diff options
| -rw-r--r-- | models/auto_encoder.py | 8 | ||||
| -rw-r--r-- | models/hpm.py | 4 | ||||
| -rw-r--r-- | models/layers.py | 20 | ||||
| -rw-r--r-- | models/model.py | 52 | ||||
| -rw-r--r-- | models/part_net.py | 13 | ||||
| -rw-r--r-- | models/rgb_part_net.py | 15 | ||||
| -rw-r--r-- | utils/configuration.py | 20 | ||||
| -rw-r--r-- | utils/dataset.py | 28 | ||||
| -rw-r--r-- | utils/sampler.py | 5 |
9 files changed, 85 insertions, 80 deletions
diff --git a/models/auto_encoder.py b/models/auto_encoder.py index 5e7558b..64c52e3 100644 --- a/models/auto_encoder.py +++ b/models/auto_encoder.py @@ -1,3 +1,5 @@ +from typing import Tuple + import torch import torch.nn as nn import torch.nn.functional as F @@ -12,7 +14,7 @@ class Encoder(nn.Module): self, in_channels: int = 3, feature_channels: int = 64, - output_dims: tuple[int, int, int] = (128, 128, 64) + output_dims: Tuple[int, int, int] = (128, 128, 64) ): super().__init__() self.feature_channels = feature_channels @@ -67,7 +69,7 @@ class Decoder(nn.Module): def __init__( self, - input_dims: tuple[int, int, int] = (128, 128, 64), + input_dims: Tuple[int, int, int] = (128, 128, 64), feature_channels: int = 64, out_channels: int = 3, ): @@ -116,7 +118,7 @@ class AutoEncoder(nn.Module): num_class: int = 74, channels: int = 3, feature_channels: int = 64, - embedding_dims: tuple[int, int, int] = (128, 128, 64) + embedding_dims: Tuple[int, int, int] = (128, 128, 64) ): super().__init__() self.encoder = Encoder(channels, feature_channels, embedding_dims) diff --git a/models/hpm.py b/models/hpm.py index 66503e3..7505ed7 100644 --- a/models/hpm.py +++ b/models/hpm.py @@ -1,3 +1,5 @@ +from typing import Tuple + import torch import torch.nn as nn @@ -9,7 +11,7 @@ class HorizontalPyramidMatching(nn.Module): self, in_channels: int, out_channels: int = 128, - scales: tuple[int, ...] = (1, 2, 4), + scales: Tuple[int, ...] = (1, 2, 4), use_avg_pool: bool = True, use_max_pool: bool = True, **kwargs diff --git a/models/layers.py b/models/layers.py index a9f04b3..7f2ccec 100644 --- a/models/layers.py +++ b/models/layers.py @@ -1,4 +1,4 @@ -from typing import Union +from typing import Union, Tuple import torch import torch.nn as nn @@ -10,7 +10,7 @@ class BasicConv2d(nn.Module): self, in_channels: int, out_channels: int, - kernel_size: Union[int, tuple[int, int]], + kernel_size: Union[int, Tuple[int, int]], **kwargs ): super().__init__() @@ -29,7 +29,7 @@ class VGGConv2d(BasicConv2d): self, in_channels: int, out_channels: int, - kernel_size: Union[int, tuple[int, int]] = 3, + kernel_size: Union[int, Tuple[int, int]] = 3, padding: int = 1, **kwargs ): @@ -47,7 +47,7 @@ class BasicConvTranspose2d(nn.Module): self, in_channels: int, out_channels: int, - kernel_size: Union[int, tuple[int, int]], + kernel_size: Union[int, Tuple[int, int]], **kwargs ): super().__init__() @@ -66,7 +66,7 @@ class DCGANConvTranspose2d(BasicConvTranspose2d): self, in_channels: int, out_channels: int, - kernel_size: Union[int, tuple[int, int]] = 4, + kernel_size: Union[int, Tuple[int, int]] = 4, stride: int = 2, padding: int = 1, is_last_layer: bool = False, @@ -104,7 +104,7 @@ class FocalConv2d(BasicConv2d): self, in_channels: int, out_channels: int, - kernel_size: Union[int, tuple[int, int]], + kernel_size: Union[int, Tuple[int, int]], halving: int, **kwargs ): @@ -124,8 +124,8 @@ class FocalConv2dBlock(nn.Module): self, in_channels: int, out_channels: int, - kernel_sizes: tuple[int, int], - paddings: tuple[int, int], + kernel_sizes: Tuple[int, int], + paddings: Tuple[int, int], halving: int, use_pool: bool = True, **kwargs @@ -151,7 +151,7 @@ class BasicConv1d(nn.Module): self, in_channels: int, out_channels: int, - kernel_size: Union[int, tuple[int]], + kernel_size: Union[int, Tuple[int]], **kwargs ): super().