diff options
Diffstat (limited to 'models')
| -rw-r--r-- | models/auto_encoder.py | 14 | ||||
| -rw-r--r-- | models/hpm.py | 4 | ||||
| -rw-r--r-- | models/layers.py | 18 | ||||
| -rw-r--r-- | models/model.py | 72 | ||||
| -rw-r--r-- | models/part_net.py | 7 | ||||
| -rw-r--r-- | models/rgb_part_net.py | 10 |
6 files changed, 66 insertions, 59 deletions
diff --git a/models/auto_encoder.py b/models/auto_encoder.py index 0694ff1..023b462 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 @@ -11,9 +13,9 @@ class Encoder(nn.Module): def __init__( self, in_channels: int = 3, - frame_size: tuple[int, int] = (64, 48), + frame_size: Tuple[int, int] = (64, 48), 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 @@ -74,9 +76,9 @@ 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, - feature_size: tuple[int, int] = (4, 3), + feature_size: Tuple[int, int] = (4, 3), out_channels: int = 3, ): super().__init__() @@ -125,9 +127,9 @@ class AutoEncoder(nn.Module): def __init__( self, channels: int = 3, - frame_size: tuple[int, int] = (64, 48), + frame_size: Tuple[int, int] = (64, 48), 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, frame_size, diff --git a/models/hpm.py b/models/hpm.py index 8186b20..8320569 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 = False, ): diff --git a/models/layers.py b/models/layers.py index c609698..a0933e8 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, @@ -106,7 +106,7 @@ 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 ): @@ -126,8 +126,8 @@ 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 @@ -153,7 +153,7 @@ 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__() diff --git a/models/model.py b/models/model.py index 9cac5e5..0c2e2b9 100644 --- a/models/model.py +++ b/models/model.py @@ -1,7 +1,7 @@ import copy import os import random -from typing import Union, Optional +from typing import Union, Optional, Tuple, List, Dict, Set import numpy as np import torch @@ -59,14 +59,14 @@ class Model: self.is_train: bool = True self.in_channels: int = 3 - self.in_size: tuple[int, int] = (64, 48) + self.in_size: Tuple[int, int] = (64, 48) self.pr: Optional[int] = None self.k: Optional[int] = None self.num_pairs: Optional[int] = None self.num_pos_pairs: 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) @@ -117,8 +117,8 @@ 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, ): @@ -165,11 +165,11 @@ class Model: train_dataset, dataloader_config )) # Prepare for model, optimizer and scheduler - model_hp: dict = self.hp.get('model', {}).copy() + model_hp: Dict = self.hp.get('model', {}).copy() triplet_is_hard = model_hp.pop('triplet_is_hard', True) triplet_is_mean = model_hp.pop('triplet_is_mean', True) triplet_margins = model_hp.pop('triplet_margins', None) - optim_hp: dict = self.hp.get('optimizer', {}).copy() + optim_hp: Dict = self.hp.get('optimizer', {}).copy() ae_optim_hp = optim_hp.pop('auto_encoder', {}) hpm_optim_hp = optim_hp.pop('hpm', {}) pn_optim_hp = optim_hp.pop('part_net', {}) @@ -460,13 +460,13 @@ class Model: def predict_all( self, - iters: tuple[int], + iters: Tuple[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]: # Transform data to features gallery_samples, probe_samples = self.transform( iters, dataset_config, dataset_selectors, dataloader_config @@ -478,10 +478,10 @@ class Model: def transform( self, - iters: tuple[int], + iters: Tuple[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, is_train: bool = False @@ -496,7 +496,7 @@ class Model: ) # Init models - model_hp: dict = self.hp.get('model', {}).copy() + model_hp: Dict = self.hp.get('model', {}).copy() model_hp.pop('triplet_is_hard', True) model_hp.pop('triplet_is_mean', True) model_hp.pop('triplet_margins', None) @@ -530,7 +530,7 @@ class Model: return gallery_samples, probe_samples - def _get_eval_sample(self, sample: dict[str, Union[list, torch.Tensor]]): + def _get_eval_sample(self, sample: Dict[str, Union[List, torch.Tensor]]): label, condition, view, clip = sample.values() with torch.no_grad(): feature_c, feature_p = self.rgb_pn(clip.to(self.device)) @@ -543,10 +543,10 @@ class Model: @staticmethod def evaluate( - gallery_samples: dict[str, dict[str, Union[list, torch.Tensor]]], - probe_samples: dict[str, dict[str, Union[list, torch.Tensor]]], + gallery_samples: Dict[str, Dict[str, Union[List, torch.Tensor]]], + probe_samples: Dict[str, Dict[str, Union[List, torch.Tensor]]], num_ranks: int = 5 - ) -> dict[str, torch.Tensor]: + ) -> Dict[str, torch.Tensor]: conditions = list(probe_samples.keys()) gallery_views_meta = gallery_samples['meta']['views'] probe_views_meta = probe_samples[conditions[0]]['meta']['views'] @@ -591,12 +591,12 @@ class Model: def _load_pretrained( self, - iters: tuple[int], + iters: Tuple[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 = {} for (iter_, total_iter, (condition, selector)) in zip( iters, self.total_iters, dataset_selectors.items() @@ -615,7 +615,7 @@ class Model: dataset_config: DatasetConfiguration, dataloader_config: DataloaderConfiguration, is_train: bool = False - ) -> tuple[DataLoader, dict[str, DataLoader]]: + ) -> Tuple[DataLoader, Dict[str, DataLoader]]: dataset_name = dataset_config.get('name', 'CASIA-B') if dataset_name == 'CASIA-B': self.is_train = is_train @@ -674,7 +674,7 @@ 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) @@ -688,7 +688,7 @@ 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)) @@ -701,9 +701,9 @@ 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 @@ -717,8 +717,8 @@ 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: @@ -726,16 +726,16 @@ 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 f2236bf..de19c8c 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) diff --git a/models/rgb_part_net.py b/models/rgb_part_net.py index 5d2c142..e8e320d 100644 --- a/models/rgb_part_net.py +++ b/models/rgb_part_net.py @@ -1,3 +1,5 @@ +from typing import Tuple + import torch import torch.nn as nn @@ -10,15 +12,15 @@ class RGBPartNet(nn.Module): def __init__( self, ae_in_channels: int = 3, - ae_in_size: tuple[int, int] = (64, 48), + ae_in_size: Tuple[int, int] = (64, 48), 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, tfa_squeeze_ratio: int = 4, tfa_num_parts: int = 16, - embedding_dims: tuple[int] = (256, 256), + embedding_dims: Tuple[int] = (256, 256), image_log_on: bool = False ): super().__init__() |