dgenerate-ultralytics-headless 8.3.190__py3-none-any.whl → 8.3.191__py3-none-any.whl

ultralytics/hub/session.py

@@ -1,11 +1,13 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from __future__ import annotations
+
 import shutil
 import threading
 import time
 from http import HTTPStatus
 from pathlib import Path
-from typing import Any, Dict, Optional
+from typing import Any
 from urllib.parse import parse_qs, urlparse
 
 from ultralytics import __version__
@@ -90,7 +92,7 @@ class HUBTrainingSession:
                 )
 
     @classmethod
-    def create_session(cls, identifier: str, args: Optional[Dict[str, Any]] = None):
+    def create_session(cls, identifier: str, args: dict[str, Any] | None = None):
         """
         Create an authenticated HUBTrainingSession or return None.
 
@@ -137,7 +139,7 @@ class HUBTrainingSession:
         self.model.start_heartbeat(self.rate_limits["heartbeat"])
         LOGGER.info(f"{PREFIX}View model at {self.model_url} 🚀")
 
-    def create_model(self, model_args: Dict[str, Any]):
+    def create_model(self, model_args: dict[str, Any]):
         """
         Initialize a HUB training session with the specified model arguments.
 
@@ -204,7 +206,7 @@ class HUBTrainingSession:
             HUBModelError: If the identifier format is not recognized.
         """
         api_key, model_id, filename = None, None, None
-        if str(identifier).endswith((".pt", ".yaml")):
+        if identifier.endswith((".pt", ".yaml")):
             filename = identifier
         elif identifier.startswith(f"{HUB_WEB_ROOT}/models/"):
             parsed_url = urlparse(identifier)
@@ -254,8 +256,8 @@ class HUBTrainingSession:
         timeout: int = 30,
         thread: bool = True,
         verbose: bool = True,
-        progress_total: Optional[int] = None,
-        stream_response: Optional[bool] = None,
+        progress_total: int | None = None,
+        stream_response: bool | None = None,
         *args,
         **kwargs,
     ):

ultralytics/hub/utils.py

@@ -11,8 +11,8 @@ from ultralytics import __version__
 from ultralytics.utils import (
     ARGV,
     ENVIRONMENT,
+    GIT,
     IS_COLAB,
-    IS_GIT_DIR,
     IS_PIP_PACKAGE,
     LOGGER,
     ONLINE,
@@ -23,7 +23,6 @@ from ultralytics.utils import (
     TQDM,
     TryExcept,
     colorstr,
-    get_git_origin_url,
 )
 from ultralytics.utils.downloads import GITHUB_ASSETS_NAMES
 from ultralytics.utils.torch_utils import get_cpu_info
@@ -205,7 +204,7 @@ class Events:
         self.t = 0.0  # rate limit timer (seconds)
         self.metadata = {
             "cli": Path(ARGV[0]).name == "yolo",
-            "install": "git" if IS_GIT_DIR else "pip" if IS_PIP_PACKAGE else "other",
+            "install": "git" if GIT.is_repo else "pip" if IS_PIP_PACKAGE else "other",
             "python": PYTHON_VERSION.rsplit(".", 1)[0],  # i.e. 3.13
             "CPU": get_cpu_info(),
             # "GPU": get_gpu_info(index=0) if cuda else None,
@@ -219,7 +218,7 @@ class Events:
             and RANK in {-1, 0}
             and not TESTS_RUNNING
             and ONLINE
-            and (IS_PIP_PACKAGE or get_git_origin_url() == "https://github.com/ultralytics/ultralytics.git")
+            and (IS_PIP_PACKAGE or GIT.origin == "https://github.com/ultralytics/ultralytics.git")
         )
 
     def __call__(self, cfg, device=None):

ultralytics/models/fastsam/model.py

@@ -1,7 +1,9 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from __future__ import annotations
+
 from pathlib import Path
-from typing import Any, Dict, List, Optional
+from typing import Any
 
 from ultralytics.engine.model import Model
 
@@ -45,10 +47,10 @@ class FastSAM(Model):
         self,
         source,
         stream: bool = False,
-        bboxes: Optional[List] = None,
-        points: Optional[List] = None,
-        labels: Optional[List] = None,
-        texts: Optional[List] = None,
+        bboxes: list | None = None,
+        points: list | None = None,
+        labels: list | None = None,
+        texts: list | None = None,
         **kwargs: Any,
     ):
         """
@@ -74,6 +76,6 @@ class FastSAM(Model):
         return super().predict(source, stream, prompts=prompts, **kwargs)
 