__init__() @@ -167,7 +167,7 @@ class HorizontalPyramidPooling(BasicConv2d): self, in_channels: int, out_channels: int, - kernel_size: Union[int, tuple[int, int]] = 1, + kernel_size: Union[int, Tuple[int, int]] = 1, use_avg_pool: bool = True, use_max_pool: bool = True, **kwargs diff --git a/models/model.py b/models/model.py index 7373dbb..5ddcf90 100644 --- a/models/model.py +++ b/models/model.py @@ -1,6 +1,6 @@ import os from datetime import datetime -from typing import Union, Optional +from typing import Union, Optional, Tuple, List, Dict, Set import numpy as np import torch @@ -59,8 +59,8 @@ class Model: self.pr: Optional[int] = None self.k: Optional[int] = None - self._gallery_dataset_meta: Optional[dict[str, list]] = None - self._probe_datasets_meta: Optional[dict[str, dict[str, list]]] = None + self._gallery_dataset_meta: Optional[Dict[str, List]] = None + self._probe_datasets_meta: Optional[Dict[str, Dict[str, List]]] = None self._model_name: str = self.meta.get('name', 'RGB-GaitPart') self._hp_sig: str = self._make_signature(self.hp) @@ -105,8 +105,8 @@ class Model: def fit_all( self, dataset_config: DatasetConfiguration, - dataset_selectors: dict[ - str, dict[str, Union[ClipClasses, ClipConditions, ClipViews]] + dataset_selectors: Dict[ + str, Dict[str, Union[ClipClasses, ClipConditions, ClipViews]] ], dataloader_config: DataloaderConfiguration, ): @@ -205,11 +205,11 @@ class Model: self, iter_: int, dataset_config: DatasetConfiguration, - dataset_selectors: dict[ - str, dict[str, Union[ClipClasses, ClipConditions, ClipViews]] + dataset_selectors: Dict[ + str, Dict[str, Union[ClipClasses, ClipConditions, ClipViews]] ], dataloader_config: DataloaderConfiguration, - ) -> dict[str, torch.Tensor]: + ) -> Dict[str, torch.Tensor]: self.is_train = False # Split gallery and probe dataset gallery_dataloader, probe_dataloaders = self._split_gallery_probe( @@ -266,10 +266,10 @@ class Model: def _evaluate( self, - gallery_samples: dict[str, Union[list[str], torch.Tensor]], - probe_samples: dict[str, dict[str, Union[list[str], torch.Tensor]]], + gallery_samples: Dict[str, Union[List[str], torch.Tensor]], + probe_samples: Dict[str, Dict[str, Union[List[str], torch.Tensor]]], num_ranks: int = 5 - ) -> dict[str, torch.Tensor]: + ) -> Dict[str, torch.Tensor]: probe_conditions = self._probe_datasets_meta.keys() gallery_views_meta = self._gallery_dataset_meta['views'] probe_views_meta = list(self._probe_datasets_meta.values())[0]['views'] @@ -316,10 +316,10 @@ class Model: self, iter_: int, dataset_config: DatasetConfiguration, - dataset_selectors: dict[ - str, dict[str, Union[ClipClasses, ClipConditions, ClipViews]] + dataset_selectors: Dict[ + str, Dict[str, Union[ClipClasses, ClipConditions, ClipViews]] ] - ) -> dict[str, str]: + ) -> Dict[str, str]: checkpoints = {} self.curr_iter = iter_ for (k, v) in dataset_selectors.items(): @@ -334,7 +334,7 @@ class Model: self, dataset_config: DatasetConfiguration, dataloader_config: DataloaderConfiguration, - ) -> tuple[DataLoader, dict[str, DataLoader]]: + ) -> Tuple[DataLoader, Dict[str, DataLoader]]: dataset_name = dataset_config.get('name', 'CASIA-B') if dataset_name == 'CASIA-B': gallery_dataset = self._parse_dataset_config( @@ -391,7 +391,7 @@ class Model: dataset_config, popped_keys=['root_dir', 'cache_on'] ) - config: dict = dataset_config.copy() + config: Dict = dataset_config.copy() name = config.pop('name', 'CASIA-B') if name == 'CASIA-B': return CASIAB(**config, is_train=self.is_train) @@ -405,7 +405,7 @@ class Model: dataset: Union[CASIAB], dataloader_config: DataloaderConfiguration ) -> DataLoader: - config: dict = dataloader_config.copy() + config: Dict = dataloader_config.copy() (self.pr, self.k) = config.pop('batch_size', (8, 16)) if self.is_train: triplet_sampler = TripletSampler(dataset, (self.pr, self.k)) @@ -418,9 +418,9 @@ class Model: def _batch_splitter( self, - batch: list[dict[str, Union[np.int64, str, torch.Tensor]]] - ) -> tuple[dict[str, Union[list[str], torch.Tensor]], - dict[str, Union[list[str], torch.Tensor]]]: + batch: List[Dict[str, Union[np.int64, str, torch.Tensor]]] + ) -> Tuple[Dict[str, Union[List[str], torch.Tensor]], + Dict[str, Union[List[str], torch.Tensor]]]: """ Disentanglement need two random conditions, this function will split pr * k * 2 samples to 2 dicts each containing pr * k @@ -434,8 +434,8 @@ class Model: return default_collate(_batch[0]), default_collate(_batch[1]) def _make_signature(self, - config: dict, - popped_keys: Optional[list] = None) -> str: + config: Dict, + popped_keys: Optional[List] = None) -> str: _config = config.copy() if popped_keys: for key in popped_keys: @@ -443,16 +443,16 @@ class Model: return self._gen_sig(list(_config.values())) - def _gen_sig(self, values: Union[tuple, list, set, str, int, float]) -> str: + def _gen_sig(self, values: Union[Tuple, List, Set, str, int, float]) -> str: strings = [] for v in values: if isinstance(v, str): strings.append(v) - elif isinstance(v, (tuple, list)): + elif isinstance(v, (Tuple, List)): strings.append(self._gen_sig(v)) - elif isinstance(v, set): + elif isinstance(v, Set): strings.append(self._gen_sig(sorted(list(v)))) - elif isinstance(v, dict): + elif isinstance(v, Dict): strings.append(self._gen_sig(list(v.values()))) else: strings.append(str(v)) diff --git a/models/part_net.py b/models/part_net.py index ac7c434..6d8d4e1 100644 --- a/models/part_net.py +++ b/models/part_net.py @@ -1,4 +1,5 @@ import copy +from typing import Tuple import torch import torch.nn as nn @@ -12,9 +13,9 @@ class FrameLevelPartFeatureExtractor(nn.Module): self, in_channels: int = 3, feature_channels: int = 32, - kernel_sizes: tuple[tuple, ...] = ((5, 3), (3, 3), (3, 3)), - paddings: tuple[tuple, ...] = ((2, 1), (1, 1), (1, 1)), - halving: tuple[int, ...] = (0, 2, 3) + kernel_sizes: Tuple[Tuple, ...] = ((5, 3), (3, 3), (3, 3)), + paddings: Tuple[Tuple, ...] = ((2, 1), (1, 1), (1, 1)), + halving: Tuple[int, ...] = (0, 2, 3) ): super().