursive_reset (line 108) | def recursive_reset( method save_states_and_detach (line 140) | def save_states_and_detach(self, worker_id: int, states: LstmStates) -... method get_states (line 143) | def get_states(self, worker_id: int) -> Optional[LstmStates]: method reset (line 150) | def reset( function mixed_collate_fn (line 163) | def mixed_collate_fn( function merge_mixed_batches (line 179) | def merge_mixed_batches(batch: Dict[str, Any]): FILE: RVT/modules/utils/fetch.py function fetch_model_module (line 8) | def fetch_model_module(config: DictConfig) -> pl.LightningModule: function fetch_data_module (line 15) | def fetch_data_module(config: DictConfig) -> pl.LightningDataModule: FILE: RVT/scripts/genx/preprocess_dataset.py class DataKeys (line 39) | class DataKeys(Enum): class SplitType (line 47) | class SplitType(Enum): class NoLabelsException (line 74) | class NoLabelsException(Exception): class H5Writer (line 79) | class H5Writer: method __init__ (line 80) | def __init__( method __enter__ (line 105) | def __enter__(self): method __exit__ (line 108) | def __exit__(self, exc_type, exc_val, exc_tb): method close_callback (line 112) | def close_callback(h5f: h5py.File): method close (line 115) | def close(self): method get_current_length (line 118) | def get_current_length(self): method add_data (line 121) | def add_data(self, data: np.ndarray): class H5Reader (line 133) | class H5Reader: method __init__ (line 134) | def __init__(self, h5_file: Path, dataset: str = "gen4"): method __enter__ (line 152) | def __enter__(self): method __exit__ (line 155) | def __exit__(self, exc_type, exc_val, exc_tb): method _close_callback (line 159) | def _close_callback(h5f: h5py.File): method close (line 162) | def close(self): method get_height_and_width (line 166) | def get_height_and_width(self) -> Tuple[int, int]: method time (line 170) | def time(self) -> np.ndarray: method _correct_time (line 181) | def _correct_time(time_array: np.ndarray): method get_event_slice (line 190) | def get_event_slice( function prophesee_bbox_filter (line 213) | def prophesee_bbox_filter(labels: np.ndarray, dataset_type: str) -> np.n... function conservative_bbox_filter (line 231) | def conservative_bbox_filter(labels: np.ndarray) -> np.ndarray: function remove_faulty_huge_bbox_filter (line 240) | def remove_faulty_huge_bbox_filter(labels: np.ndarray, dataset_type: str... function crop_to_fov_filter (line 250) | def crop_to_fov_filter(labels: np.ndarray, dataset_type: str) -> np.ndar... function prophesee_remove_labels_filter_gen4 (line 281) | def prophesee_remove_labels_filter_gen4(labels: np.ndarray) -> np.ndarray: function apply_filters (line 292) | def apply_filters( function get_base_delta_ts_for_labels_us (line 313) | def get_base_delta_ts_for_labels_us( function save_labels (line 330) | def save_labels( function labels_and_ev_repr_timestamps (line 370) | def labels_and_ev_repr_timestamps( function write_event_data (line 497) | def write_event_data( function downsample_ev_repr (line 533) | def downsample_ev_repr(x: torch.Tensor, scale_factor: float): function write_event_representations (line 548) | def write_event_representations( function process_sequence (line 619) | def process_sequence( class AggregationType (line 683) | class AggregationType(Enum): class FilterConf (line 695) | class FilterConf: class EventWindowExtractionConf (line 701) | class EventWindowExtractionConf: class StackedHistogramConf (line 707) | class StackedHistogramConf: class MixedDensityEventStackConf (line 718) | class MixedDensityEventStackConf: class EventRepresentationFactory (line 733) | class EventRepresentationFactory(ABC): method __init__ (line 734) | def __init__(self, config: DictConfig): method name (line 739) | def name(self) -> str: ... method create (line 742) | def create(self, height: int, width: int) -> Any: ... class StackedHistogramFactory (line 745) | class StackedHistogramFactory(EventRepresentationFactory): method name (line 747) | def name(self) -> str: method create (line 751) | def create(self, height: int, width: int) -> StackedHistogram: class MixedDensityStackFactory (line 761) | class MixedDensityStackFactory(EventRepresentationFactory): method name (line 763) | def name(self) -> str: method create (line 772) | def create(self, height: int, width: int) -> MixedDensityEventStack: function get_configuration (line 787) | def get_configuration( FILE: RVT/scripts/viz/viz_gt.py function draw_bboxes_bbv (line 34) | def draw_bboxes_bbv( function draw_predictions (line 85) | def draw_predictions( function gen_gt_generator (line 99) | def gen_gt_generator( FILE: RVT/train.py function main (line 35) | def main(config: DictConfig): FILE: RVT/utils/evaluation/prophesee/evaluation.py function evaluate_list (line 5) | def evaluate_list( FILE: RVT/utils/evaluation/prophesee/evaluator.py class PropheseeEvaluator (line 9) | class PropheseeEvaluator: method __init__ (line 13) | def __init__(self, dataset: str, downsample_by_2: bool): method _reset_buffer (line 23) | def _reset_buffer(self): method _add_to_buffer (line 30) | def _add_to_buffer(self, key: str, value: List[np.ndarray]): method _get_from_buffer (line 38) | def _get_from_buffer(self, key: str) -> List[np.ndarray]: method add_predictions (line 43) | def add_predictions(self, predictions: List[np.ndarray]): method add_labels (line 46) | def add_labels(self, labels: List[np.ndarray]): method reset_buffer (line 49) | def reset_buffer(self) -> None: method has_data (line 53) | def has_data(self): method evaluate_buffer (line 56) | def evaluate_buffer( FILE: RVT/utils/evaluation/prophesee/io/box_filtering.py function filter_boxes (line 19) | def filter_boxes(boxes, skip_ts=int(5e5), min_box_diag=60, min_box_side=... FILE: RVT/utils/evaluation/prophesee/io/box_loading.py function reformat_boxes (line 33) | def reformat_boxes(boxes): function loaded_label_to_prophesee (line 53) | def loaded_label_to_prophesee(loaded_labels: ObjectLabels) -> np.ndarray: function to_prophesee (line 66) | def to_prophesee( FILE: RVT/utils/evaluation/prophesee/io/dat_events_tools.py function load_td_data (line 24) | def load_td_data(filename, ev_count=-1, ev_start=0): function _dat_transfer (line 53) | def _dat_transfer(dat, dtype, xyp=None): function stream_td_data (line 88) | def stream_td_data(file_handle, buffer, dtype, ev_count=-1): function count_events (line 113) | def count_events(filename): function parse_header (line 128) | def parse_header(f): function write_header (line 190) | def write_header(filename, height=240, width=320, ev_type=0): function write_event_buffer (line 220) | def write_event_buffer(f, buffers): FILE: RVT/utils/evaluation/prophesee/io/npy_events_tools.py function stream_td_data (line 16) | def stream_td_data(file_handle, buffer, dtype, ev_count=-1): function parse_header (line 31) | def parse_header(fhandle): FILE: RVT/utils/evaluation/prophesee/io/psee_loader.py class PSEELoader (line 17) | class PSEELoader(object): method __init__ (line 22) | def __init__(self, datfile): method reset (line 66) | def reset(self): method event_count (line 72) | def event_count(self): method get_size (line 79) | def get_size(self): method __repr__ (line 83) | def __repr__(self): method load_n_events (line 101) | def load_n_events(self, ev_count): method load_delta_t (line 128) | def load_delta_t(self, delta_t): method seek_event (line 176) | def seek_event(self, ev_count): method seek_time (line 204) | def seek_time(self, final_time, term_criterion=100000): method total_time (line 248) | def total_time(self): method __del__ (line 269) | def __del__(self): FILE: RVT/utils/evaluation/prophesee/metrics/coco_eval.py function evaluate_detection (line 26) | def evaluate_detection( function _match_times (line 70) | def _match_times(all_ts, gt_boxes, dt_boxes, time_tol): function _coco_eval (line 107) | def _coco_eval( function coco_eval_return_metrics (line 164) | def coco_eval_return_metrics(coco_eval: COCOeval): function _to_coco_format (line 168) | def _to_coco_format(gts, detections, categories, height=240, width=304): FILE: RVT/utils/evaluation/prophesee/visualize/vis_utils.py function make_binary_histo (line 25) | def make_binary_histo(events, img=None, width=304, height=240): function draw_bboxes_bbv (line 54) | def draw_bboxes_bbv(img, boxes, labelmap=LABELMAP_GEN1) -> np.ndarray: function draw_bboxes (line 103) | def draw_bboxes(img, boxes, labelmap=LABELMAP_GEN1) -> None: FILE: RVT/utils/helpers.py function torch_uniform_sample_scalar (line 6) | def torch_uniform_sample_scalar(min_value: float, max_value: float): function clamp (line 13) | def clamp( FILE: RVT/utils/padding.py class InputPadderFromShape (line 7) | class InputPadderFromShape: method __init__ (line 8) | def __init__( method _pad_tensor_impl (line 35) | def _pad_tensor_impl( method pad_tensor_ev_repr (line 61) | def pad_tensor_ev_repr(self, ev_repr: th.Tensor) -> th.Tensor: method pad_token_mask (line 74) | def pad_token_mask(self, token_mask: th.Tensor): FILE: RVT/utils/preprocessing.py function _blosc_opts (line 1) | def _blosc_opts(complevel=1, complib="blosc:zstd", shuffle="byte"): FILE: RVT/utils/timers.py class CudaTimer (line 12) | class CudaTimer: method __init__ (line 13) | def __init__(self, device: torch.device, timer_name: str): method __enter__ (line 24) | def __enter__(self): method __exit__ (line 29) | def __exit__(self, *args): function cuda_timer_decorator (line 36) | def cuda_timer_decorator(device: torch.device, timer_name: str): class TimerDummy (line 49) | class TimerDummy: method __init__ (line 50) | def __init__(self, *args, **kwargs): method __enter__ (line 53) | def __enter__(self): method __exit__ (line 56) | def __exit__(self, *args): class Timer (line 60) | class Timer: method __init__ (line 61) | def __init__(self, timer_name=""): method __enter__ (line 66) | def __enter__(self): method __exit__ (line 70) | def __exit__(self, *args): function print_timing_info (line 76) | def print_timing_info(): FILE: RVT/validation.py function main (line 31) | def main(config: DictConfig):