     @property
-    def task_map(self) -> Dict[str, Dict[str, Any]]:
+    def task_map(self) -> dict[str, dict[str, Any]]:
         """Returns a dictionary mapping segment task to corresponding predictor and validator classes."""
         return {"segment": {"predictor": FastSAMPredictor, "validator": FastSAMValidator}}

ultralytics/models/nas/model.py

@@ -1,7 +1,9 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from __future__ import annotations
+
 from pathlib import Path
-from typing import Any, Dict
+from typing import Any
 
 import torch
 
@@ -80,7 +82,7 @@ class NAS(Model):
         self.model.args = {**DEFAULT_CFG_DICT, **self.overrides}  # for export()
         self.model.eval()
 
-    def info(self, detailed: bool = False, verbose: bool = True) -> Dict[str, Any]:
+    def info(self, detailed: bool = False, verbose: bool = True) -> dict[str, Any]:
         """
         Log model information.
 
@@ -94,6 +96,6 @@ class NAS(Model):
         return model_info(self.model, detailed=detailed, verbose=verbose, imgsz=640)
 
     @property
-    def task_map(self) -> Dict[str, Dict[str, Any]]:
+    def task_map(self) -> dict[str, dict[str, Any]]:
         """Return a dictionary mapping tasks to respective predictor and validator classes."""
         return {"detect": {"predictor": NASPredictor, "validator": NASValidator}}

ultralytics/models/rtdetr/train.py

@@ -1,7 +1,8 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from __future__ import annotations
+
 from copy import copy
-from typing import Optional
 
 from ultralytics.models.yolo.detect import DetectionTrainer
 from ultralytics.nn.tasks import RTDETRDetectionModel
@@ -41,7 +42,7 @@ class RTDETRTrainer(DetectionTrainer):
         >>> trainer.train()
     """
 
-    def get_model(self, cfg: Optional[dict] = None, weights: Optional[str] = None, verbose: bool = True):
+    def get_model(self, cfg: dict | None = None, weights: str | None = None, verbose: bool = True):
         """
         Initialize and return an RT-DETR model for object detection tasks.
 
@@ -58,7 +59,7 @@ class RTDETRTrainer(DetectionTrainer):
             model.load(weights)
         return model
 
-    def build_dataset(self, img_path: str, mode: str = "val", batch: Optional[int] = None):
+    def build_dataset(self, img_path: str, mode: str = "val", batch: int | None = None):
         """
         Build and return an RT-DETR dataset for training or validation.
 

ultralytics/models/rtdetr/val.py

@@ -1,7 +1,9 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from __future__ import annotations
+
 from pathlib import Path
-from typing import Any, Dict, List, Tuple, Union
+from typing import Any
 
 import torch
 
@@ -155,8 +157,8 @@ class RTDETRValidator(DetectionValidator):
         )
 
     def postprocess(
-        self, preds: Union[torch.Tensor, List[torch.Tensor], Tuple[torch.Tensor]]
-    ) -> List[Dict[str, torch.Tensor]]:
+        self, preds: torch.Tensor | list[torch.Tensor] | tuple[torch.Tensor]
+    ) -> list[dict[str, torch.Tensor]]:
         """
         Apply Non-maximum suppression to prediction outputs.
 