__init__() num_blocks = len(kernel_sizes) @@ -112,9 +113,9 @@ class PartNet(nn.Module): self, in_channels: int = 3, feature_channels: int = 32, - kernel_sizes: tuple[tuple, ...] = ((5, 3), (3, 3), (3, 3)), - paddings: tuple[tuple, ...] = ((2, 1), (1, 1), (1, 1)), - halving: tuple[int, ...] = (0, 2, 3), + kernel_sizes: Tuple[Tuple, ...] = ((5, 3), (3, 3), (3, 3)), + paddings: Tuple[Tuple, ...] = ((2, 1), (1, 1), (1, 1)), + halving: Tuple[int, ...] = (0, 2, 3), squeeze_ratio: int = 4, num_part: int = 16 ): diff --git a/models/rgb_part_net.py b/models/rgb_part_net.py index f39b40b..95a3f2e 100644 --- a/models/rgb_part_net.py +++ b/models/rgb_part_net.py @@ -1,4 +1,5 @@ import random +from typing import Tuple, List import torch import torch.nn as nn @@ -16,14 +17,14 @@ class RGBPartNet(nn.Module): num_class: int = 74, ae_in_channels: int = 3, ae_feature_channels: int = 64, - f_a_c_p_dims: tuple[int, int, int] = (128, 128, 64), - hpm_scales: tuple[int, ...] = (1, 2, 4), + f_a_c_p_dims: Tuple[int, int, int] = (128, 128, 64), + hpm_scales: Tuple[int, ...] = (1, 2, 4), hpm_use_avg_pool: bool = True, hpm_use_max_pool: bool = True, fpfe_feature_channels: int = 32, - fpfe_kernel_sizes: tuple[tuple, ...] = ((5, 3), (3, 3), (3, 3)), - fpfe_paddings: tuple[tuple, ...] = ((2, 1), (1, 1), (1, 1)), - fpfe_halving: tuple[int, ...] = (0, 2, 3), + fpfe_kernel_sizes: Tuple[Tuple, ...] = ((5, 3), (3, 3), (3, 3)), + fpfe_paddings: Tuple[Tuple, ...] = ((2, 1), (1, 1), (1, 1)), + fpfe_halving: Tuple[int, ...] = (0, 2, 3), tfa_squeeze_ratio: int = 4, tfa_num_parts: int = 16, embedding_dims: int = 256, @@ -143,8 +144,8 @@ class RGBPartNet(nn.Module): return (x_c_c1, x_p_c1), None @staticmethod - def _pose_sim_loss(f_p_c1: list[torch.Tensor], - f_p_c2: list[torch.Tensor]) -> torch.Tensor: + def _pose_sim_loss(f_p_c1: List[torch.Tensor], + f_p_c2: List[torch.Tensor]) -> torch.Tensor: f_p_c1_mean = torch.stack(f_p_c1).mean(dim=0) f_p_c2_mean = torch.stack(f_p_c2).mean(dim=0) return F.mse_loss(f_p_c1_mean, f_p_c2_mean) diff --git a/utils/configuration.py b/utils/configuration.py index 9a8c2ae..d7ebc5e 100644 --- a/utils/configuration.py +++ b/utils/configuration.py @@ -1,4 +1,4 @@ -from typing import TypedDict, Optional, Union +from typing import TypedDict, Optional, Union, Tuple, Dict from utils.dataset import ClipClasses, ClipConditions, ClipViews @@ -15,28 +15,28 @@ class DatasetConfiguration(TypedDict): train_size: int num_sampled_frames: int discard_threshold: int - selector: Optional[dict[str, Union[ClipClasses, ClipConditions, ClipViews]]] + selector: Optional[Dict[str, Union[ClipClasses, ClipConditions, ClipViews]]] num_input_channels: int - frame_size: tuple[int, int] + frame_size: Tuple[int, int] cache_on: bool class DataloaderConfiguration(TypedDict): - batch_size: tuple[int, int] + batch_size: Tuple[int, int] num_workers: int pin_memory: bool class ModelHPConfiguration(TypedDict): ae_feature_channels: int - f_a_c_p_dims: tuple[int, int, int] - hpm_scales: tuple[int, ...] + f_a_c_p_dims: Tuple[int, int, int] + hpm_scales: Tuple[int, ...] hpm_use_avg_pool: bool hpm_use_max_pool: bool fpfe_feature_channels: int - fpfe_kernel_sizes: tuple[tuple, ...] - fpfe_paddings: tuple[tuple, ...] - fpfe_halving: tuple[int, ...] + fpfe_kernel_sizes: Tuple[Tuple, ...] + fpfe_paddings: Tuple[Tuple, ...] + fpfe_halving: Tuple[int, ...] tfa_squeeze_ratio: int tfa_num_parts: int embedding_dims: int @@ -45,7 +45,7 @@ class ModelHPConfiguration(TypedDict): class OptimizerHPConfiguration(TypedDict): lr: int - betas: tuple[float, float] + betas: Tuple[float, float] weight_decay: float diff --git a/utils/dataset.py