summaryrefslogtreecommitdiff
path: root/models
diff options
context:
space:
mode:
Diffstat (limited to 'models')
-rw-r--r--models/auto_encoder.py8
-rw-r--r--models/hpm.py4
-rw-r--r--models/layers.py20
-rw-r--r--models/model.py54
-rw-r--r--models/part_net.py13
-rw-r--r--models/rgb_part_net.py15
6 files changed, 60 insertions, 54 deletions
diff --git a/models/auto_encoder.py b/models/auto_encoder.py
index 36be868..befd2d3 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 6b799ad..8992914 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)
@@ -107,8 +107,8 @@ 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,
):
@@ -140,7 +140,7 @@ class Model:
dataloader = self._parse_dataloader_config(dataset, dataloader_config)
# Prepare for model, optimizer and scheduler
model_hp = self.hp.get('model', {})
- optim_hp: dict = self.hp.get('optimizer', {}).copy()
+ optim_hp: Dict = self.hp.get('optimizer', {}).copy()
ae_optim_hp = optim_hp.pop('auto_encoder', {})
pn_optim_hp = optim_hp.pop('part_net', {})
hpm_optim_hp = optim_hp.pop('hpm', {})
@@ -222,11 +222,11 @@ class Model:
self,
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]:
self.is_train = False
# Split gallery and probe dataset
gallery_dataloader, probe_dataloaders = self._split_gallery_probe(
@@ -278,10 +278,10 @@ 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']
@@ -328,10 +328,10 @@ class Model:
self,
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_, (condition, selector)) in zip(
iters, dataset_selectors.items()
@@ -348,7 +348,7 @@ 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(
@@ -405,7 +405,7 @@ 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)
@@ -419,7 +419,7 @@ 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))
@@ -432,9 +432,9 @@ 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
@@ -448,8 +448,8 @@ 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:
@@ -457,16 +457,16 @@ 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 e707c26..326ec81 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,
@@ -142,8 +143,8 @@ 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)
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-23 20:24:19 +0000