@@ -187,7 +189,7 @@ class RTDETRValidator(DetectionValidator):
 
         return [{"bboxes": x[:, :4], "conf": x[:, 4], "cls": x[:, 5]} for x in outputs]
 
-    def pred_to_json(self, predn: Dict[str, torch.Tensor], pbatch: Dict[str, Any]) -> None:
+    def pred_to_json(self, predn: dict[str, torch.Tensor], pbatch: dict[str, Any]) -> None:
         """
         Serialize YOLO predictions to COCO json format.
 

ultralytics/models/sam/amg.py

@@ -1,15 +1,18 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from __future__ import annotations
+
 import math
+from collections.abc import Generator
 from itertools import product
-from typing import Any, Generator, List, Tuple
+from typing import Any
 
 import numpy as np
 import torch
 
 
 def is_box_near_crop_edge(
-    boxes: torch.Tensor, crop_box: List[int], orig_box: List[int], atol: float = 20.0
+    boxes: torch.Tensor, crop_box: list[int], orig_box: list[int], atol: float = 20.0
 ) -> torch.Tensor:
     """
     Determine if bounding boxes are near the edge of a cropped image region using a specified tolerance.
@@ -38,7 +41,7 @@ def is_box_near_crop_edge(
     return torch.any(near_crop_edge, dim=1)
 
 
-def batch_iterator(batch_size: int, *args) -> Generator[List[Any], None, None]:
+def batch_iterator(batch_size: int, *args) -> Generator[list[Any]]:
     """
     Yield batches of data from input arguments with specified batch size for efficient processing.
 
@@ -106,14 +109,14 @@ def build_point_grid(n_per_side: int) -> np.ndarray:
     return np.stack([points_x, points_y], axis=-1).reshape(-1, 2)
 
 
-def build_all_layer_point_grids(n_per_side: int, n_layers: int, scale_per_layer: int) -> List[np.ndarray]:
+def build_all_layer_point_grids(n_per_side: int, n_layers: int, scale_per_layer: int) -> list[np.ndarray]:
     """Generate point grids for multiple crop layers with varying scales and densities."""
     return [build_point_grid(int(n_per_side / (scale_per_layer**i))) for i in range(n_layers + 1)]
 
 
 def generate_crop_boxes(
-    im_size: Tuple[int, ...], n_layers: int, overlap_ratio: float
-) -> Tuple[List[List[int]], List[int]]:
+    im_size: tuple[int, ...], n_layers: int, overlap_ratio: float
+) -> tuple[list[list[int]], list[int]]:
     """
     Generate crop boxes of varying sizes for multiscale image processing, with layered overlapping regions.
 
@@ -163,7 +166,7 @@ def generate_crop_boxes(
     return crop_boxes, layer_idxs
 
 
-def uncrop_boxes_xyxy(boxes: torch.Tensor, crop_box: List[int]) -> torch.Tensor:
+def uncrop_boxes_xyxy(boxes: torch.Tensor, crop_box: list[int]) -> torch.Tensor:
     """Uncrop bounding boxes by adding the crop box offset to their coordinates."""
     x0, y0, _, _ = crop_box
     offset = torch.tensor([[x0, y0, x0, y0]], device=boxes.device)
@@ -173,7 +176,7 @@ def uncrop_boxes_xyxy(boxes: torch.Tensor, crop_box: List[int]) -> torch.Tensor:
     return boxes + offset
 
 
-def uncrop_points(points: torch.Tensor, crop_box: List[int]) -> torch.Tensor:
+def uncrop_points(points: torch.Tensor, crop_box: list[int]) -> torch.Tensor:
     """Uncrop points by adding the crop box offset to their coordinates."""
     x0, y0, _, _ = crop_box
     offset = torch.tensor([[x0, y0]], device=points.device)
@@ -183,7 +186,7 @@ def uncrop_points(points: torch.Tensor, crop_box: List[int]) -> torch.Tensor:
     return points + offset
 
 
-def uncrop_masks(masks: torch.Tensor, crop_box: List[int], orig_h: int, orig_w: int) -> torch.Tensor:
+def uncrop_masks(masks: torch.Tensor, crop_box: list[int], orig_h: int, orig_w: int) -> torch.Tensor:
     """Uncrop masks by padding them to the original image size, handling coordinate transformations."""
     x0, y0, x1, y1 = crop_box
     if x0 == 0 and y0 == 0 and x1 == orig_w and y1 == orig_h:
@@ -194,7 +197,7 @@ def uncrop_masks(masks: torch.Tensor, crop_box: List[int], orig_h: int, orig_w:
     return torch.nn.functional.pad(masks, pad, value=0)
 