b/utils/dataset.py index cd8b0f1..ea678fb 100644 --- a/utils/dataset.py +++ b/utils/dataset.py @@ -1,7 +1,7 @@ import os import random import re -from typing import Optional, NewType, Union +from typing import Optional, NewType, Union, List, Tuple, Set, Dict import numpy as np import torch @@ -11,9 +11,9 @@ from sklearn.preprocessing import LabelEncoder from torch.utils import data from tqdm import tqdm -ClipClasses = NewType('ClipClasses', set[str]) -ClipConditions = NewType('ClipConditions', set[str]) -ClipViews = NewType('ClipViews', set[str]) +ClipClasses = NewType('ClipClasses', Set[str]) +ClipConditions = NewType('ClipConditions', Set[str]) +ClipViews = NewType('ClipViews', Set[str]) class CASIAB(data.Dataset): @@ -26,11 +26,11 @@ class CASIAB(data.Dataset): train_size: int = 74, num_sampled_frames: int = 30, discard_threshold: int = 15, - selector: Optional[dict[ + selector: Optional[Dict[ str, Union[ClipClasses, ClipConditions, ClipViews] ]] = None, num_input_channels: int = 3, - frame_size: tuple[int, int] = (64, 32), + frame_size: Tuple[int, int] = (64, 32), cache_on: bool = False ): """ @@ -75,15 +75,15 @@ class CASIAB(data.Dataset): self.views: np.ndarray[np.str_] # Labels, classes, conditions and views in dataset, # set of three attributes above - self.metadata: dict[str, list[np.int64, str]] + self.metadata: Dict[str, List[np.int64, str]] # Dictionaries for indexing frames and frame names by clip name # and chip path when cache is on - self._cached_clips_frame_names: Optional[dict[str, list[str]]] = None - self._cached_clips: Optional[dict[str, torch.Tensor]] = None + self._cached_clips_frame_names: Optional[Dict[str, List[str]]] = None + self._cached_clips: Optional[Dict[str, torch.Tensor]] = None # Video clip directory names - self._clip_names: list[str] = [] + self._clip_names: List[str] = [] clip_names = sorted(os.listdir(self._root_dir)) if self._is_train: @@ -170,7 +170,7 @@ class CASIAB(data.Dataset): def __getitem__( self, index: int - ) -> dict[str, Union[np.int64, str, torch.Tensor]]: + ) -> Dict[str, Union[np.int64, str, torch.Tensor]]: label = self.labels[index] condition = self.conditions[index] view = self.views[index] @@ -215,8 +215,8 @@ class CASIAB(data.Dataset): def _load_cached_video( self, clip: torch.Tensor, - frame_names: list[str], - sampled_frame_names: list[str] + frame_names: List[str], + sampled_frame_names: List[str] ) -> torch.Tensor: # Mask the original clip when it is long enough if len(frame_names) >= self._num_sampled_frames: @@ -246,7 +246,7 @@ class CASIAB(data.Dataset): return clip def _sample_frames(self, clip_path: str, - is_caching: bool = False) -> list[str]: + is_caching: bool = False) -> List[str]: if self._cache_on: if is_caching: # Sort frame in advance for loading convenience diff --git a/utils/sampler.py b/utils/sampler.py index cdf1984..0977f94 100644 --- a/utils/sampler.py +++ b/utils/sampler.py @@ -1,6 +1,5 @@ import random -from collections.abc import Iterator -from typing import Union +from typing import Union, Tuple, Iterator import numpy as np from torch.utils import data @@ -12,7 +11,7 @@ class TripletSampler(data.Sampler): def __init__( self, data_source: Union[CASIAB], - batch_size: tuple[int, int] + batch_size: Tuple[int, int] ): super().__init__(data_source) self.metadata_labels = data_source.metadata['labels'] |