 
-def remove_small_regions(mask: np.ndarray, area_thresh: float, mode: str) -> Tuple[np.ndarray, bool]:
+def remove_small_regions(mask: np.ndarray, area_thresh: float, mode: str) -> tuple[np.ndarray, bool]:
     """
     Remove small disconnected regions or holes in a mask based on area threshold and mode.
 

ultralytics/models/sam/model.py

@@ -14,8 +14,9 @@ Key Features:
     - Trained on SA-1B dataset
 """
 
+from __future__ import annotations
+
 from pathlib import Path
-from typing import Dict, Type
 
 from ultralytics.engine.model import Model
 from ultralytics.utils.torch_utils import model_info
@@ -154,7 +155,7 @@ class SAM(Model):
         return model_info(self.model, detailed=detailed, verbose=verbose)
 
     @property
-    def task_map(self) -> Dict[str, Dict[str, Type[Predictor]]]:
+    def task_map(self) -> dict[str, dict[str, type[Predictor]]]:
         """
         Provide a mapping from the 'segment' task to its corresponding 'Predictor'.
 

ultralytics/models/sam/modules/blocks.py

@@ -1,9 +1,9 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+from __future__ import annotations
 
 import copy
 import math
 from functools import partial
-from typing import Optional, Tuple, Type, Union
 
 import numpy as np
 import torch
@@ -81,7 +81,7 @@ class MaskDownSampler(nn.Module):
         stride: int = 4,
         padding: int = 0,
         total_stride: int = 16,
-        activation: Type[nn.Module] = nn.GELU,
+        activation: type[nn.Module] = nn.GELU,
     ):
         """Initialize a mask downsampler module for progressive downsampling and channel expansion."""
         super().__init__()
@@ -227,7 +227,7 @@ class Fuser(nn.Module):
         torch.Size([1, 256, 32, 32])
     """
 
-    def __init__(self, layer: nn.Module, num_layers: int, dim: Optional[int] = None, input_projection: bool = False):
+    def __init__(self, layer: nn.Module, num_layers: int, dim: int | None = None, input_projection: bool = False):
         """
         Initialize the Fuser module for feature fusion through multiple layers.
 
@@ -295,7 +295,7 @@ class SAM2TwoWayAttentionBlock(TwoWayAttentionBlock):
         embedding_dim: int,
         num_heads: int,
         mlp_dim: int = 2048,
-        activation: Type[nn.Module] = nn.ReLU,
+        activation: type[nn.Module] = nn.ReLU,
         attention_downsample_rate: int = 2,
         skip_first_layer_pe: bool = False,
     ) -> None:
@@ -359,7 +359,7 @@ class SAM2TwoWayTransformer(TwoWayTransformer):
         embedding_dim: int,
         num_heads: int,
         mlp_dim: int,
-        activation: Type[nn.Module] = nn.ReLU,
+        activation: type[nn.Module] = nn.ReLU,
         attention_downsample_rate: int = 2,
     ) -> None:
         """
@@ -432,7 +432,7 @@ class RoPEAttention(Attention):
         *args,
         rope_theta: float = 10000.0,
         rope_k_repeat: bool = False,
-        feat_sizes: Tuple[int, int] = (32, 32),  # [w, h] for stride 16 feats at 512 resolution
+        feat_sizes: tuple[int, int] = (32, 32),  # [w, h] for stride 16 feats at 512 resolution
         **kwargs,
     ):
         """Initialize RoPEAttention with rotary position encoding for enhanced positional awareness."""
@@ -618,9 +618,9 @@ class MultiScaleBlock(nn.Module):
         num_heads: int,
         mlp_ratio: float = 4.0,
         drop_path: float = 0.0,
-        norm_layer: Union[nn.Module, str] = "LayerNorm",
-        q_stride: Tuple[int, int] = None,
-        act_layer: Type[nn.Module] = nn.GELU,
+        norm_layer: nn.Module | str = "LayerNorm",
+        q_stride: tuple[int, int] = None,
+        act_layer: type[nn.Module] = nn.GELU,
         window_size: int = 0,
     ):
         """Initialize a multiscale attention block with window partitioning and optional query pooling."""
@@ -728,7 +728,7 @@ class PositionEmbeddingSine(nn.Module):
         num_pos_feats: int,
         temperature: int = 10000,
         normalize: bool = True,
-        scale: Optional[float] = None,
+        scale: float | None = None,
     ):
         """Initialize sinusoidal position embeddings for 2D image inputs."""
         super().__init__()
@@ -744,7 +744,7 @@ class PositionEmbeddingSine(nn.Module):
 
         self.cache = {}
 
-    def _encode_xy(self, x: torch.Tensor, y: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
+    def _encode_xy(self, x: torch.Tensor, y: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor]:
         """Encode 2D positions using sine/cosine functions for transformer positional embeddings."""
         assert len(x) == len(y) and x.ndim == y.ndim == 1
         x_embed = x * self.scale
@@ -833,7 +833,7 @@ class PositionEmbeddingRandom(nn.Module):
         torch.Size([128, 32, 32])
     """
 
-    def __init__(self, num_pos_feats: int = 64, scale: Optional[float] = None) -> None:
+    def __init__(self, num_pos_feats: int = 64, scale: float | None = None) -> None:
         """Initialize random spatial frequency position embedding for transformers."""
         super().__init__()
         if scale is None or scale <= 0.0:
@@ -853,7 +853,7 @@ class PositionEmbeddingRandom(nn.Module):
         # Outputs d_1 x ... x d_n x C shape
         return torch.cat([torch.sin(coords), torch.cos(coords)], dim=-1)
 
-    def forward(self, size: Tuple[int, int]) -> torch.Tensor:
+    def forward(self, size: tuple[int, int]) -> torch.Tensor:
         """Generate positional encoding for a grid using random spatial frequencies."""
         h, w = size
         grid = torch.ones(
@@ -869,7 +869,7 @@ class PositionEmbeddingRandom(nn.Module):
         pe = self._pe_encoding(torch.stack([x_embed, y_embed], dim=-1))
         return pe.permute(2, 0, 1)  # C x H x W
 
-    def forward_with_coords(self, coords_input: torch.Tensor, image_size: Tuple[int, int]) -> torch.Tensor:
+    def forward_with_coords(self, coords_input: torch.Tensor, image_size: tuple[int, int]) -> torch.Tensor:
         """Positionally encode input coordinates, normalizing them to [0,1] based on the given image size."""
         coords = coords_input.clone()
         coords[:, :, 0] = coords[:, :, 0] / image_size[1]
@@ -910,12 +910,12 @@ class Block(nn.Module):
         num_heads: int,
         mlp_ratio: float = 4.0,
         qkv_bias: bool = True,
-        norm_layer: Type[nn.Module] = nn.LayerNorm,
-        act_layer: Type[nn.Module] = nn.GELU,
+        norm_layer: type[nn.Module] = nn.LayerNorm,
+        act_layer: type[nn.Module] = nn.GELU,
         use_rel_pos: bool = False,
         rel_pos_zero_init: bool = True,
         window_size: int = 0,
-        input_size: Optional[Tuple[int, int]] = None,
+        input_size: tuple[int, int] | None = None,
     ) -> None:
         """
         Initialize a transformer block with optional window attention and relative positional embeddings.
@@ -1012,7 +1012,7 @@ class REAttention(nn.Module):
         qkv_bias: bool = True,
         use_rel_pos: bool = False,
         rel_pos_zero_init: bool = True,
-        input_size: Optional[Tuple[int, int]] = None,
+        input_size: tuple[int, int] | None = None,
     ) -> None:
         """
         Initialize a Relative Position Attention module for transformer-based architectures.
@@ -1093,9 +1093,9 @@ class PatchEmbed(nn.Module):
 
     def __init__(
         self,
-        kernel_size: Tuple[int, int] = (16, 16),
-        stride: Tuple[int, int] = (16, 16),
-        padding: Tuple[int, int] = (0, 0),
+        kernel_size: tuple[int, int] = (16, 16),
+        stride: tuple[int, int] = (16, 16),
+        padding: tuple[int, int] = (0, 0),
         in_chans: int = 3,
         embed_dim: int = 768,
     ) -> None:

ultralytics/models/sam/modules/decoders.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-from typing import List, Optional, Tuple, Type
+from __future__ import annotations
 
 import torch
 from torch import nn
@@ -43,7 +43,7 @@ class MaskDecoder(nn.Module):
         transformer_dim: int,
         transformer: nn.Module,
         num_multimask_outputs: int = 3,
-        activation: Type[nn.Module] = nn.GELU,
+        activation: type[nn.Module] = nn.GELU,
         iou_head_depth: int = 3,
         iou_head_hidden_dim: int = 256,
     ) -> None:
@@ -93,7 +93,7 @@ class MaskDecoder(nn.Module):
         sparse_prompt_embeddings: torch.Tensor,
         dense_prompt_embeddings: torch.Tensor,
         multimask_output: bool,
-    ) -> Tuple[torch.Tensor, torch.Tensor]:
+    ) -> tuple[torch.Tensor, torch.Tensor]:
         """
         Predict masks given image and prompt embeddings.
 
@@ -137,7 +137,7 @@ class MaskDecoder(nn.Module):
         image_pe: torch.Tensor,
         sparse_prompt_embeddings: torch.Tensor,
         dense_prompt_embeddings: torch.Tensor,
-    ) -> Tuple[torch.Tensor, torch.Tensor]:
+    ) -> tuple[torch.Tensor, torch.Tensor]:
         """Predict masks and quality scores using image and prompt embeddings via transformer architecture."""
         # Concatenate output tokens
         output_tokens = torch.cat([self.iou_token.weight, self.mask_tokens.weight], dim=0)
@@ -158,7 +158,7 @@ class MaskDecoder(nn.Module):
         # Upscale mask embeddings and predict masks using the mask tokens
         src = src.transpose(1, 2).view(b, c, h, w)
         upscaled_embedding = self.output_upscaling(src)
-        hyper_in_list: List[torch.Tensor] = [
+        hyper_in_list: list[torch.Tensor] = [
             self.output_hypernetworks_mlps[i](mask_tokens_out[:, i, :]) for i in range(self.num_mask_tokens)
         ]
         hyper_in = torch.stack(hyper_in_list, dim=1)
@@ -221,7 +221,7 @@ class SAM2MaskDecoder(nn.Module):
         transformer_dim: int,
         transformer: nn.Module,
         num_multimask_outputs: int = 3,
-        activation: Type[nn.Module] = nn.GELU,
+        activation: type[nn.Module] = nn.GELU,
         iou_head_depth: int = 3,
         iou_head_hidden_dim: int = 256,
         use_high_res_features: bool = False,
@@ -317,8 +317,8 @@ class SAM2MaskDecoder(nn.Module):
         dense_prompt_embeddings: torch.Tensor,
         multimask_output: bool,
         repeat_image: bool,
-        high_res_features: Optional[List[torch.Tensor]] = None,
-    ) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]:
+        high_res_features: list[torch.Tensor] | None = None,
+    ) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]:
         """
         Predict masks given image and prompt embeddings.
 
@@ -385,8 +385,8 @@ class SAM2MaskDecoder(nn.Module):
         sparse_prompt_embeddings: torch.Tensor,
         dense_prompt_embeddings: torch.Tensor,
         repeat_image: bool,
-        high_res_features: Optional[List[torch.Tensor]] = None,
-    ) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]:
+        high_res_features: list[torch.Tensor] | None = None,
+    ) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]:
         """Predict instance segmentation masks from image and prompt embeddings using a transformer."""
         # Concatenate output tokens
         s = 0
@@ -431,7 +431,7 @@ class SAM2MaskDecoder(nn.Module):
             upscaled_embedding = act1(ln1(dc1(src) + feat_s1))
             upscaled_embedding = act2(dc2(upscaled_embedding) + feat_s0)
 
-        hyper_in_list: List[torch.Tensor] = [
+        hyper_in_list: list[torch.Tensor] = [
             self.output_hypernetworks_mlps[i](mask_tokens_out[:, i, :]) for i in range(self.num_mask_tokens)
         ]
         hyper_in = torch.stack(hyper_in_list, dim=1)